图像处理的交并比（IoU）

• 本文固定链接: https://www.lao-wang.com/?p=114
• 转载: searky 2017年07月31日 于 老王的网站 发表

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，即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。

计算公式：

Python实现代码：

def calculateIoU(candidateBound, groundTruthBound):
    cx1 = candidateBound[0]
    cy1 = candidateBound[1]
    cx2 = candidateBound[2]
    cy2 = candidateBound[3]

    gx1 = groundTruthBound[0]
    gy1 = groundTruthBound[1]
    gx2 = groundTruthBound[2]
    gy2 = groundTruthBound[3]

    carea = (cx2 - cx1) * (cy2 - cy1) #C的面积
    garea = (gx2 - gx1) * (gy2 - gy1) #G的面积

    x1 = max(cx1, gx1)
    y1 = max(cy1, gy1)
    x2 = min(cx2, gx2)
    y2 = min(cy2, gy2)
    w = max(0, x2 - x1)
    h = max(0, y2 - y1)
    area = w * h #C∩G的面积

    iou = area / (carea + garea - area)

    return iou

def calculateIoU(candidateBound, groundTruthBound): cx1 = candidateBound[0] cy1 = candidateBound[1] cx2 = candidateBound[2] cy2 = candidateBound[3] gx1 = groundTruthBound[0] gy1 = groundTruthBound[1] gx2 = groundTruthBound[2] gy2 = groundTruthBound[3] carea = (cx2 - cx1) * (cy2 - cy1) #C的面积 garea = (gx2 - gx1) * (gy2 - gy1) #G的面积 x1 = max(cx1, gx1) y1 = max(cy1, gy1) x2 = min(cx2, gx2) y2 = min(cy2, gy2) w = max(0, x2 - x1) h = max(0, y2 - y1) area = w * h #C∩G的面积 iou = area / (carea + garea - area) return iou