Crop disease detection: Datasets & Models
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 disease detection
This crop disease detection workflow runs an object detection model on images of plants and foliage to locate and label visual symptoms, drawing bounding boxes around affected regions and classifying them by disease type such as leaf spots, blight, and rust. It accepts imagery from drones, handheld cameras, scouting phones, or fixed field and greenhouse cameras, making it suitable for both in-field scouting and controlled monitoring.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate crop disease detection
Manual crop scouting is slow, labor-intensive, and inconsistent: agronomists can only inspect a fraction of a field, and early-stage infections are easy to miss until they spread. Automating disease detection with computer vision lets growers process thousands of images from drones or mobile devices and flag outbreaks before they escalate, enabling targeted spraying instead of blanket application. This reduces chemical costs, protects yield, and gives teams a repeatable, data-driven record of plant health across seasons and locations.
Key benefits
Teams get earlier, more consistent detection of infected plants across large acreages without adding scouting staff, and can prioritize interventions where they matter most. The model runs on imagery from cameras and drones you likely already operate, and scales from a single greenhouse to multi-field deployments. Built on RF-DETR, the detection pipeline handles cluttered canopy scenes and can be retrained as new diseases or crops are added.
How to use it
- Upload an image: Drop any photo into the widget above to try crop disease detection for free, right on this page.
- Preview instant results: The model detects diseased leaf, leaf lesion, fungal spot, wilted plant, healthy leaf within seconds and returns an annotated image with structured predictions, so you can immediately see how well it works. Adjust the detection classes and re-run until the results fit your scenario.
- Like what you see?: With a free Roboflow account, you can deploy this workflow with the Serverless Cloud API, customize it in your workspace, or train RF-DETR on your own images for production accuracy.
- Get started for free: No code or training data required to begin: upload, review the results, and make it part of your stack in a single click.
Recommended model for crop disease detection
RF-DETR is state of the art for real-time object detection, instance segmentation, and keypoint detection, with higher accuracy and lower latency than comparable models, and it's Apache 2.0 licensed. When you're ready to build a production model for crop disease detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Crop Disease Detection project to Roboflow Agent.