A half-precision compressive sensing framework for end-to-end person re-identification

  • Longlong LiaoEmail author
  • Zhibang Yang
  • Qing Liao
  • Kenli Li
  • Keqin Li
  • Jie Liu
  • Qi Tian
Review Article


Compressive sensing (CS) approaches are useful for end-to-end person re-identification (Re-ID) in reducing the overheads of transmitting and storing video frames in distributed multi-camera systems. However, the reconstruction quality degrades appreciably as the measurement rate decreases for existing CS methods. To address this problem, we propose a half-precision CS framework for end-to-end person Re-ID named HCS4ReID, which efficiently recoveries detailed features of the person-of-interest regions in video frames. HCS4ReID supports half-precision CS sampling, transmitting and storing CS measurements with half-precision floats, and CS reconstruction with two measurement rates. Extensive experiments implemented on the PRW dataset indicate that the proposed HCS4ReID achieves 1.55 \(\times\) speedups over the single-precision counterpart on average for the CS sampling on an Intel HD Graphics 530, and only half-network bandwidth and storage space are needed to transmit and store the generated CS measurements. Comprehensive evaluations demonstrate that the proposed HCS4ReID is a scalable and portable CS framework with two measurement rates, and suitable for end-to-end person Re-ID. Especially, it achieves the comparable performance on the reconstructed PRW dataset against CS reconstruction with single-precision floats and a single measurement rate.


Compressive sensing Half-precision float Pedestrian detection Person re-identification 



