CAREER: Markov Chain Monte Carlo Methods for Large Scale Correspondence Problems in Computer Vision and Robotics

职业：用于计算机视觉和机器人技术中大规模对应问题的马尔可夫链蒙特卡罗方法

• 批准号: 0448111
• 负责人: Frank Dellaert
• 金额: --
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-04-01 至 2011-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0448111&HistoricalAwards=false
• 关键词: CAREER; Markov; Chain; Monte; Carlo

The goal of this project is to investigate tractable approaches to large-scale correspondence problems in computer vision and robotics. Correspondence is a central problem in many vision and robotics applications, and the proposed research centers on three of those: large-scale 3D reconstruction from digital imagery in space and time, simultaneous localization and mapping using mobile robots, and tracking large numbers of visually similar objects, such as ants in an ant-hill or people in a crowd. To eclipse existing state of the art methods, this proposal aims to investigate approximate inference through Markov chain Monte Carlo (MCMC) sampling. MCMC provides an approximate solution for an otherwise intractable problem, and has a number of attractive advantages with respect to other approaches. In addition, practical insights gained in applying MCMC to this problem can cross-pollinate other fields and spawn new theoretical investigations. In terms of broader impact, this project's integrated research and education plan will help produce a next generation of researchers, intimately familiar with these new methods first discovered in statistical mechanics. In addition, the project has a strong outreach component through museum exhibits and interaction with local high schools. Taking a longer view, the proposed research will enable novel and large-scaleapplications of computer vision and robotics that are expected to have far-reachingimplications for society. Robots are on the verge of playing a much larger role in our lives, as evidenced for example by the increasingly popular consumer robots now available. More immediately, the advent of cheap digital photography and video is exponentially increasing the volume of digital imagery that can be used, analyzed, and re-synthesized in new and creative ways. The correspondence problem lies at the heart of many of these novel uses.

这个项目的目标是研究计算机视觉和机器人技术中大规模对应问题的易处理方法。对应是许多视觉和机器人应用中的一个核心问题，拟议的研究集中在其中三个方面：从空间和时间的数字图像进行大规模3D重建，使用移动的机器人同时定位和映射，以及跟踪大量视觉相似的物体，例如蚂蚁山中的蚂蚁或人群中的人。为了使现有的最先进的方法黯然失色，该建议的目的是通过马尔可夫链蒙特卡罗（MCMC）抽样调查近似推理。MCMC提供了一个近似的解决方案，否则棘手的问题，并有一些有吸引力的优势，相对于其他方法。此外，在应用MCMC解决这个问题时获得的实践见解可以交叉影响其他领域并产生新的理论研究。就更广泛的影响而言，该项目的综合研究和教育计划将有助于培养下一代研究人员，熟悉这些首次在统计力学中发现的新方法。此外，该项目还通过博物馆展览和与当地高中的互动进行了强有力的外展活动。从长远来看，拟议的研究将使计算机视觉和机器人技术的新的和大规模的应用，预计将对社会产生深远的影响。机器人即将在我们的生活中发挥更大的作用，例如，现在越来越受欢迎的消费机器人就证明了这一点。更直接的是，廉价的数字摄影和视频的出现正在以指数级的方式增加数字图像的数量，这些图像可以以新的和创造性的方式被使用、分析和重新合成。对应问题是许多这些新奇用途的核心。