基于深度学习的复杂环境下车型精确识别方法

Precise Vehicle Identification Method in Complex Environment Based on Deep Learning

目前在输电线路通道监控中车辆的识别主要是依据车型信息来进行的,这就需要提取大量的特征信息,针对这一复杂问题,提出了深度学习的方法来实现复杂情况下车型的识别方法.该种方法主要是基于卷积神经网路的深度学习,通过实验验证了DCNN网络结构模型在识别车型上的准确率达到96.8%,同时还验证了神经网络中卷积核的大小、神经网络的层数以及特征空间的维数在识别过程中对其性能和分辨能力的影响程度.

At present,vehicle recognition in transmission line channel monitoring is mainly based on vehicle type information,which needs to extract a lot of feature information.Aiming at this complex problem,a deep learning method is proposed to realize vehicle type recognition in complex situation.This method is mainly based on the deep learning of convolutional neural network,and the accuracy of DCNN network structure model in vehicle recognition is improved to 96.8%through experiments.At the same time,the size of convolution kernel,the number of layers of neural network and the dimension of feature space in the recognition process are also verifi ed.