A comparative study of several feature extraction methods for person re-identification

Authors:
Zhao Yang;Lianwen Jin;Dapeng Tao
Affiliations:
College of Electronic and Information, South China University of Technology, China;College of Electronic and Information, South China University of Technology, China;College of Electronic and Information, South China University of Technology, China
Venue:
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
Year:
2012

Citing 8
Cited 0

Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Information-theoretic metric learning

Proceedings of the 24th international conference on Machine learning
Representing shape with a spatial pyramid kernel

Proceedings of the 6th ACM international conference on Image and video retrieval
Learning Discriminative Appearance-Based Models Using Partial Least Squares

SIBGRAPI '09 Proceedings of the 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing
Large scale metric learning from equivalence constraints

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Reidentification by Relative Distance Comparison

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Extracting meaningful features from images is essential for many computer vision tasks. In this paper, we propose color histogram based on locality-constrained linear coding (LLC) feature representation for person reidentification. We compare the performance of five features with five metric learning methods for person re-identification. Extensive experiments on two publically available benchmarking datasets are carried out to compare the performance of various features. There are two contributions in this study. First, we present a new feature extraction technique which integrates the LLC and color histogram for person re-identification. Second, we conduct quantitative and comparative experiments of various feature extractions in the context of person re-identification and some useful conclusions are made.