Yuntao Cui, S. Samarasekera, Qian Huang, Michael Grei
{"title":"Indoor monitoring via the collaboration between a peripheral sensor and a foveal sensor","authors":"Yuntao Cui, S. Samarasekera, Qian Huang, Michael Grei","doi":"10.1109/WVS.1998.646014","DOIUrl":null,"url":null,"abstract":"In this paper, we describe a novel setup which uses a peripheral sensor and a foveal sensor to perform the indoor monitoring task. The system has the following features: 1) it is constantly aware of the global surrounding, 2) it can dynamically determine its attention to focus on some important events, 3) it achieves real time and reliable performance. In the current implementation, we focus on the events which are triggered by moving persons. Two types of visual agents are used to track moving objects: a peripheral sensing agent that performs global monitoring tasks and a foveal agent that performs focused monitoring tasks. These two heterogeneous sensing agents are coupled in a unique way to work not only asynchronously but also collaboratively via a facilitator. Compared with existing approaches, the proposed scheme provides many advantages in handling the unrestricted movement and various types of occlusions.","PeriodicalId":359599,"journal":{"name":"Proceedings 1998 IEEE Workshop on Visual Surveillance","volume":"153 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"68","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 1998 IEEE Workshop on Visual Surveillance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WVS.1998.646014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 68
Abstract
In this paper, we describe a novel setup which uses a peripheral sensor and a foveal sensor to perform the indoor monitoring task. The system has the following features: 1) it is constantly aware of the global surrounding, 2) it can dynamically determine its attention to focus on some important events, 3) it achieves real time and reliable performance. In the current implementation, we focus on the events which are triggered by moving persons. Two types of visual agents are used to track moving objects: a peripheral sensing agent that performs global monitoring tasks and a foveal agent that performs focused monitoring tasks. These two heterogeneous sensing agents are coupled in a unique way to work not only asynchronously but also collaboratively via a facilitator. Compared with existing approaches, the proposed scheme provides many advantages in handling the unrestricted movement and various types of occlusions.