AI Vision Use Cases

Abandoned object detection

Detects unattended bags, packages, and other items left in public or restricted spaces using object detection on video or image feeds.

Aircraft surface inspection

Automated detection of surface defects on aircraft fuselage, wings, and control surfaces from inspection imagery. Flags dents, corrosion, cracks, and missing fasteners for review by maintenance crews.

Airplane detection from satellite

Detect and localize airplanes in satellite and high-altitude aerial imagery using object detection. Outputs bounding boxes for each aircraft across large geospatial scenes.

Animal behavior monitoring

Computer vision workflow that detects and tracks livestock in barns, feedlots, and pastures to flag behaviors like feeding, lying, and standing. Runs on standard farm camera footage to surface behavioral changes automatically.

Anomaly detection on production line

Detect visual defects and anomalies on manufacturing production lines using object detection. Flag scratches, dents, missing components, and misaligned parts in real time as items move through inspection stations.

Apple detection

A computer vision workflow that locates and counts apples in images of orchard trees, harvested bins, or packing lines. It identifies individual fruit even under partial occlusion by leaves and branches.

Assembly verification

Computer vision that inspects assembled products against a reference configuration to catch missing, misplaced, or incorrect components before they leave the line. Detection-based checks run on images from existing station cameras.

Bakery product detection

Computer vision that identifies and locates individual bakery items in images, from loaves and rolls to pastries and cakes. Useful for inventory tracking, checkout automation, and production line quality checks.

Ball detection

Detect and localize balls in sports footage using an object detection model. Works on images and video frames to find the ball's position across a game or practice session.

Barcode detection

Locate barcodes in images of products, packaging, and shipping labels using object detection. Returns bounding boxes around each barcode instance for downstream decoding or QC checks.

Basketball detection

Detect basketballs in images and video frames using an object detection model. Useful for tracking ball position, possession, and shot events in game footage.

Bin picking object detection

Detects and localizes individual parts, components, and objects inside cluttered bins or containers so a robot can pick them one at a time. Built for automated bin picking cells in robotics and industrial automation.

Blister pack inspection

Automated visual inspection of pharmaceutical blister packs to verify that every cavity is filled with the correct tablet or capsule and to flag defects before packaging.

Blood cell detection

Automated detection and counting of blood cells in microscopy images, identifying red blood cells, white blood cells, and platelets from stained smear slides.

Bolt detection

Automated bolt detection using computer vision to locate and count bolts on assemblies, fasteners on machinery, and hardware on production lines. Built for manufacturing quality control where missing or misaligned bolts must be caught before parts ship.

Classification · Retail Tech

Bottle and can recognition for vending

A computer vision classifier that identifies bottles and cans in vending machine dispensers and camera feeds. It recognizes specific beverage products to power inventory tracking and automated checkout.

Bottle counting

A computer vision workflow that detects and counts bottles on production lines, in cases, or on shelves using object detection. It runs on standard camera feeds to automate what would otherwise be manual tallying.

Bottle defect detection

Automated visual inspection of bottles on the production line to catch defects like cracks, deformations, and fill or label errors before packaging. Uses object detection to flag flawed units in real time.

Box detection

Detect and localize cardboard boxes in images and video from warehouse and logistics environments. Useful for counting, tracking, and monitoring boxes on conveyors, pallets, and loading docks.

Brake pad inspection

Automated visual inspection of automotive brake pads to detect wear, thickness loss, and surface defects using object detection. Runs on line cameras or handheld inspection rigs to flag pads that fall below service thresholds.

Brand logo detection

Automatically detect and locate brand logos in images and video frames, identifying which logos appear and where they sit in the frame.

Building detection from aerial imagery

Automatically detect and segment building footprints from aerial and satellite imagery using instance segmentation. Outputs per-building polygon masks suitable for mapping, planning, and change detection workflows.

Segmentation · Robotics & Automation

Cable detection

Cable detection uses instance segmentation to identify and outline individual cables, wires, and connectors in images. It's applied in robotics and automation where machines need to locate, grasp, or route cabling.

Can detection

Can detection uses computer vision to locate and identify metal beverage and food cans in images or video streams. It works on production lines, in warehouses, and at retail shelves to count, classify, and track cans automatically.

Cap inspection

Automated visual inspection of bottle caps on production and packaging lines using object detection to catch missing, misaligned, or damaged closures before they ship.

Capsule inspection

Automated visual inspection of pharmaceutical capsules to catch defects like cracks, dents, and color variations on the production line. Uses object detection to flag non-conforming units before packaging.

Car damage detection

Automatically identify and localize damage on vehicles from images, flagging dents, scratches, cracks, and broken parts. Built for insurance, rental, and dealership workflows that need consistent, repeatable damage assessment.

Car detection from drone

Detect and count cars in aerial imagery captured by drones, identifying vehicle positions in overhead views across parking lots, roadways, and open areas.

Segmentation · Automotive

Car part segmentation

Instance segmentation that identifies and outlines individual car parts, bumpers, doors, hoods, fenders, in images at the pixel level. Useful for damage assessment, parts cataloging, and automated inspection workflows.

Casting defect detection

Automated visual inspection of metal castings to identify surface and structural defects like porosity, cracks, and shrinkage. Uses object detection to flag defective parts on the production line.

Cattle detection

Cattle detection uses computer vision to automatically locate and count individual cattle in images and video from pasture, feedlot, or barn cameras. It turns raw camera feeds into actionable head counts and location data without manual observation.

Cell counting

Automated counting of cells in microscopy images using object detection. Locates and tallies individual cells across blood smears, cultures, and tissue samples.

Cell detection

Automatically detect and localize individual cells in microscopy images using object detection. Useful for counting, classifying, and tracking cells across large volumes of imaging data.

Checkbox detection

Detect checkboxes in scanned forms and documents, identifying whether each box is checked or unchecked. Built for automating form data extraction pipelines.

Chicken detection

Chicken detection uses computer vision to locate and count individual birds in images and video from poultry environments. It identifies chickens across barn floors, free-range yards, and cages so their positions and numbers can be tracked automatically.

Chip defect detection

Automated visual inspection of semiconductor chips to locate and classify surface and structural defects on dies, packages, and solder connections. Uses object detection to flag faults that would otherwise require manual microscope review.

