Oil palm tree counting in drone images

When the images are captured by drones, the effect of oblique angles, distance variations and open en-vironment are the main challenges for successful palm tree detection. This paper presents a method to-wards palm tree counting in Drone images using a novel idea of detecting dominant points by exploring Generalized Gradient Vector Flow, which defines symmetry based on gradient direction of the pixels. For each dominant point, we use angle information for classifying diagonal dominant points. It is intuition that the direction of the branches of tree converges at center of tree irrespective of the type of tree and plants. This observation motivated us to expand the direction of diagonal dominant points until it finds intersection point with another diagonal dominant point and this results in candidate points. For each candidate point, the proposed method constructs the ring by considering the distance between the in-tersection point and nearest neighbor candidate point as radius. This outputs region of interest and it includes center of each tree in the image. To ease the effect of complex background, we explore YOLOv5 architecture to remove false region of interests. This step results in counting oil palm trees in the mages irrespective of tree type of palm family. Experimental results on our dataset of the images captured by drones and standard dataset of coconut images captured by unmanned aerial vehicle of different trees show that the proposed method is effective and performs better than SOTA methods. (c) 2021 Published by Elsevier B.V.

Automated summary

This paper presents a novel method for palm tree counting in drone images by exploring Generalized Gradient Vector Flow. The method classifies diagonal dominant points using angle information and expands their directions to find candidate points, constructing rings to output regions of interest. By utilizing the YOLOv5 architecture, false regions of interest are removed, resulting in effective palm tree counting in images captured by drones. Experiment results show that this method outperforms SOTA approaches.