计算机科学 ›› 2015, Vol. 42 ›› Issue (4): 268-273.doi: 10.11896/j.issn.1002-137X.2015.04.055

• 图形图像与模式识别 • 上一篇    下一篇

基于深度学习的车标识别方法研究

彭 博,臧 笛   

  1. 同济大学计算机科学与技术系 上海201804同济大学嵌入式系统与服务计算教育部重点实验室 上海200092,同济大学计算机科学与技术系 上海201804同济大学嵌入式系统与服务计算教育部重点实验室 上海200092
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受科技部国际合作专项(2012DFG11580),国家自然科学基金(61103071),教育部博士学科点新教师基金(20110072120065),留学回国人员科研启动基金资助

Vehicle Logo Recognition Based on Deep Learning

PENG Bo and ZANG Di   

  • Online:2018-11-14 Published:2018-11-14

摘要: 对交通监控录像中车牌污损、遮挡的肇事车辆信息进行确认是现阶段智能交通系统中的一个重要问题,车标作为一个关键特征,可以起到辅助判别的作用。 提出了一种基于深度学习的车标识别方法,相对于以人工提取特征为主的传统车标识别方法,该方法具有可自主学习特征、可直接输入图像等优点。实验表明,这种方法正确率较高,在光照变化和噪声污染下的准确性和稳定性较好,能够有效降低车标识别的错误率。

关键词: 肇事车辆,车标,深度学习,车标识别

Abstract: Identification of vehicles which have caused traffic accidents is an important issue in intelligent transportation system (ITS).However,due to the missing or the stains on the car license plates,it is difficult to locate the vehicles.Logos,as key features of vehicles,can also help to identify vehicles of interest.This paper proposed a method to detect and recognize vehicle logos based on deep learning.Compared with traditional approaches that extract features manually,this method uses original images as inputs to learn features automatically.Experimental results demonstrate that the proposed method has a high accuracy,and even in the conditions of illumination change and noise contamination,it is able to produce stable and accurate results.

Key words: Accident-causing vehicle,Vehicle logo,Deep learning,Vehicle logo recognition

[1] 罗彬,游志胜,曹刚.基于边缘直方图的快速汽车标志识别方法[J].计算机应用研究,2004,21(6):150-151
[2] Wang Yun-qiong,Liu Zhi-fang,Xiao Fei.A Fast Coarse-to-Fine Vehicle Logo Detection and Recognition Method[C]∥IEEE International Conference on Robotics and Biomimetics,2007(ROBIO 2007).IEEE,2007:691-696
[3] 王枚,王国宏,房培玉,等.基于PCA与不变矩的车标定位与识别[J].武汉大学学报:信息科学版,2008,3(1):36-40
[4] 磨少清,刘正光,张军.基于图像质量和PCA子空间的车标识别方法[J].计算机应用,2010(8):2244-2260
[5] Yu Shu-yuan,et al.Vehicle logo recognition based on Bag-of-Words[C]∥2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).IEEE,2013:353-358
[6] Llorca D F,Arroyo R,Sotelo M A.Vehicle logo recognition in traffic images using HOG features and SVM [C]∥2013 16th International IEEE Conference on Intelligent Transportation Systems:Intelligent Transportation Systems for All Modes(ITSC 2013).2013:2229-2234
[7] Sam K-T,Tian Xiao-lin.Vehicle Logo Recognition Using Mo-dest AdaBoost and Radial Tchebichef Moments[M].IPCSIT.Singapore:IACSIT Press,2012
[8] 王运琼,刘直芳,肖飞.基于对称性的实时车标定位和识别方法[J].系统仿真学报,2009,21(4):1095-1100
[9] Wang Sheng-ke,Liu Li-li,Xu Xiao-wei,et al.Vehicle Logo Re-cognition Based on Local Feature Descriptor[C]∥Information Technology Applications in Industry.2013:2388-2391
[10] Psyllos A P,Christos-Nikolaos E,Anagnostopoulos,et al.Vehicle Logo Recognition Using a SIFT-Based Enhanced Matching Scheme [J].IEEE Transactions on Intelligent T ransportation Systems,2010,11(2):322-328
[11] Hinton G.A Practical Guide to Training Restricted Boltzmann Machines[EB/OL].[2010-08-02].http://www.cs.toronto.edu/~hinton/absps/guideTR.pdf
[12] Hinton G E,Osindero S,Teh Y.A Fast Learning Algorithm For Deep Belief Nets [J].Neural Computation,2006,18:1527-1554
[13] Zeiler M D,Fergus R.Visualizing and Understanding Convolutional Neural Networks[C]∥Computer Vision-ECCV 2014.2014:818-833
[14] Bishop C M.Neural Networks for Pattern Recognition[M].New York: Oxford University Press,1995
[15] Xu F J,Wu W,Gong Y,et al.Tracking Using Convolutional Neural Networks [J].IEEE Transactions on Neural Networks,2010,1(10):1610-1623
[16] Karpathy A,Toderici G,Shetty S,et al.Large-scale video classification with convolutional neural networks[C]∥IEEE Confe-rence on Computer Vision and Pattern Recognition (CVPR).2014
[17] Tang Z,Xian Y,Li B.Research of Vehicle Recognition Algorithm Based on Virtual Coil and Image Features[M]∥Future Information Technology.Springer Berlin Heidelberg,2014:367-372
[18] Zhou Kai,Varadarajan K M,Vincze M,et al.Hybridization of Appearance and Symmetry for Vehicle-logo Localization[C]∥2012 15th International IEEE Conference on Intelligent Transportation Systems(ITSC 2012).2012:1396-1401
[19] An L,Thakoor N,Bhanu B,et al.Vehicle logo super-resolution by canonical correlation analysis[C]∥2012 19th IEEE international conference on image processing.2012:2229-2232
[20] Chu J L,Krzyak A.Application of Support Vector Machines,Convolutional Neural Networks and Deep Belief Networks to Recognition of Partially Occluded Objects[C]∥Artificial Intelligence and Soft Computing.Springer International Publishing,2014:34-46
[21] 李星,郭晓松,郭君斌.基于HOG特征和SVM的前向车辆识别方法[J].计算机科学,2013,0(11A):329-332
[22] Dai Shi-jie,Huang He,Gao Zhang-ying,et al.Vehicle-logo Re-cognition Method Based on Tchebichef Moment Invariants and SVM [C]∥2009 WRI World Congress on Software Engineering (WCSE 2009).Volume 3,2009:18-21
[23] LeNet-5,convolutional neural networks[EB/OL].2013-11-09.http://yann.lecun.com/exdb/lenet/index.html
[24] Bottou L.Large-scale machine learning with stochastic gradient descent[C]∥Proceedings of COMPSTAT’2010.Physica-Verlag HD,2010:177-186

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!