nms和iou

 

标准NMS(SNMS):

1)  所有检出的output bbox按cls score划分(对于正类进行划分)

2）bbox的cls score做降序排列，得到一个降序的order

3) 从order中top1 cls score 开始，计算该bbox 与 order中其他bbox的IOU，IOU大于阈值（说明为同一bbox），剔除

4）对order中所有的bbox进行上操作

 

import numpy as np
 
import numpy as np
 
def py_cpu_nms(dets, thresh):
    """Pure Python NMS baseline."""
    x1 = dets[:, 0]                #结果：[  30.   50.  210.  430.]
    y1 = dets[:, 1]
    x2 = dets[:, 2]
    y2 = dets[:, 3]
    scores = dets[:, 4]
    areas = (x2 - x1 + 1) * (y2 - y1 + 1)     #结果：[ 36381.  36081.  -5064.   2511.]
    # res是按照score降序排序的
    res = scores.argsort()[::-1]           #结果：[0 1 2 3]
    # print(res)
    # print(x1[res[0]])
 
    keep = []
    while res.size > 0:
        keep.append(res[0])
        xx1 = np.maximum(x1[res[0]], x1[res[1:]])      #res[1:] 由于每次都要与res[0]进行比较
        yy1 = np.maximum(y1[res[0]], y1[res[1:]])
        xx2 = np.minimum(x2[res[0]], x2[res[1:]])
        yy2 = np.minimum(y2[res[0]], y2[res[1:]])
 
        w = np.maximum(0.0, xx2 - xx1 + 1)
        h = np.maximum(0.0, yy2 - yy1 + 1)
        inter = w * h
        ovr = inter / (areas[res[0]] + areas[res[1:]] - inter)
        # 去除掉与分数重叠度大于设定阈值的anchor box（或滑框）
        inds = np.where(ovr <= thresh)[0]             #结果 训练3次  [1 2]表示，第二行，第三行各一个满足条件
        #返回满足条件的行索引（一行有几个满足条件，返回几次）

        # 真实行数=索引+1
        res = res[inds + 1]                       #结果 训练3次  [2 3]，[3]，[]
        print(res)
 
    return keep
 
# test
if __name__ == "__main__":
    dets = np.array([[30, 20, 230, 200, 1], [50, 50, 260, 220, 0.9], [210, 30, 420, 5, 0.8], [430, 280, 460, 360, 0.7]])
    thresh = 0.1
    keep_dets = py_cpu_nms(dets, thresh)
    print(keep_dets)

 

举例子：

import numpy as np
a = np.array([[0, 1, 2],
             [0, 2, 4],
             [0, 9, 6]])
b=np.where(a < 4)
print(b)

 结果：(array([0, 0, 0, 1, 1, 2], dtype=int64), array([0, 1, 2, 0, 1, 0], dtype=int64))

表示： 满足条件行数列表，满足条件列索引
 

 

 

 

2、计算IOU        # 标注方向 上左下右（逆时针）

def compute_iou(rec1, rec2):
    # computing area of each rectangles
    S1 = (rec1[2] - rec1[0]) * (rec1[3] - rec1[1])
    S2 = (rec2[2] - rec2[0]) * (rec2[3] - rec2[1])

    # computing the S
    S = S1 + S2

    # find the each edge of intersect rectangle     #并集面积
    left = max(rec1[1], rec2[1])
    right = min(rec1[3], rec2[3])
    top = max(rec1[0], rec2[0])
    bottom  = min(rec1[2], rec2[2])

    w=max(0,right-left)
    h=max(0,bottom-top)
    area=w*h

    return (area/ (S - area)) * 1.0

 

 

2.局部感知NMS(LNMS)

解决：文本检测面临的是成千上万个几何体（对与每个框）

提出：基