之前有简单提过IOU,在学习目标检测,和人脸识别的时候都有提到,所以打算认真学一下。
在目标检测的评价体系中,有一个参数叫做 IoU ,简单来讲就是模型产生的目标窗口和原来标记窗口的交叠率。
# ((x1[i], y1[i]), (x2[i], y2[i]))
areai = (x2[i]-x1[i]+1)*(y2[i]-y1[i]+1)
areaj = (x2[j]-x1[j]+1)*(y2[j]-y1[j]+1)
xx1 = max(x1[i], x1[j])
xx2 = min(x2[i], x2[j])
yy1 = max(y1[i], y1[j])
yy2 = min(y2[i], y2[j])
h = max(0, yy2-yy1+1)
w = max(0, xx2-xx1+1)
intersection = w * h#相交的面积
iou = intersection / (areai + areaj - intersection)#(2面积之和-相交面积)
参考
https://blog.csdn.net/lanchunhui/article/details/71190055