Computation of Vehicle Trajectories Using a Neural Network

In this paper, a method will be described to calculate vehicle trajectories using a neural network for TV imagery of vehicular traffic. Constraints on the smoothness both in time and space are successfully combined in a unified form. Other constraints, for example geometrical structures of corners, can readily be included. The neural network handles inconsistent corner data in a robust manner, and the resulting trajectory plots are, visually at least, near-optimal.

[1]  X. Xu,et al.  Effective neural algorithms for the traveling salesman problem , 1991, Neural Networks.

[2]  Mubarak Shah,et al.  Establishing motion correspondence , 1991, CVGIP Image Underst..

[3]  Willard L. Miranker,et al.  Multiscale optimization in neural nets , 1991, IEEE Trans. Neural Networks.

[4]  Ishwar K. Sethi,et al.  Feature point matching in image sequences , 1988, Pattern Recognit. Lett..

[5]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Geoffrey D. Sullivan,et al.  Model-Based Tracking , 2011, BMVC.

[7]  X. Xu,et al.  A generalized neural network model , 1988, Neural Networks.

[8]  Hans-Hellmut Nagel,et al.  Model-Based Object Tracking in Traffic Scenes , 1992, ECCV.

[9]  Ishwar K. Sethi,et al.  Finding Trajectories of Feature Points in a Monocular Image Sequence , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.