Video target tracking is an important research direction in the field of computer vision, and plays an important role in artificial intelligence and big data applications. This paper mainly studies the comparison between generative model and discriminant model based on support vector machine (SVM) algorithm. This paper constructs MSA model and Structured SVM algorithm model according to the generation model and discriminant model classical target tracking algorithm respectively. This paper mainly uses OTB and TC-128 data sets as test data sets to conduct performance comparison experiments on target tracking algorithms of generative model and discriminant model. It can be seen from the experimental results that the Structured SVM model is superior to the MSA model in all aspects.

Shuang Guo. Comparison between Generative Model and Discriminant Model Based on Support Vector Nachine Algorithm. Machine Learning Theory and Practice (2022), Vol. 3, Issue 1: 10-17. https://doi.org/10.38007/ML.2022.030102.

[1] Kamkar S, Ghezloo F, Moghaddam H A, et al. Multiple-target tracking in human and machine vision. PLoS computational biology, 2020, 16(4): e1007698. https://doi.org/10.1371/journal.pcbi.1007698

[2] Dendorfer P, Osep A, Milan A, et al. Motchallenge: A benchmark for single-camera multiple target tracking. International Journal of Computer Vision, 2021, 129(4): 845-881. https://doi.org/10.1007/s11263-020-01393-0

[3] Mahmoudi N, Ahadi S M, Rahmati M. Multi-target tracking using CNN-based features: CNNMTT. Multimedia Tools and Applications, 2019, 78(6): 7077-7096. https://doi.org/10.1007/s11042-018-6467-6

[4] Penin B, Giordano P R, Chaumette F. Vision-based reactive planning for aggressive target tracking while avoiding collisions and occlusions. IEEE Robotics and Automation Letters, 2018, 3(4): 3725-3732. https://doi.org/10.1109/LRA.2018.2856526

[5] Tian Y, Dehghan A, Shah M. On detection, data association and segmentation for multi-target tracking. IEEE transactions on pattern analysis and machine intelligence, 2018, 41(9): 2146-2160. https://doi.org/10.1109/TPAMI.2018.2849374

[6] Briñón-Arranz L, Seuret A, Pascoal A. Circular formation control for cooperative target tracking with limited information. Journal of the Franklin Institute, 2019, 356(4): 1771-1788. https://doi.org/10.1016/j.jfranklin.2018.12.011

[7] Aryankia K, Selmic R R. Neuro-adaptive formation control and target tracking for nonlinear multi-agent systems with time-delay. IEEE Control Systems Letters, 2020, 5(3): 791-796. https://doi.org/10.1109/LCSYS.2020.3006187

[8] Daniyan A, Lambotharan S, Deligiannis A, et al. Bayesian multiple extended target tracking using labeled random finite sets and splines. IEEE Transactions on Signal Processing, 2018, 66(22): 6076-6091. https://doi.org/10.1109/TSP.2018.2873537

[9] Upadhyay J, Rawat A, Deb D. Multiple Drone Navigation and Formation Using Selective Target Tracking-Based Computer Vision. Electronics, 2021, 10(17): 2125. https://doi.org/10.3390/electronics10172125

[10] Tesfaye Y T, Zemene E, Prati A, et al. Multi-target tracking in multiple non-overlapping cameras using fast-constrained dominant sets. International Journal of Computer Vision, 2019, 127(9): 1303-1320. https://doi.org/10.1007/s11263-019-01180-6

[11] Chandrakala S, Jayalakshmi S L. Generative model driven representation learning in a hybrid framework for environmental audio scene and sound event recognition. IEEE Transactions on Multimedia, 2019, 22(1): 3-14. https://doi.org/10.1109/TMM.2019.2925956

[12] Yashchenko A V, Potapov A S, Rodionov S A, et al. Application of generative deep learning models for approximation of image distribution density. Journal of Optical Technology, 2019, 86(12): 769-773. https://doi.org/10.1364/JOT.86.000769

[13] Najar F, Bourouis S, Bouguila N, et al. A new hybrid discriminative/generative model using the full-covariance multivariate generalized Gaussian mixture models. Soft Computing, 2020, 24(14): 10611-10628. https://doi.org/10.1007/s00500-019-04567-2

[14] Ding Z, Shao M, Fu Y. Generative zero-shot learning via low-rank embedded semantic dictionary. IEEE transactions on pattern analysis and machine intelligence, 2018, 41(12): 2861-2874. https://doi.org/10.1109/TPAMI.2018.2867870

[15] Ko T, Kim H. Fault classification in high-dimensional complex processes using semi-supervised deep convolutional generative models. IEEE Transactions on Industrial Informatics, 2019, 16(4): 2868-2877. https://doi.org/10.1109/TII.2019.2941486

[16] Buscombe D, Grams P E. Probabilistic substrate classification with multispectral acoustic backscatter: A comparison of discriminative and generative models. Geosciences, 2018, 8(11): 395. https://doi.org/10.3390/geosciences8110395

[17] Kim J, Oh S, Kwon O W, et al. Multi-turn chatbot based on query-context attentions and dual wasserstein generative adversarial networks. Applied Sciences, 2019, 9(18): 3908. https://doi.org/10.3390/app9183908

[18] Lopez R, Gayoso A, Yosef N. Enhancing scientific discoveries in molecular biology with deep generative models. Molecular Systems Biology, 2020, 16(9): e9198. https://doi.org/10.15252/msb.20199198