JIPS (한국정보처리학회)
Current Result Document :
| 한글제목(Korean Title) |
Object Tracking with the Multi-Templates Regression Model Based MS Algorithm |
| 영문제목(English Title) |
Object Tracking with the Multi-Templates Regression Model Based MS Algorithm |
| 저자(Author) |
Hua Zhang
Lijia Wang
|
| 원문수록처(Citation) |
VOL 14 NO. 06 PP. 1307 ~ 1317 (2018. 12) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
To deal with the problems of occlusion, pose variations and illumination changes in the object tracking system, a regression model weighted multi-templates mean-shift (MS) algorithm is proposed in this paper. Target templates and occlusion templates are extracted to compose a multi-templates set. Then, the MS algorithm is applied to the multi-templates set for obtaining the candidate areas. Moreover, a regression model is trained to estimate the Bhattacharyya coefficients between the templates and candidate areas. Finally, the geometric center of the tracked areas is considered as the object’s position. The proposed algorithm is evaluated on several classical videos. The experimental results show that the regression model weighted multitemplates MS algorithm can track an object accurately in terms of occlusion, illumination changes and pose variations.
|
| 키워드(Keyword) |
Mean Shift Algorithm
Multi-Templates
Object tracking
Regression Model
|
| 파일첨부 |
PDF 다운로드
|
