RI: A Context-Based Approach to the Recognition and Localization of Visual Object Categories

提案0713185 PI：Daniel Huttenlocher研究所：康奈尔大学标题：RI：基于上下文的视觉对象类别识别和本地化方法本项目的主要目标是通过将问题描述为单一的总体估计问题，实现对象类别识别和本地化的稳健性的质的改进。相比之下，大多数当前的方法依赖于连续的处理阶段，在该阶段中，首先检测单个特征，然后将这些特征组合以检测对象。该项目的一个中心焦点不仅是确定图像中存在哪些对象，还包括定位这些对象及其子部分。对象被建模为以可变形配置排列的局部面片的集合，其中某些部分对通过类似弹簧的连接来连接。这些模型提供了一种利用本地上下文信息的方法，延迟关于单个特征是否存在的决定，直到更多地了解其他特征以及它们之间的空间关系。这样的模型还可以适用于表示场景级上下文的更大问题，编码紧邻对象周围的上下文和场景中对象之间的更长范围的关系。该项目正在研究如何在一个基于整体优化的框架内使用局部上下文来改进特征和对象的检测，以及使用场景上下文来改进对象和对象之间的关系的检测。对象的准确识别和定位对于使用计算机视觉与世界交互的应用和系统至关重要，例如移动机器人、自动车辆、互动游戏、动画和电影制作、危险情况的远程操作和远程手术。在这样的应用中，计算机视觉系统不仅必须确定场景中是否存在对象，而且还必须识别对象的位置以及它们的姿势或配置。例如，检测汽车安全系统中的行人也应该通知汽车和司机行人的位置。在远程操作和交互式游戏等应用中，需要更详细地了解人的姿势和手势，以实现对复杂系统的免提控制。该项目寻求通过采取一种方法来提高这类系统的能力，方法是将多个信息源同时合并为一个整体决策，而不是做出多个可能每个都可能出错的较小决策。该项目的进展情况将定期在http：//www.cs.cornell.edu/~dph/Context/上报告

Abstract for Proposal 0713185 PI: Daniel HuttenlocherInstitution: Cornell UniversityTitle: RI: A Context-Based Approach to the Recognition and Localization of Visual Object CategoriesThe primary goal of this project is to achieve a qualitative improvement in the robustness of object category recognition and localization, by formulating the problem as a single overall estimation problem. In contrast, most current approaches rely on successive stages of processing, in which individual features are first detected and then those features are combined in order to detect objects. A central focus of the project is not only to determine which objects are present in an image but also to localize those objects and their subparts. Objects are modeled as a collection of local patches arranged in a deformable configuration, where certain pairs of parts are connected by spring-like connections. These models provide a way of exploiting local contextual information, delaying decisions about the presence or absence of individual features until more is known about other features and the spatial relations between them. Such models can further be adapted to the larger problem of representing scene-level context, encoding both the context immediately around an object and more long-range relationships between objects in a scene. This project is investigating both the use of local context to improve detection of features and objects, and the use of scene context to improve the detection of objects and relations between objects, within a single overall optimization-based framework.Accurate recognition and localization of objects is of central importance for applications and systems that use computer vision to interact with the world, such as mobile robots, autonomous vehicles, interactive games, animation and film-making, tele-operation for hazardous situations, and remote surgery. In such applications, a computer vision system must not only determine whether objects are present in a scene, but also identify where the objects are and what pose or configuration they are in. For instance, detecting a pedestrian for an automotive safety system should also inform the car and driver where the pedestrian is located. In applications such as tele-operation and interactive games, further detail about a person's pose and gestures are required to enable hands-free control of complex systems. This project seeks to advance the capability of such systems by taking an approach based on simultaneously combining multiple sources of information into a single overall decision, rather than making multiple smaller decisions that are each potentially error-proneProgress on this project will be regularly reported at http:// www.cs.cornell.edu/~dph/context/