Road traffic density estimation using microscopic and macroscopic parameters
Image and Vision Computing
Hi-index | 0.00 |
With a large number of traffic parameters data, it is an important issue that how to set up an efficient model of classification and prediction to identify the congestion state as soon as possible. The article provided a model of predicting traffic congestion based on the learn vector quantization neural network by making use of traffic parameters such as speed, volume and occupancy which were detected by vehicle detectors. The model can finally classify the traffic congestion situation and normal situation by training the LVQ neural network in the software matlab. The model can predict the road traffic situation by inputting the traffic flow data, thus providing exact road information for the dispersion of traffic congestion. Finally, an example was given to train and test the network. And the training result demonstrated the algorithm was feasible to the prediction of traffic congestion and can be actually useful in reality.