Field-of-View IoU for Object Detection in 360° Images
This addresses performance deterioration in object detection for 360° images, an incremental improvement for computer vision applications using such cameras.
The paper tackles object detection in distorted 360° equirectangular projection images by proposing Field-of-View IoU and 360Augmentation, which integrate with existing detectors and significantly improve performance, as shown in experiments on the 360indoor dataset.
360° cameras have gained popularity over the last few years. In this paper, we propose two fundamental techniques -- Field-of-View IoU (FoV-IoU) and 360Augmentation for object detection in 360° images. Although most object detection neural networks designed for the perspective images are applicable to 360° images in equirectangular projection (ERP) format, their performance deteriorates owing to the distortion in ERP images. Our method can be readily integrated with existing perspective object detectors and significantly improves the performance. The FoV-IoU computes the intersection-over-union of two Field-of-View bounding boxes in a spherical image which could be used for training, inference, and evaluation while 360Augmentation is a data augmentation technique specific to 360° object detection task which randomly rotates a spherical image and solves the bias due to the sphere-to-plane projection. We conduct extensive experiments on the 360indoor dataset with different types of perspective object detectors and show the consistent effectiveness of our method.