Skip to main content
SpringerLink
Log in

Weight-based sparse coding for multi-shot person re-identification

基于加权稀疏编码的多重行人再识别

  • Research Paper
  • Special Focus on Intelligent City and Big Data
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

Person re-identification (Re-ID) is the problem of matching a person from different cameras based on appearance. It has interesting algorithm challenges and extensive practical applications. This paper presents a weight-based sparse coding approach for person re-identification. First, three hypotheses are introduced to achieve a linear combination of images based on sparse coding. Then, we convert the person re-identification problem into an optimization problem with sparse constraints. To reduce the influence of abnormal residuals caused by occlusion and body variation, a weight-based sparse coding approach is proposed to achieve the optimal weights by the ordering statistics of square residuals iteratively. Experiments on various public datasets for different multi-shot modalities have shown good performance of the proposed approach compared with other state-of-the-art ones (more than 42% and 34% at rank-1 on CAVIAR4REID and i-LIDS, respectively).

创新点

行人再识别是无交叠区域的摄像机下基于表观的行人匹配问题, 它具有有趣的算法挑战性和很高的应用价值。本文提出了一种基于加权稀疏编码的行人再识别方法。首先介绍了三个基本假设, 实现了基于稀疏编码的图像线性表达。然后将行人再识别问题转换为一个具有稀疏约束的优化问题。为了减小因遮挡和人体旋转引起的异常残差的影响, 提出的加权稀疏编码方法通过方差的次序统计量, 在每次迭代中得到最优的权值。在不同的多重行人再识别数据集上的实验表明, 该方法与当前最高方法相比具有更好的识别率(在CAVIAR4REID和i-LIDS数据集上首次匹配成功率分别提高了42%和34%)。

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Theodoridis E, Mylonas G, Chatzigiannakis I. Developing an iot smart city framework. In: Proceedings of the 4th International Conference on Information, Intelligence, Systems and Applications, Piraeus-Athens, 2013. 1–6

    Google Scholar 

  2. Xiong Z, Luo W, Chen L, et al. Data vitalization: a new paradigm for large-scale dataset analysis. In: Proceedings of the 16th IEEE International Conference on Parallel and Distributed Systems, Shanghai, 2010. 251–258

    Google Scholar 

  3. Xiong Z, Zheng Y W, Li C. Data vitalization’s perspective towards smart city: a reference model for data service oriented architecture. In: Proceedings of the 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, Chicago, 2014. 865–874

    Google Scholar 

  4. Filipponi L, Vitaletti A, Landi G, et al. Smart city: an event driven architecture for monitoring public spaces with heterogeneous sensors. In: Proceedings of the 4th International Conference on Sensor Technologies and Applications, Venice, 2010. 281–286

    Google Scholar 

  5. Farenzena M, Bazzani L, Perina A, et al. Person re-identification by symmetry-driven accumulation of local features. In: Proceedings of the 23rd IEEE International Conference on Computer Vision and Pattern Recognition, San Francisco, 2010. 2360–2367

    Google Scholar 

  6. Gheissari N, Sebastian T B, Hartley R. Person reidentification using spatiotemporal appearance. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, New York, 2006. 1528–1535

    Google Scholar 

  7. Gong S, Cristani M, Loy C C, et al. The re-identification challenge. In: Gong S, Cristani M, Yan S, et al., eds. Person Re-Identification. London: Springer, 2014. 1–20

    Chapter  Google Scholar 

  8. Wang X, Zhao R. Person re-identification: system design and evaluation overview. In: Gong S, Cristani M, Yan S, et al., eds. Person Re-Identification. London: Springer, 2014. 351–370

    Chapter  Google Scholar 

  9. Tang H, Huang T S. 3D facial expression recognition based on automatically selected features. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Anchorage, 2008. 1–8

    Google Scholar 

  10. Li W, Zhao R, Xiao T, et al. Deepreid: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Columbus, 2014. 152–159

    Google Scholar 

  11. Ding S, Lin L, Wang G, et al. Deep feature learning with relative distance comparison for person re-identification. Patt Recog, 2015, 48: 2993–3003