Coil defect detection

Automatically detect surface defects on steel coils using object detection, flagging issues like scratches, dents, and rust before coils move downstream.

Component presence check

Automatically verify that every required part is present on an assembled product before it moves down the line. This detection workflow flags missing components in real time using images from existing inspection cameras.

Composite defect detection

Automated visual inspection of aerospace composite parts to identify surface and structural defects like delamination, voids, and fiber wrinkling from images.

Segmentation · Construction & Infrastructure

Concrete crack detection

Automatically detect and segment cracks in concrete surfaces from inspection images. Pixel-level masks outline crack geometry across walls, bridges, pavements, and foundations.

Connector detection

Connector detection uses computer vision to locate and identify electrical and mechanical connectors in images, enabling automated assembly, inspection, and mating tasks in robotics workflows.

Construction progress monitoring

Automated construction progress detection using computer vision to identify structural elements, equipment, and materials on a job site from images or camera feeds.

OCR · Logistics & Warehousing

Container number reading

Automatically read the ISO 6346 container numbers stamped on shipping containers using OCR, converting camera images into structured text. Useful for gate automation, yard inventory, and terminal tracking.

Contamination detection

Instance segmentation that identifies and outlines foreign particles, debris, and unwanted substances on products, surfaces, and production lines. Built for manufacturing quality control where pixel-level accuracy separates a defective unit from a clean one.

Conveyor belt monitoring

Computer vision workflow that monitors conveyor belts in mining and metals operations, detecting belt surface damage, tears, and material spillage from camera feeds. Flags issues before they escalate into failures or unplanned downtime.

Conveyor object detection

Detect and locate objects moving on a conveyor belt in real time using a computer vision model. Useful for sorting, counting, and quality checks in automated production and packaging lines.

Corn detection

Detect and localize corn plants, ears, and kernels in field or processing imagery using object detection. Built for agriculture teams working with drone, ground robot, or fixed camera feeds.

Corrosion detection

A computer vision workflow that segments corrosion on metal surfaces from inspection images, pinpointing rust, pitting, and surface degradation at the pixel level.

Segmentation · Sports Analytics

Court segmentation

Court segmentation uses instance segmentation to identify and outline playing surfaces, like basketball, tennis, and volleyball courts, along with their boundary lines and functional zones in video or image frames. It produces pixel-level masks that map the geometry of the court for downstream sports analytics.

Cow detection

Cow detection uses computer vision to automatically locate and count cattle in images or video from farm cameras, drones, or fixed feedlot monitoring systems.

Crack detection

Automated crack detection uses instance segmentation to identify and outline cracks on manufactured parts, surfaces, and structures from camera images. It flags defects that would otherwise require manual inspection.

Crane detection

Crane detection uses computer vision to automatically locate and identify cranes in images and video feeds from construction sites and infrastructure projects. It flags tower cranes, mobile cranes, and their key components so teams can monitor equipment activity and safety zones.

Crop disease detection

Automatically identify diseased plants and infected foliage in field or greenhouse imagery using object detection. Locates and classifies visual symptoms like leaf spots, blight, and rust directly on the plant.

Crop field mapping

Segment individual crop fields, boundaries, and land parcels from aerial and satellite imagery. Turn drone or orthomosaic captures into pixel-accurate field maps for acreage, coverage, and land-use analysis.

Segmentation · Agriculture

Crop row segmentation

Crop row segmentation uses computer vision to identify and outline planted rows in field imagery, separating crop lines from soil, weeds, and gaps. It provides pixel-level masks that machines and analytics tools can use to navigate and assess field structure.

Segmentation · Security & Surveillance

Crowd density estimation

A computer vision workflow that segments crowds in images and video to estimate density levels across public spaces. Built for security and surveillance teams monitoring foot traffic, gatherings, and occupancy.

Customer counting

Automatically count customers in retail spaces using object detection on video or still images from existing cameras. Track how many people enter, browse, and move through defined zones without manual tallying.

Cyclist detection

Cyclist detection uses computer vision to locate and track people riding bicycles in traffic camera and roadside footage. It draws bounding boxes around cyclists so downstream systems can count, monitor, or trigger safety responses.

Deforestation detection

Segment cleared, degraded, and intact forest areas in aerial and satellite imagery to track deforestation over time. Turns raw drone or geospatial captures into pixel-level maps of forest loss.

Dent detection

Detect dents on metal panels, body parts, and manufactured surfaces using object detection. Flags surface deformations during quality control inspection.

Dental caries detection

Automated detection of dental caries in radiographic and intraoral images using object detection. Identifies and localizes cavities and early decay for clinical review.

Dental detection

A computer vision workflow that locates and identifies individual teeth and dental structures in intraoral photos and radiographs. Useful for automating charting, numbering, and screening tasks in dental imaging.

Dial reading

Automatically read analog dial gauges from images using computer vision and OCR, converting needle position and printed scale markings into digital values. Built for manufacturing and QC environments where instruments still rely on analog displays.

Die defect detection

Automated detection of physical defects on semiconductor dies using object detection models trained on wafer and die-level imagery. Flags cracks, scratches, contamination, and other anomalies before packaging.

Document layout detection

Document layout detection locates and classifies structural regions in a page image, text blocks, tables, figures, and headers, so downstream OCR and parsing can process each element correctly.

Egg crack detection

Automated inspection of eggs on a production line to identify cracked, broken, or otherwise damaged shells using computer vision. Flags defective eggs in real time so they can be removed before packaging.

Egg detection

Egg detection uses computer vision to locate and count individual eggs in images from processing lines, cartons, or trays. It automates visual inspection and inventory tasks in food and beverage production.

Empty shelf detection in warehouse

Automatically detect empty shelves and vacant bins in warehouse racking using object detection on existing camera feeds. Flags out-of-stock locations so teams can trigger restocking before pickers arrive at empty slots.

Empty shelf detection

Detect empty or low-stock shelf sections in retail store images using object detection. Flags gaps on shelves so teams can restock before sales are lost.

Excavator detection

Detect excavators in images and video from construction sites and infrastructure projects. Locate and track heavy earthmoving equipment across cameras for safety, activity monitoring, and asset visibility.

