RI: Medium: Active Scene Interpretation by Entropy Pursuit

RI：中：熵追踪的活动场景解释

• 批准号: 0964416
• 负责人: Donald Geman
• 金额: $ 79.48万
• 依托单位: Johns Hopkins University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-07-01 至 2014-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0964416&HistoricalAwards=false
• 关键词: RI; Medium; Active; Scene; Interpretation

This project develops a new strategy for scene interpretation, especially for annotating cluttered scenes with instances from many object categories (e.g., a kitchen scene) and videos of people interacting with objects in everyday life (e.g., cooking). The research team develops a statistical model for scene interpretations and image measurements. One component of the model is a prior distribution on a huge interpretation vector. Each bit of this vector represents a high-level scene attribute with widely varying degrees of specificity and resolution ? some are very coarse (general hypotheses) and some are very fine (specific hypotheses). The other component is a simple conditional data model for a corresponding family of learned binary classifiers, one per bit. The scene interpretation is then computed by assessing hypotheses in a highly coarse-to-fine manner, using an image parsing algorithm called ?entropy pursuit? based on stepwise uncertainty reduction, and classifiers for detecting events in spatiotemporal volumes which leverage on recent advances at the intersection of machine learning and dynamical systems. The computational models and scene parsing algorithms developed in this project are broadly applicable to scene interpretation problems arising in many areas of science and engineering. Specific applications include home surveillance and security, assisted home living, infant and elderly care, etc. The project also provides research opportunities for graduate students in underrepresented minorities and even high school students.

这个项目开发了一种新的场景解释策略，特别是用来自许多对象类别的实例(例如厨房场景)和人们与日常生活中的对象交互的视频(例如烹饪)来注释杂乱的场景。研究小组开发了一个用于场景解释和图像测量的统计模型。该模型的一个组成部分是在巨大的解释向量上的先验分布。这个向量的每一位都代表一个高级别的场景属性，具有非常不同的特异性和分辨率？有些是非常粗略的(一般假设)，有些是非常精细的(特定假设)。另一个组件是对应的学习二分分类器家族的简单条件数据模型，每个比特一个。然后，通过以从粗到精的方式评估假设来计算场景解释，使用一种称为？熵追踪？的图像分析算法。基于逐步的不确定性减少，以及用于检测时空体积中的事件的分类器，该分类器利用机器学习和动态系统的交叉点的最新进展。本项目中开发的计算模型和场景解析算法广泛适用于许多科学和工程领域中的场景解释问题。具体应用包括家庭监控和安全、辅助家庭生活、婴儿和老年人护理等。该项目还为代表性不足的少数族裔的研究生甚至高中生提供研究机会。