Research on the multitarget 3D trajectory tracking method of in the thermal infrared region based on YOLOX-GMM and SORT-Pest.

Introduction: Studying the behavioral responses and movement trajectories of insects under different stimuli is crucial for developing more effective biological control measures. Therefore, accurately obtaining the movement trajectories and behavioral parameters of insects in three-dimensional space is essential.

Methods: This study used the litchi pest as the research object. A special binocular vision observation system was designed for nighttime movement. A thermal infrared camera was used for video recording of in a lightless environment. Moreover, a multi-object tracking method based on the YOLOX-GMM and SORT-Pest algorithms was proposed for tracking in thermal infrared images. By obtaining the central coordinates of the two in the video, target matching and 3D trajectory reconstruction in the parallel binocular system were achieved.

Results: Error analysis of the detection and tracking model, as well as the 3D reconstruction model, showed that the average accuracy of detection reached 89.6%, tracking accuracy was 96.9%, and the average error of the reconstructed 3D spatial coordinates was 15 mm.

Discussion: These results indicate that the method can accurately obtain the 3D trajectory and motion parameters of . Such data can greatly contribute to researchers' comprehensive understanding of insect behavioral patterns and habits, providing important support for more targeted control strategies.