Ebook: Algorithm & SoC design for automotive vision systems: for smart safe driving system

Preface -- 1 Introduction; Jae-seok Kim, Hyun-chul Shin -- 2 Lens Correction and Gamma Correction; Sang-Bock Cho -- 3 Super Resolution; Hyo-Moon Cho -- 4 Image enhancement for improving object recognition; Jae-Seok Kim -- 5 Detection of Vehicles and Pedestrians; Hyunchul Shin, Irfan Riaz -- 6 Monitoring Driver's State and Predicting Unsafe Driving Behavior; Hang-Bong Kang -- 7 SoC Architecture for Automobile Vision System; Kyounghoon Kim, Kiyoung Choi -- 8 Hardware accelerator for feature point detection and Matching; Jun-Seok Park, Lee-Sup Kim -- 9 Software Development Environment for Automotive SoC; Jeonghun Cho -- 10 Reliability issues for automobile SoCs; Sungju Park.;An emerging trend in the automobile industry is its convergence with information technology (IT). Indeed, it has been estimated that almost 90% of new automobile technologies involve IT in some form. Smart driving technologies that improve safety as well as green fuel technologies are quite representative of the convergence between IT and automobiles. The smart driving technologies include three key elements: sensing of driving environments, detection of objects and potential hazards, and the generation of driving control signals including warning signals. Although radar-based systems are primarily used for sensing the driving environments, the camera has gained importance in advanced driver assistance systems(ADAS). This book covers system-on-a-chip (SoC) designs--including both algorithms and hardware--related with image sensing and object detection by using the camera for smart driving systems. It introduces a variety of algorithms such as lens correction, super resolution, image enhancement, and object detections from the images captured by low-cost vehicle camera. This is followed by implementation issues such as SoC architecture, hardware accelerator, software development environment, and reliability techniques for automobile vision systems. This book is aimed for the new and practicing engineers in automotive and chip-design industries to provide some overall guidelines for the development of automotive vision systems. It will also help graduate students understand and get started for the research work in this field.