Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques
Fusion techniques with the aim to leverage the discriminative power of different appearance features for person representation have been widely applied in person re-identification. They are performed by concatenating all feature vectors (known as early fusion) or by combining matching scores of diff...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2021-08-01
|
| Series: | Vietnam Journal of Computer Science |
| Subjects: | |
| Online Access: | http://www.worldscientific.com/doi/epdf/10.1142/S2196888821500172 |
| _version_ | 1819093358532886528 |
|---|---|
| author | Hong-Quan Nguyen Thuy-Binh Nguyen Thi-Lan Le |
| author_facet | Hong-Quan Nguyen Thuy-Binh Nguyen Thi-Lan Le |
| author_sort | Hong-Quan Nguyen |
| collection | DOAJ |
| description | Fusion techniques with the aim to leverage the discriminative power of different appearance features for person representation have been widely applied in person re-identification. They are performed by concatenating all feature vectors (known as early fusion) or by combining matching scores of different classifiers (known as late fusion). Previous studies have proved that late fusion techniques achieve better results than early fusion ones. However, majority of the studies focus on determining the suitable weighting schemes that can reflect the role of each feature. The determined weights are then integrated in conventional similarity functions, such as Cosine [L. Zheng, S. Wang, L. Tian, F. He, Z. Liu and Q. Tian, Queryadaptive late fusion for image search and person reidentification, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 1741–1750]. The contribution of this paper is two-fold. First, a robust person re-identification method by combining the metric learning with late fusion techniques is proposed. The metric learning method Cross-view Quadratic Discriminant Analysis (XQDA) is employed to learn a discriminant low dimensional subspace to minimize the intra-person distance while maximize the inter-person distance. Moreover, product rule-based and sum rule-based late fusion techniques are applied on these distances. Second, concerning feature engineering, the ResNet extraction process has been modified in order to extract local features of different stripes in person images. To show the effectiveness of the proposed method, both single-shot and multi-shot scenarios are considered. Three state-of-the-art features that are Gaussians of Gaussians (GOG), Local Maximal Occurrence (LOMO) and deep-learned features extracted through a Residual network (ResNet) are extracted from person images. The experimental results on three benchmark datasets that are iLIDS-VID, PRID-2011 and VIPeR show that the proposed method obtains+11.86%,+3.48% and+2.22% of improvement over the best results obtained with the single feature. The proposed method that achieves the accuracy of 85.73%, 93.82% and 50.85% at rank-1 for iLIDS-VID, PRID-2011 and VIPeR, respectively, outperforms different SOTA methods including deep learning ones. Source code is publicly available to facilitate the development of person re-ID system. |
| first_indexed | 2024-12-21T23:10:15Z |
| format | Article |
| id | doaj.art-542e5e565e614c81be78fa75a290fd03 |
| institution | Directory Open Access Journal |
| issn | 2196-8888 2196-8896 |
| language | English |
| last_indexed | 2024-12-21T23:10:15Z |
| publishDate | 2021-08-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Vietnam Journal of Computer Science |
| spelling | doaj.art-542e5e565e614c81be78fa75a290fd032022-12-21T18:47:02ZengWorld Scientific PublishingVietnam Journal of Computer Science2196-88882196-88962021-08-018339741510.1142/S219688882150017210.1142/S2196888821500172Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion TechniquesHong-Quan Nguyen0Thuy-Binh Nguyen1Thi-Lan Le2School of Electronics and Telecommunications, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electronics and Telecommunications, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Electronics and Telecommunications, Hanoi University of Science and Technology, Hanoi, VietnamFusion techniques with the aim to leverage the discriminative power of different appearance features for person representation have been widely applied in person re-identification. They are performed by concatenating all feature vectors (known as early fusion) or by combining matching scores of different classifiers (known as late fusion). Previous studies have proved that late fusion techniques achieve better results than early fusion ones. However, majority of the studies focus on determining the suitable weighting schemes that can reflect the role of each feature. The determined weights are then integrated in conventional similarity functions, such as Cosine [L. Zheng, S. Wang, L. Tian, F. He, Z. Liu and Q. Tian, Queryadaptive late fusion for image search and person reidentification, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 1741–1750]. The contribution of this paper is two-fold. First, a robust person re-identification method by combining the metric learning with late fusion techniques is proposed. The metric learning method Cross-view Quadratic Discriminant Analysis (XQDA) is employed to learn a discriminant low dimensional subspace to minimize the intra-person distance while maximize the inter-person distance. Moreover, product rule-based and sum rule-based late fusion techniques are applied on these distances. Second, concerning feature engineering, the ResNet extraction process has been modified in order to extract local features of different stripes in person images. To show the effectiveness of the proposed method, both single-shot and multi-shot scenarios are considered. Three state-of-the-art features that are Gaussians of Gaussians (GOG), Local Maximal Occurrence (LOMO) and deep-learned features extracted through a Residual network (ResNet) are extracted from person images. The experimental results on three benchmark datasets that are iLIDS-VID, PRID-2011 and VIPeR show that the proposed method obtains+11.86%,+3.48% and+2.22% of improvement over the best results obtained with the single feature. The proposed method that achieves the accuracy of 85.73%, 93.82% and 50.85% at rank-1 for iLIDS-VID, PRID-2011 and VIPeR, respectively, outperforms different SOTA methods including deep learning ones. Source code is publicly available to facilitate the development of person re-ID system.http://www.worldscientific.com/doi/epdf/10.1142/S2196888821500172person re-identificationfeature fusionmetric learninghand-crafted featuresdeep-learned features |
| spellingShingle | Hong-Quan Nguyen Thuy-Binh Nguyen Thi-Lan Le Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques Vietnam Journal of Computer Science person re-identification feature fusion metric learning hand-crafted features deep-learned features |
| title | Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques |
| title_full | Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques |
| title_fullStr | Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques |
| title_full_unstemmed | Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques |
| title_short | Robust Person Re-Identification Through the Combination of Metric Learning and Late Fusion Techniques |
| title_sort | robust person re identification through the combination of metric learning and late fusion techniques |
| topic | person re-identification feature fusion metric learning hand-crafted features deep-learned features |
| url | http://www.worldscientific.com/doi/epdf/10.1142/S2196888821500172 |
| work_keys_str_mv | AT hongquannguyen robustpersonreidentificationthroughthecombinationofmetriclearningandlatefusiontechniques AT thuybinhnguyen robustpersonreidentificationthroughthecombinationofmetriclearningandlatefusiontechniques AT thilanle robustpersonreidentificationthroughthecombinationofmetriclearningandlatefusiontechniques |