Keypoint · Fitness & AR Apps

Exercise rep counting

A keypoint-based computer vision workflow that tracks body joints during exercises to automatically count repetitions. It detects pose landmarks and analyzes their motion to identify completed reps for movements like squats, push-ups, and curls.

Expiry date reading

Automatically read printed expiry and best-before dates on product packaging using OCR. Turns camera images of labels into structured date strings for verification and logging.

Fabric defect detection

Automated visual inspection that locates and classifies defects in woven, knit, and printed fabrics as they move through production or QC stations. Flags flaws like holes, stains, and broken threads in real time.

Face detection

A computer vision workflow that locates and draws bounding boxes around human faces in images and video streams. Built for security and surveillance applications where reliable face detection is a prerequisite for downstream tasks.

Fall detection

A computer vision workflow that monitors video feeds to detect when a person has fallen to the ground, distinguishing fall events from normal standing, sitting, or walking postures.

Fastener counting

Automated counting of fasteners, screws, bolts, nuts, and washers, in kits, trays, or assembly stations using object detection. Verifies quantities before packaging or assembly to catch shortages early.

Segmentation · Agriculture

Field segmentation

Field segmentation uses instance segmentation to outline and delineate individual agricultural fields from aerial or satellite imagery. It produces pixel-level masks for each field boundary so you can measure area, count parcels, and track land use.

Fill level inspection

Computer vision system that inspects containers on a production line and detects whether each is filled to the correct level. It flags underfills, overfills, and empty containers before they leave the fill station.

Fire detection

Detect fire and flames in camera feeds using a computer vision model, flagging early signs of combustion before they spread. Runs on standard surveillance footage to trigger alerts in real time.

Fish detection

Fish detection uses computer vision to automatically locate and count fish in images or video, whether on processing lines, in aquaculture tanks, or on catch inspection tables. It identifies individual fish and can distinguish species or condition for downstream sorting.

Classification · Food & Beverage

Fish freshness classification

Automatically classify fish freshness from images of whole fish, fillets, or key features like eyes and gills. A vision model assigns a freshness grade so you can sort, flag, or reject product without manual inspection.

Flare detection

Detect and monitor gas flares at industrial sites using object detection on camera feeds. Identifies active flare flames, smoke plumes, and flare stack equipment in images and video.

Flood mapping

Segment flooded areas from aerial and satellite imagery to map water extent across affected regions. Turns drone and geospatial captures into pixel-level flood boundaries for damage assessment and response planning.

Flower detection

Flower detection uses computer vision to locate and count individual flowers or blooms in field, greenhouse, or orchard imagery. It draws bounding boxes around each flower so you can quantify bloom stages, density, and distribution.

Segmentation · Food & Beverage

Food portion segmentation

Instance segmentation of individual food items on a plate or tray, outlining each portion so its area and boundaries can be measured. Useful for automating portion control, nutrition estimation, and meal auditing in food service and packaging.

Food quality inspection

Automated visual inspection of food products on production lines to catch defects, contamination, and quality issues before packaging. Uses object detection to flag out-of-spec items in real time.

Football detection

Detect footballs in images and video frames to power sports analytics workflows like play tracking, possession analysis, and automated highlight generation.

Foreign object detection

Computer vision workflow that automatically detects foreign objects and contaminants on production lines, conveyor belts, and finished goods before they reach packaging or shipping.

Forklift detection

Detect forklifts in warehouse and logistics camera feeds to track equipment movement, monitor congested zones, and flag safety-critical interactions with people.

Form field detection

Locate and classify individual fields on scanned or photographed forms, such as text inputs, checkboxes, and signature lines. Outputs bounding boxes that feed downstream OCR and data-extraction pipelines.

Fruit counting

Fruit counting detection uses computer vision to identify and tally individual fruits on trees, vines, or conveyor lines from images or video. It turns raw camera feeds into per-frame and aggregate counts without manual tallying.

Fruit detection

Fruit detection uses computer vision to locate and identify individual fruit in images from orchards, packing lines, or storage. It supports counting, sorting, and quality assessment across the agriculture supply chain.

Classification · Food & Beverage

Fruit grading

Automated fruit grading using image classification to sort produce by quality, ripeness, and defects. Takes camera images of individual fruits and assigns a grade class.

Segmentation · Aerospace

Fuselage crack detection

Computer vision workflow that segments cracks and related surface defects on aircraft fuselage skin from inspection imagery. It pinpoints crack location and extent at the pixel level to support maintenance decisions.

Segmentation · Energy & Utilities

Gas leak detection

Segmentation-based detection of gas leaks by identifying visible gas plumes, vapor clouds, and affected equipment in camera or optical-gas-imaging footage. Built for energy and utility operators monitoring pipelines, valves, and storage infrastructure.

Gauge reading

Automatically read analog gauges from camera images by detecting the dial, needle position, and printed scale, then converting them to digital values. Useful for monitoring pressure, temperature, and flow gauges that lack digital outputs.

Glass defect detection

Automated visual inspection of glass products to detect cracks, chips, scratches, and bubbles on production lines. Uses object detection to flag defective units before they reach packaging or shipping.

Glove detection

Glove detection uses computer vision to verify that workers are wearing safety gloves on construction and infrastructure sites. It flags bare hands in real time from standard camera feeds.

Goal detection

Goal detection uses computer vision to automatically identify when the ball crosses the goal line and enters the net during a match. It analyzes camera feeds to flag scoring events in real time.

Keypoint · Sports Analytics

Golf swing analysis

Track a golfer's body and club positions frame-by-frame using keypoint detection to analyze swing mechanics. Turns ordinary video into measurable pose data for coaching and performance review.

Graffiti detection

Automatically detect and locate graffiti on walls, bridges, signage, and other public infrastructure from camera imagery. Flags vandalism for review so cities can prioritize cleanup.

Grape detection

Grape detection uses computer vision to locate and count grape clusters and individual berries in vineyard and field images. It supports yield estimation, harvest timing, and crop monitoring across large plantings.

Grasp detection

Grasp detection identifies where and how a robotic gripper can pick up an object in a scene, locating graspable regions and objects for pick-and-place tasks.

Gun detection

Automated gun detection uses computer vision to identify firearms in live camera feeds and recorded footage, flagging weapons before they escalate into an incident.

