Journal of Shandong Normal University(Natural Science), Volume. 40, Issue 2, 143(2025)

FACE TRACKING BASED ON GAUSS-HERMIT PARTICLE FILTER ALGORITHM

Zhou Pingping1, Zhang Hao2, and Li Tianping3
Author Affiliations
  • 1Yancheng Agricultural College, 224051, Yancheng, Jiangsu, China
  • 2Shuifa High-Tech Development Group Co., Ltd, 250100, Jinan, China
  • 3School of Physics and Electronics, Shandong Normal University, 250358, Jinan, China
  • show less

    Traditional particle filter-based tracking methods often fail to achieve precise tracking in complex video backgrounds.This article combines traditional particle filtering algorithm and Gaussian-Hermite algorithm to preprocess the video first. To improve tracking speed, this article uses an integral histogram to describe facial features, greatly reducing the feature calculation time and weight update time of particles. Additionally, dynamic fusion of color and edge features is implemented, combined with real-time adjustment of template parameters based on the dynamic evolution of facial morphology. The experiment verified that the method proposed in this paper can effectively enhance its stability and reliability when dealing with skin color, different lighting conditions, and other complex environmental factors.

    Tools

    Get Citation

    Copy Citation Text

    Zhou Pingping, Zhang Hao, Li Tianping. FACE TRACKING BASED ON GAUSS-HERMIT PARTICLE FILTER ALGORITHM[J]. Journal of Shandong Normal University(Natural Science), 2025, 40(2): 143

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: Mar. 16, 2025

    Accepted: Aug. 22, 2025

    Published Online: Aug. 22, 2025

    The Author Email:

    DOI:10.3969/j.issn.1001-4748.2025.02.004

    Topics