Journal of Systems Engineering and Electronics ›› 2020, Vol. 31 ›› Issue (2): 272-278.doi: 10.23919/JSEE.2020.000005

• Electronics Technology • Previous Articles     Next Articles

Automatic video mosaicking algorithm via dynamic key-frame

Yufeng JI1(), Weixing LI1,*(), Kai FENG1(), Boyang XING1(), Feng PAN1,2()   

  1. 1 School of Automation, Beijing Institute of Technology, Beijing 100081, China
    2 Kunming-BIT Industry Technology Research Institute Co., Ltd, Kunming 650106, China
  • Received:2019-03-26 Online:2020-04-30 Published:2020-04-30
  • Contact: Weixing LI E-mail:jyf131462@163.com;liweixing@bit.edu.cn;bitfengkai@163.com;golaced@163.com;andropanfeng@126.com
  • About author:JI Yufeng was born in 1994. He received his B.S. degree from Beijing Institute of Technology in 2016. Since 2016, he has been a postgraduate student majoring in control science and engineering in Beijing Institute of Technology. His research interests include machine learning and objects detecting, and tracking of UAVs. E-mail: jyf131462@163.com|LI Weixing was born in 1976. He received his M.S. degree in pattern recognition and intelligent control from Beijing Institute of Technology. He is an associate professor at School of Automation in Beijing Institute of Technology, China. His research interests include pattern recognition, video analysis and machine learning. E-mail: liweixing@bit.edu.cn|FENG Kai was born in 1996. He received his B.S. degree from Beijing Institute of Technology in 2018. Since 2018, he has been a postgraduate student majoring in control science and engineering in Beijing Institute of Technology. His research interests include computer vision and deep learning. E-mail: bitfengkai@163.com|XING Boyang was born in 1990. He received his M.S. degree from Beijing Institute of Technology in 2012. Since 2015, he has been a doctoral student majoring in control science and engineering in Beijing Institute of Technology. His research interests include robotics and control, and computer vision. E-mail: golaced@163.com|PAN Feng was born in 1978. He received his M.S. and Ph.D. degrees in pattern recognition and intelligent control from Beijing Institute of Technology. He is an associate professor at School of Automation in Beijing Institute of Technology. His research interests include intelligent computing, robotics and control, and computer vision. E-mail: andropanfeng@126.com
  • Supported by:
    the National Science Foundation of China(61603040);the National Science Foundation of China(61973036);the National Science Foundation of China(61433003);This work was supported by the National Science Foundation of China (61603040; 61973036; 61433003)

Abstract:

Automatic video mosaicking is a challenging task in computer vision. Current researches consider either panoramic or mapping tasks on short videos. In this paper, an automatic mosaicking algorithm is proposed for both mapping and panoramic tasks based on the adapted key-frame on videos of any length. The speeded up robust features (SURF) and the grid motion statistic (GMS) algorithm are used for feature extraction and matching between consecutive frames, which are used to compute the transformation. In order to reduce the influence of the accumulated error during image stitching, an evaluation metric is put forward for the transformation matrix. Besides, a self-growth method is employed to stitch the global image for long videos. The algorithm is evaluated by using aerial-view and panoramic videos respectively on the graphic processing unit (GPU) device, which can satisfy the real-time requirement. The experimental results demonstrate that the proposed algorithm is able to achieve a better performance than the state-of-art.

Key words: video mosaicking, image stitching, speeded up robust feature (SURF), panorama, mapping