Username   Password       Forgot your password?  Forgot your username? 


A Novel Target Algorithm based on TLD Combining with SLBP

Volume 13, Number 4, July 2017 - Paper 13 - pp. 458-468
DOI: 10.23940/ijpe.17.04.p13.458468

Jitao Zhanga, Aili Wanga, Mingxiao Wanga, Yuji Iwahorib

aHigher Education Key Lab for Measure & Control Technology and Instrumentations of Heilongjiang, Harbin University of Science and Technology, Harbin,150080, China
bDepartment of Computer Science, Chubu University, Aichi, Japan

(Submitted on February 3, 2017; Revised on April 22, 2017; Accepted on June 16, 2017)


TLD (Tracking-Learning-Detection) algorithm can be good for a long time to track the target in rotation, occlusion, illumination and other circumstances. However, in the case of uneven illumination, occlusion, tracking target fuzzy and so on, the problem of false tracking or tracking failure often occurs. Aiming at the shortcomings of TLD tracking algorithm, this paper will take TLD as the basic framework of target tracking and improve the detection module. When the tracking target has better texture feature, the SLBP (Semantic Local Binary Pattern) classifier is used to replace the nearest neighbor classifier in the detection module, which converts the image into SLBP texture feature vector to classify the samples using. In this paper, TLD-SLBP, MEEM, SCM, Struck and TLD are compared by using CVPR2013Benchmark test platform. The experiment results show that the TLD-SLBP algorithm has a higher success rate than other algorithms.


References: 14

1.    Maliha A, Yusof R, Madani A, “Online sequential-extreme learning machine based detector on training-learning-detection framework”, Control Conference, IEEE, pp. 1-5, 2015
2.    Jia C, Wang Z, Wu X, et al, “A Tracking-Learning-Detection (TLD) method with local binary pattern improved”, IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1625-1630, 2015
3.    Zhou C, Dong Q, Ma W, et al, “PE-TLD: Parallel Extended Tracking-Learning-Detection for Multi-target Tracking”, Algorithms and Architectures for Parallel Processing, pp. 665-677
4.    Park E, Ju H, Jeong Y M, et al, “Tracking-Learning-Detection Adopted Unsupervised Learning Algorithm”, Seventh International Conference on KnowledgeFig. 1 and Systems Engineering, IEEE, pp. 234-237, 2015
5.    H Grabner, J Sochman, H bischof, et al, “Training Sequential On-line Boosting Classifier for Visual Tracking”, International Conference on Pattern Recognition, pp.1-4, 2008
6.    B Babenko, “Multiple Instance Learning With Manifold Bags”, Journal of Clinical Microbillogy, pp. 2609-2611, 2011
7.    Kalal Z, Mikolajczk K, et al, “Tracking Learning Detection”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(7), pp.:1409-1422, 2012
8.    Hu J, Hu S, Sun Z, “A Real Time Dual-Camera Surveillance System Based On Tracking-Learning-Detection Algorithm”, Control and Decision Conference, IEEE, pp. 886-891, 2013
9.    Chen L, Zhu S, Li X, et al, “Target tracking via improved TLD algorithm”, Control and Decision Conference, IEEE, pp. 5942-5947, 2015
10.    Hongjun S, Tao Y, “Crane tracking and monitoring system based on TLD algorithm”, IEEE International Instrumentation and Measurement Technology Conference Proceedings, pp. 1-5, 2016
11.    Tsai S Y, Chen C Y, Lee J S, et al, “Evaluation of Effective Dose using TLDs With Different Weighted PMMA Phantoms Undergoing Coronary Artery Calcium Computed Tomography Examination”, IEEE Transactions on Nuclear Science, Vol.60, No.3, pp. 2147-2154, 2013
12.    Z. Ping, S. Youngqi, W. Yali, and Z. Rui, “A Parallel Implementation of TLD Algorithm using CUDA”, ICWMMN2013 Proceedings,  pp. 220-224, 2013
13.    Min W P, Jung S K, “TLD based vehicle tracking system for AR-HUD using HOG and online SVM in EHMI”, IEEE International Conference on Consumer Electronics, pp. 289 – 290, 2015
14.    Kong W, Zhang D, Zhao S, et al, “Autonomous track and land a MAV using a modified tracking-learning-detection framework”, Control Conference, IEEE, pp. 5359-5366, 2015




Click here to download the paper.

Please note : You will need Adobe Acrobat viewer to view the full articles.Get Free Adobe Reader

This site uses encryption for transmitting your passwords.