Research on Tunnel Vehicle Recognition Based on Pony Edge Detection Algorithm
A Pony edge detection algorithm was studied to improve the accuracy of vehicle target detec-tion and recognition in tunnels.The median filter and USM technology were used to preprocess the tunnel video image to enhance the edge features,and the Pony operator of the algorithm was used to detect the gradient,so as to obtain the edge features of the vehicle target.Based on four kinds of tun-nel video noise images,such as uneven ambient brightness(Gaussian noise),sensor performance error(salt and pepper noise),circuit element interference(Poisson noise)and channel interference(speckle noise),the detection effects of Pony edge detection algorithm and many traditional operator edge de-tection algorithms under different noise conditions were verified and analyzed.The results show that the positive detection rates of Pony edge detection algorithm are 95.21％,95.42％,96.04％and 92.02％respectively under four kinds of environmental noise conditions,and the repeated detection rate,false detection rate and missed detection rate are better than other methods.
万方数据
维普
