Atnaujinkite slapukų nuostatas

El. knyga: Towards a Common Software/Hardware Methodology for Future Advanced Driver Assistance Systems: The DESERVE Approach

Edited by (Leibniz Universität Hannover, Germany), Edited by (Leibniz Universität Hannover, Germany)
Kitos knygos pagal šią temą:
Towards a Common Software/Hardware Methodology for Future Advanced Driver Assistance Systems: The DESERVE ApproachDidesnis paveikslėlis
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

The European research project DESERVE (DEvelopment platform for Safe and Efficient dRiVE, 2012-2015) had the aim of designing and developing a platform tool to cope with the continuously increasing complexity and the simultaneous need to reduce cost for future embedded Advanced Driver Assistance Systems (ADAS). For this purpose, the DESERVE platform profits from cross-domain software reuse, standardization of automotive software component interfaces, and easy but safety-compliant integration of heterogeneous modules. This enables the development of a new generation of ADAS applications, which challengingly combine different functions, sensors, actuators, hardware platforms, and Human Machine Interfaces (HMI).

This book presents the different results of the DESERVE project concerning the ADAS development platform, test case functions, and validation and evaluation of different approaches. The reader is invited to substantiate the content of this book with the deliverables published during the DESERVE project.

Technical topics discussed in this book include:

