ORB-Livox: A Real-time Dynamic System for Fruit Detection and Localization

Congratulations to Tianhao for the acceptance of “ORB-Livox: A Real-time Dynamic System for Fruit Detection and Localization.” for publication in Computers and Electronics in Agriculture. This work introduces an accurate fruit localization method under dynamic conditions. Firstly, an ORB-SLAM3 SLAM algorithm is utilised to estimate the camera’s pose under dynamic conditions. Secondly, YOLO-V5 is used to identify apples in RGB images. Moreover, Lidar is used to measure the depth of each apple accurately. Finally, a clustering technique based on the Gaussian distribution is proposed to mitigate the accuracy loss under dynamic conditions to optimize apple positions. The experimental result in an orchard environment demonstrates that the proposed method can detect and localize apples under dynamic conditions in unstructured natural environments.