This paper presents a laser intensity image based algorithm for automatic vehicle classification system (AVC) on highways. The algorithm performs line by line processing of laser intensity images, produced by laser sensory units, and extracts vehicle features used for the classification. The features include vehicle length, width, height, speed, and some distinguishable patterns in the vehicle profile. The proposed technique outperforms the range data technique in deteriorated atmospheric conditions (such as rain and fog). A software package with a graphical user interface has been developed to illustrate the usage of the classification algorithm and to evaluate its performance.Index terms-Automatic vehicle classification, laser telemetry, intensity based algorithm, image processing.

No abstract

No abstract

No abstract

No abstract

This paper presents a novel technique for texture modeling and synthesis using the random neural network (RNN). This technique is based on learning the weights of a recurrent network directly from the texture image. The same trained recurrent network is then used to generate a synthetic texture that imitates the original one. The proposed texture learning technique is very efficient and its computation time is much smaller than that of approaches using Markov Random Fields. Texture generation is also very fast. We have tested our method with different synthetic and natural textures. The experimental results show that the RNN can efficiently model a large category of homogeneous microtextures. Statistical features extracted from the co-occurrence matrix of the original and the RNN based texture are used to evaluate the quality of fit of the RNN based approach.

I n this paper, a neural network based direct sequence spread spectwm code synchronization system is proposed. This system is based on tmining a recurrent random neuml network (RNN) model on all the possible phases of the used spreading wde. The trained network can then be used at the receiver for the initial worse cslignment of the local code phase and the received code. One advantage of this technique over the conventional synchronization techniques is that the phase of the received PN code can be decided without searching the potential d e phases. Also the RNN, after being trained, can have a simple hardware realization that makes it candidate for implementation os a dedicated chip. This makes the neural network based technique faster and more robust than the conventional techniques. Computer simulations, carried out on maximal length sequences of length N = 7 and N = 15, show that the proposed system can eflectively indicate the phase of the received code even with very low signal to noise mtios.