基于多特征融合的前向车辆检测方法

doi:10.3969/j.issn.1000-3428.2014.02.044

计算机工程

基于多特征融合的前向车辆检测方法

李星，郭晓松，郭君斌

(第二炮兵工程大学兵器发射理论与技术国家重点学科实验室，西安 710025)

收稿日期:2013-01-18 出版日期:2014-02-15 发布日期:2014-02-13
作者简介:李星(1988－)，男，硕士研究生，主研方向：机器视觉，数字图像处理；郭晓松，教授、博士生导师；郭君斌，讲师、博士后

Forward Vehicle Detection Method Based on Multi-feature Fusion

LI Xing, GUO Xiao-song, GUO Jun-bin

(State Key Laboratory of Weapon Launching Theory and Technology, The Second Artillery Engineering University, Xi’an 710025, China)

Received:2013-01-18 Online:2014-02-15 Published:2014-02-13

摘要/Abstract

摘要： 针对传统车辆检测方法定位精度不高的问题，提出一种基于多特征融合的前向车辆检测方法。采用基于直方图分析和自适应双阈值的方法分别实现阴影和边缘特征的准确分割，并通过阴影和边缘特征的综合分析，生成车辆假设区域。利用对称性、纹理和轮廓匹配度3个特征融合得到的综合特征对获得的车辆假设区域进行验证，剔除其中的误检区域。实验结果证明，该方法能在不同光照条件下自适应地进行车辆检测，检测率可达92%以上，且在检测率和误检率2项指标上均优于传统基于学习的方法。

关键词: 自适应双阈值, 特征提取, 多特征融合, Fisher准则, 前向车辆检测

Abstract: A forward vehicle detection method based on multi-feature fusion is proposed in order to improve the accuracy of vehicle detection. The shadow and edge features of vehicle are segmented accurately by using histogram analysis method and adaptive dual-threshold method respectively. The initial candidates are generated by combining edge and shadow features and these initial candidates are further verified by using an integrated feature based on the fusion of symmetry, texture and shape matching degree features. A threshold is used to remove the non-vehicle initial candidates. Experimental results show that this method can adapt to different light conditions robustly with a detection rate over 92%. The proposed method is better than traditional methods based on learning with a higher detection rate and lower error rate.

Key words: adaptive dual-threshold, feature extraction, multi-feature fusion, Fisher criterion, forward vehicle detection

中图分类号:

TP18

李星，郭晓松，郭君斌. 基于多特征融合的前向车辆检测方法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2014.02.044.

LI Xing, GUO Xiao-song, GUO Jun-bin. Forward Vehicle Detection Method Based on Multi-feature Fusion[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2014.02.044.

https://www.ecice06.com/CN/Y2014/V40/I2/203

参考文献

参考文献 [1] WHO. World Report on Road Traffic Injury Prevention[EB/OL]. [2013-01-02]. http://www.who.int/violence_injury_prevention. [2] 公安部交通管理局. 2010年中华人民共和国道路交通事故统计年报[Z]. 2011. [3] Sun Zehang, Bebis G, Miller R. On-Road Vehicle Detection: A Review[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006, 28(5): 694-711. [4] Liu Xin, Dai Bin, He Hangen. Real-time On-Road Vehicle Detection Combining Specific Segmentation and SVM Classification[C]//Proc. of International Conference on Digital Manufacturing and Automation. Zhangjiajie, China: [s. n.], 2010. [5] Chen Chunting, Su Chung-yen, Kao Wen-Chung. An En- hanced Segmentation on Vision-Based Shadow Removal for Vehicle Detection[C]//Proc. of Conference on Green Circuits and Systems. [S. l.]: IEEE Press, 2010. [6] Song G Y, Lee K Y, Lee J W. Vehicle Detection by Edge- Based Candidate Generation and Appearance-Based Classi- fication[C]//Proc. of 2008 IEEE Intelligent Vehicles Symposium. Eindhoven, the Netherlands: IEEE Press, 2008. [7] Srinivasa N. A Vision-Based Vehicle Detection and Tracking Method for Forward Collision Warning[C]//Proc. of 2002 IEEE Intelligent Vehicle Symposium. Versailles, France: IEEE Press, 2002. [8] Bertozzi M, Broggi A, Fascioli A. Vision-Based Intelligent Vehicles: State of the Art and Perspectives[J]. Robotics and Autonomous Systems, 2000, 32(1): 1-16. [9] von Seelen W, Curio C, Gayko J E, et al. Scene Analysis and Organization of Behavior in Driver Assistance Systems[C]// Proc. of 2000 IEEE International Conference on Image Processing. Vancouver, Canada: IEEE Press, 2000. [10] Kate T, Leewen V, Ellenberger M, et al. Mid-range and Distant Vehicle Detection with a Mobile Camera[C]//Proc. of 2004 IEEE Intelligent Vehicles Symposium. Parma, Italy: IEEE Press, 2004. [11] Sun Zehang, Bebis G, Miller R. On-Road Vehicle Detection Using Gabor Filters and Support Vector Machines[C]//Proc. of 2002 IEEE International Conference on Digital Signal Processing. Santorini, Greece: IEEE Press, 2002. [12] Li Sun, Wang Bo, Zheng Zhihui, et al. Multi-View Vehicle Detection in Traffic Surveillance Combining HOG-HCT and Deformable Part Models[C]//Proc. of 2012 International Conference on Wavelet Analysis and Pattern Recognition. Xi’an, China: [s. n.], 2012. [13] 文学志, 方巍, 郑钰辉. 一种基于类Haar特征和改进Adaboost分类器的车辆识别算法[J]. 电子学报, 2011, 39(5): 1121-1126. [14] 李云翀, 何克忠, 贾培发. 基于阴影特征和Adaboost的前向车辆检测系统[J]. 清华大学学报: 自然科学版, 2007, 47(10): 1713-1716. [15] Foley D H, Sammon J W. An Optimal Set of Discriminant Vectors[J]. IEEE Trans. on Computers, 1975, 24(3): 281-289. 编辑金胡考

