创意灵感网站,中国新闻社领导名单,建设网站必备的三大要素,wordpress电影网站非极大值抑制(Non-Maximum Suppression#xff0c;NMS)#xff0c;顾名思义就是抑制不是极大值的元素#xff0c;可以理解为局部最大搜索。这个局部代表的是一个邻域#xff0c;邻域有两个参数可变#xff0c;一是邻域的维数#xff0c;二是邻域的大小。而是用于目标检测…非极大值抑制(Non-Maximum SuppressionNMS)顾名思义就是抑制不是极大值的元素可以理解为局部最大搜索。这个局部代表的是一个邻域邻域有两个参数可变一是邻域的维数二是邻域的大小。而是用于目标检测中提取分数最高的窗口的。例如在行人检测中滑动窗口经提取特征经分类器分类识别后每个窗口都会得到一个分数。但是滑动窗口会导致很多窗口与其他窗口存在包含或者大部分交叉的情况。这时就需要用到NMS来选取那些邻域里分数最高(是行人的概率最大)并且抑制那些分数低的窗口。Numpy  你语法都不懂就别往下看了图中的每个知识点都是一个小程序def stand_nms_non_max_suppression(boxes, probsNone, overlapThresh0.3, list_resNone):# if there are no boxes, return an empty listif len(boxes) 0:return []# if the bounding boxes are integers, convert them to floats -- this# is important since well be doing a bunch of divisionsif boxes.dtype.kind i:boxes boxes.astype(float)# initialize the list of picked indexespick []# grab the coordinates of the bounding boxesx1 boxes[:, 0]y1 boxes[:, 1]x2 boxes[:, 2]y2 boxes[:, 3]# compute the area of the bounding boxes and grab the indexes to sort# (in the case that no probabilities are provided, simply sort on the# bottom-left y-coordinate)area (x2 - x1 1) * (y2 - y1 1)idxs y2dt np.dtype([(age, np.int), (name, np.float)])# if probabilities are provided, sort on them insteadif probs is not None:idxs probs# sort the indexesidxs np.argsort(idxs)# keep looping while some indexes still remain in the indexes listwhile len(idxs) 0:# grab the last index in the indexes list and add the index value# to the list of picked indexeslast len(idxs) - 1i idxs[last]# pick.append(i)# find the largest (x, y) coordinates for the start of the bounding# box and the smallest (x, y) coordinates for the end of the bounding# boxxx1 np.maximum(x1[i], x1[idxs[:last]])yy1 np.maximum(y1[i], y1[idxs[:last]])xx2 np.minimum(x2[i], x2[idxs[:last]])yy2 np.minimum(y2[i], y2[idxs[:last]])# compute the width and height of the bounding boxw np.maximum(0, xx2 - xx1 1)h np.maximum(0, yy2 - yy1 1)# print(aaaa)xxx boxes[i][0]yyy boxes[i][1]# if len(list_res):#     print(xxx, yyy,list_res[int(yyy)][int(xxx)])# else:#     print(xxx, yyy)# print(bbbb,i)# compute the ratio of overlapoverlap (w * h) / area[idxs[:last]]list_similar np.where(overlap overlapThresh)# print(list_similar)# if 0:if len(list_similar) and len(list_res):get_max_list np.array([(i, list_res[int(yyy)][int(xxx)])], dtypedt)for x in np.nditer(list_similar):# print(x,,)xxx boxes[x][0]yyy boxes[x][1]nearly_rect_list np.array([(x,list_res[int(yyy)][int(xxx)])], dtypedt)get_max_list np.append(get_max_list, nearly_rect_list)after_sort np.sort(get_max_list, order[name, age])nLen1 len(after_sort) - 1# print(nLen1 ,after_sort[nLen1])# print(after_sort[nLen1][0],after_sort[nLen1][1])pick.append(after_sort[nLen1][0])else:pick.append(i)# delete all indexes from the index list that have overlap greater# than the provided overlap thresholdidxs np.delete(idxs, np.concatenate(([last],np.where(overlap overlapThresh)[0])))return boxes[pick].astype(int)