Object Recognition in Cluttered Scenes Using Appearance-Based Parts and Relationships

在复杂场景中识别一般的三维物体仍然是一个具有挑战性的问题。特别是，设计一个良好的表示，适合大量的通用对象，也是强大的遮挡和分割问题的模型，一直是在取得成功的绊脚石。 在这项研究中，一种新的表示使用外观为基础的部分（ABP）和 关系（ABR）的提出，以克服这些问题。ABPs和ABR定义的封闭区域，分割使用最小描述长度的原则，其外观是从收集的图像和压缩存储在一个层次结构的参数特征空间。 这种新的表示允许表示自由形式的对象，并且具有几个吸引人的特征，即（1）对分割问题的鲁棒性，因为它是从分割的图像中学习的：（2）对遮挡的鲁棒性，因为它是基于部分而不是全局属性的事实;以及（3）由于其分层性质，处理大型对象数据库的能力。 作为这项研究的一部分，还将开发一个概率模型的歧视性权力的建议表示。 这个模型将被用于贝叶斯框架，PI的以前的工作的基础上，设计一个识别系统。 新的表示和相关的概率模型，加上一个 贝叶斯推理引擎，将使系统能够自动识别和定位在混乱的场景中的通用对象。 本研究的主要贡献是：（1）一个新的对象表示，能够表示大型数据库的通用对象，也是强大的分割问题和遮挡;（2）概率模型， 拟议代表的歧视性权力， 一个识别系统的基础上贝叶斯框架，不需要使用的特设hopistics;和（3）一个严格的实验协议，以表征系统的性能，在存在遮挡。

The recognition of general three-dimensional objects in cluttered scenes remains a challenging problem. In particular, the design of a good representation suitable to model large numbers of generic objects that is also robust to occlusion and segmentation problems, has been an stumbling block in achieving success. In this research, a new representation using appearance-based parts (ABPs) and relationships (ABRs) is proposed to overcome these problems. ABPs and ABRs are defined in terms of closed regions, segmented using the Minimum Description Length principle, whose appearance is obtained from collections of images and compactly stored in a hierarchical structure of parametric eigenspaces. This new representation allows the representation of free form objects and has several appealing features, namely (1) robustness to segmentation problems, since it is learned from segmented images; (2) robustness to occlusion steming from the fact that it is based on parts rather than on global properties; and (3) ability to handle large object databases, due to its hierarchical nature. As part of this research a probabilistic model of the discriminatory power of the proposed representation will be also developed. This model will be used in a Bayesian framework, based on the PI's previous work, to design a recognition system. The new representation and the associated probabilistic model, coupled with a Bayesian reasoning engine, will enable the system to automatically recognize and locate generic objects in cluttered scenes. The main contributions of this research are: (1) a new object representation capable of representing large databases of generic objects that is also robust to segmentation problems and occlusion; (2) a probabilistic model of the discriminatory power of the proposed representation and a recognition system based on a Bayesian framework that does not require the use o f ad hoc heuristics; and (3) a rigorous experimental protocol to characterize the performance of the system in the presence of occlusion.