Tree detection from aerial imagery: Datasets & Models
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.
Tree detection from aerial imagery
This segmentation workflow performs tree canopy detection on aerial and drone imagery, producing a separate mask for each tree crown instead of a bounding box. It takes overhead images from drones, aircraft, or satellites as input, identifies individual tree canopies, and separates overlapping crowns from grass, shrubs, buildings, and bare ground.
Try it out
Powered by general detection model
Run on custom image
Drop an image here or click to upload
Why automate tree detection from aerial imagery
Manually digitizing tree canopy from aerial photos is slow, subjective, and impractical at the scale of a forest stand, orchard, or city tree inventory, where a single survey can cover thousands of acres. Automating this with segmentation turns hours of hand-tracing into a repeatable pipeline that measures canopy cover, tracks growth or loss over time, and flags stressed or missing trees. For drones and geospatial teams, this means faster deliverables and consistent measurements that hold up across projects and flights.
Key benefits
Instance segmentation gives you per-tree area and coverage metrics instead of rough estimates, and results plug directly into GIS workflows and existing drone imagery pipelines. The approach scales from a single field to region-wide mapping without adding labeling effort, and models can be retrained on your own orthomosaics to handle local species, resolutions, and sensor types.
How to use it
- Upload an image: Drop any photo into the widget above to try tree detection from aerial imagery for free, right on this page.
- Preview instant results: The model detects tree canopy, tree crown, shrub, bare ground, building 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 (instance segmentation) 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 tree detection from aerial imagery
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 tree detection from aerial imagery, fine-tune it on your own labeled images, then deploy to a Serverless Cloud API endpoint.
Not sure where to start?
Describe your Tree Detection From Aerial Imagery project to Roboflow Agent.