人体检测:轮廓而不是矩形 [英] Human full body detection: contour rather than rectangle

问题描述

我必须使用opencv对整个人体(从脚到头，以几种姿势，例如举起手等)进行轮廓检测.我设法编译并运行了在这里找到的代码 https://gist.github.com/yoggy/1470956，但是它仅在身体周围绘制一个矩形，而不是确切的轮廓.可以帮助我识别和显示轮廓本身吗?

I have to implement a contour detection of full human body (from feet to head, in several poses such as raising hands etc.) using opencv. I managed to compile and run code I found here https://gist.github.com/yoggy/1470956, but it only draws a rectangle around the body, and not the exact contour. Can one help me with identifying and displaying the contour itself?

谢谢！

推荐答案

恐怕这个问题的答案是:

I'm afraid the answer to this question is:

没有算法可以完美地做到这一点.

计算机视觉尚未发展到这种程度.看看CVPR，PAMI上的最新论文，您会发现，就人类标记和算法检测而言，大多数算法都是矩形"的，或更具体地说，是基于边界框的.

Computer vision has not developed to that extent yet. Take a look at recent papers in CVPR, PAMI, and you will find that most algorithms are "rectangle", or more specifically, bounding-box based, in terms of human labeling and algorithmic detecting.

确实可以在边界框内找到轮廓.但是计算机只是不知道哪个轮廓属于指定对象.

It is true that you can find the contours within the bounding-box. However the computer just doesn't know which contour belongs to the specified object.

我建议您搜索人体姿势估计"以获取更多信息.

I suggest you search for "human pose estimation" for further information.

这篇关于人体检测:轮廓而不是矩形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！