Unbiased IoU for Spherical Image Object Detection
This addresses a specific challenge in spherical image object detection, offering an incremental improvement over existing biased or approximate methods.
The paper tackled the problem of inaccurate intersection-over-union (IoU) calculation for object detection in spherical images by introducing unbiased spherical rectangles and an analytical method without approximations, resulting in better performance on two datasets.
As one of the most fundamental and challenging problems in computer vision, object detection tries to locate object instances and find their categories in natural images. The most important step in the evaluation of object detection algorithm is calculating the intersection-over-union (IoU) between the predicted bounding box and the ground truth one. Although this procedure is well-defined and solved for planar images, it is not easy for spherical image object detection. Existing methods either compute the IoUs based on biased bounding box representations or make excessive approximations, thus would give incorrect results. In this paper, we first identify that spherical rectangles are unbiased bounding boxes for objects in spherical images, and then propose an analytical method for IoU calculation without any approximations. Based on the unbiased representation and calculation, we also present an anchor free object detection algorithm for spherical images. The experiments on two spherical object detection datasets show that the proposed method can achieve better performance than existing methods.