ABSTRACT
Person re-identification is a difficult task due to variations of person pose, scale changes, different illumination, occlusions, to name a few important factors usually diminishing identification performance across different views. In this work, we train a siamese and triplet convolutional neural networks and show that they can achieve promising recognition ratios. In order to cope with spatial transformations and scale changes across multi-view images we employ deformable convolutions in a triplet convolutional neural network. We propose an unified neural network architecture consisting of three triplet convolutional neural networks to jointly learn both the local body-parts features and full-body descriptors. We demonstrate experimentally that it achieves comparable results with results achieved by state-of-the-arts methods.
- R. Vezzani, D. Baltieri, and R. Cucchiara, "People reidentification in surveillance and forensics: A survey," ACM Comput. Surv., vol. 46, no. 2, pp. 29:1--29:37, 2013. Google ScholarDigital Library
- S. Paisitkriangkrai, C. Shen, and A. van den Hengel, "Learning to rank in person re-identification with metric ensembles," in CVPR. IEEE Computer Society, 2015, pp. 1846--1855.Google Scholar
- B. Ma, Y. Su, and F. Jurie, "Local descriptors encoded by fisher vectors for person re-identification," in Proc. of the 12th Int. Conf. on Computer Vision - Part I. Springer, 2012, pp. 413--422. Google ScholarDigital Library
- B. Ma, Y. Su, and F. Jurie, "Covariance descriptor based on bio-inspired features for person re-identification and face verification," Image and Vision Computing, vol. 32, no. 6...7, pp. 379--390, 2014.Google Scholar
- Z. Li, S. Chang, F. Liang, T. S. Huang, L. Cao, and J. R. Smith, "Learning locally-adaptive decision functions for person verification," in IEEE Conf. on CVPR., June 2013, pp. 3610--3617. Google ScholarDigital Library
- F. Xiong, M. Gou, O. Camps, and M. Sznaier, Person Re-Identification Using Kernel-Based Metric Learning Methods. Springer, 2014, pp. 1--16.Google Scholar
- W.-S. Zheng, S. Gong, and T. Xiang, "Reidentification by relative distance comparison," IEEE Trans. Patern Anal. Mach. Intell., vol. 35, no. 3, pp. 653--668, 2013. Google ScholarDigital Library
- R. Zhao, W. Ouyang, and X. Wang, "Learning mid-level filters for person re-identification," in IEEE Conf. on Computer Vision and Patern Rec., 2014, pp. 144--151. Google ScholarDigital Library
- T. Matsukawa, T. Okabe, E. Suzuki, and Y. Sato, "Hierarchical gaussian descriptor for person re-identification," in IEEE Conf. on Computer Vision and Patern Rec., 2016, pp. 1363--1372.Google Scholar
- M. Hirzer, "Large scale metric learning from equivalence constraints," in CVPR, 2012, pp. 2288--2295. Google ScholarDigital Library
- W. Li and X. Wang, "Locally aligned feature transforms across views," in CVPR, 2013, pp. 3594--3601. Google ScholarDigital Library
- R. Zhao, W. Ouyang, and X. Wang, "Person re-identification by salience matching," in ICCV, 2013, pp. 2528--2535. Google ScholarDigital Library
- Z. Zhang, Y. Chen, and V. Saligrama, "Group membership prediction," in ICCV, 2015, pp. 3916--3924. Google ScholarDigital Library
- M. Song, S. Gong, C. Liu, Y. Ji, and H. Dong, "Person re-identification by improved local maximal occurrence with color names," in 8th Int. Congress on Image and Signal Processing (CISP), 2015, pp. 675--679.Google Scholar
- W. Li, R. Zhao, T. Xiao, and X. Wang, "Deepreid: Deep filter pairing neural network for person re-identification," in CVPR, 2014, pp. 152--159. Google ScholarDigital Library
- J. Bromley, I. Guyon, Y. LeCun, E. Säckinger, and R. Shah, "Signature verification using a "siamese" time delay neural network," in Proc. of the 6th Int. Conf. on Neural Information Processing Systems, 1993, pp. 737--744. Google ScholarDigital Library
