Non-Maximum Suppression for Object Detection in Python

最新推荐文章于 2021-09-09 23:28:35 发布

northeastsqure

最新推荐文章于 2021-09-09 23:28:35 发布

阅读量1.7k

点赞数

分类专栏：计算机视觉

计算机视觉专栏收录该内容

24 篇文章

订阅专栏

本文通过实例演示了非最大抑制（Non-Maximum Suppression, NMS）算法的具体实现过程，该算法主要用于去除多余的边界框，减少误检，提高目标检测的准确性。文章通过Python代码解释了NMS的工作原理，并展示了如何应用于实际图像中。

之前看很多的nms 解释都没看懂，看了代码，注释比较好，就懂了，原文有更多解释，更快实现.

想法是只留下不重合的框，过程是任何一框，与其它任何一筐，重合超过一个值，去掉它。
http://www.pyimagesearch.com/2014/11/17/non-maximum-suppression-object-detection-python/?utm_source=tuicool&utm_medium=referral

# import the necessary packages
import numpy as np


#  Felzenszwalb et al.
def non_max_suppression_slow(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)
# import the necessary packages
import numpy as np


#  Felzenszwalb et al.
def non_max_suppression_slow(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, add the index
		# value to the list of picked indexes, then initialize
		# the suppression list (i.e. indexes that will be deleted)
		# using the last index
		last = len(idxs) - 1
		i = idxs[last]
		pick.append(i)
		suppress = [last]
# import the necessary packages
import numpy as np


#  Felzenszwalb et al.
def non_max_suppression_slow(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, add the index
		# value to the list of picked indexes, then initialize
		# the suppression list (i.e. indexes that will be deleted)
		# using the last index
		last = len(idxs) - 1
		i = idxs[last]
		pick.append(i)
		suppress = [last]


		# loop over all indexes in the indexes list
		for pos in xrange(0, last):
			# grab the current index
			j = idxs[pos]


			# 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 = max(x1[i], x1[j])
			yy1 = max(y1[i], y1[j])
			xx2 = min(x2[i], x2[j])
			yy2 = min(y2[i], y2[j])


			# compute the width and height of the bounding box
			w = max(0, xx2 - xx1 + 1)
			h = max(0, yy2 - yy1 + 1)


			# compute the ratio of overlap between the computed
			# bounding box and the bounding box in the area list
			overlap = float(w * h) / area[j]


			# if there is sufficient overlap, suppress the
			# current bounding box
			if overlap > overlapThresh:
				suppress.append(pos)


		# delete all indexes from the index list that are in the
		# suppression list
		idxs = np.delete(idxs, suppress)


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

# import the necessary packages
from pyimagesearch.nms import non_max_suppression_slow
import numpy as np
import cv2


# construct a list containing the images that will be examined
# along with their respective bounding boxes
images = [
<span style="white-space:pre">	</span>("images/audrey.jpg", np.array([
<span style="white-space:pre">	</span>(12, 84, 140, 212),
<span style="white-space:pre">	</span>(24, 84, 152, 212),
<span style="white-space:pre">	</span>(36, 84, 164, 212),
<span style="white-space:pre">	</span>(12, 96, 140, 224),
<span style="white-space:pre">	</span>(24, 96, 152, 224),
<span style="white-space:pre">	</span>(24, 108, 152, 236)])),
<span style="white-space:pre">	</span>("images/bksomels.jpg", np.array([
<span style="white-space:pre">	</span>(114, 60, 178, 124),
<span style="white-space:pre">	</span>(120, 60, 184, 124),
<span style="white-space:pre">	</span>(114, 66, 178, 130)])),
<span style="white-space:pre">	</span>("images/gpripe.jpg", np.array([
<span style="white-space:pre">	</span>(12, 30, 76, 94),
<span style="white-space:pre">	</span>(12, 36, 76, 100),
<span style="white-space:pre">	</span>(72, 36, 200, 164),
<span style="white-space:pre">	</span>(84, 48, 212, 176)]))]


# loop over the images
for (imagePath, boundingBoxes) in images:
<span style="white-space:pre">	</span># load the image and clone it
<span style="white-space:pre">	</span>print "[x] %d initial bounding boxes" % (len(boundingBoxes))
<span style="white-space:pre">	</span>image = cv2.imread(imagePath)
<span style="white-space:pre">	</span>orig = image.copy()


<span style="white-space:pre">	</span># loop over the bounding boxes for each image and draw them
<span style="white-space:pre">	</span>for (startX, startY, endX, endY) in boundingBoxes:
<span style="white-space:pre">		</span>cv2.rectangle(orig, (startX, startY), (endX, endY), (0, 0, 255), 2)


<span style="white-space:pre">	</span># perform non-maximum suppression on the bounding boxes
<span style="white-space:pre">	</span>pick = non_max_suppression_slow(boundingBoxes, 0.3)
<span style="white-space:pre">	</span>print "[x] after applying non-maximum, %d bounding boxes" % (len(pick))


<span style="white-space:pre">	</span># loop over the picked bounding boxes and draw them
<span style="white-space:pre">	</span>for (startX, startY, endX, endY) in pick:
<span style="white-space:pre">		</span>cv2.rectangle(image, (startX, startY), (endX, endY), (0, 255, 0), 2)


<span style="white-space:pre">	</span># display the images
<span style="white-space:pre">	</span>cv2.imshow("Original", orig)
<span style="white-space:pre">	</span>cv2.imshow("After NMS", image)
<span style="white-space:pre">	</span>cv2.waitKey(0)