LEADER 01926nam  2200409z- 450 
001 9910805676903321
005 20260219090038.0
035   $a(CKB)5720000000263578
035   $a(oapen)doab91407
035   $a(IL-JeEL)995720000000263578
035   $a(EXLCZ)995720000000263578
100   $a20240213c2022uuuu  -u-         |
101 0 $ager
135   $aurmn|---annan
181   $ctxt$2rdacontent
182   $cc$2rdamedia
183   $acr$2rdacarrier
200 10$aKonvolutiona?re neuronale Netze in der industriellen Bildverarbeitung und Robotik /$fNorbert Mitschke
210  1$aKarlsruhe:$cKIT Scientific Publishing,$d2022.
215   $a1 online resource (212 p.)
225 1 $aForschungsberichte aus der Industriellen Informationstechnik;$v26
311 08$a9783731511977 
311 08$a3-7315-1197-5 
320   $aIncludes bibliographical references and index.
330   $aIn 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.
606   $aImage processing$xIndustrial applications
606   $aRobotics$xIndustrial applications
606   $aMachine learning$xIndustrial applications
615 00$aImage processing$xIndustrial applications.
615 00$aRobotics$xIndustrial applications.
615 00$aMachine learning$xIndustrial applications.
676   $a621.399
700   $aMitschke$b Norbert$01279000
906   $aBOOK
912   $a9910805676903321
996   $aKonvolutiona?re neuronale Netze in der industriellen Bildverarbeitung und Robotik$93014368
997   $aUNINA