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.

从真实世界的图像中检测和识别目标是一个非常具有挑战性的问题，具有许多实际应用。在过去的几年里，在检测人脸、文本和识别空间变异性有限的对象等任务方面取得了越来越大的成功。一般说来，检测和识别的难度随着目标的可变性而增加。刚性物体是最容易和最容易变形的铰接式物体是最难的。例如，没有计算机视觉系统可以在现实条件下检测高度变形和铰接性的物体，如猫或阅读自然图像中的文本。该项目开发和评估用于检测和识别可变形关节对象的计算机视觉技术。其策略是用递归组合模型(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可以在有限的监督下从自然图像中学习。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。此项目从具有固定姿势和视点的单个对象开始，然后进行到多个对象、姿势和视点。通过对这些模型的理论分析，深入了解了RCM的性能和计算复杂度，为上述应用提供了一种新的目标检测和识别技术。结果通过同行评议的出版物、网页下载和大学课程传播。