SGER: MCMC Algorithms for Object Recognition

SGER：用于对象识别的 MCMC 算法

• 批准号: 9979201
• 负责人: David Forsyth
• 金额: $ 5万
• 依托单位: University of California-Berkeley
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1999
• 资助国家: 美国
• 起止时间: 1999-09-01 至 2000-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9979201&HistoricalAwards=false
• 关键词: SGER; MCMC; Algorithms; Object; Recognition

Abstract IIS-9979201Hollerbach, JohnUniversity of Utah$50,000 - 12 mos.MCMC Algorithms for Object RecognitionThis is a standard SGER award. This exploratory research is about finding clothed people in images with a mixture of probabilistic and geometric techniques. Current theories of object recognition cannot be used to recognize such complex deformable objects, particularly because they do not allow exact geometric models and are on cluttered backgrounds. In this study, a bottom-up approach based on learning will be used to assemble image primitives (defined by invariant filters) into regions that could be clothing, and then to assemble these regions into regions that could be body segments, which will be assembled further into limbs, and so on, until a region is sufficiently large to indicate that a person is present. This purely bottom-up approach will be complemented by Markov chain Monte Carlo (MCMC) techniques to modify existing groups. The intention is to obtain cases that have high posterior probability. In particular, collections of segments that do not on their own pass assembly tests will be randomly advanced past those tests anyway, if the group that results has high posterior probability.

摘要IIS -9979201 Hollerbach，犹他州的约翰尼弗里斯蒂西$ 50,000-12 MOS.MCMC算法，用于对象识别，这是标准SGER奖。 这项探索性研究是关于在具有概率和几何技术混合物的图像中找到穿衣服的人。当前的对象识别理论不能用于识别这种复杂的可变形对象，尤其是因为它们不允许精确的几何模型，并且在混乱的背景上。 在这项研究中，将使用基于学习的自下而上的方法将图像原语（由不变过滤器定义）组装成可能是衣服的区域，然后将这些区域组装成可能是身体片段的区域，这些区域可能会进一步组装到四肢，等于依此类推，直到一个区域足够大，以表明一个人存在一个人。 Markov Chain Monte Carlo（MCMC）技术将补充这种自下而上的方法，以修改现有组。目的是获取具有高后概率的病例。特别是，如果结果具有很高的后验概率，则不按照自己的通过组装测试的片段的集合将随机超越这些测试。