Abstract Black and white films were the main form of human culture records before. Colorization of those films is creative. At present, Colorization of black and white films is still handmade which is expensive and time consuming. In this paper, a framework based on CNN and particle filter tracking algorithm is proposed, which can color black and white video and try to solve the problem of dynamic frame based on context correlation. At the same time, the objective function of CNN structure and particle filter tracking are optimized. The result of colorization on videos is satisfactory.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Video Coloring Method Based on CNN and Feature Point Tracking


    Contributors:
    Guan, George (author) / Zhang, Fuquan (author) / Ding, Gangyi (author) / Niu, Meng (author) / Xu, Lin (author)


    Publication date :

    2017-11-03


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Coloring Local Feature Extraction

    van de Weijer, J. / Schmid, C. | British Library Conference Proceedings | 2006


    Coloring Local Feature Extraction

    de Weijer, Joost / Schmid, Cordelia | Springer Verlag | 2006

    Free access

    Image feature based video object description and tracking

    Yildiz, Ramazan / Acarman, Tankut | IEEE | 2012


    Non-cooperative spacecraft pose tracking based on point cloud feature

    He, Ying / Liang, Bin / He, Jin et al. | Elsevier | 2017


    Motion Tracking of Dense Feature Point Sets

    Chetverikov, D. / Verestoy, J. / Austrian Association for Pattern Recognition | British Library Conference Proceedings | 1997