基于CNN的车辆目标检测与车型分类研究

车辆检测与分类是智能交通系统的重要任务.解决这些任务的传统方法由于受到车辆图像视角受限的影响从而导致粗粒度的识别结果.近年来深度学习成功应用于图像分类任务,并受其最新成果的启发,本文提出了一种基于卷积神经网络的车辆检测与分类方法,该方法包括车辆区域检测和车型分类两部分.在检测和分类实验中,我们详细对比分析几种典型的网络...

Research on Vehicle Detection and ClassificationUsingConvolutional Neural Network

The vehicle detection and classification is an important task of the intelligent transportation system.The traditional methods of these tasks often suffer from the limited viewpoints and cause the coarse-grained results.Inspired by the latest achievements of Deep Learning successfully applied on images classification in recent years,this paper proposes a method based on convolutional neural network,which consists of two steps:vehicle area detection and vehicle brand classification.Several typical network models have been applied in training and classification experiments for the detailed contrast analyse,such as R-CNN,Faster R-CNN,AlexNet,VggNet,Googlenet and Resnet.The proposed algorithm can identify the vehicle models,brands and other information accurately and in real time.With the original data set,the algorithm can get the result with average accuracy about 89%in the classification of seven kind of vehicle models.