Static Object Detection and Localization Technology Based on Multi Machine Information Fusion

In view of the problems of low detection efficiency, low accuracy and inaccurate target positioning of UAV static object, this paper proposes an object detection and localization technology based on multi-UAVS information fusion. Firstly, this paper designs a differentiated search algorithm for convex areas based on region segmentation for UAV formations, and conducts a coverage search of the target area. Secondly, the RT-DETR algorithm is improved, and its pre-processing and post-processing are modified. Finally, a target precise positioning algorithm based on K-means is proposed, which fuses the information of a single aircraft in the UAV formation. Experiments are carried out on the dataset constructed by the project team, and the results show that the proposed algorithm can greatly improve the accuracy and efficiency of object detection and positioning.