This page is being translated by your browser

Translation can break parts of Roboflow. If something stops working, turn translation off and reload the page.

Detection · Drones & Geospatial

Swimming pool detection: Datasets & Models

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

Swimming pool detection example
1M+
developers
16k
organizations
50B
inferences

Swimming pool detection

This detection workflow processes overhead imagery from drones, aircraft, and satellites to identify swimming pools and return bounding box coordinates for each one. Trained on a swimming pool dataset, it locates both in-ground and above-ground pools so you can inventory, count, or map them across wide geographic areas.

Try it out

Powered by general detection model

Run on custom image

Drop an image here or click to upload

Detecting classes:

Why automate swimming pool detection

Manually reviewing thousands of aerial tiles to find pools is slow, tedious, and inconsistent, whether the goal is property assessment, insurance risk analysis, permit compliance, or mosquito abatement. Analysts miss pools, disagree on edge cases, and cannot keep pace with fresh imagery captures. Automating detection with a model lets geospatial and drone teams process entire counties in hours instead of weeks, flagging new or unpermitted pools automatically. The result is a repeatable, auditable pipeline that scales with imagery volume rather than headcount.

Key benefits

Detection runs directly on imagery from your existing drone flights or satellite feeds, so there is no new hardware to deploy. RF-DETR delivers strong accuracy on small objects viewed from above and handles the visual variety of pool shapes, colors, and lighting conditions. Once trained, the workflow scales from a single neighborhood to region-wide surveys and re-runs automatically as new imagery arrives.

How to use it

  1. Upload an image: Drop any photo into the widget above to try swimming pool detection for free, right on this page.
  2. Preview instant results: The model detects swimming pool, above-ground pool, pond, hot tub, pool cover 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.
  3. 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.
  4. 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

Recommended model for swimming pool 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 swimming pool detection, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.

Train your own model
Roboflow Agent

Not sure where to start?

Describe your Swimming Pool Detection project to Roboflow Agent.

Agent