Title :
Real-time vehicle tracking and classification
Author :
Noll, Detlev ; Werner, Martin ; Von Seelen, Werner
Author_Institution :
Inst. fur Neuroinf., Ruhr-Univ., Bochum, Germany
Abstract :
In this paper a feature and model based approach to real-time vehicle tracking and classification is described. We proceed in two steps: 1) we establish correspondence between model and image features by an optimization algorithm; and 2) based on this correspondence, a matching vector is derived and used as input to either a Bayes classifier, a neural net or a combination of both. The current implementation updates the model parameters (position and scale) at a rate of 8-12 frames per second
Keywords :
Bayes methods; computer vision; feature extraction; image classification; iterative methods; neural nets; optimisation; real-time systems; road traffic; tracking; traffic control; Bayes classifier; CENET; image features; iterative method; matching vector; model based approach; neural net; optimization; real-time systems; vehicle classification; vehicle tracking; Annealing; Deformable models; Euclidean distance; Least squares methods; Uncertainty; Vehicles;
Conference_Titel :
Intelligent Vehicles '95 Symposium., Proceedings of the
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-2983-X
DOI :
10.1109/IVS.1995.528265
