Deep Learning for Person Reidentification Using Support Vector Machines
Due to the variations of viewpoint, pose, and illumination, a given individual may appear considerably different across different camera views. Tracking individuals across camera networks with no overlapping fields is still a challenging problem. Previous works mainly focus on feature representation...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-01-01
|
| Series: | Advances in Multimedia |
| Online Access: | http://dx.doi.org/10.1155/2017/9874345 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832564685970341888 |
|---|---|
| author | Mengyu Xu Zhenmin Tang Yazhou Yao Lingxiang Yao Huafeng Liu Jingsong Xu |
| author_facet | Mengyu Xu Zhenmin Tang Yazhou Yao Lingxiang Yao Huafeng Liu Jingsong Xu |
| author_sort | Mengyu Xu |
| collection | DOAJ |
| description | Due to the variations of viewpoint, pose, and illumination, a given individual may appear considerably different across different camera views. Tracking individuals across camera networks with no overlapping fields is still a challenging problem. Previous works mainly focus on feature representation and metric learning individually which tend to have a suboptimal solution. To address this issue, in this work, we propose a novel framework to do the feature representation learning and metric learning jointly. Different from previous works, we represent the pairs of pedestrian images as new resized input and use linear Support Vector Machine to replace softmax activation function for similarity learning. Particularly, dropout and data augmentation techniques are also employed in this model to prevent the network from overfitting. Extensive experiments on two publically available datasets VIPeR and CUHK01 demonstrate the effectiveness of our proposed approach. |
| format | Article |
| id | doaj-art-60f2e7aeffea4edcade2d18b74840823 |
| institution | Kabale University |
| issn | 1687-5680 1687-5699 |
| language | English |
| publishDate | 2017-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Multimedia |
| spelling | doaj-art-60f2e7aeffea4edcade2d18b748408232025-02-03T01:10:27ZengWileyAdvances in Multimedia1687-56801687-56992017-01-01201710.1155/2017/98743459874345Deep Learning for Person Reidentification Using Support Vector MachinesMengyu Xu0Zhenmin Tang1Yazhou Yao2Lingxiang Yao3Huafeng Liu4Jingsong Xu5Nanjing University of Science and Technology, Nanjing 210094, ChinaNanjing University of Science and Technology, Nanjing 210094, ChinaNanjing University of Science and Technology, Nanjing 210094, ChinaNanjing University of Science and Technology, Nanjing 210094, ChinaNanjing University of Science and Technology, Nanjing 210094, ChinaNanjing University of Science and Technology, Nanjing 210094, ChinaDue to the variations of viewpoint, pose, and illumination, a given individual may appear considerably different across different camera views. Tracking individuals across camera networks with no overlapping fields is still a challenging problem. Previous works mainly focus on feature representation and metric learning individually which tend to have a suboptimal solution. To address this issue, in this work, we propose a novel framework to do the feature representation learning and metric learning jointly. Different from previous works, we represent the pairs of pedestrian images as new resized input and use linear Support Vector Machine to replace softmax activation function for similarity learning. Particularly, dropout and data augmentation techniques are also employed in this model to prevent the network from overfitting. Extensive experiments on two publically available datasets VIPeR and CUHK01 demonstrate the effectiveness of our proposed approach.http://dx.doi.org/10.1155/2017/9874345 |
| spellingShingle | Mengyu Xu Zhenmin Tang Yazhou Yao Lingxiang Yao Huafeng Liu Jingsong Xu Deep Learning for Person Reidentification Using Support Vector Machines Advances in Multimedia |
| title | Deep Learning for Person Reidentification Using Support Vector Machines |
| title_full | Deep Learning for Person Reidentification Using Support Vector Machines |
| title_fullStr | Deep Learning for Person Reidentification Using Support Vector Machines |
| title_full_unstemmed | Deep Learning for Person Reidentification Using Support Vector Machines |
| title_short | Deep Learning for Person Reidentification Using Support Vector Machines |
| title_sort | deep learning for person reidentification using support vector machines |
| url | http://dx.doi.org/10.1155/2017/9874345 |
| work_keys_str_mv | AT mengyuxu deeplearningforpersonreidentificationusingsupportvectormachines AT zhenmintang deeplearningforpersonreidentificationusingsupportvectormachines AT yazhouyao deeplearningforpersonreidentificationusingsupportvectormachines AT lingxiangyao deeplearningforpersonreidentificationusingsupportvectormachines AT huafengliu deeplearningforpersonreidentificationusingsupportvectormachines AT jingsongxu deeplearningforpersonreidentificationusingsupportvectormachines |