sesa 20(23): e5

Research Article

Self-Controllable Super-Resolution Deep Learning Framework for Surveillance Drones in Security Applications

Download18 downloads
  • @ARTICLE{10.4108/eai.30-6-2020.165502,
        author={Soohyun Park and Yeongeun Kang and Jeman Park and Joongheon Kim},
        title={Self-Controllable Super-Resolution Deep Learning Framework for Surveillance Drones in Security Applications},
        journal={EAI Endorsed Transactions on Security and Safety},
        volume={7},
        number={23},
        publisher={EAI},
        journal_a={SESA},
        year={2020},
        month={6},
        keywords={Surveillance, Super-Resolution, Deep Learning, Drone},
        doi={10.4108/eai.30-6-2020.165502}
    }
    
  • Soohyun Park
    Yeongeun Kang
    Jeman Park
    Joongheon Kim
    Year: 2020
    Self-Controllable Super-Resolution Deep Learning Framework for Surveillance Drones in Security Applications
    SESA
    EAI
    DOI: 10.4108/eai.30-6-2020.165502
Soohyun Park1, Yeongeun Kang1, Jeman Park2,*, Joongheon Kim1,*
  • 1: School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea
  • 2: Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA
*Contact email: parkjeman@knights.ucf.edu, joongheon@korea.ac.kr

Abstract

This paper proposes a self-controllable super-resolution adaptation algorithm in drone platforms. The drone platforms are generally used for surveillance in target network areas. Thus, super-resolution algorithms which are for enhancing surveillance video quality are essential. In surveillance drone platforms, generating video streams obtained by CCTV cameras is not static, because the cameras record the video when abnormal objects are detected. The generation of streams is not predictable, therefore, this unpredictable situation can be harmful to reliable surveillance monitoring. To handle this problem, the proposed algorithm designs superresolution adaptation. With the proposed algorithm, the shallow model which is fast and low-performance will be used if the stream queue is near overflow. On the other hand, the deep model which is highperformance and slow will be used if the queue is idle to improve the performance of super-resolution.