Occlusion Handling in Generic Object Detection: A Review

TL;DR

This review paper discusses the challenges of occlusion in generic object detection, summarizes recent methods addressing these issues, and explores future research directions to improve detection performance under occlusion.

Contribution

It provides a comprehensive overview of occlusion handling techniques in object detection and highlights key challenges and future research opportunities.

Findings

Recent methods improve detection accuracy under occlusion

Occlusion varies by location, scale, and ratio

Future directions include advanced modeling and datasets

Abstract

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