Object detection and tracking benchmark in industry based on improved correlation filter

  • Shangzhen Luan
  • Yan Li
  • Xiaodi Wang
  • Baochang Zhang


Real-time object detection and tracking have shown to be the basis of intelligent production for industrial 4.0 applications. It is a challenging task because of various distorted data in complex industrial setting. The correlation filter (CF) has been used to trade off the low-cost computation and high performance. However, traditional CF training strategy can not get satisfied performance for the various industrial data; because the simple sampling(bagging) during training process will not find the exact solutions in a data space with a large diversity. In this paper, we propose Dijkstra-distance based correlation filters (DBCF), which establishes a new learning framework that embeds distribution-related constraints into the multi-channel correlation filters (MCCF). DBCF is able to handle the huge variations existing in the industrial data by improving those constraints based on the shortest path among all solutions. To evaluate DBCF, we build a new dataset as the benchmark for industrial 4.0 application. Extensive experiments demonstrate that DBCF produces high performance and exceeds the state-of-the-art methods. The dataset and source code can be found at https://github.com/bczhangbczhang.


Object detection Tracking Correlation filter Industry 4.0 Tracking in industry 



The work was supported by the Natural Science Foundation of China under Contract 61672079 and 61473086, and Shenzhen Peacock Plan KQTD2016112515134654. This work is supported by the Open Projects Program of National Laboratory of Pattern Recognition, and shenzhen peacock plan. Shangzhen Luan and Yan Li have the same contribution to this paper. We also want to thank Professor Zhu Lei of Hangzhou Dianzi University, who participated in writing and technical editing of the manuscript.