Detection · Fitness & AR Apps

Gym equipment detection

Detect and classify gym equipment, treadmills, dumbbells, benches, and machines, in images and video. Useful for fitness apps, AR experiences, and equipment tracking.

Detection · Fitness & AR Apps

Hand detection

Detect and localize human hands in images and video streams for fitness tracking and augmented reality applications. Returns bounding boxes around each hand so downstream logic can track position, count, and interaction.

Classification · Fitness & AR Apps

Hand gesture recognition

Classify hand gestures from images or camera frames to drive touchless controls in fitness and AR applications. The model maps a cropped hand image to a discrete gesture label such as open palm, fist, or thumbs up.

Handwriting recognition

Handwriting recognition converts handwritten text in scanned documents, forms, and images into machine-readable characters using OCR. It handles cursive, printed, and mixed handwriting across a range of layouts and languages.

Hard hat detection

Computer vision workflow that detects whether workers on a construction site are wearing hard hats. Runs on standard camera feeds to flag missing head protection in real time.

Haul truck detection

Detect haul trucks in mining site imagery and video using an object detection model. Useful for tracking vehicle presence, counting cycles, and monitoring haul road activity.

Headlight defect detection

Computer vision workflow that inspects automotive headlight assemblies for defects such as cracks, condensation, and lens scratches. Uses object detection to flag flawed units on the production or inspection line.

Heavy equipment detection

Detects heavy construction equipment such as excavators, bulldozers, and cranes in images and video from job sites. Useful for tracking machinery presence, location, and utilization across active construction zones.

Keypoint · Fitness & AR Apps

Human pose estimation

Human pose estimation uses keypoint detection to locate body joints, shoulders, elbows, hips, knees, wrists, and ankles, in images and video. It powers fitness form tracking, rep counting, and body-driven interactions in AR applications.

ID card detection

Detect and localize ID cards within images and document scans using object detection. Useful for pinpointing card boundaries before running OCR or verification steps.

Illegal parking detection

Automatically flag vehicles parked in no-parking zones, bus lanes, crosswalks, and restricted areas from street and traffic camera feeds. Uses object detection to identify vehicles and their positions relative to marked restrictions.

Insect detection

Computer vision workflow that detects and localizes insects in field, greenhouse, and trap imagery. Built for agricultural pest monitoring using object detection.

Insulator defect detection

Automatically detect defects on power line insulators from inspection imagery, flagging cracks, flashovers, and missing components before they cause outages.

Intrusion detection

A computer vision workflow that monitors camera feeds to detect people, vehicles, or objects entering restricted or off-limits areas. It flags unauthorized presence in real time so security teams can respond before an incident escalates.

Inventory counting

Automatically count stock items in warehouse and storage environments using object detection. Point a camera at shelves, pallets, or bins and get a per-frame count of each item type.

Invoice field extraction

Detect and extract structured fields from invoice documents using computer vision, turning scanned or photographed invoices into machine-readable data.

OCR · Sports Analytics

Jersey number recognition

Automatically read and identify player jersey numbers from game footage and photos using OCR. Turns raw video frames into structured player-tracking data without manual tagging.

Knife detection

Detect knives in images and video streams to flag potential weapon threats in real time. Built for security teams automating surveillance monitoring.

Label inspection

Computer vision that inspects product labels on packaging lines to catch defects like missing, skewed, wrinkled, or misprinted labels before goods ship.

Label misalignment detection

A computer vision workflow that inspects product packaging on the line to flag labels that are crooked, off-position, or misaligned against the container. It catches placement defects before products reach shipping or retail.

Classification · Drones & Geospatial

Land cover classification

Automatically classify land cover types from aerial and satellite imagery, assigning each image or tile to categories such as forest, water, urban, or agriculture. Built for geospatial teams that need consistent labeling across large areas.

Segmentation · Smart Cities & Traffic

Lane detection

Segment road lane markings from camera or dashcam footage to identify lane boundaries, positions, and geometry. Useful for autonomous driving, ADAS, and traffic monitoring systems.

Leaf disease detection

Computer vision that detects and localizes diseased regions on plant leaves from field or greenhouse images. Identifies symptoms like spots, blight, and rust so growers can act before damage spreads.

OCR · Automotive

License plate recognition

Automatically locate vehicle license plates in images or video and read the alphanumeric characters using OCR. Works across parking, tolling, and access-control scenarios in the automotive space.

Litter detection

A computer vision workflow that identifies litter and discarded waste in images and video from street cameras, drones, and mobile units. It flags items like plastic bottles, food wrappers, and cans so cities can prioritize cleanup.

Livestock counting

Automatically count cattle, sheep, and other livestock in images and video from field cameras, drones, or fixed feedlot cameras using object detection.

Loading dock monitoring

Computer vision that monitors loading dock activity by detecting trucks, trailers, dock doors, and forklifts in real time. Useful for tracking dock occupancy, dwell time, and safety conditions.

Detection · Media & Content Moderation

Logo detection in video

Automatically detect and localize brand logos within video content frame by frame. Useful for tracking where and how often a logo appears across footage without manual review.

Loitering detection

Loitering detection uses computer vision to flag people who linger in a monitored area longer than expected, such as building entrances, ATMs, parking lots, or restricted zones. It combines person detection with dwell-time tracking to surface potential security concerns automatically.

Lot code reading

Automatically read and verify lot codes, batch numbers, and date stamps printed on product packaging using computer vision OCR. Turns camera images of labels into structured, machine-readable text for traceability.

Lung nodule detection

Automated detection and localization of lung nodules in chest CT and radiograph images using object detection models. Flags suspicious pulmonary nodules and marks their location for radiologist review.

Mask detection

Face mask detection identifies whether people in a scene are wearing a mask, and flags uncovered or improperly worn faces. It runs on standard camera feeds to automate compliance monitoring in real time.

Meat inspection

Automated visual inspection of meat products to identify defects, contamination, and quality issues on processing lines. Uses object detection to flag problem cuts before they move downstream.

Classification · Media & Content Moderation

Meme detection

A computer vision classifier that automatically identifies whether an image is a meme, sorting user-generated content into meme and non-meme categories for downstream moderation or analytics.

