基于二元时间关系的多智能体动作视觉识别

Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149) Pub Date : 1999-06-23 DOI:10.1109/CVPR.1999.786917

S. Intille, A. Bobick

{"title":"基于二元时间关系的多智能体动作视觉识别","authors":"S. Intille, A. Bobick","doi":"10.1109/CVPR.1999.786917","DOIUrl":null,"url":null,"abstract":"A probabilistic framework for representing and visually recognizing complex multi-agent action is presented. Motivated by work in model-based object recognition and designed for the recognition of action from visual evidence, the representation has three components: (1) temporal structure descriptions representing the temporal relationships between agent goals, (2) belief networks for probabilistically representing and recognizing individual agent goals from visual evidence, and (3) belief networks automatically generated from the temporal structure descriptions that support the recognition of the complex action. We describe our current work on recognizing American football plays from noisy trajectory data.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"24","resultStr":"{\"title\":\"Visual recognition of multi-agent action using binary temporal relations\",\"authors\":\"S. Intille, A. Bobick\",\"doi\":\"10.1109/CVPR.1999.786917\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A probabilistic framework for representing and visually recognizing complex multi-agent action is presented. Motivated by work in model-based object recognition and designed for the recognition of action from visual evidence, the representation has three components: (1) temporal structure descriptions representing the temporal relationships between agent goals, (2) belief networks for probabilistically representing and recognizing individual agent goals from visual evidence, and (3) belief networks automatically generated from the temporal structure descriptions that support the recognition of the complex action. We describe our current work on recognizing American football plays from noisy trajectory data.\",\"PeriodicalId\":20644,\"journal\":{\"name\":\"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1999-06-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"24\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CVPR.1999.786917\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.1999.786917","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 24

摘要

提出了一种表示和视觉识别复杂多智能体动作的概率框架。受基于模型的对象识别工作的启发，并设计用于从视觉证据中识别动作，该表示有三个组成部分:(1)表征智能体目标间时间关系的时间结构描述;(2)基于视觉证据概率表征和识别单个智能体目标的信念网络;(3)基于时间结构描述自动生成的支持复杂动作识别的信念网络。我们描述了我们目前在从噪声轨迹数据中识别美式足球比赛方面的工作。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Visual recognition of multi-agent action using binary temporal relations

A probabilistic framework for representing and visually recognizing complex multi-agent action is presented. Motivated by work in model-based object recognition and designed for the recognition of action from visual evidence, the representation has three components: (1) temporal structure descriptions representing the temporal relationships between agent goals, (2) belief networks for probabilistically representing and recognizing individual agent goals from visual evidence, and (3) belief networks automatically generated from the temporal structure descriptions that support the recognition of the complex action. We describe our current work on recognizing American football plays from noisy trajectory data.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)

自引率

0.00%

发文量