Great Fast Algorithm Based On Independent Component Analysis Of Information On The Vehicle Sound Frequency Mixed-signal Separation

In this dissertation, according to the condition of current traffic volume detection, a new method of traffic volume detection with vehicle noise is presented. First, the models of the narrowband and broadband array signal processing are introduced simply. Subsequently, the primary knowledge of blind signal separation is analyzed. Then, the simulated mixed noise signals of passing vehicles are gathered with microphone array, and processed off line with the method of informax fast algorithm based on independent component analysis. The every independent noise signal of vehicles is received. At last, the actual mixed noise signals of passing vehicles are also successfully separated using the algorithm. Thus, accurate estimation is given about traffic volume and vehicle recognition. The result of the experiment proves it feasible to separate blind mixed noise signals of vehicles with the method of informax fast algorithm.