Geometry aware clustering improves detection of overlapping plants in drone images
Combining Object Detection with Geometry-Aware Clustering to Distinguish Overlapping Plants in UAV Imagery
Computer Vision and Pattern Recognition
Summary
It can be hard to tell where one plant ends and another begins in pictures taken from drones because plants grow close together and overlap. The authors created a method that looks at the shapes and positions of plant parts inside each detected plant area to figure out if there are really two plants stuck together. Their method uses simple math techniques like clustering points that represent leaf centers and special intersection points. This helps separate plants better without needing complicated extra tools or new training, making plant monitoring more accurate for farmers.
What this means in practice
- •For precision agriculture teams: Improve automated crop monitoring accuracy by distinguishing overlapping plants in UAV images using geometric clustering without new sensors or retraining.
- •For agricultural robotics developers: Enable better plant-level data extraction from drone images to support robotic crop management systems in dense canopy environments.
Authors
Ik Jae Lee, Hieu D. Nguyen, Mahbubur Meenar, Carlos Morrison Martinez, Cameron Connelly
Abstract
Reliable plant-level information from unmanned aerial vehicle (UAV) imagery is important for automated crop monitoring. However, in dense crop canopies, adjacent plants frequently overlap and are detected as a single object, reducing the reliability of plant-level measurements. This study presents a geometry-aware post-detection framework for resolving overlapping plant instances using standard RGB UAV imagery. The framework combines object detection with geometric clustering of plant components. Leaves or branches detected within each bush-level region are represented using two complementary geometric features: component centroids and radial intersection points (RIPs) derived from detected plant structures. K-means and Gaussian mixture models determine whether a detected region contains a single plant or two overlapping plants. Density filtering suppresses spurious radial intersections, and a post-pipeline ensemble combines spatial and directional geometric information. The framework was evaluated using UAV imagery of eggplant and tomato crops under field conditions. Centroid-based clustering achieved an F1-score of 0.89 for eggplant, while the combined centroid-RIP approach achieved the best tomato performance, with an accuracy of 0.80, precision of 1.00, and F1-score of 0.75 using K-means. Density filtering substantially improved RIP-based clustering for tomato. The proposed approach provides a lightweight, modular engineering solution that can be integrated with existing RGB UAV monitoring pipelines without additional depth sensors, pixel-level segmentation, three-dimensional reconstruction, or retraining of the primary bush detector. The results demonstrate that geometric reasoning applied to existing detector outputs can complement deep-learning-based object detection and improve plant-level interpretation in dense agricultural canopies.