Author: Otto, Carola
Publisher: KIT Scientific Publishing
ISBN: 3731500736
Category : Technology & Engineering
Languages : en
Pages : 262
Book Description
In order to develop a driver assistance system for pedestrian protection, pedestrians in the environment of a truck are detected by radars and a camera and are tracked across distributed fields of view using a Joint Integrated Probabilistic Data Association filter. A robust approach for prediction of the system vehicles trajectory is presented. It serves the computation of a probabilistic collision risk based on reachable sets where different sources of uncertainty are taken into account.
Fusion of Data from Heterogeneous Sensors with Distributed Fields of View and Situation Evaluation for Advanced Driver Assistance Systems
Author: Otto, Carola
Publisher: KIT Scientific Publishing
ISBN: 3731500736
Category : Technology & Engineering
Languages : en
Pages : 262
Book Description
In order to develop a driver assistance system for pedestrian protection, pedestrians in the environment of a truck are detected by radars and a camera and are tracked across distributed fields of view using a Joint Integrated Probabilistic Data Association filter. A robust approach for prediction of the system vehicles trajectory is presented. It serves the computation of a probabilistic collision risk based on reachable sets where different sources of uncertainty are taken into account.
Publisher: KIT Scientific Publishing
ISBN: 3731500736
Category : Technology & Engineering
Languages : en
Pages : 262
Book Description
In order to develop a driver assistance system for pedestrian protection, pedestrians in the environment of a truck are detected by radars and a camera and are tracked across distributed fields of view using a Joint Integrated Probabilistic Data Association filter. A robust approach for prediction of the system vehicles trajectory is presented. It serves the computation of a probabilistic collision risk based on reachable sets where different sources of uncertainty are taken into account.
Light Field Imaging for Deflectometry
Author: Uhlig, David
Publisher: KIT Scientific Publishing
ISBN: 3731513064
Category :
Languages : en
Pages : 284
Book Description
Optical measurement methods are becoming increasingly important for high-precision production of components and quality assurance. The increasing demand can be met by modern imaging systems with advanced optics, such as light field cameras. This work explores their use in the deflectometric measurement of specular surfaces. It presents improvements in phase unwrapping and calibration techniques, enabling high surface reconstruction accuracies using only a single monocular light field camera.
Publisher: KIT Scientific Publishing
ISBN: 3731513064
Category :
Languages : en
Pages : 284
Book Description
Optical measurement methods are becoming increasingly important for high-precision production of components and quality assurance. The increasing demand can be met by modern imaging systems with advanced optics, such as light field cameras. This work explores their use in the deflectometric measurement of specular surfaces. It presents improvements in phase unwrapping and calibration techniques, enabling high surface reconstruction accuracies using only a single monocular light field camera.
Reconstruction from Spatio-Spectrally Coded Multispectral Light Fields
Author: Schambach, Maximilian
Publisher: KIT Scientific Publishing
ISBN: 3731512106
Category : Technology & Engineering
Languages : en
Pages : 238
Book Description
In dieser Arbeit werden spektral kodierte multispektrale Lichtfelder untersucht, wie sie von einer Lichtfeldkamera mit einem spektral kodierten Mikrolinsenarray aufgenommen werden. Für die Rekonstruktion der kodierten Lichtfelder werden zwei Methoden entwickelt, eine basierend auf den Prinzipien des Compressed Sensing sowie eine Deep Learning Methode. Anhand neuartiger synthetischer und realer Datensätze werden die vorgeschlagenen Rekonstruktionsansätze im Detail evaluiert. -In this work, spatio-spectrally coded multispectral light fields, as taken by a light field camera with a spectrally coded microlens array, are investigated. For the reconstruction of the coded light fields, two methods, one based on the principles of compressed sensing and one deep learning approach, are developed. Using novel synthetic as well as a real-world datasets, the proposed reconstruction approaches are evaluated in detail.
