I need to combine SIFT
and ORB
descriptors of an image.
As you know, SIFT
descriptors are of 128-length and ORB
descriptors are of 32-length.
At this moment what I do is:
- Reshaping
SIFT
descriptors to 32-length. For instance, reshape a (135, 128) descriptor to a (540, 32) descriptor - Concatenating
SIFT
andORB
descriptors (since at this moment both have 32-length)
Code:
sift_kp, sift_desc = sift.detectAndCompute(img,None)
new_sift_desc = sift_desc.reshape((int(128/32) * sift_desc.shape[0], 32))
orb_kp, orb_img_descriptor = orb.detectAndCompute(img,None)
all_descriptors = np.concatenate((new_sift_desc , orb_img_descriptor), axis=0)
I am wondering if there is a better way to combine these descriptors.
After combinating the descriptors, the idea is to use all_descriptors
in order to perform feature matching against another image.
CodePudding user response:
In case someone is interested, what I have finally done is to use ORB in order to detect
the images keypoints and use SIFT to compute
descriptors from that keypoints
Code:
def get_orb_sift_image_descriptors(search_img, idx_img):
# Initiate SIFT detector
sift = cv.SIFT_create()
# Initiate ORB detector
orb = cv.ORB_create()
# Find keypoints with ORB
search_kp_orb = orb.detect(search_img, None)
idx_kp_orb = orb.detect(idx_img, None)
# Compute descriptors with SIFT
search_kp_sift, search_des_sift = sift.compute(search_img, search_kp_orb)
idx_kp_sift, idx_des_sift = sift.compute(idx_img, idx_kp_orb)
return search_des_sift, idx_des_sift