A novel online self-learning system with automatic object detection model for multimedia applications

Abstract

This paper proposes a novel online self-learning detection system for different types of objects. It allows users to random select detection target, generating an initial detection model by selecting a small piece of image sample and continue training the detection model automatically. The proposed framework is divided into two parts: First, the initial detection model and the online reinforcement learning. The detection model is based on the proportion of users of the Haar-like features to generate feature pool, which is used to train classifiers and get positive-negative (PN) classifier model. Second, as the videos plays, the detecting model detects the new sample by Nearest Neighbor (NN) Classifier to get the PN similarity for new model. Online reinforcement learning is used to continuously update classifier, PN model and new classifier. The experiment shows the result of less detection sample with automatic online reinforcement learning is satisfactory.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23

References

  1. 1.

    Cheng YY (2014) “Adaptive on-line boosting detector with conservative verification,” Institute of Electrical Control Engineering, National Chiao Tung University

  2. 2.

    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1:886–893

    Google Scholar 

  3. 3.

    Dollár P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743–761

    Article  Google Scholar 

  4. 4.

    Dong E, Deng M, Tong J, Jia C, du S (2019) Moving vehicle tracking based on improved tracking–learning–detection algorithm. IET Comput Vis 13(8):730–741

    Article  Google Scholar 

  5. 5.

    Farfade S et al. (2015) Multi-view Face Detection Using Deep Convolutional Neural Networks, in International Conference on Multimedia Retrieval 2015 (ICMR)

  6. 6.

    Gerónimo D et al. (2007) Haar Wavelets and Edge Orientation Histograms for On–board Pedestrian Detection, Pattern Recognition and Image Analysis. Springer Berlin Heidelberg, 418–425

  7. 7.

    Gopale R, Deshpande M. “Real time object Tracking Using Tracking Learning Detection,” International Journal of Infinite Innovations of Technology, 2014–2015 January, Paper – 01, DOI: V3I3P01

  8. 8.

    Grabner H, Bischof H (2006) On-line Boosting and Vision. in Proc. CVPR 1:260–267

    Google Scholar 

  9. 9.

    Grabner H, Grabner M, Bischof H (2006) Real-time Tracking via On-line Boosting. in Proc. BMVC 1:47–56

    Google Scholar 

  10. 10.

    Kalal Z, Mikolajczyk K, Matas J (2012) Tracking-Learning-Detection, Pattern Analysis and Machine Intelligence, IEEE Transactions on 34.7 pp. 1409–1422

  11. 11.

    Khammari A, et al. (2005) Vehicle detection combining gradient analysis and AdaBoost classification, Intelligent Transportation Systems, 2005. Proceedings. 2005 IEEE. IEEE

  12. 12.

    Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks, NIPS

  13. 13.

    Kuo CH, Nevatia R (2009) Robust multi-view Car detection using unsupervised sub-categorization, Workshop on Applications of Computer Vision, 1-8

  14. 14.

    Lee DC (2007) Boosted Classifier for Car Detection, http://www.cs.cmu.edu/~dclee/car_boosted.pdf vol. 1, no. c, pp. 1–4

  15. 15.

    Lee JF (2010) A novel vehicle detection system using local and global features, Institute of Biomedical Engineering, National Chiao Tung University

  16. 16.

    R. Lienhart and J. Maydt, “An extended set of Haar-like features for rapid object detection,” International Conference on Image Processing, vol. 1, pp. 0–3, (2002)

  17. 17.

    Oza NC (2005) Online Bagging and Boosting, Systems, Man and Cybernetics, 2005 IEEE international conference on. Vol. 3. IEEE

  18. 18.

    Riberio M, et al. (2017) A Real-Time Deep Learning Pedestrian Detector for Robot Navigation, in IEEE Int’l Conf. Autonomous Robot Systems and Competitions (ICARSC)

  19. 19.

