https://scholars.lib.ntu.edu.tw/handle/123456789/369694
標題: | A high speed feature matching architecture for real-time video stabilization | 作者: | Huang, K.-Y. Tsai, Y.-M. Yang, T.-J. LIANG-GEE CHEN |
公開日期: | 2012 | 起(迄)頁: | 1436-1439 | 來源出版物: | ISCAS 2012 - 2012 IEEE International Symposium on Circuits and Systems | 會議論文: | 2012 IEEE International Symposium on Circuits and Systems, ISCAS 2012 | 摘要: | An efficient feature matching architecture targets at real-time video stabilization is revealed in this paper. For some applications, such as vehicular application, real-time video stabilization is needed to provide instant stable video input. However, feature matching is usually the bottleneck to achieve high performance. High speed feature matching architecture is proposed to accelerate the performance of video stabilization. Locality sensitive hashing (LSH) helps us realize the feature matching procedure in hardware implementation. By applying the proposed dynamic table allocation and on-chip cache mechanism, this work achieves 422K queries/s and real-time feature matching with 90% in memory reduction and more than 50% in relieving the feature bus burden of the system. © 2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84866623100&doi=10.1109%2fISCAS.2012.6271515&partnerID=40&md5=faa55f5f2c04dfcbda43c8ad1a10459d http://scholars.lib.ntu.edu.tw/handle/123456789/369694 |
DOI: | 10.1109/ISCAS.2012.6271515 | SDG/關鍵字: | Dynamic table; Feature matching; Hardware implementations; Locality sensitive hashing; Memory reduction; On-chip cache; Real time videos; Real-time features; Vehicular applications; Video stabilization; Hardware; Stabilization |
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。