Publisher: KIT Scientific Publishing
ISBN: 3731512106
Category : Technology & Engineering
Languages : en
Pages : 238
Book Description
In dieser Arbeit werden spektral kodierte multispektrale Lichtfelder untersucht, wie sie von einer Lichtfeldkamera mit einem spektral kodierten Mikrolinsenarray aufgenommen werden. Für die Rekonstruktion der kodierten Lichtfelder werden zwei Methoden entwickelt, eine basierend auf den Prinzipien des Compressed Sensing sowie eine Deep Learning Methode. Anhand neuartiger synthetischer und realer Datensätze werden die vorgeschlagenen Rekonstruktionsansätze im Detail evaluiert. -In this work, spatio-spectrally coded multispectral light fields, as taken by a light field camera with a spectrally coded microlens array, are investigated. For the reconstruction of the coded light fields, two methods, one based on the principles of compressed sensing and one deep learning approach, are developed. Using novel synthetic as well as a real-world datasets, the proposed reconstruction approaches are evaluated in detail.
Probabilistic Models and Inference for Multi-View People Detection in Overlapping Depth Images
Author: Wetzel, Johannes
Publisher: KIT Scientific Publishing
ISBN: 3731511770
Category : Technology & Engineering
Languages : en
Pages : 204
Book Description
In this work, the task of wide-area indoor people detection in a network of depth sensors is examined. In particular, we investigate how the redundant and complementary multi-view information, including the temporal context, can be jointly leveraged to improve the detection performance. We recast the problem of multi-view people detection in overlapping depth images as an inverse problem and present a generative probabilistic framework to jointly exploit the temporal multi-view image evidence.
Publisher: KIT Scientific Publishing
ISBN: 3731511770
Category : Technology & Engineering
Languages : en
Pages : 204
Book Description
In this work, the task of wide-area indoor people detection in a network of depth sensors is examined. In particular, we investigate how the redundant and complementary multi-view information, including the temporal context, can be jointly leveraged to improve the detection performance. We recast the problem of multi-view people detection in overlapping depth images as an inverse problem and present a generative probabilistic framework to jointly exploit the temporal multi-view image evidence.
Wireless Data Transmission for the Battery Management System of Electric and Hybrid Vehicles
Author: Alonso, Damián Ezequiel
Publisher: KIT Scientific Publishing
ISBN: 373150670X
Category : Technology (General)
Languages : en
Pages : 190
Book Description
This work introduces a novel wireless approach for the data transmission within automotive battery management systems. The main target is the reduction of the wiring harness deployed in a battery. The characteristics of the wireless in-battery channel are investigated by means of measurements and software-based electromagnetic simulations. Different types of antennas and frequency bands are analyzed. The performance of the proposed system is evaluated by means of simulations and prototypes.
Publisher: KIT Scientific Publishing
ISBN: 373150670X
Category : Technology (General)
Languages : en
Pages : 190
Book Description
This work introduces a novel wireless approach for the data transmission within automotive battery management systems. The main target is the reduction of the wiring harness deployed in a battery. The characteristics of the wireless in-battery channel are investigated by means of measurements and software-based electromagnetic simulations. Different types of antennas and frequency bands are analyzed. The performance of the proposed system is evaluated by means of simulations and prototypes.
Computational, label, and data efficiency in deep learning for sparse 3D data
Author: Li, Lanxiao
Publisher: KIT Scientific Publishing
ISBN: 3731513463
Category :
Languages : en
Pages : 256
Book Description
Deep learning is widely applied to sparse 3D data to perform challenging tasks, e.g., 3D object detection and semantic segmentation. However, the high performance of deep learning comes with high costs, including computational costs and the effort to capture and label data. This work investigates and improves the efficiency of deep learning for sparse 3D data to overcome the obstacles to the further development of this technology.
Publisher: KIT Scientific Publishing
ISBN: 3731513463
Category :
Languages : en
Pages : 256
Book Description
Deep learning is widely applied to sparse 3D data to perform challenging tasks, e.g., 3D object detection and semantic segmentation. However, the high performance of deep learning comes with high costs, including computational costs and the effort to capture and label data. This work investigates and improves the efficiency of deep learning for sparse 3D data to overcome the obstacles to the further development of this technology.
