Improved Single Target Tracking Learning Detection Algorithm

In order to improve the robustness and the speed of single target tracking, this paper proposes an improved Tracking Learning Detection method. By modifying the tracking module in the traditional TLD algorithm, introducing the ORB feature points with fast matching speed and retaining the original uniform distribution points, the execution speed and robustness of the algorithm can be improved. The experiment shows that the improved TLD algorithm has strong robustness in different experimental environments and can quickly and accurately track the single object. The algorithm proposed in this paper effectively overcomes the tracking failures caused by the moving target‘s partial occlusion, rapid movement and departure from the tracking field of vision. It has better robustness, accuracy and faster execution speed than traditional TLD algorithm.

[1]  Ye Zhu,et al.  Copy-move forgery detection based on scaled ORB , 2015, Multimedia Tools and Applications.

[2]  Philip H. S. Torr,et al.  Struck: Structured output tracking with kernels , 2011, ICCV.

[3]  Vincent Lepetit,et al.  Fast Keypoint Recognition Using Random Ferns , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Zhenyu He,et al.  Connected Component Model for Multi-Object Tracking , 2016, IEEE Transactions on Image Processing.

[5]  Xiaofeng Liu,et al.  Fish Tracking Based on Improved TLD Algorithm in Real-World Underwater Environment , 2019, Marine Technology Society Journal.

[6]  Zdenek Kalal,et al.  Tracking-Learning-Detection , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Lizhong Xu,et al.  Object tracking with improved firefly algorithm , 2018, Int. J. Comput. Sci. Math..

[8]  Li Zhuo,et al.  ORB feature based web pornographic image recognition , 2016, Neurocomputing.

[9]  Xianyi Chen,et al.  A GLCM-Feature-Based Approach for Reversible Image Transformation , 2019, Computers, Materials & Continua.

[10]  Vibhav Vineet,et al.  Struck: Structured Output Tracking with Kernels , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[12]  Assia Maamar,et al.  A Hybrid Model for Anomalies Detection in AMI System Combining K-means Clustering and Deep Neural Network , 2019, Computers, Materials & Continua.

[13]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[14]  Nadjiba Terki,et al.  Improved object tracking via joint color-LPQ texture histogram based mean shift algorithm , 2018, Signal Image Video Process..

[15]  Zhiqiang Wang,et al.  Cross-camera multi-person tracking by leveraging fast graph mining algorithm , 2018, J. Vis. Commun. Image Represent..

[16]  Yi Wu,et al.  Online Object Tracking: A Benchmark , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Li Zhao,et al.  An Adaptive Superpixel Tracker Using Multiple Features , 2019 .

[18]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.