githublqs

Results 4 issues of githublqs

测试同一幅图片两个不同区域的icp效果,多次测试发现,以文字为模板会存在一定比例的明显偏移,请问该如何解决? 有没有遇到同样问题的人? 说明: 白色是canny边缘 紫色是icp之前特征点的位置 绿色是icp后的特征点的位置 文字-正常情况: ![图片](https://user-images.githubusercontent.com/4864431/115945818-fd600700-a4ef-11eb-9ad5-45d99fcb3e7b.png) 文字-失败情况 ![图片](https://user-images.githubusercontent.com/4864431/115945937-ac9cde00-a4f0-11eb-9fee-fc77262e5353.png) 非文字未出现失败情况 ![图片](https://user-images.githubusercontent.com/4864431/115946004-0c938480-a4f1-11eb-97bf-13a4b0998c1a.png) ![图片](https://user-images.githubusercontent.com/4864431/115946042-351b7e80-a4f1-11eb-88d8-b4168cf047c6.png)

my data generate code below: cv::Mat detected_edges(Size(640,480),CV_8UC1,Scalar(0)); cv::line(detected_edges, Point(detected_edges.cols / 4, detected_edges.rows / 4), Point(detected_edges.cols * 3 / 4, detected_edges.rows * 3 / 4), Scalar(255)); cv::Mat points(0, 2, CV_64F), point(1,...

Is it convenient to share a source code of the canny dynamic library?

![image](https://github.com/CASIA-IVA-Lab/FastSAM/assets/4864431/6e6ce754-1ede-474b-b8df-961fb9e009a0)