Cover Image

Konvolutionäre neuronale Netze in der industriellen Bildverarbeitung und Robotik

Show other versions (1)

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...

Full description

Saved in:
Bibliographic Details
Main Author: Mitschke, Norbert (auth)
Format: Electronic Book Chapter
Published: KIT Scientific Publishing 2022
Series:Forschungsberichte aus der Industriellen Informationstechnik
Subjects:
Electrical engineering
künstliche neuronale Netze; Bildverarbeitung; bildbasierte Regelung; FPGA; CNN; image based visual servoing
Online Access:DOAB: download the publication
DOAB: description of the publication
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Physical Description:1 electronic resource (212 p.)
ISBN:KSP/1000146397
Access:Open Access

Similar Items