• 本文固定鏈接: https://www.lao-wang.com/?p=114
• 轉載: searky 2017年07月31日 于 老王的網站 發表

交并比（Intersection-over-Union，IoU），目標檢測中使用的一個概念，是產生的候選框（candidate bound）與原標記框（ground truth bound）的交疊率，即它們的交集與并集的比值。最理想情況是完全重疊，即比值為1。

計算公式：

Python實現代碼：

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的面積garea = (gx2 - gx1) * (gy2 - gy1) #G的面積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的面積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的面積garea = (gx2 - gx1) * (gy2 - gy1) #G的面積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的面積iou = area / (carea + garea - area)return iou<br /><br />

?

?

總結

以上是生活随笔為你收集整理的图像处理的交并比（IoU）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。