快速NMS算法无重叠抑制盒

2024-03-29 07:02:23 发布

您现在位置:Python中文网/ 问答频道 /正文

我正在测试Fast NMS algorithm by Malisiewicz et al。我在运行示例时注意到,在一个例子中,如果我输入两个没有重叠的特定框,并且IoU阈值低于大约0.75,那么仍然会抑制一个框。在

我误解NMS了吗?我认为如果它们之间没有重叠,就不应该丢弃任何框,不管IoU阈值设置在哪里。在

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))

Tags: oftheboxreturnnplistlastx1
1条回答
网友
1楼 · 发布于 2024-03-29 07:02:23

您的输入测试用例是不合法的,参数boxes期望框坐标为绝对格式,例如像素坐标。在

您可以注意到,当计算所有长方体的面积时

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

+1是一个添加的像素,确保area是方框实际占用的像素数。在

试试这个:

^{pr2}$

相关问题 更多 >