梯度直方图卷积特征的胶囊网络在交通监控下的车型分类

doi:10.11772/j.issn.1001-9081.2020020152

计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 2881-2889.DOI: 10.11772/j.issn.1001-9081.2020020152

梯度直方图卷积特征的胶囊网络在交通监控下的车型分类

陈立潮¹, 张雷¹, 曹建芳^1,2, 张睿¹

1. 太原科技大学计算机科学与技术学院, 太原 030024;
2. 忻州师范学院计算机系, 山西忻州 034000

收稿日期:2020-02-19 修回日期:2020-04-13 出版日期:2020-10-10 发布日期:2020-04-30
通讯作者: 曹建芳
作者简介:陈立潮(1961-),男,山西万荣人,教授,博士,CCF高级会员,主要研究方向:大数据软件工程、智能图像信息处理;张雷(1994-),男,山西临汾人,硕士研究生,CCF会员,主要研究方向:图像处理、深度学习;曹建芳(1976-),女,山西忻州人,教授,博士,CCF高级会员,主要研究方向:数字图像理解、大数据;张睿(1987-),男,山西太原人,副教授,博士,CCF会员,主要研究方向:智能信息处理。
基金资助:
山西省应用基础研究项目（201801D221179）。

Vehicle classification based on HOG-C CapsNet in traffic surveillance scenarios

CHEN Lichao¹, ZHANG Lei¹, CAO Jianfang^1,2, ZHANG Rui¹

1. College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan Shanxi 030024, China;
2. Department of Computer, Xinzhou Teachers University, Xinzhou Shanxi 034000, China

Received:2020-02-19 Revised:2020-04-13 Online:2020-10-10 Published:2020-04-30
Supported by:
This work is partially supported by the Applied Basic Research Project of Shanxi Province (201801D221179).

摘要/Abstract

摘要： 为了充分利用图像信息以提高现有交通监控下车型分类的效果，在胶囊网络的基础上增加梯度直方图卷积（HOG-C）特征提取方法，提出HOG-C特征的胶囊网络模型——HOG-C CapsNet。首先，使用梯度统计特征提取层对图像中的梯度信息进行统计，构建方向梯度直方图（HOG）特征图；其次，使用卷积层提取出图像的颜色信息，把提取出的颜色信息与HOG特征图融合构成HOG-C特征图；最后，输入卷积层提取HOG-C特征图的抽象特征，并通过胶囊网络对提取的抽象特征进行具有三维空间特征表达的胶囊封装，使用动态路由算法实现车型分类。在BIT-Vehicle数据集上对该模型和其他相关模型进行的对比实验中，该模型得到98.17%的准确率、97.98%的平均精确率均值（MAP）、98.42%的平均召回率均值（MAR）和98.20%的综合评价指标。实验结果表明，该模型在交通监控下的车型分类上具有更好的效果。

关键词: 交通监控, 胶囊网络, 方向梯度直方图, 车型分类, 卷积神经网络

Abstract: To improve the performance of vehicle classification by making full use of image information from traffic surveillance, Histogram of Oriented Gradient Convolutional (HOG-C) features extraction method was added on the capsule network, and a Capsule Network model fusing with HOG-C features (HOG-C CapsNet) was proposed. Firstly, the gradient data in the images were calculated by the gradient statistical feature extraction layer, and then the Histogram of Oriented Gradient (HOG) feature map was plotted. Secondly, the color information of the image was extracted by the convolutional layer, and then the HOG-C feature map was plotted with the extracted color information and HOG feature map. Finally, the HOG feature map was input into to the convolutional layer extract its abstract features, and the abstract features were encapsulated through a capsule network into capsules with the three-dimensional spatial feature representation, so as to realize the vehicle classification by dynamic routing algorithm. Compared with other related models on the BIT-Vehicle dataset, the proposed model has the accuracy of 98.17%, the Mean Average Precision (MAP) of 97.98%, the Mean Average Recall (MAR) of 98.42% and the comprehensive evaluation index of 98.20%. Experimental results show that the vehicle classification in traffic surveillance scenarios can be achieved with better performance by using HOG-C CapsNet.

Key words: traffic surveillance, Capsule Network (CapsNet), Histogram of Oriented Gradient (HOG), vehicle classification, convolutional neural network

中图分类号:

TP391.3

陈立潮, 张雷, 曹建芳, 张睿. 梯度直方图卷积特征的胶囊网络在交通监控下的车型分类[J]. 计算机应用, 2020, 40(10): 2881-2889.

CHEN Lichao, ZHANG Lei, CAO Jianfang, ZHANG Rui. Vehicle classification based on HOG-C CapsNet in traffic surveillance scenarios[J]. Journal of Computer Applications, 2020, 40(10): 2881-2889.

