Computer Science ›› 2018, Vol. 45 ›› Issue (5): 280-284.doi: 10.11896/j.issn.1002-137X.2018.05.048

Previous Articles     Next Articles

Vehicle Type Recognition Based on Deep Convolution Neural Network

SHI Lei, WANG Ya-min, CAO Yang-jie and WEI Lin   

  • Online:2018-05-15 Published:2018-07-25

Abstract: The accuracy of traditional convolution neural network recognizing the vehicle model is not high when recognizing similar models,and the gray scale of image can only be used in the network training with the loss of color information of the image.Based on this,a method of extracting image features based on deep convolution neural network(DCNN) was proposed.The deep convolution neural network is used to carry out network training for the vehicle model with complex background,so as to achieve the purpose of recognizing models.In this paper,by using advanced deep learning framework Caffe,a deep convolution neural network based on AlexNet structure was proposed with the trai-ning of the image of vehicle model and the comparison with traditional convolution neural network.The experimental results show that the accuracy rate of DCNN network model can reach 96.9% with a higher accuracy.

Key words: Convolution neural network,Vehicle identification,Deep learning

[1] TAKAMOTO M,ISHIKAWA H,SHIMIZU K,et al.Newmeasurement method for very low liquid flow rates using ultrasound[J].Flow Measurement & Instrumentation,2001,12(4):267-273.
[2] WARRIACH E U,CLAUDEL C.Poster abstract:a machinelearning approach for vehicle classification using passive infrared and ultrasonic sensors[C]∥International Conference on Information Processing in Sensor Networks.2013:333-334.
[3] TANG S J,WU H W.A Robust Face Recognition MethodBased on Snake Model and Collaborative Representation Classification[J].Natural Science Journal of Xiangtan University,2016,8(2):104-108.(in Chinese) 唐守军,吴洪武.基于Snake模型和协作表示分类的鲁棒人脸识别方法[J].湘潭大学自科学报,2016,8(2):104-108.
[4] LIU R,LIU J Q,LIU H.Gesture feature extraction and recognition based on acceleration track[J].Application Research of Computers,2017,4(3):924-927.(in Chinese) 刘蓉,刘家祺,刘红.基于加速度轨迹图像的手势特征提取与识别[J].计算机应用研究,2017,4(3):924-927.
[5] HUA L Q,XU W,WANG T,et al.Vehicle Recognition Using Improved SIFT and Multi-View Model [J].Journal of Xi’an Jiaotong University,2013,47(4):92-99.(in Chinese) 华莉琴,许维,王拓,等.采用改进的尺度不变特征转换及多视角模型对车型识别[J].西安交通大学学报,2013,7(4):92-99.
[6] TAIGMAN Y,YANG M,RANZATO M,et al.DeepFace:Clo-sing the Gap to Human-Level Performance in Face Verification[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2014:1701-1708.
[7] RAHATI S,MORAVEJIAN R,KAIEMI E M,et al.Vehiclerecognition using contourlet transform and SVM [C]∥5th International Conference on Information Technology:New Genera-tions.IEEE,2008:894-898.
[8] ZHANG J.Research on Image Retrieval Based on Fusion Feature of AlexNet[D].Chongqing:Chongqing University of Posts and Telecommunications,2016.(in Chinese) 张俊.基于AlexNet融合特征的图像检索研究[D].重庆:重庆邮电大学,2016.
[9] GOODFELLOW I J,WARDE-FARLEY D,MIRZA M,et al.Maxout networks [J].Computer Science,2013,28(3):1319-1327.
[10] YAN F,WANG L Z,SHI L,et.al.Digital Image Watermarking Algorithm Based on DWT and PNN[J].Natural Science Journal of Xiangtan University,2016,8(3):89-93.(in Chinese) 闫凤,王立中,石磊,等.基于DWT和PNN的数字图像水印算法[J].湘潭大学自然科学学报,2016,8(3):89-93.
[11] ANDREW A M.An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[J].Kybernetes,2001,32(1):1-28.
[12] CHEN L F,CHEN L,LIU B X.Research of SVM Multicalss Model Based on Granular Computing & Huffman Tree[J] Computer Science,2016,3(1):64-68.(in Chinese) 陈丽芳,陈亮,刘保相.基于粒计算的哈夫曼树SVM多分类模型研究[J].计算机科学,2016,3(1):64-68.
[13] ZHAO H X,XU F,CHEN J Y.Face Recognition Based onMulti-Scale LBP[J].Computer Applications and Software,2012,9(1):257-259.(in Chinese) 赵怀勋,徐锋,陈家勇.基于多尺度LBP的人脸识别[J].计算机应用与软件,2012,9(1):257-259.
[14] HUANG F C,HUANG S Y,KER J W,et al.High-performance SIFT hardware accelerator for real-time image feature extraction [J].IEEE Transaction on Circuits and Systems for Video Technology,2012,22(3):340-351.
[15] DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection[C]∥IEEE Computer Society Conference on Computer Vision & Pattern Recognition.IEEE Computer Society,2005:886-893.
[16] DENG L.Deep Convolutional Neural Networks for VehicleClassification[D].Chengdu:Southwest Jiaotong University,2015.(in Chinese) 邓柳.基于深度卷积神经网络的车型识别[D].成都:西南交通大学,2015.
[17] PI S Y,TANG H,XIAO N F.Fully Convolutional Deep Lear-ning Model Based Graspable Object Etection[J].Journal of Chongqing University of Technology(Natural Science),2018,32(2):166-173.(in Chinese) 皮思远,唐洪,肖南峰.基于全卷积深度学习模型的可抓取物品识别[J].重庆理工大学学报(自然科学),2018,32(2):166-173.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!