https://scholars.lib.ntu.edu.tw/handle/123456789/500527
標題: | Multi-cue integration for multi-camera tracking | 作者: | Chen, K.-W. YI-PING HUNG |
公開日期: | 2010 | 起(迄)頁: | 145-148 | 來源出版物: | Proceedings - International Conference on Pattern Recognition | 摘要: | For target tracking across multiple cameras with disjoint views, previous works usually employed multiple cues and focused on learning a better matching model of each cue, separately. However, none of them had discussed how to integrate these cues to improve performance, to our best knowledge. In this paper, we look into the multi-cue integration problem and propose an unsupervised learning method since a complicated training phase is not always viable. In the experiments, we evaluate several types of score fusion methods and show that our approach learns well and can be applied to large camera networks more easily. © 2010 IEEE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/500527 https://www.scopus.com/inward/record.uri?eid=2-s2.0-78149481241&doi=10.1109%2fICPR.2010.44&partnerID=40&md5=ecc80a3f33b8914bfe20fb6200675855 |
ISSN: | 10514651 | DOI: | 10.1109/ICPR.2010.44 | SDG/關鍵字: | Camera network; Cue integration; Disjoint views; Matching models; Multi-camera tracking; Multiple cameras; Score fusion; Training phase; Unsupervised learning method; Pattern recognition; Target tracking; Unsupervised learning; Video cameras; Cameras |
顯示於: | 電機工程學系 |
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。