I'm afraid Hough Lines will fail here. You could try ransac
to get best estimated line, erase those points and run next ransac
. Tough you still can encounter some troubles: exactly how many clusters do you want to recognize? You could set min score sample score for a line model. You'd also need to filter out horizontal lines.
There're ransac
implementations in both scikit-learn and scikit-image .
如果您还没有尝试过,请使用 OpenCV 函数HoughLines()
和HoughLinesP()
来检测图像中的线条。
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.