目标检测 选择性搜索算法——Selective Search

#!/usr/bin/env python
'''
Usage:
    ./ssearch.py input_image (f|q)
    f=fast, q=quality
Use "l" to display less rects, 'm' to display more rects, "q" to quit.
'''

import sys
import cv2

if __name__ == '__main__':

    # speed-up using multithreads
    cv2.setUseOptimized( True );
    cv2.setNumThreads( 4 );

    # read image
    im = cv2.imread( './test.jpg' )
    # resize image
    newHeight = 200
    newWidth = int( im.shape[1] * 200 / im.shape[0] )
    im = cv2.resize( im, (newWidth, newHeight) )

    # create Selective Search Segmentation Object using default parameters
    ss = cv2.ximgproc.segmentation.createSelectiveSearchSegmentation()

    # set input image on which we will run segmentation
    ss.setBaseImage( im )

    if 1:
        # Switch to fast but low recall Selective Search method
        ss.switchToSelectiveSearchFast()
    else:
        # Switch to high recall but slow Selective Search method
        ss.switchToSelectiveSearchQuality()


    # run selective search segmentation on input image
    rects = ss.process()
    print( 'Total Number of Region Proposals: {}'.format( len( rects ) ) )

    # number of region proposals to show
    numShowRects = 100
    # increment to increase/decrease total number
    # of reason proposals to be shown
    increment = 50

    while True:
        # create a copy of original image
        imOut = im.copy()

        # itereate over all the region proposals
        for i, rect in enumerate( rects ):
            # draw rectangle for region proposal till numShowRects
            if (i < numShowRects):
                x, y, w, h = rect
                cv2.rectangle( imOut, (x, y), (x + w, y + h), (0, 255, 0), 1, cv2.LINE_AA )
            else:
                break

        # show output
        cv2.imshow( "Output", imOut )

        # record key press
        k = cv2.waitKey( 0 ) & 0xFF

        # m is pressed
        if k == 109:
            # increase total number of rectangles to show by increment
            numShowRects += increment
        # l is pressed
        elif k == 108 and numShowRects > increment:
            # decrease total number of rectangles to show by increment
            numShowRects -= increment
        # q is pressed
        elif k == 113:
            break
    # close image show window
    cv2.destroyAllWindows()

opencv实现了选择性搜索算法，可以给出上千个根据有物体的可能性降序排列的候选区域。
下图是画出了前面200250个候选区域的效果。一般来说。10001200个候选区域基本能胜任物体检测的任务了
主要实现是靠createSelectiveSearchSegmentation这个函数

# v2.useOptimized()函数可以查看当前优化是否开启
# cv2.setUseOptimized()可以设置是否开启优化
cv2.setUseOptimized(True);
# 如果报错，检查是否安装的是opencv，如果安装的opencv(简版不包含一些函数)，卸载安装opencv-contrib-python 
ss = cv2.ximgproc.segmentation.createSelectiveSearchSegmentation()
#读入图片
im = cv2.imread(os.path.join(path,"42850.jpg"))
ss.setBaseImage(im)
ss.switchToSelectiveSearchFast()
#提取的候选框
rects = ss.process()
imOut = im.copy()
print(rects.shape)
# plt.imshow(im)
for i, rect in (enumerate(rects)):
    x, y, w, h = rect
#     print(x,y,w,h)
#     imOut = imOut[x:x+w,y:y+h]
    cv2.rectangle(imOut, (x, y), (x+w, y+h), (0, 255, 0), 1, cv2.LINE_AA)
# plt.figure()
plt.imshow(imOut)