Metal surface inspection

Automated visual inspection of metal surfaces to detect and locate defects like scratches, pitting, and cracks on sheet metal, castings, and machined parts.

OCR · Energy & Utilities

Meter reading

Automatically read numeric values from utility meters using computer vision OCR. Takes a photo of an electric, gas, or water meter and extracts the digits from the display.

Mitosis detection

Automated detection of mitotic figures in histopathology images using object detection. Identifies dividing cells across whole-slide scans and tissue microscopy.

Classification · Media & Content Moderation

NSFW content detection

A computer vision workflow that classifies images as safe or NSFW so platforms can automatically flag or block explicit content before it reaches users.

Detection · Media & Content Moderation

Object blurring for privacy

Automatically detect faces, license plates, and other sensitive objects in images and video so they can be blurred before publishing. Built for detection-based privacy redaction in media and content pipelines.

Keypoint · Robotics & Automation

Object pose estimation

Estimate the 3D position and orientation of physical objects from camera images using keypoint detection. Built for robotics and automation teams that need to know where an object is and how it's oriented before acting on it.

Segmentation · Energy & Utilities

Oil spill detection

Computer vision that segments oil spills in imagery from satellites, drones, and fixed cameras, outlining the exact extent of contaminated water or ground. Built for energy and utilities operators monitoring offshore rigs, pipelines, and storage facilities.

Ore detection

Ore detection uses computer vision to identify and locate ore material in images from mine sites, conveyor belts, and processing lines. It automatically flags rock fragments, ore chunks, and waste material for downstream sorting or analysis.

Out of stock detection

Detect empty shelf space and out-of-stock products on retail shelves using object detection on camera or shelf-scan imagery.

Package damage detection

Automatically identify dented, crushed, torn, or punctured packages moving through logistics operations using object detection on camera feeds.

Package detection

Detects packages, parcels, and boxes in images and video streams from warehouse and logistics environments. Locates each package with a bounding box so downstream systems can count, track, or route items.

Paint defect detection

Automated visual inspection that finds paint defects like runs, sags, orange peel, and scratches on painted surfaces using object detection. Runs on line cameras or inspection-station images to flag flawed parts before they move downstream.

Paint scratch detection on cars

Automated detection of paint scratches, scuffs, and surface defects on vehicle exteriors from images. Flags and localizes damage on body panels for inspection workflows.

Pallet detection

Detect and localize pallets in warehouse and dock imagery using object detection, identifying pallet position, count, and load state from camera or video feeds.

Parcel counting

Automatically count parcels moving through a warehouse or distribution center using object detection on camera feeds. The model identifies and tallies individual packages as they appear on conveyors, in staging areas, or during loading.

Parking occupancy detection

Detect whether individual parking spaces are occupied or vacant from overhead or fixed-mount camera feeds. Turns raw video into real-time occupancy counts per lot, level, or zone.

Parking space detection

Detect and classify parking spaces as occupied or vacant from overhead or fixed camera feeds. Turns raw camera images into real-time counts of available spots.

Part counting

Automatically count discrete parts in an image using object detection, so you can verify quantities on trays, bins, and assembly stations without manual tallying.

Passport reading

A computer vision workflow that locates and reads the machine-readable zone (MRZ) on passport pages, extracting identity fields from the passport document image. It combines MRZ region detection with OCR to turn a photographed or scanned passport into structured text.

Segmentation · Construction & Infrastructure

Pavement distress detection

Computer vision that segments pavement distress in road and runway imagery, pinpointing cracks, potholes, and surface damage at the pixel level. Built for automated road condition surveys and infrastructure maintenance planning.

PCB defect detection

Automated visual inspection of printed circuit boards to locate manufacturing defects like missing components, solder bridges, and open traces. Uses object detection to flag faulty boards before they move downstream.

Pedestrian detection

Detect and locate pedestrians in street-level and intersection camera feeds. Useful for traffic management, crossing safety, and smart city analytics.

People counting

Detect and count people in images and video streams using object detection. Built for security and surveillance teams who need accurate headcounts across cameras.

Perimeter monitoring

Computer vision for monitoring secured perimeters, detecting people, vehicles, and objects that cross or approach a defined boundary line or fence.

Person detection

Person detection locates and identifies people in images and video frames, drawing bounding boxes around each individual for downstream tracking, counting, or alerting. It's a foundational task for security and surveillance systems that need to know when and where people appear.

Pest detection

Computer vision that detects and localizes insect pests in crop imagery, so you can identify infestations from field cameras, traps, or scouting photos.

Pig detection

Detect and locate individual pigs in images and video from barn or pen cameras. Useful for counting animals, monitoring movement, and building the foundation for automated livestock analytics.

Pill counting

A computer vision workflow that detects and counts individual pills in an image, giving an automated tally for quality control, dispensing, and packaging verification.

Pill detection

Pill detection uses computer vision to locate and identify individual pills in images, whether on a conveyor line, in a blister pack, or in a fill tray. It supports counting, sorting, and defect flagging tasks in pharmaceutical manufacturing and packaging.

Pipe detection

Pipe detection uses computer vision to locate and identify pipes, fittings, and connections in images from construction sites and infrastructure inspections. It flags pipe segments, joints, and valves automatically so teams can count, track, and verify pipework.

Pipeline leak detection

Computer vision detection of pipeline leaks and related failure signs from camera imagery, flagging oil spills, gas plumes, and surface anomalies along pipeline infrastructure.

Planogram compliance

Automated planogram compliance detection uses object detection to verify that products are placed on retail shelves according to the intended planogram. It checks facings, positions, and stock presence from shelf images.

Plant counting

Automatically count individual plants in field or greenhouse imagery using object detection. Works with drone, tractor-mounted, or handheld camera images to produce accurate per-plot or per-row counts.

Classification · Agriculture

Plant disease classification

Classify crop leaf images into healthy or specific disease categories using a fine-tuned image classification model. Useful for scouting apps, greenhouse monitoring, and precision agriculture pipelines.

Plastic part defect detection

A computer vision workflow that inspects molded plastic parts on the production line and flags surface and structural defects. It uses object detection to localize flaws like scratches, flash, and sink marks on each part.

