Abstract To improve the low recognition rate caused by the poor similarity measure in person re-identification, a method of person re-identification via multiple confidences re-ranking is proposed, and the accuracy of person re-identification is improved by evaluating the confidences of test samples. Firstly, the target samples and test samples are described by characteristics from deep learning network ResNet50, and the initial ranking is obtained based on the similarity between the target samples and test samples. Secondly, the classified sample sets are formed by samples with similar ranking, and then the cluster center of each category, the minimum, maximum and mean distance between samples and cluster center are acquired to set three confidence intervals with different confidences. Finally, Jaccard distance is used to sort the similarity between the target samples and test samples. The experimental results of three standard test datasets verify the effectiveness of the proposed algorithm.
[1] ZHENG W S, GONG S G, XIANG T. Person Re-identification by Probabilistic Relative Distance Comparison // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 649-656. [2] ZHAO R, OUYANG W L, WANG X G. Unsupervised Salience Learning for Person Re-identification // Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2013: 3586-3593. [3] LI A N, LIU L Q, YAN S C. Person Re-identification by Attribute-Assisted Clothes Appearance // GONG S G, CRISTANI M, YAN S C, et al., eds. Person Re-identification. London, UK: Springer, 2014: 119-138. [4] SHI Z Y, HOSPEDALES T M, XIANG T. Transferring a Semantic Representation for Person Re-identification and Search // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 4184-4193. [5] GRAY D, TAO H. Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features // Proc of the 10th European Conference on Computer Vision. Berlin, Germany: Springer, 2008, I: 262-275. [6] MA A J, LI J, YUEN P C, et al. Cross-Domain Person Re-identification Using Domain Adaptation Ranking SVMs. IEEE Transactions on Image Processing, 2015, 24(5): 1599-1613. [7] ZHENG L, BIE Z, SUN Y, et al. MARS: A Video Benchmark for Large-Scale Person Re-identification // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 868-884. [8] WANG J, WANG Z, GAO C X, et al. DeepList: Learning Deep Features with Adaptive Listwise Constraint for Person Reidentification. IEEE Transactions on Circuits and Systems for Video Techno-logy, 2017, 27(3): 513-524. [9] KESTINGER M, HIRZER M, WOHLHART P, et al. Large Scale Metric Learning from Equivalence Constraints // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 2288-2295. [10] LIAO S C, HU Y, ZHU X Y, et al. Person Re-identification by Local Maximal Occurrence Representation and Metric Learning // Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2015: 2197-2206. [11] ARANDJELOVI R, ZISSERMAN A. Three Things Everyone Should Know to Improve Object Retrieval // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 2911-2918. [12] BAI S, BAI X. Sparse Contextual Activation for Efficient Visual Re-ranking. IEEE Transactions on Image Processing, 2016, 25(3): 1056-1069. [13] CHUM O, PHILBIN J, SIVIC J, et al. Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval // Proc of the 11th IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2007. DOI: 10.1109/ICCV.2007.4408891. [14] LI W, WU Y, MUKUNOKI M, et al. Common-Near-Neighbor Analysis for Person Re-identification // Proc of the 19th IEEE International Conference on Image Processing. Washington, USA: IEEE, 2012: 1621-1624. [15] GARCIA J, MARTINEL N, MICHELINI C, et al. Person Re-identification Ranking Optimisation by Discriminant Context Information Analysis // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 1305-1313. [16] YE M, CHEN J, LENG Q M, et al. Coupled-View Based Ranking Optimization for Person Re-identification // Proc of the Internatio-nal Conference on Multimedia Modeling. Berlin, Germany: Sprin-ger, 2015: 105-117. [17] YE M, LIANG C, YU Y, et al. Person Reidentification via Ran-king Aggregation of Similarity Pulling and Dissimilarity Pushing. IEEE Transactions on Multimedia, 2016, 18(12): 2553-2566. [18] ZHONG Z, ZHENG L, CAO D, et al. Re-ranking Person Re-identification with k-reciprocal Encoding[C/OL]. [2017-05-21]. https://arxiv.org/pdf/1701.08398.pdf. [19] ZHENG L, SHEN L Y, TIAN L, et al. Scalable Person Re-identification: A Benchmark // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 1116-1124. [20] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object Detection with Discriminatively Trained Part-Based Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1627-1645. [21] LI W, ZHAO R, XIAO T, et al. Deepreid: Deep Filter Pairing Neural Network for Person Re-identification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 152-159. [22] DEHGHAN A, ASSARI S M, SHAH M. GMMCP Tracker: Glo-bally Optimal Generalized Maximum Multi-clique Problem for Multiple Object Tracking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 4091-4099. [23] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet Cla- ssification with Deep Convolutional Neural Networks // PEREIRA F, BURGES C J C, BOTTOU L, et al., eds. Advances in Neural Information Processing Systems 25. Cambridge, USA: The MIT Press, 2012: 1097-1105. [24] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778.
2017, Vol. 30 