The research was partially funded by the Program of National Natural Science Foundation of China (Grant No. 61751204), the National Outstanding Youth Science Program of National Natural Science Foundation of China (Grant No. 61625202), the International (Regional) Cooperation and Exchange Program of National Natural Science Foundation of China (Grant No. 61661146006), the National Key R&D Program of China (Grant Nos. 2016YFB0201303, 2016YFB0200201), the National Natural Science Foundation of China (Grant Nos. 61772182, 61802032), Science and Technology Plan of Changsha (K1705032). The authors would like to thank Tianming Jin for his help in improving the paper.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3908–3916.
  2. 2.
    Bashir K, Xiang T, Gong S (2008) Feature selection on gait energy image for human identification. In: 2008 IEEE international conference on acoustics, speech and signal processing, pp 985–988.
  3. 3.
    Chen C, Li K, Teo SG, Chen G, Zou X, Yang X, Vijay RC, Feng J, Zeng Z (2018) Exploiting spatio-temporal correlations with multiple 3d convolutional neural networks for citywide vehicle flow prediction. In: 2018 IEEE international conference on data mining (ICDM), pp 893–898.
  4. 4.
    Chen J, Fang J, Liu W, Tang T, Yang C (2018) CLMF: a fine-grained and portable alternating least squares algorithm for parallel matrix factorization. Future Gener Comput Syst. Google Scholar
  5. 5.
    Chen J, Li K, Tang Z, Bilal K, Yu S, Weng C, Li K (2017) A parallel random forest algorithm for big data in a spark cloud computing environment. IEEE Trans Parallel Distrib Syst 28(4):919–933. CrossRefGoogle Scholar
  6. 6.
    Chen S, Guo C, Lai J (2016) Deep ranking for person re-identification via joint representation learning. IEEE Trans Image Process 25(5):2353–2367. MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Chen Y, Duffner S, Baskurt A, Stoian A, Dufour JY (2018) Similarity learning with listwise ranking for person re-identification. In: 2018 25th IEEE international conference on image processing (ICIP), pp 843–847.
  8. 8.
    Cheng D, Gong Y, Zhou S, Wang J, Zheng N (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 1335–1344.
  9. 9.
    Courbariaux M, Bengio Y, David JP (2015) Training deep neural networks with low precision multiplications. ArXiv preprint arXiv:1412.7024v5
  10. 10.
    Ding S, Lin L, Wang G, Chao H (2015) Deep feature learning with relative distance comparison for person re-identification. Pattern Recognit 48(10):2993–3003. CrossRefGoogle Scholar
  11. 11.
    Dinh KQ, Jeon B (2017) Iterative weighted recovery for block-based compressive sensing of image/video at a low subrate. IEEE Trans Circuits Syst Video Technol 27(11):2294–2308. CrossRefGoogle Scholar
  12. 12.
    Dollár P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. IEEE Trans Pattern Anal Mach Intell 36(8):1532–1545. CrossRefGoogle Scholar
  13. 13.
    Duan M, Li K, Li K (2018) An ensemble cnn2elm for age estimation. IEEE Trans Inf Forensics Secur 13(3):758–772. CrossRefGoogle Scholar
  14. 14.
    Duarte MF, Davenport MA, Takhar D, Laska JN, Sun T, Kelly KF, Baraniuk RG (2008) Single-pixel imaging via compressive sampling. IEEE Signal Process Mag 25(2):83–91. CrossRefGoogle Scholar
  15. 15.
    Fang J, Varbanescu AL, Liao X, Sips H (2014) Evaluating vector data type usage in opencl kernels. Concurr Comput Pract Exp 27(17):4586–4602. CrossRefGoogle Scholar
  16. 16.
    Fang J, Zhang P, Tang C, Huang T, Yang C (2017) Implementing and evaluating OpenCL on an ARMv8 multi-core CPU. In: IEEE international symposium on parallel and distributed processing with applications. IEEE Computer Society, Guangzhou, Guangdong, China, pp 860–867.
  17. 17.
    Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645. CrossRefGoogle Scholar
  18. 18.
    Ge Y, Gu X, Chen M, Wang H, Yang D (2018) Deep multi-metric learning for person re-identification. In: 2018 IEEE international conference on multimedia and expo (ICME), pp 1–6.
  19. 19.
    Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Forsyth D, Torr P, Zisserman A (eds) Computer Vision: ECCV 2008. Springer, Berlin, pp 262–275CrossRefGoogle Scholar
  20. 20.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778.
  21. 21.
    Iliadis M, Spinoulas L, Katsaggelos AK (2018) Deep fully-connected networks for video compressive sensing. Dig Signal Process 72:9–18. CrossRefGoogle Scholar
  22. 22.
    Joseph R, Ali F (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767
  23. 23.
    Kulkarni K, Lohit S, Turaga P, Kerviche R, Ashok A (2016) Reconnet: non-iterative reconstruction of images from compressively sensed measurements. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 449–458.
  24. 24.
    Li J, Liang X, Shen S, Xu T, Feng J, Yan S (2018) Scale-aware fast R-CNN for pedestrian detection. IEEE Trans Multimed 20(4):985–996. Google Scholar
  25. 25.
    Li K, Tang X, Li K (2014) Energy-efficient stochastic task scheduling on heterogeneous computing systems. IEEE Trans Parallel Distrib Syst 25(11):2867–2876. CrossRefGoogle Scholar
  26. 26.
    Li K, Tang X, Veeravalli B, Li K (2015) Scheduling precedence constrained stochastic tasks on heterogeneous cluster systems. IEEE Trans Comput 64(1):191–204. MathSciNetCrossRefzbMATHGoogle Scholar
  27. 27.
    Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: 2014 IEEE conference on computer vision and pattern recognition, pp 152–159.
  28. 28.
    Liao L, Li K, Li K, Yang C, Tian Q (2018) UHCL-Darknet: an OpenCL-based deep neural network framework for heterogeneous multi-/many-core clusters. In: Proceedings of the 47th international conference on parallel processing, ICPP 2018. ACM, New York, NY, USA, pp 44:1–44:10.
  29. 29.
    Metzler CA, Maleki A, Baraniuk RG (2016) From denoising to compressed sensing. IEEE Trans Inf Theory 62(9):5117–5144. MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Micikevicius P, Narang S, Alben J, Diamos GF, Elsen E, Garca D, Ginsburg B, Houston M, Kuchaiev O, Venkatesh G, Wu H (2018) Mixed precision training. In: The 6th international conference on learning representations (ICLR 2018), pp 1–12Google Scholar