Plate detection

Detect and localize food plates in images and video streams using object detection. Useful for automating plate counting, portion tracking, and meal identification in food service environments.

Player detection

Player detection locates and tracks individual athletes in sports footage, drawing bounding boxes around each player on the field or court. It's the foundation for automated game analysis, tracking, and event tagging.

Player tracking

Player tracking uses object detection to locate and follow individual athletes across video frames during a game or practice session. It outputs bounding boxes and positional data that can be stitched into movement trajectories for analysis.

Polyp detection

Automated detection of polyps in endoscopy and colonoscopy imagery, flagging suspicious lesions in real time to support clinical review.

Keypoint · Sports Analytics

Pose estimation for sports

Detect and track athlete body keypoints from images and video to quantify posture, joint angles, and movement mechanics in sports.

Pothole detection

Automatically detect potholes in road imagery using object detection. Takes camera or dashcam frames and flags road surface defects with bounding boxes.

Power line inspection

Automated visual inspection of power lines and transmission infrastructure using object detection to flag defects like damaged insulators, corroded hardware, and vegetation encroachment from aerial or ground imagery.

PPE detection

PPE detection uses computer vision to automatically verify that workers on construction and infrastructure sites are wearing required personal protective equipment. It flags missing hard hats, safety vests, and other gear in real time from camera feeds.

OCR · Retail Tech

Price tag reading

Automatically read prices, product names, and barcodes from retail shelf price tags using OCR. Converts photographed or scanned tags into structured text data.

Product detection

Product detection identifies and locates retail items on shelves, in carts, or across store imagery using bounding boxes. It powers automated inventory checks, planogram compliance, and checkout systems.

Classification · Retail Tech

Product recognition

Product recognition uses image classification to identify which retail product appears in a photo, matching it against a known catalog of SKUs. It turns a shelf, cart, or checkout image into a product label.

QR code detection

Locate and localize QR codes in images and video frames, returning bounding boxes for each code found. Useful as a front-end step before decoding, cropping, or routing documents.

Queue length detection

Computer vision that counts people waiting in line and measures queue length from overhead or wall-mounted cameras. Detects individuals and shopping carts in checkout and service areas to estimate wait conditions in real time.

Rebar counting

Automatically count rebar in bundles from a single photo using object detection. Replaces manual tally counting of steel reinforcement bars at delivery, fabrication, and inventory checkpoints.

Receipt OCR

Receipt OCR uses computer vision to detect and read text from scanned or photographed receipts, extracting fields like merchant name, line items, totals, and dates. It turns unstructured paper and image-based receipts into structured, machine-readable data.

Referee detection

Referee detection locates and tracks match officials in sports footage, distinguishing them from players so analytics pipelines don't confuse referees with athletes.

Classification · Healthcare Imaging

Retina disease detection

A computer vision workflow that classifies retinal fundus images to detect and grade diabetic retinopathy and other retinal conditions. It takes standard fundus photographs as input and outputs disease severity classifications.

Rivet inspection

Automated visual inspection of rivets on aerospace fuselage, wing, and panel assemblies to flag defects like missing, loose, or improperly seated rivets. Uses object detection to locate and classify each rivet and its condition in captured images.

Segmentation · Construction & Infrastructure

Road crack detection

Automatically detect and segment cracks in road surfaces from images captured by vehicle-mounted or handheld cameras. Outputs pixel-level masks that pinpoint crack location, extent, and type.

Road extraction from satellite

Automated road extraction from satellite and aerial imagery using instance segmentation to trace road networks pixel by pixel. Converts raw geospatial tiles into clean vector road maps.

Segmentation · Smart Cities & Traffic

Road segmentation

Road segmentation uses computer vision to identify and outline drivable road surfaces, lane markings, and adjacent features at the pixel level from camera or vehicle imagery.

Segmentation · Mining & Metals

Rock fragmentation analysis

Automated measurement of rock fragment size distribution from images of muck piles, conveyor belts, and haul truck loads using instance segmentation. Each rock is segmented individually so fragment dimensions and gradation can be computed.

Rooftop detection

Rooftop detection uses instance segmentation to identify and outline individual building roofs in aerial and satellite imagery. It captures precise roof boundaries, shapes, and extents for downstream measurement and mapping.

Rust detection

Segmentation-based detection of rust and corrosion on metal surfaces, pinpointing the exact affected regions in inspection images. Useful for automating visual quality control across manufacturing and asset inspection workflows.

Safety vest detection

Computer vision detection that identifies whether workers are wearing high-visibility safety vests in images and video from construction and infrastructure sites. Flags people with and without proper vests in real time.

Scaffolding detection

Computer vision workflow that detects scaffolding structures and their components in images and video from construction and infrastructure sites. Uses object detection to locate scaffolds, frames, and related elements for monitoring and compliance.

Scratch detection

Automated visual inspection that detects surface scratches on manufactured parts and finished goods using object detection. It flags scratched regions in images captured from inspection cameras or handheld devices.

Screw detection

Screw detection uses computer vision to locate and count screws in images of assembled products, fastener trays, and production lines. It flags missing, misaligned, or incorrectly seated screws during manufacturing and quality control.

Seal integrity inspection

Automated seal defect detection on packaging lines using object detection to flag incomplete, wrinkled, or contaminated seals before products ship. Runs on inline camera feeds to catch failures the human eye misses at line speed.

Seedling detection

Detect and localize individual seedlings in field or greenhouse images to support automated crop counting, stand assessment, and plant health monitoring.

Self checkout monitoring

Computer vision that watches self checkout lanes to detect scanned items, unscanned products, and customer actions in real time. Helps flag potential shrink and scanning errors as they happen.

Serial number reading

Automatically locate and read serial numbers stamped, printed, or laser-etched on parts and products using computer vision OCR. Turns camera images into structured, searchable text without manual data entry.

Sheep counting

A computer vision workflow that detects and counts sheep in images or video from farm cameras and drones. Useful for tracking flock size across pastures, pens, and gates.

Shelf monitoring

Automated shelf monitoring uses object detection to identify products, gaps, and stock levels on retail shelves from camera or mobile images. It flags out-of-stock items and misplaced products without manual audits.

Ship detection from satellite

Detect and localize ships in satellite and aerial imagery using object detection. Turns raw overhead pixels into structured vessel locations for maritime monitoring.

