Object Tracking Based on Exactly Reweighted Online Total-Error-Rate Minimization

정확히 재가중되는 온라인 전체 에러율 최소화 기반의 객체 추적

  • JANG, Se-In (Department of Statistics and Applied Probability, National University of Singapore) ;
  • PARK, Choong-Shik (Department of Smart IT, U1 University)
  • 장세인 (싱가폴국립대학 통계학과) ;
  • 박충식 (U1대학교 스마트IT학과)
  • Received : 2019.11.12
  • Accepted : 2019.12.16
  • Published : 2019.12.31


Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.


Supported by : 한국연구재단


  1. Babenko, B., M.-H. Yang, and S. Belongie, "Robust Object Tracking with Online Multiple Instance Learning," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.33, No.8(2011), 1619-1632.
  2. Batkhuu, B., A. Jumabek, F. Yang, S. Ko, and G. S. Jo, "Transfer Learning using Multiple ConvNet Layers Activation Features with Principal Component Analysis for Image Classification," Journal of Intelligence and Information Systems, Vol. 24, No. 1(2018), 205-225.
  3. Crammer, K., O. Dekel, J. Keshet, S. Shalev-Shwartz, and Y. Singer, "Online Passive-Aggressive Algorithms," Journal of Machine Learning Research, Vol.7(2006), 551-585.
  4. Crammer, K., A. Kulesza, and M. Dredze, "Adaptive Regularization of Weight Vectors," Advances in Neural Information Processing Systems, (2009), 414-422.
  5. Dredze, M., K. Crammer, and F. Pereira, "Confidence-Weighted Linear Classification," International Conference on Machine Learning, (2008), 264-271.
  6. Hu, W., T. Tan, L. Wang, and S. Maybank, "A Survey on Visual Surveillance of Object Motion and Behaviors," IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol.34, No.3 (2004), 334-352.
  7. Hare, S., A. Saffari, and P. H. S. Torr, "Struck: Structured Output Tracking with Kernels," IEEE International Conference on Computer Vision, (2011), 263-270.
  8. Lee, M.-S., and H. Ahn, "A Time Series Graph based Convolutional Neural Network Model for Effective Input Variable Pattern Learning : Application to the Prediction of Stock Market," Journal of Intelligence and Information Systems, Vol. 24, No. 1(2018), 167-181.
  9. Jang, S.-I., K. Choi, K.-A. Toh, A.B.J. Teoh, and J. Kim, "Object Tracking Based on An Online Learning Network with Total Error Rate Minimization," Pattern Recognition, Vol.48, No.1(2015), 126-139.
  10. Kim, Y., K.-A. Toh, A. B. J. Teoh, H.-L. Eng, and W.-Y. Yau, "An Online Learning Network for Biometric Scores Fusion," Neurocomputing, Vol.102(2013), 65-77.
  11. Kalal, Z., J. Matas, and K. Mikolajczyk, "P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints," IEEE Conference on Computer Vision and Pattern Recognition, (2010), 49-56.
  12. Yilmaz, A., O. Javed, and M. Shah, "Object Tracking: A Survey," ACM Computing Surveys, Vol.38, No.4(2006), 1-46.
  13. Ross, D. A., R.-S. Lin, and M.-H. Yang, "Incremental Learning for Robust Visual Tracking," International Journal of Computer Vision, Vol.77, No.1(2008), 125-141.
  14. Rosenblatt, F., "The Perceptron: A Probabilistic Model for Information Storage and Organization in The Brain," Psychological Review, Vol.65, No.6(1958), 386-408.
  15. Kim, S., and J. Kim, "Customer Behavior Prediction of Binary Classification Model Using Unstructured Information and Convolution Neural Network: The Case of Online Storefront," Journal of Intelligence and Information Systems, Vol. 24, No. 2(2018), 221-241.
  16. Toh, K.-A., "Deterministic neural classification," Neural computation, Vol.20, No.6(2008), 1565-1595.
  17. Grabner, H., M. Grabner, and H. Bischof, "Real-Time Tracking via On-line Boosting," British Machine Vision Conference, (2006), 47-56.
  18. Zhong, W., H. Lu, and M.-H. Yang, "Robust Object Tracking via Sparsity-based Collaborative Model," IEEE Conference on Computer Vision and Pattern Recognition, (2012), 1838-1845.