Research Project "High-Scene"

The goal of High-Scene is to generate valuable information out of the huge amount of data that is available in the more than 9000 Highway cameras in Austria. The project investigates novel and innovative on-line learning algorithms for vehicle detection and tracking to improve the localization performance, especially in difficult weather and illumination conditions. Vehicle trajectories will be clustered and analyzed to identify outliers on the one hand, e.g. dangerous traffic situations.

Related Publications

Research Results (Peer-reviewed):

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
J. Micorek, H. Possegger, D. Narnhofer, H. Bischof, M. Koziński
In Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
ActMAD: Activation Matching to Align Distributions for Test-Time-Training
M. J. Mirza, P. J. Soneira, W. Lin, M. Kozinski, H. Possegger, H. Bischof
In Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Towards Large-Scale Video-Based Highway Traffic Monitoring
J. Spoecklberger, J. Micorek, H. Possegger, H. Bischof
In Proc. of the IEEE International Conference on Intelligent Transportation Systems (ITSC), 2023.
MATE: Masked Autoencoders are Online 3D Test-Time Learner
M. J. Mirza, I. Shin, W. Lin, A. Schriebl, K. Sun, J. Choe, M. Kozinski, H. Possegger, I. S. Kweon, K. Yoon, H. Bischof
In Proc. of the International Conference on Computer Vision (ICCV), 2023.
Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
S. Leitner, M. J. Mirza, W. Lin, J. Micorek, M. Masana, M. Kozinski, H. Possegger, H. Bischof
In Proc. of the IEEE Intelligent Vehicles Symposium (IV), 2023.
The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
M. J. Mirza, J. Micorek, H. Possegger, H. Bischof
In Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
An Efficient Domain-Incremental Learning Approach to Drive in All Weather Condition
M. J. Mirza, M. Masana, H. Possegger, H. Bischof
In Proc. of the Vision for all Seasons: Adverse Weather and Lighting Conditions Workshop (V4AS, CVPR Workshop), 2022.

Additional public results and project overview reports are included in the annual BMK reports:

Project Partners

Graz University of Technology

Institute of Computer Graphics and Vision

ASFINAG

Motorway and Expressway Financing Joint-Stock Company

ALP.Lab GmbH

Funding Programme

This project has received funding from the Mobility of the Future programme. Mobility of the Future is a research, technology and innovation funding programme of the Republic of Austria, Ministry for Climate Action. The Austrian Research Promotion Agency (FFG) has been authorised for the programme management.

The High-Scene project started on 01.04.2021 and ended on 29.09.2024.