Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline
This work tackles the problem of accurate object detection for autonomous driving systems using fisheye cameras, which are prone to strong radial distortion.
This paper addresses object detection on fisheye cameras for autonomous driving, where standard bounding boxes fail due to radial distortion. The authors propose a novel curved bounding box model and a curvature-adaptive perimeter sampling method, achieving a 40.3% relative improvement in mIoU accuracy with their polygon model.
Object detection is a comprehensively studied problem in autonomous driving. However, it has been relatively less explored in the case of fisheye cameras. The standard bounding box fails in fisheye cameras due to the strong radial distortion, particularly in the image's periphery. We explore better representations like oriented bounding box, ellipse, and generic polygon for object detection in fisheye images in this work. We use the IoU metric to compare these representations using accurate instance segmentation ground truth. We design a novel curved bounding box model that has optimal properties for fisheye distortion models. We also design a curvature adaptive perimeter sampling method for obtaining polygon vertices, improving relative mAP score by 4.9% compared to uniform sampling. Overall, the proposed polygon model improves mIoU relative accuracy by 40.3%. It is the first detailed study on object detection on fisheye cameras for autonomous driving scenarios to the best of our knowledge. The dataset comprising of 10,000 images along with all the object representations ground truth will be made public to encourage further research. We summarize our work in a short video with qualitative results at https://youtu.be/iLkOzvJpL-A.