Academic Journal of Computing & Information Science, 2024, 7(9); doi: 10.25236/AJCIS.2024.070910.
Xiaokai Jiang, Xuewen Ding, Chunyu Liu, Yuan Zhang, Shaosai Wang
School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, China
In today's society, computer vision technology has become an important part of the field of artificial intelligence, and plays a key role in many practical application scenarios. This paper mainly discusses the research progress and application of target tracking algorithm based on computer vision. Firstly, the basic concept and technical background of target tracking are summarized, including key technical links such as target detection, feature extraction and motion prediction. Then, several mainstream target tracking methods, such as correlation filter tracking, deep learning tracking and model-based tracking, are analyzed, and their advantages and disadvantages are compared. Additionally, this paper accords prominence to the utilization of deep learning technology in the domain of target tracking, presenting a selection of sophisticated neural network-based tracking algorithms and assessing their respective performances. In addition, some improvement measures and solutions are proposed to solve the challenges of existing tracking algorithms, such as occlusion, illumination change, scale change, etc. Finally, this paper compares the performance of different tracking algorithms through experiments.
Computer vision; Target tracking; Deep learning; Feature matching; Algorithm evaluation
Xiaokai Jiang, Xuewen Ding, Chunyu Liu, Yuan Zhang, Shaosai Wang. Research on artificial intelligence target tracking algorithm based on computer vision. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 9: 74-81. https://doi.org/10.25236/AJCIS.2024.070910.
[1] Konstantinova, Pavlina D., Alexander Udvarev, and Tzvetan Semerdjiev. "A study of a target tracking algorithm using global nearest neighbor approach." Compsystech. Vol. 3. 2003.
[2] Uhlmann, Jeffrey K. "Algorithms for multiple-target tracking." American Scientist 80.2 (1992): 128-141.
[3] Souza, Éfren L., Eduardo F. Nakamura, and Richard W. Pazzi. "Target tracking for sensor networks: A survey." ACM Computing Surveys (CSUR) 49.2 (2016): 1-31.
[4] Fiaz, Mustansar, Arif Mahmood, and Soon Ki Jung. "Tracking noisy targets: A review of recent object tracking approaches." arxiv preprint arxiv:1802.03098 (2018).
[5] Zefenfen, et al. "Target tracking approach via quantum genetic algorithm." IET Computer Vision 12.3 (2018): 241-251.
[6] Kim, JeongWoon, and David Hyunchul Shim. "A vision-based target tracking control system of a quadrotor by using a tablet computer." 2013 international conference on unmanned aircraft systems (icuas). IEEE, 2013.
[7] Kamkar, Shiva, et al. "Multiple-target tracking in human and machine vision." PLoS computational biology 16.4 (2020): e1007698.
[8] Jeong, Jaehoon, et al. "Mcta: Target tracking algorithm based on minimal contour in wireless sensor networks." IEEE INFOCOM 2007-26th IEEE International Conference on Computer Communications. IEEE, 2007.
[9] Arnold, James, S. W. Shaw, and H. E. N. R. I. Pasternack. "Efficient target tracking using dynamic programming." IEEE transactions on Aerospace and Electronic Systems 29.1 (1993): 44-56.
[10] Rameshbabu, K., et al. "Target tracking system using kalman filter." International Journal of Advanced Engineering Research and Studies 2 (2012): 90-94.
[11] Fan, Litong, et al. "A survey on multiple object tracking algorithm." 2016 IEEE International Conference on Information and Automation (ICIA). IEEE, 2016.
[12] Khedr, Ahmed M., and Walid Osamy. "Effective target tracking mechanism in a self-organizing wireless sensor network." Journal of Parallel and Distributed Computing 71.10 (2011): 1318-1326.