Swin-fisheye: Object detection for fisheye images

Fisheye cameras have been widely used in autonomous navigation, visual surveillance, and automatic driving. Due to severe geometric distortion, fisheye images cannot be processed effectively by conventional methods. The existing object detection algorithms cannot better detect the small targets or the objects with large distortion in the fisheye images. The size and scene of available fisheye datasets (such as WoodScape and VOC-360) cannot satisfy the training of robust network models. Herein, the authors propose Swin-Fisheye, an end-to-end object detection algorithm based on Swin Transformer. A feature pyramid module based on deformable convolution (DFPM) is designed to obtain richer contextual information from the multi-scale feature maps. In addition, a projection transformation algorithm (PTA) is proposed, which can convert rectilinear images into fisheye images more accurately, and then create a fisheye image dataset (COCO-Fish). The results of extensive experiments conducted on VOC-360, WoodScape, and COCO-Fish demonstrate that the proposed algorithm can achieve satisfactory results compared with state-of-the-art methods. The authors propose Swin-Fisheye, an end-to-end object detection algorithm based on Swin Transformer. A feature pyramid module based on deformable convolution (DFPM) is designed to obtain richer contextual information from the multi-scale feature maps. Projective transformation algorithm (PTA) is also proposed, which can convert rectilinear images into fisheye images more accurately, and create a fisheye image dataset (COCO-Fish). image