Occlusion Handling in Generic Object Detection: A Review

The significant power of deep learning networks has led to enormous\ndevelopment in object detection. Over the last few years, object detector\nframeworks have achieved tremendous success in both accuracy and efficiency.\nHowever, their ability is far from that of human beings due to several factors,\nocclusion being one of them. Since occlusion can happen in various locations,\nscale, and ratio, it is very difficult to handle. In this paper, we address the\nchallenges in occlusion handling in generic object detection in both outdoor\nand indoor scenes, then we refer to the recent works that have been carried out\nto overcome these challenges. Finally, we discuss some possible future\ndirections of research.\n