Color guided thermal image super resolution
Xiaohui Chen, Guangtao Zhai, Jia Wang, Chunjia Hu, Yuanchun Chen · 2016
IR imaging is playing an important role in industry these days. However, the IR cameras only support low resolution for technical reasons. In this paper, we propose to use the visible camera as a guidance to super resolution the IR images. We setup a prototype of the IR-Color multi-sensor imaging system and construct a dataset including videos collected from different scenes for further research. Then we present our color guided algorithm which is suitable for this kind of super resolution problem. We test our algorithm on our dataset. The experiment results indicate that our algorithm performs well, and avoids the over-texture problems that traditional solutions suffer from. In further work, we will apply our multi-sensor system to more applications in computer vision.