Various methods are available to classify tracked road users.
- Speed-based classification
- use the classifyUserTypeSpeed method in the MovingObject Python class
- Classification based on frequency analysis of speed profiles (see Saunier, N.; El Husseini, A.; Ismail, K.; Morency, C.; Auberlet, J.-M. & Sayed, T. Pedestrian Stride Frequency and Length Estimation in Outdoor Urban Environments using Video Sensors. Transportation Research Record: Journal of the Transportation Research Board, 2011, 2264, 138-147, preprint)
- Classification based on appearance (being implemented from Zangenehpour, S.; Miranda-Moreno, L. F. & Saunier, N. Automated Classification in Traffic Video at Intersections with Heavy Pedestrian and Bicycle Traffic. Transportation Research Board Annual Meeting Compendium of Papers, 2014): see methods classifyUserTypeSpeed and classifyUserTypeHoGSVM (example scripts under work for training and classifying tracked road users)
An alternative, not implemented, would be to use object classifiers for tracking, e.g. as in Breitenstein et al.'s work.