[1]郜雨桐,宁慧,王巍,等.基于卷积神经网络的车辆型号识别研究[J].应用科技,2018,45(06):53-58,62.[doi:10.11991/yykj.201803011]
 GAO Yutong,NING Hui,WANG Wei,et al.Research on vehicle model identification based on convolutional neural network[J].Applied science and technology,2018,45(06):53-58,62.[doi:10.11991/yykj.201803011]
点击复制

基于卷积神经网络的车辆型号识别研究(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第45卷
期数:
2018年06期
页码:
53-58,62
栏目:
计算机技术与应用
出版日期:
2018-11-05

文章信息/Info

Title:
Research on vehicle model identification based on convolutional neural network
作者:
郜雨桐 宁慧 王巍 赵梓成 孙煜彤
哈尔滨工程大学 计算机科学与技术学院, 黑龙江 哈尔滨150001
Author(s):
GAO Yutong NING Hui WANG Wei ZHAO Zicheng SUN Yutong
College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
关键词:
图像识别车辆识别卷积神经网络选择性搜索特征提取候选窗口识别时间识别准确率
Keywords:
image recognitionconvolutional neural networkvehicle recognitionselective searchfeature extractioncandidate windowrecognition timerecognition accuracy
分类号:
TP311
DOI:
10.11991/yykj.201803011
文献标志码:
A
摘要:
为了解决交通系统中车辆型号识别率还不够高的情况,通过可视化手段优化了特征提取的步骤,同时设计了车辆识别的分类器模型和一系列训练策略。运用选择性搜索方法对样本进行分析,由此得出候选区域,之后利用融合算法和边框回归算法得出真实车辆所在区域的候选窗口。在车辆候选窗口被标出后,利用卷积神经网络对候选窗口的特征进行提取,送入到神经网络中进行分类,最终得出车辆的具体型号。通过实验表明,提出的基于卷积神经网络的图像识别算法与传统的卷积神经网络以及SVM比较,在车辆识别上都有更好的识别率。
Abstract:
In order to solve the problem that the vehicle type recognition rate is not high enough in the traffic system, in this paper, steps of feature extraction are optimized by visualization means, and the classification model for vehicle recognition and a series of training strategies are designed at the same time. Apply the selective search algorithm to analysis of samples, then get the candidate region, and further, derive the candidate window of the actual area of vehicles by a fusion algorithm and a bounding box regression algorithm. After a vehicle candidate window is marked out, extract the feature of the candidate window by a convolutional neural network, and send the feature to the neural network for classification, and finally obtain the specific model of vehicle. Experiments show that the proposed image recognition algorithm based on convolutional neural network has better recognition rate than the vehicle based on traditional convolution neural network and SVM.

参考文献/References:

[1] JI Peijn, JIN Lianwen, LI Xutao. Vision-based vehicle type classification using partial gabor filter bank[C]//IEEE International Conference on Automation and Logistics. Jinan, China, 2007:1037-1040.
[2] 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.
[3] ITO Y. Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory[J]. Neural networks, 1991, 4(3):385-394.
[4] 李琳辉, 伦智梅, 连静, 等. 基于卷积神经网络的道路车辆检测方法[J]. 吉林大学学报:工学版, 2017, 47(2):384-391.
[5] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, 2012:1097-1105.
[6] GUZMAN S, GOMEZ A, DIEZ G, et al. Car detection methodology in outdoor environment based on histogram of oriented gradient (HOG) and support vector machine (SVM)[C]//6th Latin-American Conference on Networked and Electronic Media (LACNEM 2015). Medellin, Colombia, 2017.
[7] FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graph-based image segmentation[J]. International journal of computer vision, 2004, 59(2):167-181.
[8] 史凯静, 鲍泓, 徐冰心, 等. 基于Faster RCNN的智能车道路前方车辆检测方法[J]. 计算机工程, 2018, 44(7):36-41.
[9] 余烨, 金强, 傅云翔, 等. 基于Fg-CarNet的车辆型号精细分类研究[J]. 自动化学报, 2018:1-12.
[10] BABU K M, RAGHUNADH M V. Vehicle number plate detection and recognition using bounding box method[C]//2006 International Conference on Advanced Communication Control and Computing Technologies (ICACCCT). Ramanathapuram, India, 2017:106-110.
[11] 甘凯今, 蔡晓东, 杨超, 等. 融合整体与局部特征的车辆型号识别方法[J]. 现代电子技术, 2017, 40(7):127-130.
[12] 张银苹, 葛广英. 基于HALCON的车牌识别研究[J]. 现代电子技术, 2014, 37(16):92-9.

相似文献/References:

[1]丁虎,姚磊,刘少刚,等.基于神经网络和图像分割的林火图像识别研究[J].应用科技,2016,43(03):82.[doi:10.11991/yykj.201510011]
 DING Hu,YAO Lei,LIU Shaogang,et al.The forest fire image recognition based on neural network and image segmentation[J].Applied science and technology,2016,43(06):82.[doi:10.11991/yykj.201510011]
[2]邢俊,李庆武,何飞佳,等.基于智能视觉物联网的水产养殖监测系统[J].应用科技,2017,44(05):46.[doi:10.11991/yykj.201609019]
 XING Jun,LI Qingwu,HE Feijia,et al.Aquaculture monitoring system based on intelligent visual Internet of Things[J].Applied science and technology,2017,44(06):46.[doi:10.11991/yykj.201609019]

备注/Memo

备注/Memo:
收稿日期:2018-03-09。
基金项目:国家自然科学基金项目(61672180)
作者简介:郜雨桐(1995-),男,硕士研究生;宁慧(1964-),女,副教授
通讯作者:宁慧,E-mail:ninghui@hrbeu.edu.cn
更新日期/Last Update: 2018-11-02