TIIS (Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Multiple-Shot Person Re-identification by Features Learned from Third-party Image Sets |
¿µ¹®Á¦¸ñ(English Title) |
Multiple-Shot Person Re-identification by Features Learned from Third-party Image Sets |
ÀúÀÚ(Author) |
Yanna Zhao
Lei Wang
Xu Zhao
Yuncai Liu
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 09 NO. 02 PP. 0775 ~ 0792 (2015. 02) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Person re-identification is an important and challenging task in computer vision with numerous real world applications. Despite significant progress has been made in the past few years, person re-identification remains an unsolved problem. This paper presents a novel appearance-based approach to person re-identification. The approach exploits region covariance matrix and color histograms to capture the statistical properties and chromatic information of each object. Robustness against low resolution, viewpoint changes and pose variations is achieved by a novel signature, that is, the combination of Log Covariance Matrix feature and HSV histogram (LCMH). In order to further improve re-identification performance, third-party image sets are utilized as a common reference to sufficiently represent any image set with the same type. Distinctive and reliable features for a given image set are extracted through decision boundary between the specific set and a third-party image set supervised by max-margin criteria. This method enables the usage of an existing dataset to represent new image data without time-consuming data collection and annotation. Comparisons with state-of-the-art methods carried out on benchmark datasets demonstrate promising performance of our method.
|
Å°¿öµå(Keyword) |
Person re-identification
Appearance modeling
Max-margin feature learning
Covariance matrix
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|