2024, Vol. 4, Issue 1, Part A
Enhanced generative adversarial network for improved target tracking methodology
Author(s): Daniela Riva and Michele Mastroiacovo
Abstract: This research introduces an innovative approach to target tracking through the development of an Enhanced Generative Adversarial Network (GAN). By leveraging the adversarial training mechanism, our methodology significantly improves the robustness and accuracy of target tracking systems, particularly in challenging conditions such as occlusion, dynamic backgrounds, and varying target appearances. Comparative experiments conducted on standard tracking datasets demonstrate the superiority of our method over conventional tracking algorithms and standard GAN-based approaches in terms of precision, recall, and tracking stability.
Pages: 13-15 | Views: 335 | Downloads: 99
Download Full Article: Click Here
How to cite this article:
Daniela Riva, Michele Mastroiacovo. Enhanced generative adversarial network for improved target tracking methodology. Int J Electron Microcircuits 2024;4(1):13-15.
