UAV (Unmanned Aerial Vehicle) is serving as a major platform for developing and testing the artificial intelligence technology. However, how to develop the technology of UAV visual object tracking encounters many numerous difficulties given that the further development of UAV technology is based on it. Firstly, based on the kernel correlation filtering algorithm, this paper uses multiple features to train the regressor respectively, and then fuses the feature map adaptively. Secondly, the template update strategy is changed according to the peak to sideline ratio of the feature map and the similarity between the templates. Next, through the verification on OTB100, the algorithm proposed in this paper is greatly improved compared with others seeing that tracking speed exceeds 30 fps, meeting the real-time requirements. Last but not least, the simulation system of UAV object tracking is built under the ROS (Robot Operating System) platform, and further verified the feasibility of the algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Object Tracking Algorithm of UAV Based on Fast Kernel Correlation Filter


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Jia, Yingmin (editor) / Zhang, Weicun (editor) / Fu, Yongling (editor) / Liu, Xukuai (author) / Sun, Mingjian (author) / Meng, Lingbo (author)

    Conference:

    Chinese Intelligent Systems Conference ; 2020 ; Shenzhen City, China October 24, 2020 - October 25, 2020



    Publication date :

    2020-09-30


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    UAV Target Tracking Algorithm Based on Kernel Correlation Filter

    Qu, Jingkun / Xu, Jinxiang | British Library Conference Proceedings | 2022


    UAV Target Tracking Algorithm Based on Kernel Correlation Filter

    Qu, Jingkun / Xu, Jinxiang | Springer Verlag | 2022


    Multiple object tracking with kernel particle filter

    Cheng Chang, / Ansari, R. / Khokhar, A. | IEEE | 2005