【CV基石】Soft-NMS

 
import numpy as np
 
# 定义一个nms函数
def soft_nms(dets, thresh=0.3, sigma=0.5): # score大于thresh的才能存留下来，当设定的thresh过低，存留下来的框就很多,所以要根据实际情况调参
    '''
    input：
        dets: dets是(n,5)的ndarray，第0维度的每个元素代码一个框：[x1, y1, x2, y2, score] 
        thresh: float
        sigma: flaot
    output：
        index
    '''
 
    x1 = dets[:, 0] # dets:(n,5)  x1:(n,)  dets是ndarray, x1是ndarray
    y1 = dets[:, 1]
    x2 = dets[:, 2]
    y2 = dets[:, 3]
    scores = dets[:, 4] # scores是ndarray
 
 
    # 每一个候选框的面积
    areas = (x2 - x1 + 1) * (y2 - y1 + 1) # areas:(n,)
 
    # order是按照score降序排序的
    order = scores.argsort()[::-1] # order:(n,) 降序下标 order是ndarray
 
 
    keep = []
    while order.size > 0:
        i = order[0] # i 是当下分数最高的框的下标
        # print(i)
        keep.append(i)
        # 计算当前概率最大矩形框与其他矩形框的相交框的坐标，会用到numpy的broadcast机制，得到的是向量
 
        # 当order只有一个值的时候，order[1]会报错说index out of range，而order[1:]会是[]，不报错，[]也可以作为x1的索引，x1[[]]为[]
   
        xx1 = np.maximum(x1[i], x1[order[1:]]) # xx1:(n-1,)的ndarray x1[i]:numpy_64浮点数一个，x1[order[1:]]是个ndarray，可以是空的ndarray，如果是空ndarray那么xx1为空ndarray，如果非空，那么x1[order[1:]]有多少个元素，xx1就是有多少个元素的ndarray。x1[]是不是ndarray看中括号内的是不是ndarray，看中括号内的是不是ndarray看中括号内的order[]的中括号内有没有冒号，有冒号的是ndarray，没有的是一个数。
        yy1 = np.maximum(y1[i], y1[order[1:]])
        xx2 = np.minimum(x2[i], x2[order[1:]])
        yy2 = np.minimum(y2[i], y2[order[1:]])
        
 
        # 计算相交框的面积,注意矩形框不相交时w或h算出来会是负数，用0代替
        w = np.maximum(0.0, xx2 - xx1 + 1) # xx2-xx1是(n-1,)的ndarray，w是(n-1,)的ndarray, n会逐渐减小至1
        # 当xx2和xx1是空的，那w是空的
        h = np.maximum(0.0, yy2 - yy1 + 1)
 
        inter = w * h # inter是(n,)的ndarray
        # 当w和h是空的，inter是空的
 
        # 计算重叠度IOU：重叠面积/（面积1+面积2-重叠面积）
        eps = np.finfo(areas.dtype).eps # 除法考虑分母为0的情况，np.finfo(dtype).eps，np.finfo(dtype)是个类，它封装了机器极限浮点类型的数，比如eps，episilon的缩写，表示小正数。
        ovr = inter / np.maximum(eps, areas[i] + areas[order[1:]] - inter) # n-1   #一旦（面积1+面积2-重叠面积）为0，就用eps进行替换
        # 当inter为空，areas[i]无论inter空不空都是有值的，那么ovr也为空
 
        # 更新分数
        weight = np.exp(-ovr*ovr/sigma)
        scores[order[1:]] *= weight
 
        # 更新order
        score_order = scores[order[1:]].argsort()[::-1] + 1
        order = order[score_order]
 
        keep_ids = np.where(scores[order]>thresh)[0]
 
        order = order[keep_ids]
 
 
    return keep
 
 
import numpy as np
import cv2
 
# 读入图片，录入原始人框（[x1, y1, x2, y2, score]）
image = cv2.imread('w.jpg')
 
boxes = np.array([
    [5,	52,	171, 270, 0.9999],
    [13, 1,	179, 268, 0.9998],
    [20, 7,	176, 262, 0.8998],
    [7,	5, 169,	272, 0.9687],
    [3,	43,	162, 256, 0.9786],
    [10, 56, 167, 266, 0.8988]
])
 
 
# 将框绘制在图像上
image_for_nms_box = image.copy()
for box in boxes:
    x1, y1, x2, y2, score = int(box[0]), int(box[1]), int(box[2]), int(box[3]), box[4] # x:col y:row
    image_for_nms_box = cv2.rectangle(image_for_nms_box, (x1, y1), (x2, y2), (0,255,0), 2)
cv2.imwrite("w_all.jpg", image_for_nms_box)
cv2.imshow('w_all', image_for_nms_box)
 
# 使用soft_nms对框进行筛选
keep = soft_nms(boxes)
soft_nms_boxs = boxes[keep]
 
# 将筛选过后的框绘制在图像上
image_for_nms_box = image.copy()
for box in soft_nms_boxs:
    x1, y1, x2, y2, score = int(box[0]), int(box[1]), int(box[2]), int(box[3]), box[4]
    image_for_nms_box = cv2.rectangle(image_for_nms_box, (x1, y1), (x2, y2), (0,255,0), 2)
# Syntax: cv2.imwrite(filename, image)
cv2.imwrite("w_soft_nms.jpg", image_for_nms_box)
cv2.imshow('w_soft_nms', image_for_nms_box)
 
cv2.waitKey()
cv2.destroyAllWindows()
 
 

https://blog.csdn.net/AliceH1226/article/details/123429849