    Article  Google Scholar 

  12. Harandi M T, Sanderson C, Hartley R. Sparse coding and dictionary learning for symmetric positive definite matrices: a kernel approach. In: Proceedings of the 12th European Conference on Computer Vision, Florence, 2012. 216–229

    Google Scholar 

  13. Bazzani L, Cristani M, Murino V. SDALF: modeling human appearance with symmetry-driven accumulation of local features. In: Gong S, Cristani M, Yan S, et al., eds. Person Re-Identification. London: Springer, 2014. 43–69

    Chapter  Google Scholar 

  14. Ma B, Su Y, Jurie F. Bicov: a novel image representation for person re-identification and face verification. In: Proceedings of the 23rd British Machine Vision Conference, Surrey, 2012. 1–11

    Google Scholar 

  15. Ma B, Su Y, Jurie F. Covariance descriptor based on bio-inspired features for person re-identification and face verification. Image Vis Comput, 2014, 32: 379–390

    Article  Google Scholar 

  16. Layne R, Hospedales T M, Gong S, et al. Person re-identification by attributes. In: Proceedings of the 23rd British Machine Vision Conference, Surrey, 2012. 1–11

    Google Scholar 

  17. Layne R, Hospedales T M, Gong S. Towards person identification and re-identification with attributes. In: Proceedings of the 23rd European Conference on Computer Vision, Surrey, 2012. 402–412

    Google Scholar 

  18. Zhao R, Ouyang W, Wang X. Learning mid-level filters for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Columbus, 2014. 144–151

    Google Scholar 

  19. Li A, Liu L, Wang K, et al. Clothing attributes assisted person re-identification. IEEE Trans Circ Syst Video Technol, 2014, 25: 869–878

    Google Scholar 

  20. Satta R, Pala F, Fumera G, et al. Real-time appearance-based person re-identification over multiple KinectTM cameras. In: Proceedings of the 8th International Conference on Computer Vision Theory and Applications, Barcelona, 2013. 407–410

    Google Scholar 

  21. Zheng W S, Gong S, Xiang T. Associating groups of people. In: Proceedings of the 20th British Machine Vision Conference, London, 2009. 1–11

    Google Scholar 

  22. Liu C, Gong S, Loy C C. On-the-fly feature importance mining for person re-identification. Patt Recog, 2014, 47: 1602–1615

    Article  Google Scholar 

  23. Avraham T, Gurvich I, Lindenbaum M, et al. Learning implicit transfer for person re-identification. In: Proceedings of the 23rd European Conference on Computer Vision, Surrey, 2012. 381–390

    Google Scholar 

  24. Roth P M, Hirzer M, Kostinger M, et al. Mahalanobis distance learning for person re-identification. In: Gong S, Cristani M, Yan S, et al., eds. Person Re-Identification. London: Springer, 2014. 247–267

    Chapter  Google Scholar 

  25. Bak S, Corvee E, Bremond F, et al. Multiple-shot human re-identification by mean riemannian covariance grid. In: Proceedings of the 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Klagenfurt, 2011. 179–184

    Google Scholar 

  26. Bazzani L, Cristani M, Perina A, et al. Multiple-shot person re-identification by HPE signature. In: Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, 2010. 1413–1416

    Google Scholar 

  27. Bazzani L, Cristani M, Perina A, et al. Multiple-shot person re-identification by chromatic and epitomic analyses. Patt Recog Lett, 2012, 33: 898–903

    Article  Google Scholar 

  28. Hirzer M, Roth P M, Kostinger M, et al. Relaxed pairwise learned metric for person re-identification. In: Proceedings of the 23rd European Conference on Computer Vision, Surrey, 2012. 780–793

    Google Scholar 

  29. Hirzer M, Roth P M, Bischof H. Person re-identification by efficient impostor-based metric learning. In: Proceedings of the 9th International Conference on Advanced Video and Signal-Based Surveillance, Beijing, 2012. 203–208

    Google Scholar 

  30. Schwartz WR, Davis L S. Learning discriminative appearance-based models using partial least squares. In: Proceeding of the XXII Brazilian Symposium on Computer Graphics and Image Processing, Brazil, 2009. 322–329