  31. 31.
    Mousavi A, Baraniuk RG (2017) Learning to invert: signal recovery via deep convolutional networks. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2272–2276.
  32. 32.
    Mousavi A, Patel AB, Baraniuk RG (2015) A deep learning approach to structured signal recovery. In: 2015 53rd annual allerton conference on communication, control, and computing (Allerton), pp 1336–1343.
  33. 33.
    Nugteren C (2018) Clblast: a tuned OpenCL BLAS library. In: Proceedings of the international workshop on OpenCL, IWOCL ’18. ACM, New York, NY, USA, pp 5:1–5:10.
  34. 34.
    Ouyang W, Wang X (2013) Joint deep learning for pedestrian detection. In: 2013 IEEE international conference on computer vision, pp 2056–2063.
  35. 35.
    Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. CrossRefGoogle Scholar
  36. 36.
    Shi L, Chen H, Sun J, Li K (2012) vCUDA: GPU-accelerated high-performance computing in virtual machines. IEEE Trans Comput 61(6):804–816. MathSciNetCrossRefzbMATHGoogle Scholar
  37. 37.
    Shi W, Jiang F, Zhang S, Zhao D (2017) Deep networks for compressed image sensing. In: 2017 IEEE international conference on multimedia and expo (ICME). IEEE, pp 877–882Google Scholar
  38. 38.
    Sun Y, Zheng L, Yang Y, Tian Q, Wang S (2018) Beyond part models: person retrieval with refined part pooling. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) European conference on computer vision (ECCV). Springer, Cham, pp 501–518Google Scholar
  39. 39.
    Tao D, Guo Y, Yu B, Pang J, Yu Z (2018) Deep multi-view feature learning for person re-identification. IEEE Trans Circuits Syst Video Technol 28(10):2657–2666. CrossRefGoogle Scholar
  40. 40.
    Vezzani R, Baltieri D, Cucchiara R (2013) People reidentification in surveillance and forensics: a survey. ACM Comput Surv 46(2):29:1–29:37. CrossRefGoogle Scholar
  41. 41.
    Wang G, Yuan Y, Chen X, Li J, Zhou X (2018) Learning discriminative features with multiple granularities for person re-identification. In: Proceedings of the 26th ACM international conference on multimedia, MM ’18. ACM, New York, NY, USA, pp 274–282.
  42. 42.
    Wojek C, Dollar P, Schiele B, Perona P (2012) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34:743–761. CrossRefGoogle Scholar
  43. 43.
    Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR) pp 1249–1258.
  44. 44.
    Xiao T, Li S, Wang B, Lin L, Wang X (2017) Joint detection and identification feature learning for person search. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 3376–3385.
  45. 45.
    Xu Y, Li K, He L, Zhang L, Li K (2015) A hybrid chemical reaction optimization scheme for task scheduling on heterogeneous computing systems. IEEE Trans Parallel Distrib Syst 26(12):3208–3222. CrossRefGoogle Scholar
  46. 46.
    Zhang H, Cao X, Ho JKL, Chow TWS (2017) Object-level video advertising: an optimization framework. IEEE Trans Ind Inform 13(2):520–531. CrossRefGoogle Scholar
  47. 47.
    Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl. Google Scholar
  48. 48.
    Zhang J, Ghanem B (2018) ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1828–1837Google Scholar
  49. 49.
    Zhang L, Li K, Xu Y, Mei J, Zhang F, Li K (2015) Maximizing reliability with energy conservation for parallel task scheduling in a heterogeneous cluster. Inf Sci 319:113–131. MathSciNetCrossRefGoogle Scholar
  50. 50.
    Zhang L, Lin L, Liang X, He K (2016) Is faster R-CNN doing well for pedestrian detection? In: Leibe B, Matas J, Sebe N, Welling M (eds) ECCV 2016. Springe, Cham, pp 443–457Google Scholar
  51. 51.
    Zhang N, Paluri M, Taigman Y, Fergus R, Bourdev L (2015) Beyond frontal faces: improving person recognition using multiple cues. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 4804–4813.
  52. 52.
    Zhang P, Fang J, Tang T, Yang C, Wang Z (2018) Mocl: an efficient OpenCL implementation for the matrix-2000 architecture. In: ACM international conference on computing frontiers. ACM, Ischia, Italy.
  53. 53.
    Zhang P, Fang J, Tang T, Yang C, Wang Z (2018) Tuning streamed applications on Intel Xeon Phi: a machine learning based approach. In: the 32nd IEEE international parallel and distributed processing symposium (IPDPS’18). Vancouver, British Columbia, Canada, pp 515–525Google Scholar
  54. 54.
    Zhang S, Benenson R, Omran M, Hosang J, Schiele B (2016) How far are we from solving pedestrian detection? In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 1259–1267.
  55. 55.
    Zhao L, Li X, Zhuang Y, Wang J (2017) Deeply-learned part-aligned representations for person re-identification. In: 2017 IEEE international conference on computer vision (ICCV), pp 3239–3248.
  56. 56.
    Zheng L, Bie Z, Sun Y, Wang J, Su C, Wang S, Tian Q (2016) Mars: a video benchmark for large-scale person re-identification. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision: ECCV 2016. Springer, Cham, pp 868–884CrossRefGoogle Scholar
  57. 57.
    Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: 2015 IEEE international conference on computer vision (ICCV), pp 1116–1124.
  58. 58.
    Zheng L, Zhang H, Sun S, Chandraker M, Yang Y, Tian Q (2017) Person re-identification in the wild. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 3346–3355.
  59. 59.
    Zheng W, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: CVPR 2011, pp 649–656.

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of ComputerNational University of Defense TechnologyChangshaChina
  2. 2.State Key Laboratory of High Performance ComputingChangshaChina
  3. 3.College of Computer Engineering and Applied MathematicsChangsha UniversityChangshaChina
  4. 4.Department of Computer Science and TechnologyHarbin Institute of TechnologyShenzhenChina
  5. 5.College of Information Science and EngineeringHunan UniversityChangshaChina
  6. 6.Department of Computer ScienceState University of New YorkNew PaltzUSA
  7. 7.Department of Computer ScienceUniversity of Texas at San AntonioSan AntonioUSA

Personalised recommendations