IOU 与 IOF

IOU 与 IOF

IOU是指：重叠区域/联合区域的面积，也就是box1与box2的交集面积和并集面积的比例。

IOF是指：重叠区域/前景区域编辑，也就是box1与box2的交集面积和box1面积的比例。

参考资料：https://github.com/open-mmlab/mmdetection/issues/393

IoU is used most of the time. I think that IoF may be used in NMS processing, for example, you’ve got two detection bboxes of ‘person’ class, one bbox surrounded person completely and another surrounded only upper part of the same person, in this situation the IoU may be less than 0.5 but IoF is 1.0, choosing IoU>0.5 as the threshold may not suppress duplicate bbox and IoF>0.5 works well.

典型使用场景是NMS处理阶段，如果两个box重叠，一个box完全包含另一个box，但是第二个box的IOU可能不足0.5，但是IOF可能高达1，这种情况下利用IOF判据就能达到删除重复框的目的。