基于GPU的立体视觉信念传播

The 3rd Canadian Conference on Computer and Robot Vision (CRV'06) Pub Date : 2006-06-07 DOI:10.1109/CRV.2006.19

A. Brunton, Chang Shu, G. Roth

{"title":"基于GPU的立体视觉信念传播","authors":"A. Brunton, Chang Shu, G. Roth","doi":"10.1109/CRV.2006.19","DOIUrl":null,"url":null,"abstract":"The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern desktop and notebook computers, and applies it to the stereo problem. The stereo problem is used for comparison to other BP algorithms.","PeriodicalId":369170,"journal":{"name":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"70","resultStr":"{\"title\":\"Belief Propagation on the GPU for Stereo Vision\",\"authors\":\"A. Brunton, Chang Shu, G. Roth\",\"doi\":\"10.1109/CRV.2006.19\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern desktop and notebook computers, and applies it to the stereo problem. The stereo problem is used for comparison to other BP algorithms.\",\"PeriodicalId\":369170,\"journal\":{\"name\":\"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)\",\"volume\":\"23 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2006-06-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"70\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CRV.2006.19\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CRV.2006.19","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 70

摘要

马尔可夫随机场公式在低水平视觉问题(如立体)中的作用已经为人所知一段时间了。然而，最近的进展，无论是算法还是处理能力，都使它们的应用变得实际。本文提出了一种新的贝叶斯信念传播方法，用于大多数现代台式机和笔记本电脑的图形处理单元，并将其应用于立体问题。将立体问题与其他BP算法进行比较。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Belief Propagation on the GPU for Stereo Vision

The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern desktop and notebook computers, and applies it to the stereo problem. The stereo problem is used for comparison to other BP algorithms.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)

自引率

0.00%

发文量