ABSTRACT
This chapter provides an introduction to the Super-Resolution (SR) research area, by explaining some basic techniques of SR, an overview of the literature, and discussions about some challenging issues for future research. SR are techniques that construct high-resolution (HR) images from several observed low-resolution (LR) images, thereby increasing the high-frequency components and removing the degradations caused by the imaging process of the low-resolution camera. In the imaging process, the camera captures several LR frames, which are downsampled from the HR scene with subpixel shifts between each other. In most digital imaging applications, high-resolution images or videos are usually desired for later image processing and analysis. The image spatial resolution is first limited by the imaging sensors or the imaging acquisition device. The HR image and motions among low-resolution inputs can be both regarded as stochastic variables. Due to limited low-resolution observations, the SR reconstruction problem is ill-posed in nature.
