Research on Target Tracking Algorithm of Twin Networks Integrating Attention Mechanism

Authors

  • Relizha Yeerlanbieke
  • Huazhang Wang

DOI:

https://doi.org/10.54097/fbem.v2i3.203

Keywords:

Deep learning, Twin neural network, Target tracking, Attention mechanism

Abstract

Aiming at the current stage of the twin network target tracking algorithm, the tracking target is occluded, the tracking is affected by illumination, and the target's scale change from far to near or from near to far causes tracking failure. This article will optimize and improve from two directions. The twin neural network first uses an adaptive detailed feature extraction, adds a residual network to the twin network, and embeds a detailed feature retention module in each layer, amplifies the changes in the target feature, and retains the important structure of the original target feature Details: Secondly, the introduction of a spatial attention mechanism allows the main branch to pay more attention to the area to be matched, improves the ability to distinguish features, and makes the tracking effect better. In order to verify the effectiveness of this experiment, this experiment was tested on the data set OTB2015. The experiment proved that the proposed algorithm performs better in accuracy and success rate.

Downloads

Download data is not yet available.

References

PENG J Y, CHEN X B. Novel models for one-sided hysteresis of piezoelectric actuator [J]. Mechatronics, 2012, 22(6):757-765.

Yang Kang, Song Huihui, Zhang Kaihua. Real-time visual tracking based on dual attention siamese network [J]. Journal of Computer Applications, 2019, 39(6):1652-1656. (in Chinese)

Kuai Y,WenG,Li D.Hyper-Siamese network forrobust visual tracking[J]. Signal, Image and Video Processing, 2019, 1 3(1):35-42.

Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and MachineIntelli -gence, 2015, 37(3): 583-596.

XU T, FENG Z H,WU X,etal. Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual object tracking [J]. IEEE Transactions on Image Processing, 2019, 28(11):5596-5609.

Abbas Manuel, Somme Dominique, Le Bouquin Jeannès Régine. D-SORM: A digital solution for remote monitoring based on the attitude of wearable devices[J]. Computer Methods and Programs in Biomedicine,2021,208:

[7] Bai Xingzhen, et al."Target tracking for wireless localization systems using set-membership filtering: A component-based event-triggered mechanism." Automatica 132.(2021): doi:10.1016/J.AUTOMATICA.2021.109795.

Bednarz Bryan P.,Jupitz Sydney,Lee Warren,Mills David,Chan Heather,Fiorillo Timothy,Sabitini James,Shoudy David, Patel Aqsa, Mitra Jhimli,Sarcar Shourya,Wang Bo, Shepard Andrew, Matrosic Charles,Holmes James, Culberson Wesley, Bassetti Michael, Hill Patrick, McMillan Alan,Zagzebski James,Smith L. Scott,Foo Thomas K.. First-in-human imaging using a MR-compatible e4D ultrasound probe for motion management of radiotherapy[J]. Physica Medica, 2021, 88:

Elgamoudi Abulasad,Benzerrouk Hamza,Elango G. Arul, Landry René. A Survey for Recent Techniques and Algorithms of Geolocation and Target Tracking in Wireless and Satellite Systems[J]. Applied Sciences,2021,11(13):

Sun Peng,Zhu Bing,Zuo Zongyu,Basin Michael V.. Vision-based finite-time uncooperative target tracking for UAV subject to actuator saturation[J]. Automatica,2021,130.

Downloads

Published

16 December 2021

How to Cite

Yeerlanbieke, R., & Wang, H. (2021). Research on Target Tracking Algorithm of Twin Networks Integrating Attention Mechanism. Frontiers in Business, Economics and Management, 2(3), 78–81. https://doi.org/10.54097/fbem.v2i3.203

Issue

Section

Articles