It is meaningful for moving target detection to maximize the advantages of the three-frame difference method and the background difference method and compensate their respective disadvantages. Therefore, this paper proposes the fusion of three-frame difference method and background difference method for infrared human motion target detection and uses a mixed gaussian model for background modeling. Aiming at the ghost region problem caused by mixed gaussian background modeling in the fusion process of two algorithms, the proposed solution is to determine whether the results of the mixed gaussian background modeling method include the results of the three-frame difference method. Through the experimental demonstration on the OTCBVS Benchmark Database, the results show that the proposed method is better than using the three-frame difference method and the background difference method alone in moving target detection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fusion of Three-frame Difference Method and Background Difference Method to Achieve Infrared Human Target Detection


    Contributors:


    Publication date :

    2019-10-01


    Size :

    334443 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    The application of difference method to dim point target detection in infrared images

    Wei-Ping Yang / Zhen-Kang Shen / Zhi-Yong Li | IEEE | 1994


    The Application of Difference Method to Dim Point Target Detection in Infrared Images

    Yang, W.-P. / Shen, Z.-K. / Li, Z.-Y. et al. | British Library Conference Proceedings | 1994


    Small Target Detection Algorithm Based on Average Absolute Difference Maximum and Background Forecast

    Chen, Z. / Wang, G. / Liu, J. et al. | British Library Online Contents | 2007



    Static vehicle detection method and system based on frame difference method

    ZHANG ZHILIN / LI HONGBO / ZHANG JUNJIE et al. | European Patent Office | 2020

    Free access