选择文件类型/文献管理软件名称

选择包含的内容

基于多特征融合的前向车辆检测方法

Forward Vehicle Detection Method Based on Multi-feature Fusion

PDF

可视化

被引次数

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

本文评价

[1]	赵俊涛, 李陶深, 卢志翔. 基于最优近邻的局部保持投影方法[J]. 计算机工程, 2024, 50(9): 161-168.
[2]	钱清, 龙永, 蒋忠远, 段春红, 王宏. 基于深度强化学习的自适应图像隐写算法[J]. 计算机工程, 2024, 50(8): 319-327.
[3]	胡庆. 多尺度融合与双输出U-Net网络的行人重识别[J]. 计算机工程, 2024, 50(6): 102-109.
[4]	梁松林, 林伟, 王珏, 杨庆. 面向后渗透攻击行为的网络恶意流量检测研究[J]. 计算机工程, 2024, 50(5): 128-138.
[5]	李振鲁, 黄威, 孙锴. 复杂环境下的轻量化道路目标识别算法研究[J]. 计算机工程, 2024, 50(4): 219-227.
[6]	袁文涛, 卫文韬, 高德民. 融合注意力机制的多视图卷积手势识别研究[J]. 计算机工程, 2024, 50(3): 208-215.
[7]	谢帅康, 熊风光, 朱新杰, 宋宁栋, 李文清, 王廷凤. 基于空间可变形Transformer的三维点云配准方法[J]. 计算机工程, 2024, 50(3): 224-232.
[8]	任义, 苏博, 袁帅. 教育领域下多维度特征命名实体识别方法[J]. 计算机工程, 2024, 50(10): 110-118.
[9]	马娜, 温廷新, 贾旭, 李晓会. 复杂光照条件下自适应的车脸重识别模型[J]. 计算机工程, 2023, 49(8): 275-282, 290.
[10]	戴浩磊, 黄永慧, 周郭许. 基于超图正则化非负张量链分解的聚类分析[J]. 计算机工程, 2023, 49(6): 81-89.
[11]	宋羽凯, 谢江. 基于多任务学习的轻量级语音情感识别模型[J]. 计算机工程, 2023, 49(5): 122-128.
[12]	霍跃华, 赵法起. 基于Stacking与多特征融合的加密恶意流量检测[J]. 计算机工程, 2023, 49(5): 165-172,180.
[13]	陈文轩, 曾碧, 郭植星. 融合多特征与语义图卷积网络的摔倒检测方法[J]. 计算机工程, 2023, 49(5): 277-285,294.
[14]	张博熠, 者甜甜, 赵新旭, 刘庆华, 王家晨. 基于眼嘴状态识别网络的疲劳驾驶检测[J]. 计算机工程, 2023, 49(5): 310-320.
[15]	关日鹏, 况立群, 焦世超, 熊风光, 韩燮. 多模态特征融合与词嵌入驱动的三维检索方法[J]. 计算机工程, 2023, 49(4): 101-107,113.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于多特征融合的前向车辆检测方法

Forward Vehicle Detection Method Based on Multi-feature Fusion

PDF

可视化

被引次数

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

本文评价