In recent years, with the explosive growth of research in the field of computer vision, TT has an important application in visual recognition tasks. It can assist target detection and improve the speed of recognition, which has certain theoretical value and research significance. However, in practical application scenarios, target tracking (TT) still faces the problems of inaccurate tracking, poor robustness, and low overall system speed caused by scene changes. Since the TT algorithm based on convolutional neural network (CNN) was proposed, it has attracted the attention of a large number of researchers with the advantages of both speed and accuracy. The multi-layer convolution features extracted from the input image through the CNN have a good appearance representation ability for the target under a variety of complex interference factors. Therefore, this paper uses the CNN to build a feature TT algorithm model, and experiments prove that the accuracy of the model can be improved by increasing the order of magnitude and deepening the ResNet backbone network design. After comparing the tracking effects of the CNN algorithm and other algorithms, it shows that the CNN algorithm has the highest tracking accuracy and success rate.

Rashid Almulihi. Algorithm Research of Neural Network for Feature Target Tracking. International Journal of Neural Network (2022), Vol. 3, Issue 4: 9-16. https://doi.org/10.38007/NN.2022.030402.

[1] Rohan A, Rabah M, Kim S H. Convolutional Neural Network-based Real-Time Object Detection and Tracking for Parrot AR Drone 2. IEEE Access, 2019, PP(99):1-1. https://doi.org/10.1109/ACCESS.2019.2919332

[2] Jondhale S R, Wakchaure M A, Agarkar B S, et al. Improved Generalized Regression Neural Network for Target Localization. Wireless Personal Communications, 2021, 125(2):1677-1693. https://doi.org/10.1007/s11277-022-09627-9

[3] Sebkhi N, Sahadat N, Hersek S, et al. A Deep Neural Network-Based Permanent Magnet Localization for Tongue Tracking. IEEE Sensors Journal, 2019, PP(99):1-1.

[4] Bohush R, Zakharava I. 109-116. - Citation: Bohush RP, Zakharava IY. Person Tracking Algorithm Based on Convolutional Neural Network for Indoor Video Surveillance. Computer Optics, 2020, 44(1):109-116. https://doi.org/10.18287/2412-6179-CO-565

[5] Issaadi S, Issaadi W, Khireddine A. New Intelligent Control Strategy by Robust Neural Network Algorithm for Real Time Detection Of An Optimized Maximum Power Tracking Control In Photovoltaic Systems. Energy, 2019, 187(Nov.15):115881.1-115881.21. https://doi.org/10.1016/j.energy.2019.115881

[6] Ham D, Cho H C, Yoon Y J, et al. Feature Based Extended TT Using Automotive 2D LIDAR. Transactions of the Korean Institute of Electrical Engineers, 2021, 70(1):224-235. https://doi.org/10.5370/KIEE.2021.70.1.224

[7] Mayorca-Torres D, Guerrero-Chapal H, J Mejía-Manzano, et al. Multi-TT for Sperm Motility Measurement Using the Kalman Filter and JPDAF: Preliminary Results. RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao, 2019, 1(E22):282-294.

[8] Shiozuka M, Yotsumoto T, Takahashi K, et al. Agent-based Tracking Method Addressing Target Recognition Errors. IEEJ Transactions on Electronics Information and Systems, 2020, 140(4):484-491. https://doi.org/10.1541/ieejeiss.140.484

[9] Moorthy S, Joo Y H. Multi-Expert Visual Tracking Using Hierarchical Convolutional Feature Fusion Via Contextual Information. Information Sciences, 2021, 546(2021):996-1013. https://doi.org/10.1016/j.ins.2020.09.060

[10] Bhat P G, Subudhi B N, Veerakumar T, et al. Multi-Feature Fusion in Particle Filter Framework for Visual Tracking. IEEE Sensors Journal, 2020, 20(5):2405-2415. https://doi.org/10.1109/JSEN.2019.2954331

[11] Wulff D, Kuhlemann I, Ernst F, et al. Robust Motion Tracking of Deformable Targets in the Liver Using Binary Feature Libraries in 4D Ultrasound. Current Directions in Biomedical Engineering, 2019, 5(1):601-604. https://doi.org/10.1515/cdbme-2019-0151

[12] Pichlmeier S, Pfeiffer T. Adaptive Target Enhancement Determines Levels of Guidability in Multiple Object Tracking. Vision Research, 2021, 183(13):61-72. https://doi.org/10.1016/j.visres.2021.02.001

[13] Hsu H M, Cai J, Wang Y, et al. Multi-Target Multi-Camera Tracking of Vehicles Using Metadata-Aided Re-ID and Trajectory-Based Camera Link Model. IEEE Transactions on Image Processing, 2021, PP(99):1-1. https://doi.org/10.1109/TIP.2021.3078124

[14] Walia G, Ahuja H, Kumar A, et al. Unified Graph-Based Multicue Feature Fusion for Robust Visual Tracking. IEEE Transactions on Cybernetics, 2020, 50(6):2357-2368. https://doi.org/10.1109/TCYB.2019.2920289

[15] Chu V C, D'Zmura M. Tracking Feature-Based Attention. Journal of Neural Engineering, 2019, 16(1):308-321. https://doi.org/10.1088/1741-2552/aaed17

[16] Dash P P, Patra D. Efficient Visual Tracking Using Multi-Feature Regularized Robust Sparse Coding and Quantum Particle Filter Based Localization. Journal of Ambient Intelligence and Humanized Computing, 2019, 10(2):449-462. https://doi.org/10.1007/s12652-017-0663-5

[17] Nodehi H, Shahbahrami A. Multi-Metric Re-identification for Online Multi-Person Tracking. IEEE Transactions on Circuits and Systems for Video Technology, 2021, PP(99):1-1. https://doi.org/10.1109/TCSVT.2021.3059250

[18] Sliti O, Hamam H. Efficient Visual Tracking Via Sparse Representation and Back-Projection Histogram. Multimedia Tools and Applications, 2019, 78(15):21759-21783. https://doi.org/10.1007/s11042-019-7439-1