Summary
|
For Full-Text PDF, please login, if you are a member of IEICE, or go to Pay Per View on menu list, if you are a nonmember of IEICE. |
|
A Fast Non-Overlapping Multi-Camera People Re-Identification Algorithm and Tracking Based on Visual Channel Model Chi-Chia SUN Ming-Hwa SHEU Jui-Yang CHI Yan-Kai HUANG Publication IEICE TRANSACTIONS on Information and Systems Vol.E102-D No.7 pp.1342-1348 Publication Date: 2019/07/01 Publicized: 2019/04/18 Online ISSN: 1745-1361 DOI: 10.1587/transinf.2018EDP7348 Type of Manuscript: PAPER Category: Image Processing and Video Processing Keyword: multi-camera, people re-identification, visual channel model, embedded, Full Text: PDF(3.4MB)>>
Summary: In this paper, a nonoverlapping multi-camera and people re-identification algorithm is proposed. It applies inflated major color features for re-identification to reduce computation time. The inflated major color features can dramatically improve efficiency while retaining high accuracy of object re-identification. The proposed method is evaluated over a wide range of experimental databases. The accuracy attains upwards of 40.7% in Rank 1 and 84% in Rank 10 on average, while it obtains three to 15 times faster than algorithms reported in the literature. The proposed algorithm has been implemented on a SOC-FPGA platform to reach 50 FPS with 1280×720 HD resolution and 25 FPS with 1920×1080 FHD resolution for real-time processing. The results show a performance improvement and reduction in computation complexity, which is especially ideal for embedded platform. | ||||||||||
| ||||||||||