参考文献

[1] 刘虎, 周野, 袁家斌. 基于多尺度双线性卷积神经网络的多角度下车型精细识别[J]. 计算机应用,2019,39(8):2402-2407. (LIU H,ZHOU Y,YUAN J B. Fine-grained vehicle recognition under multiple angles based on multi-scale bilinear convolutional neural network[J]. Journal of Computer Applications,2019,39(8):2402-2407.)
[2] 吴峰华, 杨哲海, 张玉萍, 等. 仿人足球机器人快速多目标识别方法[J]. 计算机辅助设计与图形学学报,2019,31(12):2152-2165.(WU F H,YANG Z H,ZHANG Y P,et al. Fast multi-target recognition method for humanoid robot playing soccer[J]. Journal of Computer-Aided Design and Computer Graphics,2019,31(12):2152-2165.)
[3] CAO J,CHEN L,WANG M,et al. A parallel AdaBoost-backpropagation neural network for massive image dataset classification[J]. Scientific Reports,2016,6:No. 38201.
[4] 徐守坤, 邱亮, 李宁, 等. 基于HOG-CSLBP及YOLOv2的行人检测[J]. 计算机工程与设计,2019,40(10):2964-2968.(XU S K,QIU L,LI N,et al. Pedestrian detection based on HOG-CSLBP and YOLOv2[J]. Computer Engineering and Design,2019,40(10):2964-2968.)
[5] 赵越, 吴莹. 自适应PSO-SVM上产期油气操作成本预测模型[J]. 计算机仿真,2019,36(11):69-74.(ZHAO Y,WU Y. Selfadaption PSO-SVM oil-gas operating cost in the rapid growing period forecasting model[J]. Computer Simulation, 2019, 36(11):69-74.)
[6] ZHAO S,CHEN L. Hoisting equipment of coal mine condition monitoring and early warning based on BP neural network[J].Advanced Science Letters,2012,5(1):590-592.
[7] CHEN L,PAN L,YANG C. Using APPM-trained ANN to solve stochastic expected value mode[J]. International Journal of BioInspired Computation,2013,5(3):192-196.
[8] 李洪均, 周泽. 分层式宽度模型的实时车型识别算法[J]. 数据采集与处理,2019,34(1):80-90.(LI H J,ZHOU Z. Real-time vehicle type recognition algorithm based on layered broad model[J]. Journal of Data Acquisition and Processing,2019,34(1):80-90.)
[9] 邓棋, 雷印杰, 田锋. 用于肺炎图像分类的优化卷积神经网络方法[J]. 计算机应用,2020,40(1):71-76.(DENG Q,LEI Y J, TIAN F. Optimized convolutional neural network method for classification of pneumonia images[J]. Journal of Computer Applications,2020,40(1):71-76.)
[10] 徐姗姗, 颜超, 高琳明. 基于三维卷积神经网络的湖泊提取算法[J]. 计算机应用,2019,39(12):3450-3455.(XU S S,YAN C, GAO L M. Lake extraction algorithm based on three-dimensional convolutional neural network[J]. Journal of Computer Applications,2019,39(12):3450-3455.)
[11] 张文彬, 朱敏, 张宁, 等. 基于卷积神经网络的偏色光下植物图像分割方法[J]. 计算机应用,2019,39(12):3665-3672. (ZHANG W B, ZHU M, ZHANG N, et al. Plant image segmentation method under bias light based on convolutional neural network[J]. Journal of Computer Applications,2019,39(12):3665-3672.)
[12] ZHEN D,WU Y,PEI M,et al. Vehicle type classification using a semisupervised convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems,2015,16(4):2247-2256.
[13] 桑军, 郭沛, 项志立, 等. Faster-RCNN的车型识别分析[J]. 重庆大学学报,2017,40(7):32-36.(SANG J,GUO P,XIANG Z L,et al. Vehicle detection based on Faster-RCNN[J]. Journal of Chongqing University,2017,40(7):32-36.)
[14] SABOUR S,FROSST N,HINTON G E. Dynamic routing between capsules[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook,NY:Curran Associates Inc.,2017:3859-3869.
[15] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2005:886-893.
[16] 舒娜, 刘波, 林伟伟, 等. 分布式机器学习平台与算法综述[J]. 计算机科学,2019,46(3):9-18.(SHU N,LIU B,LIN W W, et al. Survey of distributed machine learning platforms and algorithms[J]. Computer Science,2019,46(3):9-18.)
[17] SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-04-10]. https://arxiv.org/pdf/1409.1556.pdf.
[18] 袁公萍, 汤一平, 韩旺明, 等. 基于深度卷积神经网络的车型识别方法[J]. 浙江大学学报(工学版),2018,52(4):694-702. (YUAN G P,TANG Y P,HAN W M,et al. Vehicle category recognition based on deep convolutional neural network[J]. Journal of Zhejiang University(Engineering Science),2018,52(4):694-702.)

梯度直方图卷积特征的胶囊网络在交通监控下的车型分类

Vehicle classification based on HOG-C CapsNet in traffic surveillance scenarios

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

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[9]	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.
[10]	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.
[11]	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.
[12]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.
[13]	谭道强, 曾诚, 乔金霞, 张俊. 基于混合注意力模型的阴影检测方法[J]. 计算机应用, 2021, 41(7): 2076-2081.
[14]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.
[15]	杨粟, 欧阳智, 杜逆索. 基于相关度距离的无监督并行哈希图像检索[J]. 计算机应用, 2021, 41(7): 1902-1907.