Image Analysis and Evaluation of Cylinder Bore Surfaces in Micrographs
Author: Wang, Limeng
Publisher: KIT Scientific Publishing
ISBN: 3731502399
Category : Technology & Engineering
Languages : en
Pages : 134
Book Description
This work presents two image-based inspection approaches for the quality evaluation of cylinder bore surfaces. In the first algorithm, metal folds on plateau-honed surfaces are inspected with scanning electron microscopy. An edge-aware structure tensor is proposed for feature extraction and localization of surface defects. The second algorithm uses a morphgraphical method for detecting graphite grains in optical micrographs. Based on the inspection results, quality parameters are proposed.
Publisher: KIT Scientific Publishing
ISBN: 3731502399
Category : Technology & Engineering
Languages : en
Pages : 134
Book Description
This work presents two image-based inspection approaches for the quality evaluation of cylinder bore surfaces. In the first algorithm, metal folds on plateau-honed surfaces are inspected with scanning electron microscopy. An edge-aware structure tensor is proposed for feature extraction and localization of surface defects. The second algorithm uses a morphgraphical method for detecting graphite grains in optical micrographs. Based on the inspection results, quality parameters are proposed.
Design and analysis of a content-based image retrieval system
Author: Hernández Mesa, Pilar
Publisher: KIT Scientific Publishing
ISBN: 3731506920
Category : Technology (General)
Languages : en
Pages : 268
Book Description
The automatic retrieval of images according to the similarity of their content is a challenging task with many application fields. In this book the automatic retrieval of images according to human spontaneous perception without further effort or knowledge is considered. A system is therefore designed and analyzed. Methods for the detection and extraction of regions and for the extraction and comparison of color, shape, and texture features are also investigated.
Publisher: KIT Scientific Publishing
ISBN: 3731506920
Category : Technology (General)
Languages : en
Pages : 268
Book Description
The automatic retrieval of images according to the similarity of their content is a challenging task with many application fields. In this book the automatic retrieval of images according to human spontaneous perception without further effort or knowledge is considered. A system is therefore designed and analyzed. Methods for the detection and extraction of regions and for the extraction and comparison of color, shape, and texture features are also investigated.
Model-based Filtering of Interfering Signals in Ultrasonic Time Delay Estimations
Author: Bächle, Matthias
Publisher: KIT Scientific Publishing
ISBN: 3731512521
Category : Technology & Engineering
Languages : en
Pages : 218
Book Description
This work presents model-based algorithmic approaches for interference-invariant time delay estimation, which are specifically suited for the estimation of small time delay differences with a necessary resolution well below the sampling time. Therefore, the methods can be applied particularly well for transit-time ultrasonic flow measurements, since the problem of interfering signals is especially prominent in this application.
Publisher: KIT Scientific Publishing
ISBN: 3731512521
Category : Technology & Engineering
Languages : en
Pages : 218
Book Description
This work presents model-based algorithmic approaches for interference-invariant time delay estimation, which are specifically suited for the estimation of small time delay differences with a necessary resolution well below the sampling time. Therefore, the methods can be applied particularly well for transit-time ultrasonic flow measurements, since the problem of interfering signals is especially prominent in this application.
Machine Learning for Camera-Based Monitoring of Laser Welding Processes
Author: Hartung, Julia
Publisher: KIT Scientific Publishing
ISBN: 3731513331
Category :
Languages : en
Pages : 258
Book Description
The increasing use of automated laser welding processes causes high demands on process monitoring. This work demonstrates methods that use a camera mounted on the focussing optics to perform pre-, in-, and post-process monitoring of welding processes. The implementation uses machine learning methods. All algorithms consider the integration into industrial processes. These challenges include a small database, limited industrial manufacturing inference hardware, and user acceptance.
Publisher: KIT Scientific Publishing
ISBN: 3731513331
Category :
Languages : en
Pages : 258
Book Description
The increasing use of automated laser welding processes causes high demands on process monitoring. This work demonstrates methods that use a camera mounted on the focussing optics to perform pre-, in-, and post-process monitoring of welding processes. The implementation uses machine learning methods. All algorithms consider the integration into industrial processes. These challenges include a small database, limited industrial manufacturing inference hardware, and user acceptance.