OCR · Logistics & Warehousing

Shipping label reading

Automatically locate and read shipping labels on parcels using computer vision, extracting text such as tracking numbers, addresses, and barcodes from images.

Shopping cart detection

Detect and locate shopping carts in retail images and video feeds using object detection. Useful for tracking cart availability, positioning, and movement across store and parking areas.

Shrinkage detection

A computer vision workflow that monitors retail environments to detect behaviors and events associated with inventory shrinkage, such as concealment, unscanned items, and unauthorized removal of goods. It runs object detection on camera feeds to flag potential loss events in real time.

Signature detection

Locate handwritten signatures within scanned documents, contracts, and forms using object detection. Returns bounding boxes around each signature so downstream systems can crop, verify, or route them.

Classification · Healthcare Imaging

Skin lesion classification

A computer vision workflow that classifies dermatoscopic and clinical skin images into lesion categories such as melanoma, nevus, and benign keratosis. Built to support skin lesion detection and triage in healthcare imaging pipelines.

SKU detection

Automated SKU detection identifies and localizes individual product units on shelves, pallets, and conveyor lines using object detection. It turns camera feeds and still images into structured data about what products are present and where.

Slag detection

Computer vision for detecting slag in molten metal streams and pour operations during steelmaking and casting. Flags slag carryover in real time so operators can catch it before it contaminates downstream product.

Segmentation · Security & Surveillance

Smoke detection

Instance segmentation that identifies and outlines smoke in camera imagery, distinguishing smoke plumes from fog, steam, and background clutter for early fire and hazard detection.

Soccer player detection

Soccer player detection uses computer vision to locate and track players on the pitch from broadcast or fixed-camera footage. It turns raw match video into structured position data for analysis.

Segmentation · Agriculture

Soil crack detection

Computer vision that segments cracks in soil surfaces from field or drone imagery, outlining each crack region at the pixel level. Useful for monitoring dryness, erosion, and structural soil health across farmland.

Solar panel defect detection

A computer vision workflow that inspects solar panels and identifies physical defects like cracks, hotspots, and soiling from imagery. Built for automating solar farm and rooftop array inspections.

Solar panel inspection

Automated visual inspection of solar panels using object detection to locate panels and flag physical defects across rooftop and utility-scale installations.

Solar potential rooftop segmentation

Segment rooftop surfaces from aerial and satellite imagery to estimate usable area for solar panel installation. Identifies roof planes, existing panels, and obstructions that reduce viable coverage.

Solder joint inspection

Automated visual inspection of solder joints on printed circuit boards to detect defects like insufficient solder, bridging, and cold joints. Uses object detection to flag problem joints from inline or bench camera images.

Stamp detection

Stamp detection locates rubber stamps, official seals, and ink imprints on scanned documents. It flags where each stamp appears so downstream systems can verify, crop, or route the document.

Steel surface defect detection

Automated visual inspection of steel surfaces to locate and classify defects like cracks, scratches, and inclusions on rolled or finished product. Uses object detection to flag flaws in real time on production lines.

Strawberry detection

Detect and locate individual strawberries in images and video from field cameras, greenhouse rigs, or harvesting robots. Useful for counting fruit, assessing ripeness, and guiding automated picking.

Streetlight detection

Streetlight detection uses computer vision to locate and classify streetlights and their components in imagery from street-level cameras, drones, or vehicle-mounted sensors. It automates asset identification across urban and roadway environments.

Surface defect detection

Automated visual inspection that locates and classifies surface defects like scratches, dents, and cracks on manufactured parts. Runs on production line cameras to flag flawed units in real time.

Surgical instrument detection

Computer vision that detects and localizes surgical instruments in images and video from the operating room or sterile processing area. Useful for automating instrument tracking, counting, and workflow monitoring.

Swimming pool detection

Detect swimming pools in aerial and satellite imagery using object detection. Takes drone or overhead photos and outputs bounding boxes around each pool.

Syringe detection

Computer vision that locates syringes in images and video, whether on a pharma production line, in an automated filling station, or in medical waste handling. Built on object detection to flag position, count, and orientation.

Table detection

Table detection locates tables within document images and PDFs so their structure can be extracted downstream. It draws bounding boxes around tabular regions to separate them from paragraphs, headers, and figures.

Table extraction

Detect and localize tables within document images so their contents can be extracted downstream. Built for document AI and OCR pipelines that need reliable table region detection before parsing rows and columns.

Tablet defect detection

Automated inspection of pharmaceutical tablets to flag surface defects like chips, cracks, and discoloration on production lines. Uses object detection to locate and classify defective units in camera images.

Tennis ball tracking

Detect and track the tennis ball across video frames to capture ball position, trajectory, and speed during play. Built for sports analytics teams working from broadcast or court-side camera feeds.

OCR · Media & Content Moderation

Text detection in images

Detect and localize text regions in photographs, screenshots, and user-generated media so downstream OCR can read them. Built for finding words on signs, packaging, and overlays anywhere in a scene.

Textile flaw detection

Automated visual inspection that detects fabric defects like holes, stains, and broken threads on textile production lines. Uses object detection to flag flaws in woven and knitted materials before they reach finished goods.

Thermal hotspot detection

Automatically detect thermal hotspots in infrared imagery of electrical and mechanical equipment, flagging overheating components before they fail.

Tile defect detection

Automated visual inspection of ceramic and porcelain tiles that flags surface defects like cracks, chips, and glaze flaws before they reach packaging or shipment.

Tire defect detection

Automated visual inspection of tires to identify surface and structural defects like cracks, bulges, and tread wear. Uses object detection to flag faulty tires before they reach customers or the road.

Segmentation · Automotive

Tire tread wear detection

Automated inspection of tire tread using instance segmentation to identify tread patterns, wear zones, and depth-related surface features from camera images. Built for automotive service, fleet, and manufacturing workflows.

Classification · Agriculture

Tomato ripeness detection

A computer vision workflow that classifies tomatoes by ripeness stage from images, distinguishing unripe, ripening, and fully ripe fruit for harvest and sorting decisions.

