https://scholars.lib.ntu.edu.tw/handle/123456789/607210
標題: | Multi-viewpoint patterns and occlusions handling using hybrid features for vehicle tracking | 作者: | Wu C.-W JIAN-JIUN DING |
關鍵字: | Excluding overlapping part;Occlusion;Partial sections;Salient features;Vehicle tracking;Motion compensation;Object detection;Hybrid features;Including rule;Learning-based methods;Multi-viewpoints;Partial similarities;Saliency features;State of the art;Tracking algorithm;Hybrid vehicles | 公開日期: | 2021 | 卷: | 2021-May | 來源出版物: | Proceedings - IEEE International Symposium on Circuits and Systems | 摘要: | A novel vehicle tracking algorithm robust to multi-viewpoint pattern and occlusion is proposed. To improve accuracy, after object detection, the overlapping parts of bounding boxes are removed before block matching. It is helpful for reducing the interference from nearby vehicles or objects. To perform block matching well, in addition to partial similarity and position correlation, many advanced features, including saliency features and several new global features, are adopted. These features can retrieve important information from vehicles and are helpful for tracking. Experiments show that the proposed algorithm achieves favorable performance against state-of-the-art vehicle tracking methods, including rule-based and learning-based methods. ? 2021 IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85109011908&doi=10.1109%2fISCAS51556.2021.9401298&partnerID=40&md5=6cca2e1f2857c8b9b1fbe1c92bd3cbc6 https://scholars.lib.ntu.edu.tw/handle/123456789/607210 |
ISSN: | 02714310 | DOI: | 10.1109/ISCAS51556.2021.9401298 |
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。