A comprehensive guide to restoring images degraded by motion blur, bridging the traditional approaches and emerging computational photography-based techniques, and bringing together a wide range of methods emerging from basic theory as well as cutting-edge research. It encompasses both algorithms and architectures, providing detailed coverage of practical techniques by leading researchers. From an algorithms perspective, blind and non-blind approaches are discussed, including the use of single or multiple images; projective motion blur model; image priors and parametric models; high dynamic range imaging in the irradiance domain; and image recognition in blur. Performance limits for motion deblurring cameras are also presented. From a systems perspective, hybrid frameworks combining low-resolution-high-speed and high-resolution-low-speed cameras are described, along with the use of inertial sensors and coded exposure cameras. Also covered is an architecture exploiting compressive sensing for video recovery. A valuable resource for researchers and practitioners in computer vision, image processing, and related fields.Algorithms and Systems A. N. Rajagopalan, Rama Chellappa ... For reference, the publicly available Matlab code takes 10 minutes to process a 255 A 255 image on a PC with an Intel i3 2.13 GHz CPU. ... It leads to an expectationa maximization (EM) framework that treats l as a latent variable and computes expectation on itanbsp;...
|Author||:||A. N. Rajagopalan, Rama Chellappa|
|Publisher||:||Cambridge University Press - 2014-05-08|