konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf

konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf

In the first part of this dissertation, a framework for the design of a CNN for FPGAs is presented, consisting of a preprocessing algorithm, an augmentation technique, a custom quantization scheme and a pruning step of the CNN. The combination of conventional image processing with neural networks is...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Γλώσσα:ger
Έκδοση: KIT Scientific Publishing 2022
Διαθέσιμο Online:https://doi.org/10.5445/KSP/1000146397
id oapen-20.500.12657-58037
record_format dspace
spelling oapen-20.500.12657-580372022-08-23T03:00:01Z Konvolutionäre neuronale Netze in der industriellen Bildverarbeitung und Robotik Mitschke, Norbert künstliche neuronale Netze; Bildverarbeitung; bildbasierte Regelung; FPGA; CNN; image based visual servoing bic Book Industry Communication::T Technology, engineering, agriculture::TH Energy technology & engineering::THR Electrical engineering In the first part of this dissertation, a framework for the design of a CNN for FPGAs is presented, consisting of a preprocessing algorithm, an augmentation technique, a custom quantization scheme and a pruning step of the CNN. The combination of conventional image processing with neural networks is shown in the second part by an example from robotics, where an image-based visual servoing process is successfully conducted for a gripping process of a robot. 2022-08-22T09:17:26Z 2022-08-22T09:17:26Z 2022 book https://library.oapen.org/handle/20.500.12657/58037 ger Forschungsberichte aus der Industriellen Informationstechnik application/pdf Attribution-ShareAlike 4.0 International konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf https://doi.org/10.5445/KSP/1000146397 KIT Scientific Publishing 10.5445/KSP/1000146397 10.5445/KSP/1000146397 44e29711-8d53-496b-85cc-3d10c9469be9 26 212 open access
institution OAPEN
collection DSpace
language ger
description In the first part of this dissertation, a framework for the design of a CNN for FPGAs is presented, consisting of a preprocessing algorithm, an augmentation technique, a custom quantization scheme and a pruning step of the CNN. The combination of conventional image processing with neural networks is shown in the second part by an example from robotics, where an image-based visual servoing process is successfully conducted for a gripping process of a robot.
title konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf
spellingShingle konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf
title_short konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf
title_full konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf
title_fullStr konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf
title_full_unstemmed konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf
title_sort konvolutionare-neuronale-netze-in-der-industriellen-bildverarbeitung-und-robotik.pdf
publisher KIT Scientific Publishing
publishDate 2022
url https://doi.org/10.5445/KSP/1000146397
_version_ 1771297493751955456

Παρόμοια τεκμήρια