作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 图形图像处理 • 上一篇    下一篇

基于LLC与加权SPM的车辆品牌型号识别

李熙莹  1,2,3,袁敏贤 1,2,3,吕硕 1,2,3,江倩殷 1,2,3   

  1. (1.中山大学 工学院 智能交通研究中心,广州 510006; 2.广东省智能交通系统重点实验室,广州 510006;3.视频图像智能分析与应用技术公安部重点实验室,广州 510006)
  • 收稿日期:2016-04-11 出版日期:2017-05-15 发布日期:2017-05-15
  • 作者简介:李熙莹(1972—),女,副教授,主研方向为图像处理、目标检测与跟踪;袁敏贤,硕士研究生;吕硕、江倩殷,硕士。
  • 基金资助:

    国家科技支撑计划项目(2014BAG01B04)。

Vehicle Make and Model Recognition Based on LLC and Weighted SPM

LI Xiying  1,2,3,YUAN Minxian  1,2,3,LÜ  Shuo  1,2,3,JIANG Qianyin  1,2,3   

  1. (1.Research Center of Intelligent Transportation System,School of Engineering,Sun Yat-Sen University,Guangzhou 510006,China;2.Guangdong Provincial Key Laboratory of Intelligent Transportation System,Guangzhou 510006,China;3.Key Laboratory of Video and Image Intelligent Analysis and Application Technology,Ministry of Public Security,Guangzhou 510006,China)
  • Received:2016-04-11 Online:2017-05-15 Published:2017-05-15

摘要:

针对传统车辆识别算法鲁棒性及实时性不强的问题,结合局部线性约束编码(LLC)和加权空间金字塔匹配(SPM)模型,提出一种车辆品牌型号精细识别算法。提取图像方向梯度直方图特征,通过LLC对图像特征进行编码映射,得到具有语义信息的图像表达向量,以提高识别的准确率。利用加权SPM模型将空间位置信息引入图像表达向量中,并将每个图像的最终表达送入线性支持向量机分类器进行训练与识别。使用交通监控摄像头在不同天气和光照条件下采集150种车辆类型共56 827张图像进行实验,结果表明,该算法可有效改善识别效果,提高识别速度。

关键词: 车辆品牌型号识别, 方向梯度直方图, 局部约束线性编码, 加权空间金字塔匹配, 支持向量机

Abstract:

In order to enhance the robustness and the instantaneity of the traditional vehicle recognition algorithms,a fine vehicle make and model recognition algorithm is proposed by incorporating Locality-constrained Linear Coding(LLC) and the weighted Spatial Pyramid Matching(SPM) model.Firstly,the Histogram of Oriented Gradient(HOG) feature is extracted to obtain the image representation vector which improves the recognition accuracy.Then the weighted SPM is applied to integrate the spatial information of vehicle images into their final representation vector.Finally,the final representation of vehicle images generated by above steps is sent to a linear Support Vector Machine(SVM) classifier for training and testing.Experiments are conducted on 56 827 vehicle images coming from 150 vehicle makes and models which are captured by real-time traffic surveillance system in various weather conditions and illuminations.The results demonstrate that the proposed algorithm has better performance both in recognition accuracy and the recognition time.

Key words: vehicle make and model recognition, Histogram of Oriented Gradient(HOG), Locality-constrained Linear Coding(LLC), weighted Spatial Pyramid Matching(SPM), Support Vector Machine(SVM)

中图分类号: