Projects

Some of our projects in KVS:

KI-SIGS

AI Space for Intelligent Health Systems

This project addresses the critical issue of the privacy of AI models in healthcare to prevent sensitive patient data from leaking or being reconstructed.

COMET-Project transMVS (2019-2022)

Transfer Learning Based Machine Vision Systems

This project addresses the efficient semi-automatic setup of a knowledge base of domain-specific image data for training and analysis of deep models for machine vision applications.

COMET-Project deepTrust (2019-2022)

Deep Models in Trust Critical Image Analysis Systems

This project focuses on developing and advancing analysis methods towards more trustworthiness and transparency in deep learning driven image analysis systems.

AutoQual-I

Transfer Learning for Automatic Quality Inspection

The research project shows how current data-driven modelling technologies of artificial intelligence can be transferred to the needs of the manufacturing industry with the help of transfer learning.

 

ALOHA

Integrate artificial intelligence quite simply

The research goal of the ALOHA project is to optimize machine learning so that it can be easily integrated into machines on embedded systems.

TRESSPASS

Secure border control

The HORIZON 2020 project focuses on risk-based border management.

AI@Work

Human Centered AI in Digitized Working Environments

This project takes up a central question of the current discussion of Human Centered AI for a European AI Strategy by tackling the threat of increasing polarization between AI-enabled machine intelligence and people in the world of work.

Flagship Project Connecting Austria

Connecting energy-efficient and goods traffic trucks from the motorway to the city

The flagship project Connecting Austria(bmvit/Innovation) researches on semi-automated and energy-efficient truck platoons with specific focus on infrastructure and ovrall traffic issues.

What is needed to safely and efficiently setup an energy-efficient platoon, to maintain a platoon, and to go back to a regular transport mode at Austrian roads? Key objective is evidence-based evaluation of energy-efficient and semi-automated truck platoons.

VISIOMICS

Analysis platform for better prediction of relapse in childhood cancer

In this FFG-funded project, analyses of "OMICS" data sets and image data using methods of machine learning and artificial intelligence are combined using the example of neuroblastoma, a tumour of infants and young children, to enable earlier and more precise detection of relapses.

Strategic COMET-Project FExFE

Strategic research on extraction, representation and comparison of characteristics for frame-based versus event-driven machine perception

The aim of this strategic project is to gain an insights into the complex questions of stability, robustness, solidity and efficiency of image feature extraction, aggregation and representation on the basis of mathematical modelling and analysis.

COMET-Project iKM

Knowledge extraction from visual pattern recognition systems with faster adaptation to new and changed scenarios as goal

Future approaches from machine and deep learning will be used to significantly accelerate the initialization phase of a visual pattern recognition system and to improve the accuracy and quality of the system.

COMET-Project iCME

Knowledge-based computer aided support of the engineering process of designing, assembling, calibrating and deploying visual quality inspection software solutions.

The overall goal is to guide the engineer by providing algorithmic approaches of similar inspection problems, and to unburden the engineer from recurrent design, tuning and implementation steps.

WiMoiS - Modeling of Game Performance

A little man stands in the forest, not at all still and quiet

In order to assess the performance of individual athletes in team sports such as soccer or ice hockey, the concept of individual playing ability is of great importance.

As part of the WiMois project, SCCH and its partners are working together on the conceptual basis for a software system for semantic and data-based evaluation of individual performance in team sports.

The Round Thing...

... has to go in the rectangular thing.

The analysis of game strategies, player positions, running routes, speeds and acceleration curves in combination with biometric player data, such as heart and respiratory rate, has become state of the art.

The SCCH helps not to lose sight of the essence: the ball.

The Right Light

High-performance quality inspection with the right illumination

The way of illuminating a thing does not change its essence. Stanislaw Jerzy Lec (1909-66), Polish author.

However, the type of lighting is essential to be able to see certain defects on surfaces. Especially with high-quality products made of stainless steel, for example, surface defects alone reduce product quality. Consequently, visual quality control is essential for, e.g., stainless steel panels .With its patented lighting technology and high-performance algorithms, the SCCH helps with quality inspection.

InCeM

Integrated Component Cycling in Epithelial Cell Motility

InCeM is an European Training Network (ETN) formed by universities, research institutions and companies from Europe and Israel comprising a PhD program which offers to early stage researchers interdisciplinary research topics and training related to cellular motility.

 

TisQuant

Procedures for a highly automated assessment and classification of cells in tissue sections by means of spatial marker profiles

In TisQuant we aim for a highly integrated computational tissue analysis comprising the identification of specific antibodies and adjusted staining methods, high-performance image analysis and pattern recognition techniques as well as new user interaction work flows.  For instance, for selected tumors this shall allow us an accurate computational assessment of tumor dignity and an assignment to their respective class of aggressiveness.

 

Hyperion3D

The overall goal of Hyperion3D is the development of an intelligent and cost-efficient workflow for producing high quality 3D film content for for stereoscopic and multi-view 3D displays. The key idea for that goal is the conception of a smart tri-camera system that would be superior to comparable systems on the market, above all w.r.t. operability, efficiency and quality.