其他
【综述专栏】点云距离度量:完全解析EMD距离(Earth Mover's Distance)
在科学研究中,从方法论上来讲,都应“先见森林,再见树木”。当前,人工智能学术研究方兴未艾,技术迅猛发展,可谓万木争荣,日新月异。对于AI从业者来说,在广袤的知识森林中,系统梳理脉络,才能更好地把握趋势。为此,我们精选国内外优秀的综述文章,开辟“综述专栏”,敬请关注。
地址:https://www.zhihu.com/people/liu-xin-chen-64
01
我们为什么需要度量点云距离
02
EMD距离是怎么做的
2.1 从运输问题说起
是不是感觉上面写的挺抽象的?不是很好理解?那我们整点具体的!
03
EMD距离的优势
Naturally extends the notion of a distance between single elements to that of a distance between sets, or distributions, of elements. Can be applied to the more general variable-size signatures, which subsume histograms. Signatures are more compact, and the cost of moving "earth" reflects the notion of nearness properly, without the quantization problems of most other measures. Allows for partial matches in a very natural way. This is important, for instance, for image retrieval and in order to deal with occlusions and clutter. Is a true metric if the ground distance is metric and if the total weights of two signatures are equal. This allows endowing image spaces with a metric structure. Is bounded from below by the distance between the centers of mass of the two signatures when the ground distance is induced by a norm. Using this lower bound in retrieval systems significantly reduced the number of EMD computations. Matches perceptual similarity better than other measures, when the ground distance is perceptually meaningful. This was shown by[2] for color- and texture-based image retrieval.
04
其他度量方式
4.1 CD(Chamfer Distance)
4.2 HD(Hausdorff Disance)
directed distance
distance(symmetry)
05
参考资料
http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/RUBNER/emd.htm
本文目的在于学术交流,并不代表本公众号赞同其观点或对其内容真实性负责,版权归原作者所有,如有侵权请告知删除。
直播预告
“综述专栏”历史文章
One Shot NAS总结
图神经网络与深度学习在智能交通中的应用:综述Survey
异质图神经网络学习笔记
Self-supervised Learning
元学习综述
异常检测:Anomaly Detection综述
计算机视觉基本任务综述
小样本学习——概念、原理与方法简介
基于元学习的现实场景应用论文介绍
单阶段实例分割
知识图谱学习资源——知识图谱综述总结
薛建儒: 自动驾驶的场景理解研究
arXiv最新论文:自动驾驶中深度学习
SLAM回环检测方法
视频摘要最新综述文章,附45页综述全文下载
更多综述专栏文章,
请点击文章底部“阅读原文”查看
分享、点赞、在看,给个三连击呗!