opencv - 如何更准确地比较两张图像之间的特征？

Question

我已经使用 SIFT 和 ORB 开发了两种方法，但在我看来，这些点并没有正确对应。我是错误地使用了这些功能还是需要不同的东西？

orb = cv2.ORB_create()
keypoints_X, descriptor_X = orb.detectAndCompute(car1_gray, None)
keypoints_y, descriptor_y = orb.detectAndCompute(car2_gray, None)
bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck = True)
matches = bf.match(descriptor_X, descriptor_y)
matches = sorted(matches, key = lambda x: x.distance)
result = cv2.drawMatches(car1_gray, keypoints_X, car2_gray, keypoints_y, matches[:10], car2_gray, flags = 2)

---

sift = cv2.SIFT_create()

keypoints_X, descriptor_X = sift.detectAndCompute(car1_gray, None)
keypoints_y, descriptor_y = sift.detectAndCompute(car2_gray, None)
bf = cv2.BFMatcher()
matches = bf.knnMatch(descriptor_X, descriptor_y, k=2)

bom = []

for m,n in matches:
    if m.distance < 0.75*n.distance:
        bom.append([m])

result = cv2.drawMatchesKnn(car1_gray, keypoints_X, car2_gray, keypoints_y, bom, None, flags=cv2.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS)

下面是 SIFT 和 ORB 的结果：

标签： opencvcomputer-visionconv-neural-networksiftorb

Answer 1

看看SuperGlue，基于图神经网络的特征匹配。虽然，他们不提供训练代码，但有两种用于室内、室外的预训练模型。链接，

https://github.com/magicleap/SuperGluePretrainedNetwork

https://psarlin.com/superglue/

https://arxiv.org/pdf/1911.11763.pdf