ABSTRACT
Most of the open challenges in person re-identification are introduced by the large variations of human appearance and from the different camera views deployed to monitor the environment. To tackle these challenges, almost all state-of-the-art methods assume that all image pixels are equally relevant to the task, hence they are used in the feature extraction procedure. However, it is not guaranteed the a pixel sensed by one camera is viewed by a different one, so computing the person signature using such pixel might bring uninformative data in the feature matching phase. We believe that only some portions of the image are relevant to the re-identification task. Inspired by this, we introduce a novel algorithm that: (i) randomly samples a set of image patches to compute the person signature; (ii) uses the correlation matrix computed between such patches as a weighing tool in the signature matching process; (iii) brings sparsity in the correlation matrix so as only relevant patches are used in the matching phase. To validate the proposed approach, we have compared our performance to state-of-the-art methods using two publicly available benchmark datasets. Results show that superior performance to existing approaches are achieved.
- T. Avraham, I. Gurvich, M. Lindenbaum, and S. Markovitch. Learning Implicit Transfer for Person Re-identification. In ECCV Workshops and Demonstrations, pages 381--390, 2012. Google ScholarDigital Library
- L. Bazzani, M. Cristani, and V. Murino. Symmetry-driven accumulation of local features for human characterization and re-identification. CVIU, 117(2):130--144, Nov. 2013. Google ScholarDigital Library
- L. Bazzani, M. Cristani, A. Perina, and V. Murino. Multiple-shot person re-identification by chromatic and epitomic analyses. Pattern Recognition Letters, Nov. 2011. Google ScholarDigital Library
- S. Bäěk, E. Corvée, F. Brémond, and M. Thonnat. Boosted human re-identification using Riemannian manifolds. Image and Vision Computing, 30(6-7):443--452, June 2012. Google ScholarDigital Library
- N. Dalal and B. Triggs. Histograms of Oriented Gradients for Human Detection. In CVPR, pages 886--893, June 2005. Google ScholarDigital Library
- M. Dikmen, E. Akbas, T. S. Huang, and N. Ahuja. Pedestrian Recognition with a Learned Metric. In ACCV, 2010. Google ScholarDigital Library
- M. Hirzer, P. M. Roth, and H. Bischof. Person Re-identification by Efficient Impostor-Based Metric Learning. In AVSS, pages 203--208, 2012. Google ScholarDigital Library
- M. Hirzer, P. M. Roth, K. Martin, and H. Bischof. Relaxed Pairwise Learned Metric for Person Re-identification. In ECCV, pages 780--793, 2012. Google ScholarDigital Library
- O. Javed, K. Shafique, Z. Rasheed, and M. Shah. Modeling inter-camera space-time and appearance relationships for tracking across non-overlapping views. CVIU, 109(2):146--162, Feb. 2008. Google ScholarDigital Library
- I. Kviatkovsky, A. Adam, and E. Rivlin. Color Invariants for Person Re-Identification. IEEE TPAMI, 35(7):1622--1634, 2013. Google ScholarDigital Library
- C. Liu, S. Gong, C. C. Loy, and X. Lin. Person Re-identification: What Features Are Important? In ECCV Workshops and Demonstrations, pages 391--401, 2012. Google ScholarDigital Library
- B. Ma, Y. Su, and F. Jurie. BiCov: a novel image representation for person re-identification and face verification. BMVC, pages 57.1--57.11, 2012.Google ScholarCross Ref
- B. Ma, Y. Su, and F. Jurie. Local Descriptors Encoded by Fisher Vectors for Person Re-identification. In ECCV Workshops and Demonstrations, pages 413--422, 2012. Google ScholarDigital Library
- N. Martinel and C. Micheloni. Re-identify people in wide area camera network. In CVPRW, pages 31--36, June 2012.Google ScholarCross Ref
- N. Martinel, C. Micheloni, and G. L. Foresti. Saliency Weighted Features for Person Re-Identification. In ECCV Workshops and Demonstrations, number i, pages 1--17, 2014.Google Scholar
- N. Martinel, C. Micheloni, and C. Piciarelli. Distributed Signature Fusion for Person Re-Identification. In ICDSC, pages 1--6, 2012.Google Scholar
- N. Martinel, C. Micheloni, and C. Piciarelli. Learning pairwise feature dissimilarities for person re-identification. In ICDSC, pages 1--6, Oct. 2013.Google ScholarCross Ref
- N. Martinel, C. Micheloni, C. Piciarelli, and G. L. Foresti. Camera Selection for Adaptive Human-Computer Interface. IEEE TSMC: Systems, 44(5):653--664, May 2014.Google Scholar
- T. Ojala, M. Pietikainen, and T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE TPAMI, 24(7):971--987, 2002. Google ScholarDigital Library
- C. Piciarelli, C. Micheloni, and G. Foresti. PTZ camera network reconfiguration. In ICDSC, pages 1--7, Aug. 2009.Google ScholarCross Ref
- W. R. Schwartz and L. S. Davis. Learning Discriminative Appearance-Based Models Using Partial Least Squares. In Brazilian Symposium on Computer Graphics and Image Processing, pages 322--329, Oct. 2009. Google ScholarDigital Library
- M. Vernier, N. Martinel, C. Micheloni, and G. L. Foresti. Remote feature learning for mobile re-identification. In ICDSC, pages 1--6, Oct. 2013.Google ScholarCross Ref
- Y. Wu, M. Minoh, M. Mukunoki, W. Li, and S. Lao. Collaborative Sparse Approximation for Multiple-Shot Across-Camera Person Re-identification. In AVSS, pages 209--214, Sept. 2012. Google ScholarDigital Library
- G. Zhang, Y. Wang, J. Kato, T. Marutani, and M. Kenji. Local distance comparison for multiple-shot people re-identification. In ACCV, pages 677--690, 2013. Google ScholarDigital Library
- R. Zhao, W. Ouyang, and X. Wang. Unsupervised Salience Learning for Person Re-identification. In CVPR, pages 3586--3593, June 2013. Google ScholarDigital Library
Index Terms
- Sparse Matching of Random Patches for Person Re-Identification
Recommendations
Sparse representation matching for person re-identification
The need for recognizing people across distributed surveillance cameras leads to the growth of recent research interest in person re-identification. Person re-identification aims at matching people in non-overlapping cameras at different time and ...
Person Re-identification by Salience Matching
ICCV '13: Proceedings of the 2013 IEEE International Conference on Computer VisionHuman salience is distinctive and reliable information in matching pedestrians across disjoint camera views. In this paper, we exploit the pair wise salience distribution relationship between pedestrian images, and solve the person re-identification ...
Multi-view feature fusion for person re-identification
AbstractPerson re-identification (ReID) suffers from camera view variants. Existing works, which typically learn a feature for each image, share a limitation that the learned features are single-view: each feature only contains information in ...
Highlights- The complementary-view features are defined to mitigate view bias.
- Multi-view ...
Graphical abstractDisplay Omitted
Comments