def set_keypoints():
[detected_keypoints1, descriptors1] = detect_keypoints(image_pathes[0], 5)
[detected_keypoints2, descriptors2] = detect_keypoints(image_pathes[1], 5)
[detected_keypoints3, descriptors3] = detect_keypoints(image_pathes[2], 5)
[detected_keypoints4, descriptors4] = detect_keypoints(image_pathes[3], 5)
with open('keypoints.pkl', 'w') as f:
pickle.dump([detected_keypoints1, descriptors1,detected_keypoints2,descriptors2,detected_keypoints3,descriptors3,detected_keypoints4,descriptors4], f)
def match_template(imagename, templatename, threshold, cutoff):
img = cv2.imread(imagename)
template = cv2.imread(templatename)
[kpi, di] = detect_keypoints(imagename, threshold)
[kpt, dt] = detect_keypoints(templatename, threshold)
flann_params = dict(algorithm=1, trees=4)
flann = cv2.flann_Index(np.asarray(di, np.float32), flann_params)
idx, dist = flann.knnSearch(np.asarray(dt, np.float32), 1, params={})
del flann
dist = dist[:,0]/2500.0
dist = dist.reshape(-1,).tolist()
idx = idx.reshape(-1).tolist()
indices = range(len(dist))
indices.sort(key=lambda i: dist[i])
dist = [dist[i] for i in indices]
idx = [idx[i] for i in indices]
kpi_cut = []
for i, dis in itertools.izip(idx, dist):
print ("distance: " + str(dis))
if dis < cutoff:
kpi_cut.append(kpi[i])
else:
break
kpt_cut = []
for i, dis in itertools.izip(indices, dist):
print ("distance: " + str(dis))
if dis < cutoff:
kpt_cut.append(kpt[i])
else:
break
h1, w1 = img.shape[:2]
h2, w2 = template.shape[:2]
nWidth = w1 + w2
nHeight = max(h1, h2)
hdif = (h1 - h2) / 2
newimg = np.zeros((nHeight, nWidth, 3), np.uint8)
newimg[hdif:hdif+h2, :w2] = template
newimg[:h1, w2:w1+w2] = img
for i in range(min(len(kpi), len(kpt))):
pt_a = (int(kpt[i,1]), int(kpt[i,0] + hdif))
pt_b = (int(kpi[i,1] + w2), int(kpi[i,0]))
cv2.line(newimg, pt_a, pt_b, (255, 0, 0))
cv2.imwrite('matches.jpg', newimg)
def match_template(imagename, templatename, threshold, cutoff):
img = cv2.imread(imagename)
template = cv2.imread(templatename)
[kpi, di] = detect_keypoints(imagename, threshold)
[kpt, dt] = detect_keypoints(templatename, threshold)
flann_params = dict(algorithm=1, trees=4)
flann = cv2.flann_Index(np.asarray(di, np.float32), flann_params)
idx, dist = flann.knnSearch(np.asarray(dt, np.float32), 1, params={})
del flann
dist = dist[:,0]/2500.0
dist = dist.reshape(-1,).tolist()
idx = idx.reshape(-1).tolist()
indices = range(len(dist))
indices.sort(key=lambda i: dist[i])
dist = [dist[i] for i in indices]
idx = [idx[i] for i in indices]
kpi_cut = []
for i, dis in itertools.izip(idx, dist):
if dis < cutoff:
kpi_cut.append(kpi[i])
else:
break
kpt_cut = []
for i, dis in itertools.izip(indices, dist):
if dis < cutoff:
kpt_cut.append(kpt[i])
else:
break
h1, w1 = img.shape[:2]
h2, w2 = template.shape[:2]
nWidth = w1 + w2
nHeight = max(h1, h2)
hdif = (h1 - h2) / 2
newimg = np.zeros((nHeight, nWidth, 3), np.uint8)
newimg[hdif:hdif+h2, :w2] = template
newimg[:h1, w2:w1+w2] = img
for i in range(min(len(kpi), len(kpt))):
pt_a = (int(kpt[i,1]), int(kpt[i,0] + hdif))
pt_b = (int(kpi[i,1] + w2), int(kpi[i,0]))
cv2.line(newimg, pt_a, pt_b, (255, 0, 0))
cv2.imwrite('matches.jpg', newimg)
def match_template(imagename, pos):
img = cv2.imread(imagename)
kpi = detect_keypoints(imagename)
fichier = open(pos + "/sift.txt", "a")
#print(kpi)
if kpi is not None:
fichier.write("\n" + str(Id) + "," + str(Class[int(pos) - 1]) + ",")
f, n = 0, 0
for i in kpi:
f += 1
for y in i:
n += 1
if (f == len(kpi)) & (n == len(i)):
fichier.write(str(y))
else:
fichier.write(str(y) + ",")
fichier.close()
"""else:
keypoints_kitti11_94 = np.loadtxt('Kitti11_94_Keypoints', delimiter=',')
descriptors_kitti11_94 = np.loadtxt('Kitti11_94_Descriptors', delimiter=',')
keypoints_kitti11_94_cv2 = to_cv2_kplist(keypoints_kitti11_94)
descriptors_kitti11_94_cv2 = to_cv2_di(descriptors_kitti11_94)
print("Anzahl Keypoints in Kitti11_94: " + str(len(keypoints_kitti11_94_cv2)))
cv2.drawKeypoints(gray_Kitti11_94,
keypoints_kitti11_94_cv2,
kitti11_94_img,
flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv2.imwrite('Kitti11_94_Keypoints.png', kitti11_94_img)
[keypoints_kitti11_96_raw,
descriptors_kitt11_96_raw] = detect_keypoints(imagesKitti11_paths[1], 5)
np.savetxt('Kitti11_96_Keypoints', keypoints_kitti11_96_raw, delimiter=',')
np.savetxt('Kitti11_96_Descriptors', descriptors_kitt11_96_raw, delimiter=',')
keypoints_kitti11_96 = np.loadtxt('Kitti11_96_Keypoints', delimiter=',')
descriptors_kitt11_96 = np.loadtxt('Kitti11_96_Descriptors', delimiter=',')
keypoints_kitti11_96_cv2 = to_cv2_kplist(keypoints_kitti11_96)
descriptors_kitti11_96_cv2 = to_cv2_di(descriptors_kitt11_96)
print("Anzahl Keypoints in Kitti11_96: " + str(len(keypoints_kitti11_96_cv2)))
cv2.drawKeypoints(gray_Kitti11_96,
keypoints_kitti11_96_cv2,
kitti11_96_img,
flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv2.imwrite('Kitti11_96_Keypoints.png', kitti11_96_img)
[keypoints_kitti14_left_raw,
descriptors_kitt14_left_raw] = detect_keypoints(imagesKitti14_paths[0], 5)
def find_descriptor(path):
resize_image(path)
kp, target_des = detect_keypoints(path, 0.01)
return target_des
import cv2
from siftdetector import detect_keypoints
img1 = cv2.imread('iiitb.jpg', cv2.COLOR_BGR2GRAY) # queryImage
[keypoints, descriptors] = detect_keypoints(imagename, 15)
cv2.imshow("a", keypoints)
cv2.waitKey(0)