Modern ADAS development platforms;
Design space exploration;
Driving modelling;
Video-based and Radar-based ADAS functions;
HMI for ADAS;
Vehicle-hardware-in-the-loop validation systems
Preface xiii
List of Contributors xvii
List of Figures xxi
List of Tables xxxiii
List of Abbreviations xxxv
1 The DESERVE Project: Towards Future ADAS Functions
1(8)
Matti Kutila
Nereo Pallaro
1.1 Project Aim
1(3)
1.2 Project Structure
4(1)
1.3 DESERVE Platform Design
5(1)
1.4 The Project Innovation Summary
5(1)
1.5 Conclusions
6(3)
Part I: ADAS Development Platform
2 The DESERVE Platform: A Flexible Development Framework to Seemlessly Support the ADAS Development Levels
9(36)
Frank Badstubner
Ralf Kodel
Wilhelm Maurer
Martin Kunert
Andre Rolfsmeier
Joshue Perez
Florian Giesemann
Guillermo Paya-Vaya
Holger Blume
Gideon Reade
2.1 Introduction to the DESERVE Platform Concept
9(3)
2.2 The DESERVE Platform-A Flexible Development Framework to Seamlessly Support the ADAS Development Levels
12(4)
2.3 DESERVE Platform Requirements
16(7)
2.3.1 DESERVE Platform Framework
16(2)
2.3.2 Generic DESERVE Platform Requirements (Relevant to all Development Levels)
18(3)
2.3.3 Rapid Prototyping Framework Requirements (Development Level 2)
21(1)
2.3.4 Additional Requirements for Embedded Multicore Platform with FPGA (Development Level 3)
22(1)
2.4 DESERVE Platform Specification and Architecture
23(12)
2.4.1 DESERVE Platform Architecture
23(1)
2.4.1.1 Hardware architecture
25(1)
2.4.1.2 Software architecture
26(4)
2.4.2 DESERVE Platform Interface Definition
30(1)
2.4.2.1 Definition of DESERVE interface architecture
30(1)
2.4.2.2 Existing ADAS interfaces
32(1)
2.4.2.3 Definition of next generation interfaces
33(2)
2.5 Safety Standards and Certification Concepts
35(8)
2.5.1 Safety Impact of DESERVE
36(1)
2.5.2 Functional Safety of Road Vehicles (ISO 26262)
36(1)
2.5.3 Guidelines Related to ISO 26262
37(1)
2.5.4 Safety and AUTOSAR
38(1)
2.5.5 Safety Mechanisms for DESERVE Platform
39(4)
References
43(2)
3 Driver Modelling
45(20)
Jens Klimke
Lutz Eckstein
3.1 Introduction
45(3)
3.2 Driver Modelling
48(2)
3.3 Requirements for DESERVE
50(2)
3.4 Generic Structure
52(7)
3.4.1 Model Structure
52(4)
3.4.2 Parameter Structure
56(3)
3.5 Implementation
59(2)
3.6 Applications in DESERVE and Results
61(1)
3.7 Conclusions and Outlook
62(1)
References
63(2)
4 Component Based Middleware for Rapid Development of Multi-Modal Applications
65(12)
Gwenael Dunand
4.1 Introduction
65(1)
4.2 Using a Middleware
65(1)
4.3 The Multisensor Problem
66(6)
4.3.1 Knowing the Date and Time of Your Data
67(1)
4.3.2 Component-based GUI
68(1)
4.3.3 The Off-the-Shelf Component Library
69(2)
4.3.4 Custom Extensions
71(1)
4.3.5 About Performance
71(1)
4.4 Compatibility with Other Tools
72(2)
4.4.1 dSPACE Prototyping Systems
72(1)
4.4.2 Simulators
73(1)
4.4.3 Other Standards
74(1)
4.5 Conclusion
74(1)
References
75(2)
5 Tuning of ADAS Functions Using Design Space Exploration
77(28)
Abhishek Ravi
Hans Michael Koegeler
Andrea Saroldi
5.1 Introduction
77(7)
5.1.1 Parameter Tuning: An Overview
77(1)
5.1.2 Industrial Tuning Applications: Challenges and Opportunities
78(3)
5.1.3 Model-based Tuning
81(2)
5.1.4 Model-based Validation
83(1)
5.2 Demonstrative Example
84(14)
5.2.1 Function: An Overview
84(1)
5.2.2 Design Variables
85(3)
5.2.3 Key Performance Indicators (KPI)
88(1)
5.2.4 Test Maneuver
89(1)
5.2.5 Test Run Overview
89(2)
5.2.6 Raw Data Plausibility Check
91(1)
5.2.7 Meta Modelling
92(3)
5.2.8 Optimization
95(2)
5.2.9 Verification
97(1)
5.3 Model-based Validation
98(3)
5.4 Conclusions
101(1)
Acknowledgement
101(1)
References
101(4)
Part II: Test Case Functions
6 Deep Learning for Advanced Driver Assistance Systems
105(28)
Florian Giesemann
Guillermo Paya-Vaya
Holger Blume
Matthias Limmer
Werner R. Ritter
6.1 Introduction
105(1)
6.2 Scene Labeling in Advanced Driver Assistance Systems
106(1)
6.3 Convolutional Neural Networks and Detp Learning
107(8)
6.3.1 Introduction to Neural Networks
108(1)
6.3.2 Supervised Learning
109(3)
6.3.3 Convolutional Neural Networks
112(3)
6.4 CNN for Scene Labeling
115(5)
6.4.1 Exemplary Network for Scene Labeling
116(1)
6.4.2 Evaluation
116(4)
6.5 Hardware Platforms for Scene Labeling
120(7)
6.5.1 Theoretical Performance Requirements
121(4)
6.5.2 CPU-based Platforms
125(1)
6.5.3 GPU-based Platforms
125(1)
6.5.4 FPGA-based Platforms
125(2)
6.6 Summary
127(1)
References
127(6)
