RI: Small: Recursive Compositional Models for Vision

RI：小型：视觉递归组合模型

• 批准号: 0917141
• 负责人: Alan Yuille
• 金额: $ 40万
• 依托单位: University of California-Los Angeles
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-09-01 至 2013-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0917141&HistoricalAwards=false
• 关键词: RI; Small; Recursive; Compositional; Models

Detecting and recognizing objects from real world images is a very challenging problem with many practical applications. The past few years have shown growing success for tasks such as detecting faces, text, and for recognizing objects which have limited spatial variability. Broadly speaking, the difficulty of detection and recognition increases with the variability of the objects ? rigid objects being the easiest and deformable articulated objects being the hardest.There is, for example, no computer vision system which can detect a highly deformable and articulated object such as a cat in realistic conditions or read text in natural images. This project develops and evaluates computer vision technology for detecting and recognizing deformable articulated objects. The strategy is to represent objects by recursive compositional models (RCMs) which describe objects into compositions of subparts. Preliminary work has shown that these RCMs can be learnt with only limited supervision from natural images. In addition, inference algorithms have been developed which can rapidly detect and describe a limited class of objects. This project starts withsingle objects with fixed pose and viewpoint and proceeds to multiple objects, poses, and viewpoints. Theoretical analysis of these models gives insight and understanding of the performance and computational complexity of RCMs.The expected results are a new technology for detecting and recognizing objects for the applications mentioned above. The results are disseminated by peer reviewed publications, webpage downloads, and by university courses.

从现实世界图像中检测和识别对象对于许多实际应用来说是一个非常具有挑战性的问题。 过去几年，检测人脸、文本以及识别空间可变性有限的物体等任务取得了越来越大的成功。从广义上讲，检测和识别的难度随着物体的变化而增加 ?刚性物体是最简单的，而可变形的铰接物体是最难的。例如，没有计算机视觉系统可以检测高度变形和铰接的物体（例如现实条件下的猫）或读取自然图像中的文本。该项目开发和评估用于检测和识别可变形铰接物体的计算机视觉技术。该策略是通过递归组合模型（RCM）来表示对象，该模型将对象描述为子部分的组合。初步工作表明，这些 RCM 可以仅在自然图像的有限监督下学习。此外，还开发了推理算法，可以快速检测和描述有限类别的对象。该项目从具有固定姿势和视点的单个对象开始，然后发展到多个对象、姿势和视点。这些模型的理论分析使人们能够深入了解和理解 RCM 的性能和计算复杂性。预期结果是一种用于检测和识别上述应用中的物体的新技术。 结果通过同行评审出版物、网页下载和大学课程进行传播。