快速NMS算法会抑制没有重叠的盒子

Question

我正在测试Malisiewicz等人的快速NMS算法。我注意到在示例中跑步时，如果我输入了两个没有重叠的特定盒子，并且阈值低于大约0.75，则无论如何都会抑制一个盒子。

我误解了NMS吗？我认为如果它们之间的重叠零，则不应丢弃任何盒子，无论设置在哪里。

示例：

import numpy as np
def non_max_suppression_fast(boxes, overlapThresh):
    # if there are no boxes, return an empty list
    if len(boxes) == 0:
        return []
    # 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]
    # compute the area of the bounding boxes and sort the bounding
    # boxes by the bottom-right y-coordinate of the bounding box
    area = (x2 - x1 + 1) * (y2 - y1 + 1)
    idxs = np.argsort(y2)
    # 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]

# Two test boxes
                   #xmin,ymin,xmax,ymax
boxes = np.vstack([[0.3, 0.2, 0.4, 0.5], 
                  [0.1, 0.1, 0.2, 0.2]])

# no box suppression
print(non_max_suppression_fast(boxes, overlapThresh=.75))
# one box is suppressed
print(non_max_suppression_fast(boxes, overlapThresh=.74))

Answer 1

您的输入测试用例不合法，参数boxes期望框以绝对格式的盒子坐标，例如。在像素坐标中。

您可以注意到，在计算所有盒子的区域时，它是

area = (x2 - x1 + 1) * (y2 - y1 + 1)

+1是一个添加的像素，确保area是盒子占据的实际像素数。

尝试以下操作：

boxes = np.vstack([[3, 2, 4, 5], 
              [1, 1, 2, 2]])