https://scholars.lib.ntu.edu.tw/handle/123456789/124412
標題: | An Adaptive Learning Method for Target Tracking across Multiple Cameras | 作者: | KUAN-WEN CHEN Lai, Chih-Chuan YI-PING HUNG CHU-SONG CHEN |
公開日期: | 2008 | 起(迄)頁: | 1 | 來源出版物: | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR | 摘要: | This paper proposes an adaptive learning method for tracking targets across multiple cameras with disjoint views. Two visual cues are usually employed for tracking targets across cameras: spatio-temporal cue and appearance cue. To learn the relationships among cameras, traditional methods used batch-learning procedures or hand-labeled correspondence, which can work well only within a short period of time. In this paper, we propose an unsupervised method which learns both spatio-temporal relationships and appearance relationships adaptively and can be applied to long-term monitoring. Our method performs target tracking across multiple cameras while also considering the environment changes, such as sudden lighting changes. Also, we improve the estimation of spatio-temporal relationships by using the prior knowledge of camera network topology. ©2008 IEEE. |
URI: | http://ntur.lib.ntu.edu.tw//handle/246246/232897 https://www.scopus.com/inward/record.uri?eid=2-s2.0-51949115376&doi=10.1109%2fCVPR.2008.4587505&partnerID=40&md5=0b3c1ea049901e1b7c38111c4ee69596 |
DOI: | 10.1109/CVPR.2008.4587505 | SDG/關鍵字: | Artificial intelligence; Cameras; Computer vision; Education; Electric network topology; Feature extraction; Image processing; Pattern recognition; Targets; Video cameras; Adaptive learning method; Camera networks; Learning procedures; Lighting changes; Long-term monitoring; Multiple cameras; Prior knowledge; Spatio-Temporal; Spatio-temporal relationships; Tracking targets; Unsupervised method; Visual cues; Target tracking |
顯示於: | 資訊網路與多媒體研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。