Robust Target Detection and Localization for UAV Autonomous Landing with Partially Occluded Targets

This paper presents an approach for robust target detection and localization in the context of UAV autonomous landing with partially occluded targets. Since the performance of the autonomous landing system largely depends on the accurate detection and positioning of the landing target, it is very important to deal with the local occlusion caused by obstacles or environmental factors. In order to improve the overall performance of the system, we propose a fault-tolerant target detection method and target completion strategy. The proposed target detection method combines image processing technology with feature extraction algorithm, which can recognize and locate the landing target even in the case of occlusion. The target completion strategy aims to recover the missing part of the occluded target and make the detection and location algorithm execute more reliably. We perform experiments on image data sets with different horizontal object occlusion to evaluate the performance of the proposed method. The results show that our method successfully detects and locates the landing target under different occlusion levels, and significantly improves the performance of UAV autonomous landing system in the real scene.