NMS——非极大值抑制-优快云博客

该博客介绍了非极大值抑制（NMS）算法在行人检测中的作用，通过消除滑动窗口检测中高重叠区域的重复框，只保留得分最高的边界框。文章提供了一个Python实现的NMS快速算法，包括步骤详解和代码展示，用于选择得分最高的边界框并抑制低得分框。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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，并且抑制那些分数低的窗口。
参考python算法

(Faster) Non-Maximum Suppression in Python - PyImageSearch

#参数 boxes 为矩形框，overlapThresh为阈值
def non_max_suppression_fast(boxes, overlapThresh):
  # if there are no boxes, return an empty list
  if len(boxes) == 0:
    return []

  print('boxes shape:',boxes.shape)
  # initialize the list of picked indexes 
  pick = []

  # grab the coordinates of the bounding boxes
  x1 = boxes[:,0]
  y1 = boxes[:,1]
  x2 = boxes[:,2]
  y2 = boxes[:,3]
  scores = boxes[:,4]
  # compute the area of the bounding boxes and sort the bounding
  # boxes by the score/probability of the bounding box
  area = (x2 - x1 + 1) * (y2 - y1 + 1)
  idxs = np.argsort(scores)[::-1]

  # keep looping while some indexes still remain in the indexes
  # list
  while len(idxs) > 0:
    # grab the last index in the indexes list and add the
    # index value to the list of picked indexes
    last = len(idxs) - 1
    i = 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 box
    xx1 = 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 box
    w = np.maximum(0, xx2 - xx1 + 1)
    h = np.maximum(0, yy2 - yy1 + 1)

    # compute the ratio of overlap
    overlap = (w * h) / area[idxs[:last]]

    # delete all indexes from the index list that have
    idxs = np.delete(idxs, np.concatenate(([last],
      np.where(overlap > overlapThresh)[0])))

  # return only the bounding boxes that were picked
  return boxes[pick]