- S. Chopra, R. Hadsell, and Y. LeCun, "Learning a similarity metric discriminatively, with application to face verification," in CVPR, 2005, pp. 539--546. Google ScholarDigital Library
- R. Hadsell, S. Chopra, and Y. LeCun, "Dimensionality reduction by learning an invariant mapping," in CVPR, 2006, pp. 1735--1742. Google ScholarDigital Library
- D. Yi, Z. Lei, S. Liao, and S. Z. Li, "Deep metric learning for person re-identification," in 22nd Int. Conf. on Patern Rec., 2014, pp. 34--39. Google ScholarDigital Library
- E. Ahmed, M.Jones, and T. Marks, "An improved deep learning architecture for person re-identification," in IEEE Conf. on Comp. Vision and Patern Rec., 2015, pp. 3908--3916.Google Scholar
- R. R. Varior, M. Haloi, and G. Wang, Gated Siamese Convolutional Neural Network Architecture for Human Re-identification. Springer, 2016, pp. 791--808.Google Scholar
- X. Deng, B. Ma, H. Chang, S. Shan, and X. Chen, Deep Second-Order Siamese Network for Pedestrian Re-identification. Springer, 2017, pp. 321--337.Google Scholar
- D. Cheng, Y. Gong, S. Zhou, J. Wang, and N. Zheng, "Person re-identification by multi-channel parts-based CNN with improved triplet loss function," in CVPR, 2016, pp. 1335--1344.Google Scholar
- J. Liu, Z.-J. Zha, Q. Tian, D. Liu, T. Yao, Q. Ling, and T. Mei, "Multi-scale triplet CNN for person re-identification," in Proc. of the ACM on Multimedia Conf., 2016, pp. 192--196. Google ScholarDigital Library
- A. Bedagkar-Gala and S. K. Shah, "Editor's choice article: A survey of approaches and trends in person re-identification," Image Vision Comput., vol. 32, no. 4, pp. 270--286, 2014. Google ScholarDigital Library
- Y. LeCun, L. Botou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," in Proc. of the IEEE, 1998, pp. 2278--2324.Google ScholarCross Ref
- E. Hoffer and N. Ailon, Deep Metric Learning Using Triplet Network. Springer, 2015, pp. 84--92.Google Scholar
- J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, H. Hu, and Y. Wei, "Deformable convolutional networks," 2017.Google Scholar
- D. Yi, Z. Lei, and S. Z. Li, "Deep metric learning for practical person re-identification," CoRR, 2014.Google Scholar
- L. van der Maaten and G. Hinton, "Visualizing high-dimensional data using t-SNE," Journal of Machine Learning Research, vol. 9, pp. 2579--2605, 2008.Google Scholar
- F. Schroff, D. Kalenichenko, and J. Philbin, "Facenet: A unified embedding for face rec. and clustering," in IEEE Conf. on Computer Vision and Patern Rec., 2015, pp. 815--823.Google Scholar
Index Terms
- Person Re-Identification Using Multi-region Triplet Convolutional Network
Recommendations
Cross-dataset person re-identification using deep convolutional neural networks: effects of context and domain adaptation
Over the past years, the impact of surveillance systems on public safety increases dramatically. One significant challenge in this domain is person re-identification, which aims to detect whether a person has already been captured by another camera in ...
Novel multi-convolutional neural network fusion approach for smile recognition
The smile is one of the most common human facial expressions encountered in our daily lives. Smile recognition can be used in many scenarios, such as emotion monitoring, human-to-robot games, and camera shutter control, which is why smile recognition ...
Deep feature embedding learning for person re-identification based on lifted structured loss
Person re-identification (re-id) aims at matching the same individual in videos captured by multiple cameras, and much progress has been made in recent years due to large scale pedestrian data sets and deep learning-based techniques. In this paper, we ...
Comments