Abstract
Person re-identification receives increasing attentions in computer vision due to its potential applications in video surveillance. In order to alleviate wrong matches caused by misalignment or missing features among cameras, we propose to learn a multi-view gallery of frequently appearing objects in a relatively closed environment. The gallery contains appearance models of these objects from different cameras and viewpoints. The strength of the learned appearance models lies in that they are invariant to viewpoint and illumination changes. To automatically estimate the number of frequently appearing objects in the environment and update their appearance models online, we propose a dynamic gallery learning algorithm. We specifically build up two datasets to validate the effectiveness of our approach in realistic scenarios. Comparisons with benchmark methods demonstrate promising performance in accuracy and efficiency of re-identification.
Similar content being viewed by others
References
Bak S, Corvee E, Bremond F and Thonnat M (2010) “Person Re-identification Using Spatial Covariance Regions of Human Body Parts,” in Proc. of IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), pp. 435–440
Bak S, Corvee E, Bremond F, and Thonnat M (2010) “Person re-identification using Haar-based and DCD-based signature,” in Proc. of IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), pp.1-8
Bak S, Corvee E, Bremond F, and Thonnat M (2011) “Multiple-shot human re-identification by Mean Riemannian Covariance Grid,” in Proc. of IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), pp. 179–184
Bak S, Corvee E, Bremond F, Thonnat M (2012) Boosted human re-identification using riemannian manifolds. Image Vis Comput 30(6):443–452
Bazzani L, Cristani M, Perina A, Murino V (2012) Multiple-shot person re-identification by chromatic and epitomic analyses. Pattern Recogn Lett 33(7):898–903
Chen K, Lai C, Hung Y and Chen C (2008) “An Adaptive Learning Method for Target Tracking across Multiple Cameras,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp. 1–8
Cheng D, Cristani M, Stoppa M, Bazzani L, and Murino V, (2011) “Custom pictorial structures for re-identification,” in Proc. of British Machine Vision Conference (BMVC)
Dikmen M, Akbas E, Huang T, and Ahuja N (2010) “Pedestrian recognition with a learned metric,” in Proc. of Asian Conference on Computer Vision (ACCV), pp. 501–512
Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2013) Symmetry-driven accumulation of local features for human characterization and re-identification. Comput Vis Image Underst 117(2):130–144
Gandhi T, Trivedi M (2007) Person tracking and reidentification: introducing panoramic appearance Map (PAM) for feature representation. Mach Vis Appl (MVA) 18(3):207–220
Gheissari N, Sebastian T, and Hartley R (2006) “Person reidentification using spatiotemporal appearance,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1528–1535
Gray D and Tao T (2008) “Viewpoint invariant pedestrian recognition with an ensemble of localized features,” in Proc. of European Conference on Computer Vision (ECCV), pp. 262–275
Hamdoun O, Moutarde F, Stanciulescu B, and Steux B (2008) “Person re-identification in multi-camera system by signature based on interest point descriptors collected on short video sequences,” in International Conference on Distributed Smart Cameras (ICDSC), pp. 1–6
Hirzer M and Beleznai C and Roth P and Bischof H (2011) “Person re-identification by descriptive and discriminative classification,” Image Analysis, pp. 91–102
Javed O, Shafique K, and Shah M (2005) “Appearance modeling for tracking in multiple non-overlapping cameras,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 26–33
Jeong K, Jaynes C (2008) Object matching in disjoint cameras using a color transfer approach. Mach Vis Appl (MVA) 19(5–6):443–455
Kaufman L, Rousseeuw P (1990) Finding groups in data: an introduction to cluster analysis. John Wiley & Sons, Hoboken
Kostinger M, Hirzer M, Wohlhart P, Roth P, and Bischof H (2012) “Large scale metric learning from equivalence constraints,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2288–2295
Kviatkovsky I, Amit A, Rivlin E (2013) Color invariants for person reidentification. IEEE Trans Pattern Anal Mach Intell (PAMI) 35(7):1622–1634
Li Wand Wang X (2013) “Locally Aligned Feature Transforms across Views,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3594–3601
Li Z, Chang S, Liang F, Huang T, Cao L and Smith J (2013) “Learning Locally-Adaptive Decision Functions for Person Verification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3610–3617
Li W, Zhao R, and Wang X (2012) “Human reidentification with transferred metric learning,” in Proc. of Asian Conference on Computer Vision (ACCV), pp. 31–44
Loy C, Xiang T, Gong S (2010) Time-delayed correlation analysis for multi-camera activity understanding. Int J Comput Vis 90(1):106–129
Ma B, Su Y, and Jurie F (2012) “Local descriptors encoded by fisher vectors for person re-identification,” in Proc. of European Conference on Computer Vision Workshops and Demonstrations, pp. 413–422
Ma B, Su Y, and Jurie F, (2012) “Bicov: a novel image representation for person re-identification and face verification,” in Proc. of British Machine Vision Conference (BMVC)
Makris D and Ellis T (2003) “Automatic Learning of an Activity-based Semantic Scene Model,” in Proc. of IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 183–188
Mignon A, and Jurie F (2012) “PCCA: A new approach for distance learning from sparse pairwise constraints,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2666–2672
Prosser B, Zheng W, Gong S, and Xiang T (2010) “Person re-identification by support vector ranking,” in Proc. of British Machine Vision Conference (BMVC), pp. 1–11
Schwartz W and Davis L (2009) “Learning discriminative appearance-based models using partial least squares,” in Proc. of Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI), pp. 322–329
Stauffer C and Grimson W (1999) “Adaptive Background Mixture Models for Real-time Tracking,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Wang X, Doretto G, Sebastian T, Rittscher J, and Tu P (2007) “Shape and appearance context modeling,” in Proc. of IEEE International Conference on Computer Vision (ICCV), pp. 1–8
Xiang Z, Chen Q, and Liu Y. (2012)“Person re-identification by fuzzy space color histogram,” Multimedia Tools and Applications, pp. 1–17, 2012
Xiang Z, Chen Q, and Liu Y (2013) “Feature correspondence in a non-overlapping camera network,” Multimedia Tools and Applications, pp. 1–17
Zhao R, Ouyang W, and Wang X, (2013) “Unsupervised Salience Learning for Person Re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Zheng W, Gong S, and Xiang T (2011) “Person Re-identification by Probabilistic Relative Distance Comparison,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 649–656
Zivkovic Z (2004) “Improved Adaptive Gaussian Mixture Model for Background Subtraction,” in Proc. of IEEE International Conference on Pattern Recognition (ICPR), vol. 2, pp. 28–31
Acknowledgments
This research has been partially supported by the grants of China 973 project 2011CB302203, NSFC 61375019 and NSFC 61273285.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Zhao, Y., Zhao, X., Xiang, Z. et al. Online learning of dynamic multi-view gallery for person Re-identification. Multimed Tools Appl 76, 217–241 (2017). https://doi.org/10.1007/s11042-015-3015-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-015-3015-5