TY - GEN
T1 - Person re-identification based on hierarchical bipartite graph matching
AU - Huang, Yan
AU - Sheng, Hao
AU - Xiong, Zhang
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/8/3
Y1 - 2016/8/3
N2 - This work proposes a novel person re-identification method based on Hierarchical Bipartite Graph Matching. Because human eyes observe person appearance roughly first and then goes further into the details gradually, our method abstracts person image from coarse to fine granularity, and finally into a three layer tree structure. Then, three bipartite graph matching methods are proposed for the matching of each layer between the trees. At the bottom layer Non-complete Bipartite Graph matching is proposed to collect matching pairs among small local regions. At the middle layer Semi-complete Bipartite Graph matching is used to deal with the problem of spatial misalignment between two person bodies. Complete Bipartite Graph matching is presented to refine the ranking result at the top layer. The effectiveness of our method is validated on the CAVIAR4REID and VIPeR datasets, and competitive results are achieved on both datasets.
AB - This work proposes a novel person re-identification method based on Hierarchical Bipartite Graph Matching. Because human eyes observe person appearance roughly first and then goes further into the details gradually, our method abstracts person image from coarse to fine granularity, and finally into a three layer tree structure. Then, three bipartite graph matching methods are proposed for the matching of each layer between the trees. At the bottom layer Non-complete Bipartite Graph matching is proposed to collect matching pairs among small local regions. At the middle layer Semi-complete Bipartite Graph matching is used to deal with the problem of spatial misalignment between two person bodies. Complete Bipartite Graph matching is presented to refine the ranking result at the top layer. The effectiveness of our method is validated on the CAVIAR4REID and VIPeR datasets, and competitive results are achieved on both datasets.
KW - Bipartite graph matching
KW - Cross views
KW - Person re-identification
UR - https://www.scopus.com/pages/publications/85006716997
U2 - 10.1109/ICIP.2016.7533162
DO - 10.1109/ICIP.2016.7533162
M3 - 会议稿件
AN - SCOPUS:85006716997
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 4255
EP - 4259
BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PB - IEEE Computer Society
T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016
Y2 - 25 September 2016 through 28 September 2016
ER -