Intersection over Union(IoU) algorithms
阿新 • • 發佈：2018-12-06
IoU演算法可用與評估兩個多維度資料的相似度，舉一個實際應用，做CV，物件檢測，我們需要評估模型的識別準確率，不同於二元類問題，普通的評估演算法不合適，於是用到了這個演算法，這個演算法簡單易懂，評估效果也不錯。
這裡主要討論如何計算並評估兩個矩形相交程度。有空再訓練一個物件檢測器，來試試水。。
第一種對於資料形狀是這樣的 $ (x_{top-left}, y_{top-left}, w, h) $，意思是：給出了起始座標，矩形沿著 $ w, h $ 擴充套件開。
演算法實現：
double IoU(int*a, int*b)
{
int overlap_w = min(a[0] + a[2], b[0] + b[2]) - max(a[0], b[0]);
int overlap_h = min(a[1] + a[3], b[1] + b[3]) - max(a[1], b[1]);
int overlap_s = overlap_w*overlap_h;
return overlap_s / double(a[2]*a[3] + b[2]*b[3] - overlap_s);
}
第二種資料形狀是這樣的 $ (x_{top-left}, y_{top-left}, x_{right-down}, y_{right-down}) $，意思是：給出了起始座標和終點座標，如圖：
演算法實現：
double IoU_2(int*a, int*b)
{
int overlap_w = min(a[2], b[2]) - max(a[0], b[0]);
int overlap_h = min(a[3], b[3]) - max(a[1], b[1]);
int overlap_s = overlap_w*overlap_h;
return overlap_s / double((a[2] - a[0])*(a[3] - a[1]) + (b[2] - b[0])*(b[3] - b[1]) - overlap_s);
}
用這幾組資料測試一下：
1: [39, 63, 203, 112], [54, 66, 198, 114] 2: [49, 75, 203, 125], [42, 78, 186, 126] 3: [31, 69, 201, 125], [18, 63, 235, 135] 4: [50, 72, 197, 121], [54, 72, 198, 120] 5: [35, 51, 196, 110], [36, 60, 180, 108]
output:
0.825758 0.795771 ===================== 0.809624 0.787838 ===================== 0.791962 0.609319 ===================== 0.947743 0.946628 ===================== 0.79667 0.727656 =====================
參考：
1.https://www.pyimagesearch.com/2016/11/07/intersection-over-union-iou-for-object-detection/
2.https://en.wikipedia.org/wiki/Jaccard_index