OARPD: occlusion-aware rotated people detection in overhead fisheye images

The mainstream rotated object detection primarily focus on remote sensing images. However, people detection under fisheye images, compared to remote sensing image detection tasks, often faces significant occlusion phenomena. Currently, there is a lack of comprehensive research specifically targeting occlusion issues in overhead fisheye images. Therefore, this paper proposes an occlusion-aware rotated people detection in overhead fisheye images. To address the prevalent occlusion problem in overhead fisheye images, we design a rotated detection network model based on YOLOv8. In the network structure, AFPN is introduced into the Neck of YOLOv8 to improve the network’s feature extraction capability. We propose a mechanism for allocating positive and negative samples based on the Center Distance Intersection over Union (CDIoU) and incorporate Center Distance Loss into the regression loss function. Lastly, we design a training strategy for fisheye images and introduce DIoU-NMS to further enhance the robustness against occlusion issues. Experimental results demonstrate the effectiveness of our approach.