7 Real-Time Data Preprocessing for High-Resolution MIMO Radar Sensors
133(24)
Frank Meinl
Eugen Schubert
Martin Kunert
Holger Blume
7.1 Introduction
133(1)
7.2 Signal Processing for Automotive Radar Sensors
134(11)
7.2.1 FMCW Radar System Architecture
134(4)
7.2.2 Two-Dimensional Spectrum Analysis for Range and Velocity Estimation
138(1)
7.2.3 Thresholding and Target Detection
139(4)
7.2.4 Angle Estimation
143(2)
7.3 Hardware Accelerators for MIMO Radar Systems
145(8)
7.3.1 Basic Structure of a Streaming Hardware Accelerator
145(1)
7.3.2 Pipelined FFT Accelerator
146(5)
7.3.3 Rank-Only OS-CFAR Accelerator
151(2)
7.4 Conclusion
153(1)
References
154(3)
8 Self-Calibration of Wide Baseline Stereo Camera Systems for Automotive Applications
157(44)
Nico Mentzer
Guillermo Paya-Vaya
Holger Blume
Nora von Egloffstein
Lars Kruger
8.1 Introduction
157(5)
8.1.1 Extraction of Image Features
158(3)
8.1.2 Matching of Image Features
161(1)
8.1.3 Extrinsic Online Self-Calibration
161(1)
8.2 Algorithmic Overview
162(15)
8.2.1 Survey of Image Features Extraction
162(1)
8.2.1.1 Detection of features
162(1)
8.2.1.2 Description of features
167(1)
8.2.1.3 Characteristics of features
169(3)
8.2.2 Feature Matching
172(4)
8.2.3 Survey of Feature-based Self-Calibration
176(1)
8.3 Extraction of Image Features
177(2)
8.3.1 Detection of SIFT-Feature Points
177(1)
8.3.2 Description of SIFT-Image Features
178(1)
8.4 Matching of Image Features
179(2)
8.5 Extrinsic Online Self-Calibration
181(1)
8.6 Application-Specific Algorithmic Parameterization
182(10)
8.6.1 Decreasing Bit Depth of Input Images for Extraction of SIFT-features
182(4)
8.6.2 Threshold-based Feature Matching
186(2)
8.6.3 Parameterization of Matching Methods
188(4)
8.7 Hardware Based SIFT-Feature Extraction
192(4)
8.7.1 Challenges of SIFT-Feature Extraction
193(1)
8.7.2 Existing Systems for Hardware Based SIFT-Feature Extraction
194(2)
8.8 Conclusion
196(1)
References
197(4)
9 Arbitration and Sharing Control Strategies in the Driving Process
201(26)
David Gonzalez
Joshue Perez
Vicente Milanes
Fawzi Nashashibi
Marga Saez Tort
Angel Cuevas
9.1 Introduction
201(1)
9.2 ADAS Functions Available in the Market
202(13)
9.2.1 Longitudinal Control Systems
203(4)
9.2.2 Lateral Control Systems
207(2)
9.2.3 Other Control Systems
209(2)
9.2.4 Control Solution in ADAS
211(1)
9.2.4.1 Perception platform
212(1)
9.2.4.2 Application platform
214(1)
9.2.4.3 Information Warning Intervention (IWI) platform
214(1)
9.3 Survey on Arbitration and Control Solutions in ADAS
215(1)
9.4 Human-Vehicle Interaction
216(1)
9.5 Driver Monitoring
217(3)
9.5.1 Legal and Liability Aspects
219(1)
9.6 Sharing and Arbitration Strategies: DESERVE Approach
220(1)
9.7 Conclusions
221(1)
References
222(5)
Part III: Validation and Evaluation
10 The HMI of Preventing Warning Systems: The DESERVE Approach
227(24)
Caterina Calefato
Chiara Ferrarini
Elisa Landini
Roberto Montanari
Fabio Tango
Marga Saez Tort
Eva M. Garcia Quinteiro
10.1 Introduction
227(1)
10.2 Prevent Imminent Accidents: The Role of Humans, the Role of Technology
228(5)
10.2.1 From Passive to Preventive Safety
228(2)
10.2.2 The Role of Driver Model in ADAS Design
230(3)
10.3 HMI Design Flow: The DESERVE Approach
233(1)
10.3.1 Different Approaches in the HMI of the Preventing Warning Systems: A State of Art in a Glance
233(1)
10.4 HMI Concepts Design
234(6)
10.4.1 Concept 1: Holistic HMI
235(3)
10.4.2 Concept 2: Immersive HMI
238(1)
10.4.3 Concept 3: Smart HMI
239(1)
10.5 Preliminary Testing by Focus Group
240(3)
10.5.1 Participants
241(1)
10.5.2 Results
241(1)
10.5.3 List of the Winning Features and Redesign Recommendations
242(1)
10.6 Users Test at Driving Simulator
243(3)
10.6.1 Participants
244(1)
10.6.2 Procedure
244(1)
10.6.3 Results
244(2)
10.7 Conclusions
246(1)
Acknowledgments
247(1)
References
247(4)
11 Vehicle Hardware-In-the-Loop System for ADAS Virtual Testing
251(18)
Romain Rossi
Clement Galko
Hariharan Narasimman
Xavier Savatier
11.1 Introduction
251(1)
11.2 State of the Art
252(2)
11.3 Proposed System
254(2)
11.4 Hardware Implementation
256(4)
11.4.1 Sensors Stimulation Solutions
256(2)
11.4.2 Software Implementation
258(2)
11.5 Experimental Setup
260(2)
11.6 Results
262(3)
11.7 Conclusion and Future Work
265(1)
Acknowledgment
266(1)
References
267(2)
Index 269(2)
About the Editors 271
Guillermo Payį-Vayį, Holger Blume
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97887935191382e.html