Home  |  Centre for Mathematical Sciences  |  LTH  |  LU

Video in traffic

Modern video analysis techniques help to understand traffic better

Since the early 1980s when an intensive work on validation of the Swedish Traffic Conflict Technique started at Lund University, the idea of automation of video records analysis was in the air. Several generations of computer programs for working with video data have been developed and used in research, but none of them allowed eliminating the long hours of manual operator's work.

Now we have come as close as never before in reaching our goal - to develop an automated video analysis system for studying the traffic environment and road users' behaviour in it. The research team joins experts both in traffic and in image and video processing and focuses on the practical application of the video analysis techniques for the needs of traffic research.

Project publications

Below is a selection of the publications within the project.

Measuring and evaluating bitumen coverage of stones using two different digital image analysis methods
Källén, Hanna; Heyden, Anders; Åström, Kalle; Lindh, Per, 2016, Published in: Measurement

Towards grading Gleason score using generically trained deep convolutional neural networks
Källén, Hanna; Molin, Jesper; Heyden, Anders; Lundström, Claes; Åström, Kalle, 2016, Published at: International Symposium on Biomedical Imaging: From Nano to Macro

A Public Video Dataset for Road Transportation Applications
Saunier, Nicolas; Ardö, Håkan; Jodoin, Jean-Philippe; Laureshyn, Aliaksei; Nilsson, Mikael; Svensson, Åse; Miranda-Moreno, Luis; Bilodeau, Guillaume-Alexandre; Åström, Kalle, 2014, Published at: 2014 TRB Annual Meeting Workshop on Comparison of Surrogate Measures of Safety Extracted from Video Data, Fulltext: PDF

Minimal Structure and Motion Problems for TOA and TDOA Measurements with Collinearity Constraints
Ask, Erik; Burgess, Simon; Åström, Kalle, 2013, Published at: 2nd International Conference on Pattern Recognition Applications and Methods, Fulltext: PDF

Bayesian Formulation of Image Patch Matching Using Cross-correlation
Ardö, Håkan; Åström, Kalle, 2012, Published in: Journal of Mathematical Imaging and Vision, Fulltext: PDF

Supervised Feature Quantization with Entropy Optimization
Kuang, Yubin; Byröd, Martin; Åström, Kalle, 2011, Published at: IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition, Fulltext: PDF

Tracking and Reconstruction of Vehicles for Accurate Position Estimation
Källén, Hanna; Ardö, Håkan; Enqvist, Olof, 2011, Published at: IEEE Workshop on Applications of Computer Vision, Fulltext: PDF

Conjugate Gradient Bundle Adjustment
Byröd, Martin; Åström, Kalle, 2010, Published at: European Conference on Computer Vision, Fulltext: PDF

Optimizing Visual Vocabularies Using Soft Assignment Entropies
Kuang, Yubin; Åström, Kalle; Kopp, Lars; Oskarsson, Magnus; Byröd, Martin, 2010, Published at: Asian Conference on Computer Vision, Fulltext: PDF

Bayesian Formulation of Image Patch Matching Using Cross-correlation
Ardö, Håkan; Åström, Kalle, 2009, Published at: Third ACM/IEEE International Conference on Distributed Smart Cameras, Fulltext: PDF

Bundle Adjustment using Conjugate Gradients with Multiscale Preconditioning
Byröd, Martin; Åström, Kalle, 2009, Published at: ], in Proc. The 20th British Machine Vision Conference

Fast and Stable Polynomial Equation Solving and Its Application to Computer Vision
Byröd, Martin; Josephson, Klas; Åström, Kalle, 2009, Published in: International Journal of Computer Vision, Fulltext: PDF


Questions: webmaster
Last updated: 2012-01-13

Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Phone: 046-222 00 00