Abstract
Many features have been proposed to improve the accuracy of person re-identification. Due to the illumination and viewpoint changes between different cameras, individual feature is less discriminative to separate different persons. In this paper, we propose a saliency-weighted feature descriptor and global-local fusion optimization for person re-identification. Firstly, the weights on pixels are calculated via saliency detection method, then the computed weights are integrated into local maximal occurrence (LOMO) feature descriptor. Secondly, the saliency weights are used to update the metric learning distance in training so that we can learn a new metric matrix for testing. And then, the whole person image is divided into upper and lower halves. A novel global-local fusion method is proposed to combine local and global regions together in the most appropriate way. After that an optimization algorithm is proposed to learn the weights among upper half, lower half and the whole image. According to those weights, a final fused distance is obtained. Experimental results show that the proposed method outperforms many state-of-the-art person re-identification methods.
B. Luo—This work was supported in part by National Natural Science Foundation of China under Grant 61472002, 61572030 and 61671018, and Collegiate Natural Science Fund of Anhui Province under Grant KJ2017A014.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chai, Y., Ren, J., Zhao, H., Li, Y., Ren, J., Murray, P.: Hierarchical and multi-featured fusion for effective gait recognition under variable scenarios. Pattern Anal. Appl. 19(4), 905–917 (2016)
Chen, C.L., Xiang, T., Gong, S.: Multi-camera activity correlation analysis. In: CVPR, pp. 1988–1995 (2009)
Frintrop, S., Werner, T., Garcła, G.M.: Traditional saliency reloaded: a good old model in new shape. In: 2015 IEEE CVPR, pp. 82–90 (2015)
Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking (2007)
Han, K., Wan, W., et al.: Distance aggregation for person re-identification using simulated annealing algorithm. In: International Conference on Audio, Language and Image Processing, pp. 399–403 (2016)
Liao, S., Hu, Y., et al.: Person re-identification by local maximal occurrence representation and metric learning. In: CVPR, pp. 2197–2206 (2015)
Ren, J., Han, J., Mura, M.D.: Special issue on multimodal data fusion for multidimensional signal processing. Multidimens. Syst. Signal Process. 27(4), 1–5 (2016)
Wang, Z., Ren, J., Zhang, D., Sun, M., Jiang, J.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68–83 (2018)
Wu, S., Chen, Y.C., et al.: An enhanced deep feature representation for person re-identification. In: Applications of Computer Vision, pp. 1–8 (2016)
Yan, Y., Ren, J., Li, Y., Windmill, J., Ijomah, W.: Fusion of dominant colour and spatial layout features for effective image retrieval of coloured logos and trademarks. In: IEEE International Conference on Multimedia Big Data, pp. 306–311 (2015)
Yan, Y., Ren, J., Li, Y., Windmill, J.F.C., Ijomah, W., Chao, K.M.: Adaptive fusion of color and spatial features for noise-robust retrieval of colored logo and trademark images. Multidimens. Syst. Signal Process. 27(4), 1–24 (2016)
Yan, Y., et al.: Unsupervised image saliency detection with gestalt-laws guided optimization and visual attention based refinement. Pattern Recognit. 79, 65–78 (2018)
Yan, Y., et al.: Cognitive fusion of thermal and visible imagery for effective detection and tracking of pedestrians in videos. Cogn. Comput. 9, 1–11 (2017)
Yang, Y., Liao, S., et al.: Large scale similarity learning using similar pairs for person verification. In: AAAI, pp. 3655–3661 (2016)
Zheng, J., Liu, Y., Ren, J., Zhu, T., Yan, Y., Yang, H.: Fusion of block and keypoints based approaches for effective copy-move image forgery detection. Multidimens. Syst. Signal Process. 27(4), 989–1005 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, SB., Song, WM., Luo, B. (2018). Saliency-Weighted Global-Local Fusion for Person Re-identification. In: Ren, J., et al. Advances in Brain Inspired Cognitive Systems. BICS 2018. Lecture Notes in Computer Science(), vol 10989. Springer, Cham. https://doi.org/10.1007/978-3-030-00563-4_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-00563-4_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00562-7
Online ISBN: 978-3-030-00563-4
eBook Packages: Computer ScienceComputer Science (R0)