基于联合层特征的卷积神经网络在车标识别中的应用

doi:10.11772/j.issn.1001-9081.2016.02.0444

计算机应用 ›› 2016, Vol. 36 ›› Issue (2): 444-448.DOI: 10.11772/j.issn.1001-9081.2016.02.0444

• 第三届CCF大数据学术会议(CCF BigData 2015) • 上一篇下一篇

基于联合层特征的卷积神经网络在车标识别中的应用

张力^1,2, 张洞明^1,2, 郑宏^1,2

1. 武汉大学电子信息学院, 武汉 430072;
2. 湖北省视觉感知与智能交通技术研发中心, 武汉 430072

收稿日期:2015-08-29 修回日期:2015-09-14 出版日期:2016-02-10 发布日期:2016-02-03
通讯作者: 张力(1992-),男,湖北孝感人,硕士研究生,主要研究方向:机器学习、模式识别。
作者简介:张洞明(1989-),男,湖北荆州人,硕士研究生,主要研究方向:机器学习、模式识别;郑宏(1967-),男,江苏扬州人,教授,博士生导师,博士,主要研究方向:人工智能、模式识别。
基金资助:
国家973计划项目(2012CB719905)。

Vehicle logo recognition using convolutional neural network combined with multiple layer feature

ZHANG Li^1,2, ZHANG Dongming^1,2, ZHENG Hong^1,2

1. School of Electronic Information, Wuhan University, Wuhan Hubei 430072, China;
2. Hubei Research and Development Center of Vision Perception and Intelligent Transportation Technology, Wuhan Hubei 430072, China

Received:2015-08-29 Revised:2015-09-14 Online:2016-02-10 Published:2016-02-03

摘要/Abstract

摘要： 针对现有智能交通系统仅仅通过车牌信息获取车辆信息存在不准确的情况,提出一种基于联合层特征的卷积神经网络(Multi-CNN)进行车标识别。该方法将通过卷积神经网络中不同层提取的特征联合起来,一起作为全连接层的输入,训练获得分类器。通过理论分析和实验表明,与传统的卷积神经网络训练获得的分类器相比,Multi-CNN方法能够减少训练所需计算量,同时将车标识别准确率提升至98.7%。

关键词: 深度学习, 卷积神经网络, 联合特征, 车标识别

Abstract: Concerning the inaccurate vehicle information captured by the license plate of the existing intelligent traffic system, a vehicle logo recognition method based on the Convolutional Neural Network (CNN) combined with different layer features, namely Multi-CNN, was proposed. Firstly, the different layer features were obtained using CNN. Secondly, the extracted features were joined together and regarded as the input of the fully connected layer to get classifiers. The theoretical analysis and simulation results show that, compared with the traditional method, Multi-CNN method can reduce the training time and increase the recognition accuracy to 98.7%.

Key words: deep learning, Convolutional Neural Network(CNN), multiple feature, vehicle logo recognition

中图分类号:

TP399
TP181

张力, 张洞明, 郑宏. 基于联合层特征的卷积神经网络在车标识别中的应用[J]. 计算机应用, 2016, 36(2): 444-448.

ZHANG Li, ZHANG Dongming, ZHENG Hong. Vehicle logo recognition using convolutional neural network combined with multiple layer feature[J]. Journal of Computer Applications, 2016, 36(2): 444-448.

参考文献

[1] 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),2008,33(1):36-40. (WANG M, WANG G H, FANG P Y, et al. Vehicle logo detection and recognition based on PCA and invariant moment[J].Geomatics and Information Science of Wuhan University, 2008, 33(1): 36-40.)
[2] LLORCA D F, ARROYO R, SOTELO M A. Vehicle logo recognition in traffic images using hog features and SVM[C]//Proceedings of the 2013 16th International IEEE Conference on Intelligent Transportation Systems. Piscataway, NJ: IEEE, 2013: 2229-2234.
[3] SUN Q, LU X, CHEN L, et al. An improved vehicle logo recognition method for road surveillance images[C]//Proceedings of the 2014 Seventh International Symposium on Computational Intelligence and Design. Piscataway, NJ: IEEE, 2014, 1: 373-376.
[4] 鲁丰,刘芸,张仁辉.基于改进 HOG 特征值的车标检测与识别方法[J].光通信研究,2012(5):26-29. (LU F, LIU Y, ZHANG R H. An improved HOG-based vehicle logo location and recognition method[J]. Study on Optical Communications, 2012(5): 26-29.)
[5] DAI S, HUANG H, GAO Z, et al. Vehicle-logo recognition method based on Tchebichef moment invariants and SVM[C]//WCSE '09: Proceedings of the 2009 WRI World Congress on Software Engineering. Washington, DC: IEEE Computer Society, 2009, 3: 18-21.
[6] SAM K-T, TIAN X-L. Vehicle logo recognition using modest AdaBoost and radial Tchebichef moments[C]//ICMLC 2012: Proceedings of the 2012 14th International Conference on Machine Learning and Computing. Singapore: IACSIT Press, 2012: 91-95.
[7] YU S, ZHENG S, YANG H, et al. Vehicle logo recognition based on bag-of-words[C]//Proceedings of the 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance. Washington, DC: IEEE Computer Society, 2013: 353-358.
[8] 彭博,臧笛.基于深度学习的车标识别方法研究[J].计算机科学,2015,42(4):268-273. (PENG B, ZANG D. Study on vehicle logo method based on deep learning[J].Computer Science, 2015, 42(4): 268-273.)
[9] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[10] BOUVRIE J. Notes on convolutional neural networks [EB/OL]. 2006 [2015-04-02]. http://core.ac.uk/display/86960
[11] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//ECCV 2014: Proceedings of the 13th European Conference on Computer Vision, LNCS 8689. Berlin: Springer-Verlag, 2014: 818-833

[1]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[2]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[3]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[4]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[5]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[6]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[7]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[8]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[9]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[10]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[11]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[12]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[13]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[14]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[15]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.

基于联合层特征的卷积神经网络在车标识别中的应用

Vehicle logo recognition using convolutional neural network combined with multiple layer feature

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics