Scene parsing using graph matching on street-view data.pdfVIP

下载本文档

10
0
约5.58万字
约 11页
2017-03-16 发布于天津
举报
版权申诉

Scene parsing using graph matching on street-view data.pdf

1、本文档共11页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Scene parsing using graph matching on street-view data.pdf

Computer Vision and Image Understanding 145 (2016) 70–80 Contents lists available at ScienceDirect Computer Vision and Image Understanding journal homepage: /locate/cviu Scene parsing using graph matching on street-view dataR Tianshu Yu a,?, Ruisheng Wang a Department of Geomatics Engineering, University of Calgary, 2500 University Dr NW Calgary, Alberta T2N1N4, Canada article info Article history: Received 28 April 2015 Accepted 11 January 2016 Available online 21 January 2016 Keywords: Scene parsing Graph matching Markov random ?eld Street view abstract Scene parsing, using both images and range data, is one of the key problems in computer vision and robotics. In this paper, a street scene parsing scheme that takes advantages of images from perspective cameras and range data from LiDAR is presented. First, pre-processing on the image set is performed and the corresponding point cloud is segmented according to semantics and transformed into an image pose. A graph matching approach is introduced into our parsing framework, in order to identify similar sub-regions from training and test images in terms of both local appearance and spatial structure. By using the sub-graphs inherited from training images, as well as the cues obtained from point clouds, this approach can effectively interpret the street scene via a guided MRF inference. Experimental results show a promising performance of our approach. ? 2016 Elsevier Inc. All rights reserved. 1. Introduction Scene parsing, which is the segmentation and classi?cation of regions in an image with different semantics, is of great importance in the computer vision community. For decades, various approaches have been developed to parse scenes on image sets, so that algorithms can learn and infer results from the signi?cant amount of information provided by images. However, there are dif?culties when only images are used. First, it is di?cult to train a su?ciently effective classi?er to label the regions due to the diversity