    Roth PM, Bischof H (2008) Conservative Learning for Object Detectors, Machine Learning Techniques for Multimedia. Springer Berlin Heidelberg, 139-158

  20. 20.

    Roth PM et al. (2005) On-line Conservative Learning for Person Detection, Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2005. 2nd joint IEEE international workshop on. IEEE

  21. 21.

    Sabzmeydani P, Mori G (2007) Detecting pedestrians by learning Shapelet features, IEEE Conference on Computer Vision and Pattern Recognition, 1-8

  22. 22.

    Scharcanski J, Calvalcanti PG (2011) “A Particular Filtering Approach for Vehicular Tracking Adaptive to Occlusions,” IEEE Trans. Veh. Tech. vol. 6, no. 2

  23. 23.

    Sivaraman S, Trivedi MM (2010) A general active learning framework for on-road vehicle recognition and tracking. IEEE Trans Intell Transp Syst 11:267–276

    Article  Google Scholar 

  24. 24.

    Song Z, Cong Z, Yanan Z, et al. (2017) An Improved TLD Target Tracking Algorithm based on Mean Shift, 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI). IEEE, 2017: 387–391

  25. 25.

    Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks, NIPS

  26. 26.

    Su J, Gao L, Li W, Xia Y, Cao N, Wang R (2019) Fast face tracking-by-detection algorithm for secure monitoring. Appl Sci 9(18):3774

    Article  Google Scholar 

  27. 27.

    Sun Z, Bebis G, Miller R (2006) On-road vehicle detection: a review. IEEE Trans Pattern Anal Mach Intell 28:694–711

    Article  Google Scholar 

  28. 28.

    Suo P, Wang YJ (2008) An Improved Adaptive Background Modeling Algorithm based on Gaussian Mixture Model, in 9th IEEE Proc. Int Conf on Signal Processing, vol. 2, pp. 1436–1439

  29. 29.

    Tome D, Bondi L et al. (2016) Reduced Memory Region Based Deep Convolutional Neural Network Detection, 2016 IEEE 6th International Conference on Consumer Electronics – Berlin (ICCE-Berlin)

  30. 30.

    Viola P, Jones M (2004) Robust real-time face detection. Int J Comput Vis 57(2):137–154

    Article  Google Scholar 

  31. 31.

    Walk S, Majer N, Schindler K, Schiele B (2010) New features and insights for pedestrian detection, IEEE Conference on Computer Vision and Pattern Recognition, 1030–1037

  32. 32.

    Wang L, Lu Y, et al. (2017) “Evolving Boxes for Fast Vehicle Detection,” in IEEE International Conference on Multimedia and Expo (ICME), pp. 1135–1140

  33. 33.

    Wu BS (2013) “Detection and tracking of multi-angle, partially occluded vehicles by boosting-based part detectors”, Institute of Electrical Control Engineering, National Chiao Tung University

  34. 34.

    Yang M, Lv F, Xu W, et al. (2009) “Detection driven adaptive multi-cue integration for multiple human tracking” 2009 IEEE 12th international conference on computer vision. IEEE, 2009: 1554–1561

  35. 35.

    Zhou S, Peng Y, Gong K, et al. (2018) An Improved TLD Tracking Algorithm for Fast-moving Object, 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018). Atlantis Press

Download references

Acknowledgements

This work was supported in part by the Australian Research Council (ARC) under Grant DP180100670 and Grant DP180100656, in part by the U.S. Army Research Laboratory under Agreement W911NF-10-2-0022, and in part by the Taiwan Ministry of Science and Technology under Grant MOST 106-2218-E-009-027-MY3.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Mukesh Prasad.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cheng, E.J., Prasad, M., Yang, J. et al. A novel online self-learning system with automatic object detection model for multimedia applications. Multimed Tools Appl 80, 16659–16681 (2021). https://doi.org/10.1007/s11042-020-09055-6

Download citation

Keywords

  • Object detection
  • Online learning
  • Real-time learning
  • Feature pool
  • Classifier