To main content

Deep Learning

Deep Learning

Deep learning utilizes GPUs to efficiently train neural networks for learning representations from large (labeled) image databases. Our research focuses on design and training of networks for object detection, classification, prediction and anomaly detection.

A successfull deep learning based system relies on being trained on a large and representative dataset which can be costly to acquire. We are also working on methods to create realistic looking labeled datasets based on simulated data, which can be created more cost-efficiently.

Our expertise

  • Development of deep CNNs for image classification/detection/prediction problems.
  • Generation of realistic simulated training data.

 

Senior Research Scientist
+47 958 95 329

Deep learning related projects

Deep learning based bin-picking

To further develop and link novel technologies and methodologies within automation to support innovation processes and advanced work systems in the manufacturing industries. First case is developing a flexible and robust bin-picking system based on deep learning. The convolutional neural network is trained in a simulation environment and deployed on real 3D data.

This work is done in the project:

Create large realistically labeled datasets based on simulated data

Deep learning requires large annotated datasets which can be difficult and costly to acquire. We are developing a framework that exploits generative adversarial networks (GAN) for creating realistic training datasets based on simulated and unsupervised images. Images (RGB-D) are simulated by a rendering process together with relevant annotation information. A model is learnt to improve the realism of the simulated images using realistic unannotated images while preserving the simulated annotation information. This model allow us to very cost efficient generate large realistic annotated datasets suitable for training deep-learning networks.

In-cage robot system for inspection of net-cage

Normality" focused pipeline for understanding ROV and diver video from fish cages. Data driven detection of regions containing fish-cage structures (moorings, ropes etc) and defects (holes, fouling). Semantic classification of extracted regions.

This work is done in the project:

About

Deep learning based object detection.
Deep learning based object detection.