    Google Scholar 

  31. Bak S, Charpiat G, Corvee E, et al. Learning to match appearances by correlations in a covariance metric space. In: Proceedings of the 23rd European Conference on Computer Vision, Surrey, 2012. 806–820

    Google Scholar 

  32. Zhao R, Ouyang W, Wang X. Unsupervised salience learning for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Portland, 2013. 3586–3593

    Google Scholar 

  33. Felzenszwalb P F, Huttenlocher D P. Pictorial structures for object recognition. Int J Comput Vis, 2005, 61: 55–79

    Article  Google Scholar 

  34. Cheng D S, Cristani M, Stoppa M, et al. Custom pictorial structures for re-identification. In: Proceedings of the 22nd British Machine Vision Conference, Dundee, 2011. 1–11

    Google Scholar 

  35. Cao X, Zhang H, Guo X, et al. SLED: semantic label embedding dictionary representation for multi-label image annotation. IEEE Trans Image Process, 2015, 24: 2746–2759

    Article  MathSciNet  Google Scholar 

  36. Meng D Y, Zhao Q, Xu Z B. Improve robustness of sparse PCA based on L1-norm maximization. Patt Recog, 2012, 45: 487–497

    Article  MATH  Google Scholar 

  37. Zhao Q, Meng D Y, Xu Z B. Robust sparse principal component analysis. Sci China Inf Sci, 2014, 57: 092115

    MathSciNet  Google Scholar 

  38. Li Y L, Meng L, Feng J F, et al. Downsampling sparse representation and discriminant information aided occluded face recognition. Sci China Inf Sci, 2014, 57: 032112

    Google Scholar 

  39. Zhou C, Zhang C, Li X, et al. Video face clustering via constrained sparse representation. In: Proceedings of the IEEE International Conference on Multimedia and Expo, Chengdu, 2014. 1–6

    Google Scholar 

  40. Tibshirani R. Regression shrinkage and selection via the lasso. J Roy Stat Soc Ser B-Stat Method, 1996, 58: 267–288

    MATH  MathSciNet  Google Scholar 

  41. Zhang C, Han Y, Guo X, et al. Output feature augmented lasso. In: Proceedings of the IEEE International Conference on Data Mining, Shenzhen, 2014. 680–686

    Google Scholar 

  42. Cheng D S, Cristani M, Stoppa M, et al. Custom pictorial structures for re-identification. In: Proceedings of the 22nd British Machine Vision Conference, Dundee, 2011. 1–11

    Google Scholar 

  43. Ess A, Leibe B, Van Gool L. Depth and appearance for mobile scene analysis. In: Proceedings of the 11th IEEE International Conference on Computer Vision, Brazil, 2007. 1–8

    Google Scholar 

  44. Wang T, Gong S, Zhu X, et al. Person re-identification by video ranking. In: Proceedings of the 13th European Conference on Computer Vision, Zurich, 2014. 688–703

    Google Scholar 

  45. Bak S, Corvee E, Brmond F, et al. Person re-identification using spatial covariance regions of human body parts. In: Proceedings of the 7th IEEE International Conference on Advanced Video and Signal Based Surveillance, Boston, 2010. 435–440

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, 100191, China

    YanWei Zheng, Hao Sheng, BeiChen Zhang & Zhang Xiong

  2. Shenzhen Key Laboratory of Data Vitalization, Research Institute in Shenzhen, Beihang University, Shenzhen, 518057, China

    YanWei Zheng & Hao Sheng

  3. Department of Electrical Engineering and Computer Science, University of Wisconsin-Milwaukee, Milwaukee, 53201, USA

    Jun Zhang

Authors
  1. YanWei Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hao Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. BeiChen Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhang Xiong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hao Sheng.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zheng, Y., Sheng, H., Zhang, B. et al. Weight-based sparse coding for multi-shot person re-identification. Sci. China Inf. Sci. 58, 1–15 (2015). https://doi.org/10.1007/s11432-015-5404-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11432-015-5404-9

Keywords

关键词

Search

Navigation