摘要
近年来,使用深度学习技术的超分辨率图像的质量和速度都有很大的提升。最新研究的重点是恢复普通图像的高分辨率的细节。由于感兴趣的目标在法庭科学应用中非常具体,本文提出了利用已知感兴趣目标有所认知的一种总体操作框架。所提出的基于ROI的视频超分辨率框架不仅十分有效,而且能够重建出高质量图像。实验结果显示,算法比传统的基于帧的方法平均快35%和提高0.44dB的图像质量。
In recent years, there have been significant improvement in both the quality and speed of super resolution imaging using deep learning techniques. The focus of recent research was to recover high resolution details of general images. However, ＂the object of interest is very specific in forensic applications. Therefore, we propose in this paper, a general framework that exploits the domain knowledge of the object of interest. The proposed ROI-based video super resolution framework is not only efficient but also able to reconstruct high quality images. The experimental results show that it is on average35% faster and0. 44 dBbetter than the conventional frame-based approach.
作者
林庆帆
柳颖
毕萍
刘颖
LIM Keng-Pang;LIU Ying;BI Ping;LIU Ying(Siliconvision Pte.Ltd,449 Tagore Industrial Avenue # 03-02,Singapore;Key Laboratory of Electronic Information Application Technology for Crime Scene Investigation.Ministry of Public Security,Xi＇an,710121,China;Science and Technology Information（）ffice,Public Security Department of Shaanxi Province,Xi＇an 710002,China;Center for Image and Information Processing,Xi＇an University of Posts and Telecommunications,Xi＇an 710121,China)
出处
《西安邮电大学学报》
2018年第4期15-20,共6页
Journal of Xi’an University of Posts and Telecommunications
基金
Natural Science Foundation of China(61601362,61571361,61671377,41504115)
