[1]阮航,王立春.基于特征图的车辆检测和分类[J].计算机技术与发展,2018,28(11):39-43.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
　RUAN Hang,WANG Li-chun.Vehicle Detection and Classification Based on Feature Map[J].,2018,28(11):39-43.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
点击复制

基于特征图的车辆检测和分类()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年11期
页码:
39-43
栏目:
智能、算法、系统工程
出版日期:
2018-11-10

文章信息/Info

Title:
Vehicle Detection and Classification Based on Feature Map
文章编号:
1673-629X(2018)11-0039-05
作者:
阮航; 王立春
南京航空航天大学 计算机科学与技术学院,江苏 南京 211100
Author(s):
RUAN Hang; WANG Li-chun
School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics, Nanjing 211100,China
关键词:
车辆检测; 车辆识别; 深度学习; 图像分类; 卷积神经网络
Keywords:
vehicle detection; vehicle recognition; depth learning; image classification; convolutional neural network
分类号:
TP391
DOI:
10.3969/ j. issn.1673-629X.2018.11.009
文献标志码:
A
摘要:
在交通视频监控中,有很多因素影响车辆检测和分类的准确率,包括复杂的道路环境,光照和天气变化,以及摄像机的角度方向等。 传统的图像处理方法很难解决这样的问题。 对此,提出了一种基于加权特征映射的车辆检测和分类的卷积神经网络模型。 首先,将原始图像输入到卷积神经网络中,通过一次前向计算得到各层特征图。然后,通过特征图计算图像局部区域的响应,并生成加权特征地图。 通过阈值分割技术,得到车辆目标区域。 最后,提取车辆图像的卷积神经网络特征,实现细粒度的车辆分类。在该模型中,无需复杂的图像预处理,具有很强的通用性和鲁棒性。 实验结果表明,该模型具有较高的检测精度和分类准确率,适用于交通视频监控中的车辆检测和细粒度分类。
Abstract:
In traffic video surveillance,there are many factors that can affect the accuracy of vehicle detection and classification,including complex road environment,light and weather changes,and the camera’s angle direction. The traditional image processing method is difficult to solve these problems. Therefore,we propose a convolution neural network model of vehicle detection and classification based on weighted feature mapping. Firstly,the original image is input into the convolutional neural network,and the feature maps of each layer are obtained through a forward calculation. Then,we calculate the local area of the image by the feature map and generate the weighted feature map. Through the threshold segmentation technology,we get the vehicle target. Finally,we extract the convolution neural network features of vehicle images to achieve fine-grained vehicle classification. No complicated image preprocessing is required in this model which has strong universality and robustness. The experiment shows that the model has high detection accuracy and classification precision,which is suitable for traffic video surveillance vehicle detection and classification.

相似文献/References:

[1]方宏 杜正春.车辆检测线远程监控系统的研制[J].计算机技术与发展,2009,(12):185.
　FANG Hong,DU Zheng-chun.Development of Remote Monitoring System of Vehicle Inspection Lane[J].,2009,(11):185.
[2]张明恒 王华莹 郭烈.基于改进K—Means算法的车辆识别方法[J].计算机技术与发展,2012,(05):53.
　ZHANG Ming-heng,WANG Hua-ying,GUO Lie.Method of Vehicle Detection Based on Improved K-Means Algorithm[J].,2012,(11):53.
[3]刘亚非 辛飞飞.基于综合特征的车辆检测识别系统[J].计算机技术与发展,2012,(09):18.
　LIU Ya-fei,XIN Fei-fei.Vehicle Detection and Recognition System Based on Comprehensive Features[J].,2012,(11):18.
[4]吴玉枝,吴志红,熊运余.基于卷积神经网络的小样本车辆检测与识别[J].计算机技术与发展,2018,28(06):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
　WU Yu-zhi,WU Zhi-hong,XIONG Yun-yu.Vehicle Detection and Recognition of a Few Samples Based on Convolutional Neural Network[J].,2018,28(11):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
[5]洪浩[],霍春宝[],王京[],等. 基于改进Otsu算法在前方目标车辆识别中的研究[J].计算机技术与发展,2016,26(06):78.
　HONG Hao[],HUO Chun-bao[],WANG Jing[],et al. Research on Front Target Vehicle Identification Based on Improved Otsu Algorithm[J].,2016,26(11):78.
[6]王传钦[],曹江涛[],姬晓飞[]. 基于视频分析技术的车距测量及预警系统设计[J].计算机技术与发展,2016,26(09):87.
　WANG Chuan-qin[],CAO Jiang-tao[],JI Xiao-fei[]. Design of a Vehicle Distance Measurement and Early Warning System Based on Video Analysis Techniques[J].,2016,26(11):87.
[7]阮航,孙涵.基于 Faster R-CNN 的车辆多属性识别[J].计算机技术与发展,2018,28(10):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
　RUAN Hang,SUN Han.Vehicle Multi-attribute Recognition Based on Faster R-CNN[J].,2018,28(11):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
[8]杨岳航,孙涵.基于部件模型的复杂场景车辆检测方法[J].计算机技术与发展,2018,28(12):34.[doi:10．3969/j． issn．1673－629X．2018．12．007]
　YANG Yuehang,SUN Han.A Vehicle Detection Method Based on Part Model in Complex Traffic Scenes[J].,2018,28(11):34.[doi:10．3969/j． issn．1673－629X．2018．12．007]
[9]陶晓力,刘宁钟,沈家全.基于深度信息融合的航拍车辆检测[J].计算机技术与发展,2019,29(09):117.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 023]
　TAO Xiao-li,LIU Ning-zhong,SHEN Jia-quan.Aerial Vehicle Detection Based on Depth Information Fusion[J].,2019,29(11):117.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 023]
[10]王 翎,孙 涵.基于域适应的多场景车辆检测[J].计算机技术与发展,2019,29(12):158.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 028]
　WANG Ling,SUN Han.Vehicle Detection in Different Scenes Based on Domain Adaptation[J].,2019,29(11):158.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 028]

更新日期/Last Update: 2018-11-10