问题描述

我正在尝试使用 ORB 关键点检测器，它返回的点似乎比 SIFT 检测器和 FAST 检测器少得多.

I'm trying to use the ORB keypoint detector and it seems to be returning much fewer points than the SIFT detector and the FAST detector.

此图显示了 ORB 检测器发现的关键点:

This image shows the keypoints found by the ORB detector:

这张图显示了 SIFT 检测阶段发现的关键点(FAST 返回的点数相似).

and this image shows the keypoints found by the SIFT detection stage (FAST returns a similar number of points).

只有这么少的点会导致跨图像的特征匹配结果非常差.我现在只是对 ORB 的检测阶段感到好奇，因为这似乎我得到了不正确的结果.我已经尝试使用 ORB 检测器和默认参数以及下面详述的自定义参数.

Having such few points is resulting in very poor feature matching results across images. I'm just curious about the detection stage of ORB right now though because this seems like I'm getting incorrect results. I've tried using the ORB detector with default parameters and also custom parameters detailed below as well.

为什么会有这么大的差异?

Why such a big difference?

代码:

orb = cv2.ORB_create(edgeThreshold=15, patchSize=31, nlevels=8, fastThreshold=20, scaleFactor=1.2, WTA_K=2,scoreType=cv2.ORB_HARRIS_SCORE, firstLevel=0, nfeatures=500)
#orb = cv2.ORB_create()
kp2 = orb.detect(img2)
img2_kp = cv2.drawKeypoints(img2, kp2, None, color=(0,255,0), 
        flags=cv2.DrawMatchesFlags_DEFAULT)

plt.figure()
plt.imshow(img2_kp)
plt.show()

推荐答案

增加 nfeatures 会增加检测到的角点的数量.关键点提取器的类型似乎无关紧要.我不确定如何将此参数传递给 FAST 或 Harris，但它似乎可以工作.

Increasing nfeatures increases the number of detected corners. The type of keypoint extractor seems irrelevant. I'm not sure how this parameter is passed to FAST or Harris but it seems to work.

orb = cv2.ORB_create(scoreType=cv2.ORB_FAST_SCORE)

orb = cv2.ORB_create(nfeatures=100000, scoreType=cv2.ORB_FAST_SCORE)

这篇关于OpenCV ORB 检测器发现的关键点很少的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持跟版网！