交并比(Intersection-over-Union,IoU):

目标检测中使用的一个概念
是产生的候选框(candidate bound)与原标记框(ground truth bound)的交叠率
它们的交集与并集的比值。最理想情况是完全重叠,即比值为1。

基础知识:

交集:
集合论中,设A,B是两个集合,由所有属于集合A且属于集合B的元素所组成的集合,叫做集合A与集合B的交集,记作A∩B。

eg:
A={1,2,3} B={2,3,4}
A n B = {2,3}

并集:
给定两个集合A,B,把他们所有的元素合并在一起组成的集合,叫做集合A与集合B的并集,记作A∪B,读作A并B。
eg:
A={1,2,3} B={2,3,4}
A U B = {1,2,3,4}

图示

目标检测 IOU(交并比) 理解笔记-LMLPHP

IOU:
目标检测 IOU(交并比) 理解笔记-LMLPHP

python实现

import numpy as np
def compute_iou(box1, box2, wh=False):
"""
compute the iou of two boxes.
Args:
box1, box2: [xmin, ymin, xmax, ymax] (wh=False) or [xcenter, ycenter, w, h] (wh=True)
wh: the format of coordinate.
Return:
iou: iou of box1 and box2.
"""
if wh == False:
xmin1, ymin1, xmax1, ymax1 = box1
xmin2, ymin2, xmax2, ymax2 = box2
else:
xmin1, ymin1 = int(box1[0]-box1[2]/2.0), int(box1[1]-box1[3]/2.0)
xmax1, ymax1 = int(box1[0]+box1[2]/2.0), int(box1[1]+box1[3]/2.0)
xmin2, ymin2 = int(box2[0]-box2[2]/2.0), int(box2[1]-box2[3]/2.0)
xmax2, ymax2 = int(box2[0]+box2[2]/2.0), int(box2[1]+box2[3]/2.0) ## 获取矩形框交集对应的左上角和右下角的坐标(intersection)
xx1 = np.max([xmin1, xmin2])
yy1 = np.max([ymin1, ymin2])
xx2 = np.min([xmax1, xmax2])
yy2 = np.min([ymax1, ymax2]) ## 计算两个矩形框面积
area1 = (xmax1-xmin1) * (ymax1-ymin1)
area2 = (xmax2-xmin2) * (ymax2-ymin2) inter_area = (np.max([0, xx2-xx1])) * (np.max([0, yy2-yy1])) #计算交集面积
iou = inter_area / (area1+area2-inter_area+1e-6) #计算交并比 return iou

参考

https://blog.csdn.net/sinat_34474705/article/details/80045294
https://blog.csdn.net/mdjxy63/article/details/79343733

05-11 13:32