Skip to main content

Über dieses Buch

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.



Chapter 1. Introduction

This chapter introduces concepts and trends related to the development of advanced driver assistance systems (ADAS), which aid human drivers in collision avoidance. Some industrial developments and major functional blocks of ADAS are also introduced. We have focused on the camera vision-based systems, which are very popular mainly because of their low development costs and very diverse potential applications. The system-on-chip (SoC) architecture and components of automobile vision systems are also presented.
Jaeseok Kim, Hyunchul Shin

Chapter 2. Lens Correction and Gamma Correction

Recently, the necessity of camera in vehicle industry is increasing now as increasing the smart car needs. Almost smart car concepts are implemented by using the camera system based on image processing technology. Actually, the rear view camera for parking assistance system, the forward view camera for lane departure warning and forward collision warning system, and multi-view camera for vehicle black box and blind spot warning system and so on, so many systems those adopted the camera system are already released. However, performance of these functions strongly depends on the image quality through the camera system. Especially, distortion of a thing pictured by the lens and suddenly illumination changing by environments are core factors affecting the image quality for smart car performance. Thus, in this chapter, we introduced a vehicle friendly lens correction algorithm and a gamma correction algorithm with objective illumination estimation method. In the lens correction part, we introduced a simple lens correction method in low-cost camera and we propose a method that leads to guarantee of the restrictions simultaneously for the determination. In the gamma correction part, we introduced the objective illumination estimation methods and the gamma correction methods based on tone mapping.
Sang-Bock Cho

Chapter 3. Super Resolution

We introduced, in this chapter, what the definition of a super resolution is and what the key approaching methods for major super resolution algorithms are. Numerous super resolution algorithms have based on the observation model and they have followed the warp-blur sequence. But, some cases which have large movements and warp factors such as video by taking in a vehicle are worse than normal interpolation methods. We introduce the smart and robust registration algorithm with rotation and shift estimation. To reduce the registration error, this algorithm decides the optimal reference image even other super resolution algorithms discard this registration error. This algorithm follows the warp-blur observation model because the blurring parameter is much bigger than warp parameter for camera rotation and/or vibration.
Hyo-Moon Cho

Chapter 4. Image Enhancement for Improving Object Recognition

Image enhancement techniques are increasingly needed for improving object recognition in automobile driving. In driving conditions, there are many variables that degrade the quality of the image captured from the camera, such as fog, rain, a sudden change of illumination, or lack of illumination. If the quality of the obtained image is degraded, object recognition (cars, pedestrians, fixed objects, and traffic signals) can be unsatisfactory. To improve the recognition rate of objects, several image enhancement algorithms are proposed and evaluated. In this chapter, general image enhancement techniques are introduced, followed by a discussion of advanced techniques for the driving environment.
Jaeseok Kim

Chapter 5. Detection of Vehicles and Pedestrians

Vehicle and pedestrian detection has gained the attention of researchers in the past decade because of the increasing number of on road vehicles and traffic accidents. Vehicle and pedestrian detection system is of utmost importance since it can be used to take instantaneous and calculated decisions where human failure might occur resulting in reduction of road mishaps. But designing a detection system which is robust to various shapes of vehicles, different human postures/clothing, and weather/environment conditions is a challenging problem. In the following sections, the state of the art methods in vehicle and pedestrian detection are discussed.
Hyunchul Shin, Irfan Riaz

Chapter 6. Monitoring Driver’s State and Predicting Unsafe Driving Behavior

In recent years, driver drowsiness and distraction have been important factors in a large number of accidents because they reduce driver perception level and decision making capability, which negatively affect the ability to control the vehicle. One way to reduce these kinds of accidents would be through monitoring driver and driving behavior and alerting the driver when they are drowsy or in a distracted state. In addition, if it were possible to predict unsafe driving behavior in advance, this would also contribute to safe driving. In this chapter, we will discuss various monitoring methods for driver and driving behavior as well as for predicting unsafe driving behaviors. In respect to measurement methods of driver drowsiness, we discussed visual and non-visual features of driver behavior, as well as driving performance behaviors related to vehicle-based features. Eye related measurements such as PERCLOS, yawning detection and some limitations in measuring visual features are discussed in detail. As for non-visual features, we explore various physiological signals and possible drowsiness detection methods that use these signals. As for vehicle-based features, we describe steering wheel movement and the standard deviation of lateral position. To detect driver distraction, we describe head pose and gaze direction methods. To predict unsafe driving behavior, we explain predicting methods based on facial expressions and car dynamics. Finally, we discuss several issues to be tackled for active driver safety systems. They are (1) hybrid measures for drowsiness detection, (2) driving context awareness for safe driving, (3) the necessity for public data sets of simulated and real driving conditions.
Hang-Bong Kang