Tool detection

Tool detection uses computer vision to locate and identify hand tools and equipment in images or video feeds. It powers automated inventory, robotic pick-and-place, and workspace safety checks in robotics and automation settings.

Traffic congestion detection

A computer vision workflow that detects and counts vehicles on roadways to identify traffic congestion in real time from camera feeds. It classifies road segments as free-flowing or congested based on vehicle density and occupancy.

Traffic detection

Detect and classify vehicles and road users in traffic scenes from fixed cameras or drone footage. Built for object detection workflows that need per-object bounding boxes across cars, trucks, buses, and more.

Traffic light detection

Automatically detect and locate traffic lights in images and video streams, identifying signal position and state to support driving and traffic systems.

Traffic sign detection

Detect and classify traffic signs in images and video streams, identifying stop signs, speed limits, yield signs, and other roadway markers by type and location.

Transformer inspection

Detect defects and anomalies on electrical transformers from inspection imagery, flagging issues like oil leaks, corrosion, and damaged bushings automatically.

Transmission tower inspection

Detect transmission towers and their key structural components in aerial, drone, and ground-level imagery. Automates visual inspection of high-voltage transmission infrastructure across large service territories.

Tree detection from aerial imagery

Detect and segment individual tree canopies from aerial and drone imagery, outputting precise per-tree masks rather than bounding boxes. Useful for canopy mapping, tree counting, and vegetation analysis across large areas.

Truck detection

Truck detection uses computer vision to automatically identify and locate trucks in images or video feeds from cameras at warehouses, loading docks, and yard entrances. It supports real-time monitoring, gate automation, and yard management without manual observation.

Tumor detection

Automatically locate and bounding-box tumors in medical images such as MRI, CT, and ultrasound scans. A detection model flags suspicious regions to support radiologists in review.

Turbine blade inspection

Automated visual inspection of turbine blades to detect surface defects like cracks, nicks, and coating loss from inspection imagery. Built for aerospace maintenance teams evaluating computer vision for quality control.

Classification · Food & Beverage

Vegetable sorting

A computer vision workflow that classifies vegetables by type, quality, and ripeness on sorting lines. It takes camera images of produce and assigns each item a category label for grading or routing.

Segmentation · Energy & Utilities

Vegetation encroachment detection

Automatically detect and segment vegetation growing into power lines, transmission corridors, and utility infrastructure from aerial, drone, or vehicle-mounted imagery. Pinpoints exactly where trees and brush encroach on rights-of-way so crews can prioritize trimming.

Classification · Automotive

Vehicle classification

A computer vision workflow that classifies vehicles by type from images or video frames. It assigns each detected vehicle a category label such as car, truck, bus, or motorcycle.

Vehicle dent detection

Computer vision workflow that automatically locates and classifies dents on vehicle body panels from images. Built for automotive inspection, insurance claims, and rental fleet condition checks.

Vehicle detection

Vehicle detection locates and classifies cars, trucks, and other road vehicles in images or video frames. It's a foundational computer vision task for traffic monitoring, parking management, and automotive analytics.

Vehicle in restricted zone detection

A computer vision workflow that detects vehicles entering or parked in designated restricted zones using camera feeds. It flags unauthorized vehicles in real time to support security and surveillance operations.

Vehicle speed estimation

Estimate vehicle speed from camera footage by detecting and tracking vehicles across frames. Combines object detection with frame-to-frame motion analysis to calculate how fast each vehicle is moving.

Vial inspection

Automated visual inspection of pharmaceutical vials using object detection to flag cracks, particulates, fill-level errors, and closure defects on the production line.

OCR · Automotive

VIN reading

Automatically locate and read Vehicle Identification Numbers from photos of cars, dashboards, door jambs, and paperwork using computer vision OCR. Turns a raw image into a verified 17-character VIN string.

Wafer defect detection

Automated visual inspection of semiconductor wafers to locate and classify surface defects such as scratches, particles, and pattern anomalies. Uses object detection to flag failures on individual dies before packaging.

Warehouse worker safety detection

Computer vision that monitors warehouse floors to detect whether workers are wearing required safety gear and identify unsafe proximity to equipment. Runs on existing camera feeds to flag hazards in real time.

Detection · Media & Content Moderation

Watermark detection

Automatically locate watermarks, logos, and overlaid stamps in images and video frames. Useful for flagging copyrighted or branded content during moderation and asset review.

Weapon detection

Automatically detect firearms and knives in live video or images using object detection. Built for security teams that need to flag weapons the moment they appear on camera.

Weed detection

A computer vision workflow that locates and identifies weeds among crops in field imagery, enabling targeted intervention instead of blanket spraying.

Weld defect detection

Automatically identify defects in welded joints from inspection images, flagging issues like porosity, cracks, and undercut before parts move downstream.

Weld seam inspection

Automated visual inspection of weld seams using instance segmentation to identify weld beads and surface defects like porosity, cracks, and spatter. Turns camera images from the production line into pass/fail QC decisions.

Wheat head detection

Detect and count individual wheat heads in field images using object detection. Useful for yield estimation, phenotyping, and crop density analysis across varieties and growth stages.

Wheel detection

A computer vision workflow that locates and identifies wheels on vehicles in images and video. Useful for automotive inspection, assembly verification, and inventory tracking.

Wildfire detection from aerial

Segment fire and smoke regions in aerial imagery from drones and satellites to locate active wildfires and map their spread. Turns overhead camera feeds into pixel-level burn and smoke masks.

Wind turbine blade inspection

Automated detection of surface defects on wind turbine blades from drone or camera imagery, flagging cracks, erosion, and lightning damage for maintenance teams.

Windshield crack detection

Automatically detect cracks, chips, and other damage on vehicle windshields from images using object detection. Useful for inspection lines, insurance claims, and fleet maintenance.

Wood defect detection

Computer vision that inspects wood surfaces and boards to locate defects like knots, cracks, and stains. Built for automated grading and quality control on lumber and panel production lines.

Worker detection

Worker detection uses computer vision to locate and count people on construction sites from camera feeds and images. It identifies workers in real time to support safety monitoring, access control, and site awareness.

$X-ray fracture detection example$

X-ray fracture detection

Detect and localize bone fractures in X-ray images using object detection. Draws bounding boxes around fracture sites to flag potential breaks for radiologist review.