Hierarchical Architecture for View-Based Object Recognition in Cluttered Scenes

为了让计算机和机器人充分发挥其作为人类助手的潜力，它们必须能够可靠地感知环境中的人和物体。该项目解决了复杂日常场景(例如，办公室、家庭或交通场景)中物体的识别问题。生物视觉系统已经成功地解决了视觉问题，本项目的理念是试图从灵长类视觉系统的信息处理中提取原理，并将其应用于目标识别算法的设计。其目标是了解如何在模仿灵长类大脑中物体识别路径布局的分层体系结构中实现复杂环境中的物体识别，并建立一个能够识别复杂日常场景中的大量物体的演示系统。特别是，本项目将重点关注三个处理原则：层次表示、海量反馈和主动场景分析。如果成功，该项目将进一步加深我们对如何使用基于分层视图的对象表示来识别对象、如何从未分割的训练图像中学习这些表示以及反馈如何在这种分层识别架构中帮助识别的理解。这可能会为计算机视觉系统开辟一系列新的应用领域，还可能导致对大脑中物体识别的更好理解。

For computers and robots to live up to their full potential as human assistants, they must be able to reliably perceive humans and objects in their environment. This project addresses the recognition of objects in complex everyday scenes (e.g.\ office, household, or traffic scenes). Biological vision systems have successfully solved the vision problem and the philosophy of this project is to try to extract principles from the information processing in the primate visual system and to apply them in the design of object recognition algorithms. The goal is to understand how object recognition in complex environments can be achieved in a hierarchical architecture that mimics the layout of the object recognition pathway in the primate brain, and to build a demonstration system capable of recognizing a large number of objects in complex everyday scenes. In particular, this project will focus on three processing principles: hierarchical representations, massive feedback, and active scene analysis. If successful, the project will further our understanding of how objects can be recognized using hierarchical view based object representations, how these representations can be learned from unsegmented training images, and how feedback can aid recognition in this kind of hierarchical recognition architecture. This will potentially open a range of new application areas for computer vision systems and may also lead to a better understanding of object recognition in the brain.