  1. 1.
    Benhimane S, Najafi H, Grundmann M, Malis E, Genc Y, Navab N (2008) Real-time object detection and tracking for industrial applications. In: Visapp 2008: Proceedings of the Third International Conference on Computer Vision Theory and Applications, Funchal, Madeira, Portugal, pp 337–345Google Scholar
  2. 2.
    Bolme DS, Ross Beveridge J, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: 2010 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 2544–2550Google Scholar
  3. 3.
    Bolme DS, Draper BA, Ross Beveridge J (2009) Average of synthetic exact filters. In: 2009 IEEE Conference on computer vision and pattern recognition, CVPR 2009. IEEE, pp 2105–2112Google Scholar
  4. 4.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer society conference on computer vision and pattern recognition, CVPR 2005, vol 1. IEEE, pp 886–893Google Scholar
  5. 5.
    Danelljan M, Häger G, Khan F, Felsberg M (2014) Accurate scale estimation for robust visual tracking. In: British machine vision conference, Nottingham, September 1-5, 2014. BMVA PressGoogle Scholar
  6. 6.
    Dijkstra EW (1959) A note on two problems in connexion with graphs. Numerische mathematik 1(1):269–271MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Ding G, Chen W, Zhao S, Han J, Liu Q (2017) Real-time scalable visual tracking via quadrangle kernelized correlation filters. IEEE Trans Intell Transp Syst 19 (1):140–150CrossRefGoogle Scholar
  8. 8.
    Han J, Pauwels EJ, Zeeuw PM, With PHN (2012) Employing a rgb-d sensor for real-time tracking of humans across multiple re-entries in a smart environment. IEEE Trans Consum Electron 58(2):255–263CrossRefGoogle Scholar
  9. 9.
    Henriques J, Caseiro R, Martins P, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with kernels. Comput Vision–ECCV 2012:702–715Google Scholar
  10. 10.
    Henriques JF, Caseiro R, Martins P, Batista J (2015) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37(3):583–596CrossRefGoogle Scholar
  11. 11.
    Hester CF, Casasent D (1980) Multivariant technique for multiclass pattern recognition. Appl Opt 19(11):1758–1761CrossRefGoogle Scholar
  12. 12.
    Kiani H, Sim T, Lucey S (2014) Multi-channel correlation filters for human action recognition. In: 2014 IEEE International conference on image processing (ICIP). IEEE, pp 1485–1489Google Scholar
  13. 13.
    Galoogahi HK, Sim T, Lucey S (2013) Multi-channel correlation filters. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3072–3079Google Scholar
  14. 14.
    Galoogahi HK, Sim T, Lucey S (2015) Correlation filters with limited boundaries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4630–4638Google Scholar
  15. 15.
    Lan X, Ma AJ, Yuen PC, Chellappa R (2015) Joint sparse representation and robust feature-level fusion for multi-cue visual tracking. IEEE Trans Image Process A Publication IEEE Signal Process Society 24(12):5826MathSciNetCrossRefGoogle Scholar
  16. 16.
    Lan X, Ma A, Yuen PC (2014) Multi-cue visual tracking using robust feature-level fusion based on joint sparse representation. In: Computer vision and pattern recognition, pp 1194–1201Google Scholar
  17. 17.
    Lan X, Yuen PC, Chellappa R (2017) Robust mil-based feature template learning for object tracking. In: AAAI, pp 4118–4125Google Scholar
  18. 18.
    Lan X, Zhang S, Yuen PC (2016) Robust joint discriminative feature learning for visual tracking. In: International joint conference on artificial intelligence, pp 3403–3410Google Scholar
  19. 19.
    Lan X, Zhang S, Yuen PC, Chellappa R (2017) Learning common and feature-specific patterns: A novel multiple-sparse-representation-based tracker. IEEE Trans Image Process PP(99):1–1CrossRefGoogle Scholar
  20. 20.
    Si L, Zhang T, Cao X, Changsheng X (2016) Structural correlation filter for robust visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4312–4320Google Scholar
  21. 21.
    Liu T, Wang G, Yang Q (2015) Real-time part-based visual tracking via adaptive correlation filters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4902–4912Google Scholar
  22. 22.
    Ma C, Huang J-B, Yang X, Yang M-H (2015) Hierarchical convolutional features for visual tracking. In: Proceedings of the IEEE International Conference on Computer VisionGoogle Scholar
  23. 23.
    Ma C, Yang X, Zhang C, Yang M-H (2015) Long-term correlation tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5388–5396Google Scholar
  24. 24.
    Mahalanobis A, Vijaya Kumar BVK, Casasent D (1987) Minimum average correlation energy filters. Appl Opt 26(17):3633–3640CrossRefGoogle Scholar
  25. 25.
    Mahalanobis A, Vijaya Kumar BVK, Sims SRF (1996) Distance-classifier correlation filters for multiclass target recognition. Appl Opt 35(17):3127–3133CrossRefGoogle Scholar
  26. 26.
    Mahalanobis A, Vijaya Kumar BVK, Song S, Sims SRF, Epperson JF (1994) Unconstrained correlation filters. Appl Opt 33(17):3751–3759CrossRefGoogle Scholar
  27. 27.
    Boddeti VN, Kanade T, Vijaya Kumar BVK (2013) Correlation filters for object alignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2291–2298Google Scholar
  28. 28.
    Refregier P (1991) Optimal trade-off filters for noise robustness, sharpness of the correlation peak, and horner efficiency. Opt Lett 16(11):829–831CrossRefGoogle Scholar
  29. 29.
    Rodriguez A, Boddeti VN, Vijaya Kumar BVK, Mahalanobis A (2013) Maximum margin correlation filter: a new approach for localization and classification. IEEE Trans Image Process 22(2):631–643MathSciNetCrossRefMATHGoogle Scholar
  30. 30.
    Savvides M, Vijaya Kumar BVK (2003) Efficient design of advanced correlation filters for robust distortion-tolerant face recognition. In: IEEE Conference on advanced video and signal based surveillance, 2003. Proceedings. IEEE, pp 45–52Google Scholar
  31. 31.
    Yang L, Chen C, Wang H, Zhang B, Han J (2016) Adaptive multi-class correlation filters. In: Pacific rim conference on multimedia. Springer, pp 680–688Google Scholar
  32. 32.
    Zhang B, Gu J, Chen C, Han J, Su X, Cao X, Liu J (2018) One-two-one network for compression artifacts reduction in remote sensing. ISPRS Journal of Photogrammetry and Remote SensingGoogle Scholar
  33. 33.
    Zhang B, Li Z, Cao X, Ye Q, Chen C, Shen L, Perina A, Jill R (2016) Output constraint transfer for kernelized correlation filter in tracking. IEEE Trans Syst Man Cybern Syst 47(4):693–703CrossRefGoogle Scholar
  34. 34.
    Zhang B, Li Z, Perina A, Bue AD, Murino V, Liu J (2017) Adaptive local movement modeling for robust object tracking. IEEE Trans Circuits Syst Video Technol 27(7):1515–1526CrossRefGoogle Scholar
  35. 35.
    Zhang B, Luan S, Chen C, Han J, Wang W, Perina A, Shao L (2017) Latent constrained correlation filter. IEEE Trans Image Process PP(99):1–1Google Scholar
  36. 36.
    Zhang B, Perina A, Li Z, Murino V, Liu J, Ji R (2016) Bounding multiple gaussians uncertainty with application to object tracking. Int J Comput Vis 118(3):364–379MathSciNetCrossRefGoogle Scholar
  37. 37.
    Zhang B, Perina A, Murino V, Bue AD (2015) Sparse representation classification with manifold constraints transfer. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4557–4565Google Scholar
  38. 38.
    Zhang B, Yang Y, Chen C, Yang L, Han J, Shao L (2017) Action recognition using 3d histograms of texture and a multi-class boosting classifier. IEEE Trans Image Process 26(10):4648–4660MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Shangzhen Luan
    • 1
  • Yan Li
    • 2
  • Xiaodi Wang
    • 1
  • Baochang Zhang
    • 1
    • 3
  1. 1.School of Automation Science and Electrical EngineeringBeihang UniversityBeijingChina
  2. 2.School of Electronics and Information EngineeringBeihang UniversityBeijingChina
  3. 3.Shenzhen Academy of Aerospace TechnologyShenzhenChina

Personalised recommendations