卷积神经网络的四边形/矩形检测的新思路 [英] ideas on quadrangle/rectangle detection using convolutional neural networks

问题描述

我一直在尝试进行四边形检测和定位几周，我的目标是要有一个可靠的方法来获取四边形(矩形)的4个点，因此我可以对图像应用投影变换，然后将其附加到源图像.我尝试了经典的opencv等高线方法，并且还使用了hough变换来查找线，然后计算交点，当将其应用于现实生活中的图像时，这两种方法将无法使用.

I'v been trying to do quadrangle detection and localization for weeks, my goal is to have a robust way of getting the 4 points of an quadrangle(rectangle), so I can apply projective transform to an Image then attach it to the source image. I have try the classic opencv contour method, and also using hough transform to find lines then calculate intersections, those two methods is unusable when apply it to real life images.

因此，我向CNN寻求帮助，但目前我还没有找到任何尝试使用CNN来解决此简单问题的方法.

So I turn to CNN for help, but currently i haven't find any one try to use CNN to solve this simple problem.

我的第一个尝试是使用最新的对象检测和定位方法来获取四边形的边界框，以便我可以缩小4个点的搜索范围，然后使用图像处理和计算机视觉方法进一步寻找4分.但是在尝试使用YOLOv2和Faster-RCNN之后，预测精度并不理想.

My first attempt is to use state-of-art object detection and localization methods to get quadrangle's bounding box so i can narrow the search of 4 points, then use image processing & computer vision methods to further the search for 4 points. but after trying YOLOv2 and Faster-RCNN, the prediction accuracy is not ideal.

所以我想知道是否有任何想法可以使用单个神经网络来端到端地完成所有这些培训和前馈.它也必须能够很好地处理遮挡.

So I'm wondering if there is any idea i can do this end to end, training and feedforward all using a single neural network. it also must be able to deal with occlusion reasonably well.

目前，我的想法是删除fc层，并制作一个与第一个输入层具有相同宽度和高度的巨大激活图(例如448x448)，然后使用argmax优化4个激活程度最高的区域，位置.但是该方法仅适用于一个四边形，不适用于拐角遮挡.

Currently my idea is to remove the fc-layers and make a huge activation map that has the same width and height as the first input layer(eg. 448x448) then optimize the 4 most highly activated areas, using argmax to get the position. but this method only works for one quadrangle it doesn't work well with corner occlusions as well.

如果有人可以提供任何建议，我将不胜感激.非常感谢！

I'll be appreciated if anyone can provide any suggestions. Thanks a lot!

推荐答案

对于您提到的第一种方法，您绝对正确.像Hough变换这样的方法很旧，对于野外的图像没有用.当然，随着深度学习的兴起，计算机视觉领域将其目光转向了对象检测和识别.

You are absolutely right about the first methods you mentioned. Hough transform like methods are old and not useful for images in the wild. And of course, computer vision field turned its face to object detection and recognition with rise of deep learning.

但是，最近有一个非常好的讨论.我们是否忘记了计算机视觉中的几何?

However, there is a very nice discussion came up recently. Have we forgotten about Geometry in Computer Vision?

我的建议是轮廓检测，然后应用Hough变换(使用最新技术)方法来检测所需的矩形，关于遮挡，您可以为Hough变换设置参数，以更宽容带有参数的缺失边缘像素.例如，您可以检查最新的轮廓检测方法，如最近的 CVPR论文.

My suggestion would be contour detection and then apply Hough transform(use state of the art) methods to detect rectangles you want, about the occlusion, you can set parameters for Hough transform to be more forgiving for missing edge pixels with parameters. You can for example check most recent contour detection methods as in recent CVPR paper.

这篇关于卷积神经网络的四边形/矩形检测的新思路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IT屋！