X Conferencia Internacional de Ingeniería Mecánica "COMEC 2019" -V Simposio de Logística y Gestión de la Calidad

X Conferencia Internacional de Ingeniería Mecánica

COMEC 2019

Simulation of image data to support the training of convolutional neural networks for objects recognition

Resumen [ES]

The recognition of logistics objects is an essential prerequisite for the optimization of operational logistics processes and can be performed among others via image-based methods. However, the lack of available data for training domain-specific recognition models remains a practical problem. For this reason, we present an approach to solving this problem. The core principle of our approach is the automated generation of image data from 3D models, in which the appearance of the objects varies through variations of different parameters. The first results are promising: Without any real image data, we have created a neural network for recognition of real objects with a recall quality of 86%.

Resumen [EN]

The recognition of logistics objects is an essential prerequisite for the optimization of operational logistics processes and can be performed among others via image-based methods. However, the lack of available data for training domain-specific recognition models remains a practical problem. For this reason, we present an approach to solving this problem. The core principle of our approach is the automated generation of image data from 3D models, in which the appearance of the objects varies through variations of different parameters. The first results are promising: Without any real image data, we have created a neural network for recognition of real objects with a recall quality of 86%.

Sobre el ponente

Hagen Borstell

Hagen Borstell

Otto von Guericke University Magdeburg, Germany Flag of Cuba
Información Práctica
Ponencia
English (US)
No definido
30 minutos
No definido
Autores
Jan Nonnen
Hagen Borstell
Palabras clave
Deep Learning
Image Processing
Logistics
Simulation