Chapter 7. SoC Architecture for Automobile Vision System

Advanced Driver Assistance System (ADAS) is becoming more and more popular and increasing its importance in a car with the advancement in electronics and computer engineering that provides key enabling technologies for such a system. Among others, vision is one of the most important technologies since the current practice of automotive driving is mostly, if not entirely, based on vision. This chapter discusses architectural issues to be considered when designing Systems-on-a-Chip (SoC) for automobile vision system. Various existing architectures are introduced together with some analysis and comparison.
Kyounghoon Kim, Kiyoung Choi

Chapter 8. Hardware Accelerator for Feature Point Detection and Matching

Recently, many vehicle manufacturers have adopted a vision processing based driver assistance system (DAS) for safety. Since vehicles cannot allow any crash or collision even when running very fast, all vision algorithms should be operated in real-time without any error. Since many algorithms such as object recognition/tracking, image matching, and simultaneous localization and mapping (SLAM) are based on the interest point detection and matching algorithm, interest point detection and matching algorithms should be accelerated to provide result data for overall vision system in real-time. However, they are one of the most compute-intensive operations in DAS and even the state-of-the-art hardwired accelerators hardly achieve 60 frames per second (fps) only in VGA resolution (640 × 480). They suffer from tremendous hardware overhead because they are implemented based on heterogeneous many-core system. To overcome these limitations, we aims to implement hardware which achieve more than 90 frames per second in full HD resolution (1080p) only with 30 % of logic gates compared to the state-of-the-art object recognition processors. In this chapter, we introduces three techniques to design this hardware : (1) Joint algorithm-architecture optimizations for exploiting bit-level parallelism, (2) A low-power unified hardware platform for interest point detection and matching, and (3) scalable hardware architecture.
Jun-Seok Park, Lee-Sup Kim

Chapter 9. Software Development Environment for Automotive SoC

Model-based development (MBD) uses models to describe various development processes and products. The model can provide development processes, requirement traceability, verification, validation and documentation. MBD can reduce the errors and increase the maturity level of the development process. This system is being used increasingly for the development of automotive software systems. AUTOSAR is a type of model-based development method for an automotive electronic system, which was developed by the automotive industry. AUTOSAR provides several models for model-based system development, e.g. the software component model, platform model and system model. The basic benefits of AUTOSAR in the development process are the relocation of the software components regardless of the hardware and the reuse of software components already developed. The case study of AUTOSAR development for automotive SoC is described. The automotive SoC consists of multiple processors, a customized vision process engine for an automotive vision system and peripheral. Each component of the SoC is mapped to the AUTOSAR layered architecture, such as MCAL, ECU abstraction and CCD.
Jeonghun Cho

Chapter 10. Reliability Issues for Automobile SoCs

Current vehicles are built with complex electronic systems embedded with more than a hundred microprocessors through complicated automotive networks. In the de facto ISO 26262 standard in the automotive industry, Automotive Safety Integrity Level (ASIL) is classified into four different levels. In this chapter, the ISO 26262 hardware ASIL is described in detail. Then, we introduce fault diagnosis architectures that use various design for testability techniques such as scan design, built-in self-test, IEEE boundary scan design, and error correcting codes for increasing hardware reliability.
Sungju Park
Weitere Informationen

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Globales Erdungssystem in urbanen Kabelnetzen

Bedingt durch die Altersstruktur vieler Kabelverteilnetze mit der damit verbundenen verminderten Isolationsfestigkeit oder durch fortschreitenden Kabelausbau ist es immer häufiger erforderlich, anstelle der Resonanz-Sternpunktserdung alternative Konzepte für die Sternpunktsbehandlung umzusetzen. Die damit verbundenen Fehlerortungskonzepte bzw. die Erhöhung der Restströme im Erdschlussfall führen jedoch aufgrund der hohen Fehlerströme zu neuen Anforderungen an die Erdungs- und Fehlerstromrückleitungs-Systeme. Lesen Sie hier über die Auswirkung von leitfähigen Strukturen auf die Stromaufteilung sowie die Potentialverhältnisse in urbanen Kabelnetzen bei stromstarken Erdschlüssen. Jetzt gratis downloaden!