def main():
image_dir = sys.argv[1]
image_dir = image_dir.rstrip('/')
locations = get_locations(image_dir)
detectstr = sys.argv[2]
detector, matcher = init_feature(detectstr)
results = processDirectory(image_dir, detector, matcher, locations)
outfile = open(image_dir + detectstr + 'result.txt', 'w')
for line in results:
outfile.write('#' + line + '\n')
outfile.write(str(results[line]) + '\n')
outfile.close()
for i, (k, d) in enumerate(ires):
print('affine sampling: %d / %d\r' % (i+1, len(params)), end='')
keypoints.extend(k)
descrs.extend(d)
return keypoints, np.array(descrs)
if __name__ == '__main__':
if len(sys.argv) < 4:
print ("Usage %s <image1> <image2> <keypoint_detector>" % sys.argv[0])
exit()
img1 = cv2.imread(sys.argv[1], 0) # queryImage
img2 = cv2.imread(sys.argv[2], 0) # trainImage
detectstr = sys.argv[3]
detector, matcher = init_feature(detectstr)
print('using', detectstr)
cpucount = cv2.getNumberOfCPUs() / 2
pool=ThreadPool(processes = cpucount)
print("No. of CPUs: %d" % cpucount)
kp1, desc1 = affine_detect(detector, img1, pool=None)
kp2, desc2 = affine_detect(detector, img2, pool=None)
print('img1 - %d features, img2 - %d features' % (len(kp1), len(kp2)))
raw_matches = matcher.knnMatch(desc1, trainDescriptors = desc2, k = 2) #2
p1, p2, kp_pairs = filter_matches(kp1, kp2, raw_matches)
if len(p1) >= 4:
H, matchMask = cv2.findHomography(p1, p2, cv2.RANSAC, 5.0)
print('%d / %d inliers/matched' % (np.sum(matchMask), len(matchMask)))
# do not draw outliers (there will be a lot of them)
def main():
image_dir = sys.argv[1]
detectstr = sys.argv[2]
detector, matcher = init_feature(detectstr)
processDirectory(image_dir, detector)