Application of automated video analysis for behavioural studies: concept and experience

Lund University, Sweden, is developing a video analysis system for making long-term behavioural studies, primarily in complex urban environments. Road users are detected using the KLT (Kanade-Lucas-Tomasi) interest point tracker. Trajectories are estimated using foreground–background segmentation, whereas speed is estimated using the shape analysis of interest points. The extracted trajectories are further used for behavioural analysis. The authors present the experience from an ongoing study in Stockholm city, where the task was to find out if allowing two-way bicycle traffic on one-way streets had negative effects on safety. The video analysis system was applied to detect biking in the ‘wrong’ direction and analyse traffic conflicts between cyclists and other road users. The manual observations done in parallel allowed validating the accuracy of system performance.