| spelling |
oapen-20.500.12657-573752022-07-14T03:02:18Z Deep Neural Networks and Data for Automated Driving Fingscheidt, Tim Gottschalk, Hanno Houben, Sebastian Highly Automated Driving Autonomous Driving Environment Perception Deep Learning Safety bic Book Industry Communication::T Technology, engineering, agriculture::TR Transport technology & trades::TRC Automotive technology & trades bic Book Industry Communication::P Mathematics & science::PB Mathematics::PBW Applied mathematics::PBWH Mathematical modelling bic Book Industry Communication::U Computing & information technology::UY Computer science::UYT Image processing bic Book Industry Communication::U Computing & information technology::UN Databases This open access book brings together the latest developments from industry and research on automated driving and artificial intelligence. Environment perception for highly automated driving heavily employs deep neural networks, facing many challenges. How much data do we need for training and testing? How to use synthetic data to save labeling costs for training? How do we increase robustness and decrease memory usage? For inevitably poor conditions: How do we know that the network is uncertain about its decisions? Can we understand a bit more about what actually happens inside neural networks? This leads to a very practical problem particularly for DNNs employed in automated driving: What are useful validation techniques and how about safety? This book unites the views from both academia and industry, where computer vision and machine learning meet environment perception for highly automated driving. Naturally, aspects of data, robustness, uncertainty quantification, and, last but not least, safety are at the core of it. This book is unique: In its first part, an extended survey of all the relevant aspects is provided. The second part contains the detailed technical elaboration of the various questions mentioned above. 2022-07-13T12:28:03Z 2022-07-13T12:28:03Z 2022 book ONIX_20220713_9783031012334_46 9783031012334 9783031034893 https://library.oapen.org/handle/20.500.12657/57375 eng application/pdf n/a 978-3-031-01233-4.pdf https://link.springer.com/978-3-031-01233-4 Springer Nature Springer International Publishing 10.1007/978-3-031-01233-4 10.1007/978-3-031-01233-4 6c6992af-b843-4f46-859c-f6e9998e40d5 b109a7e8-25a8-47dd-add5-51424b6d2960 9783031012334 9783031034893 Springer International Publishing 427 Cham [...] open access
|
| description |
This open access book brings together the latest developments from industry and research on automated driving and artificial intelligence. Environment perception for highly automated driving heavily employs deep neural networks, facing many challenges. How much data do we need for training and testing? How to use synthetic data to save labeling costs for training? How do we increase robustness and decrease memory usage? For inevitably poor conditions: How do we know that the network is uncertain about its decisions? Can we understand a bit more about what actually happens inside neural networks? This leads to a very practical problem particularly for DNNs employed in automated driving: What are useful validation techniques and how about safety? This book unites the views from both academia and industry, where computer vision and machine learning meet environment perception for highly automated driving. Naturally, aspects of data, robustness, uncertainty quantification, and, last but not least, safety are at the core of it. This book is unique: In its first part, an extended survey of all the relevant aspects is provided. The second part contains the detailed technical elaboration of the various questions mentioned above.
|
