复杂交通场景中采用稀疏表示的车辆识别方法  

Sparse representation method of vehicle recognition in complex traffic scenes

作　　者：李修志[1] 吴健[1,2] 崔志明[1,2] 陈建明[1,2] 

机构地区：[1]苏州大学智能信息处理及应用研究所,苏州215006 [2]江苏怡和科技股份有限公司,苏州215002

出　　处：《中国图象图形学报》2012年第3期387-392,共6页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60970015);2009年江苏省省级现代服务业(软件产业)发展专项引导资金项目([2009]332-64);苏州市应用基础研究(工业)项目(SYJG0927;SYG201032);苏州大学科研预研基金项目

摘　　要：针对智能交通系统中复杂交通场景下对于车辆识别的难点问题,提出一种基于方向梯度直方图特征和稀疏表示的车辆目标识别方法。该方法首先使用方向梯度直方图特征分别提取训练样本和待测目标信息,通过稀疏表示的方法将训练样本训练为过完备字典,最后通过待测目标在字典中稀疏度和重构残差判定目标是否为车辆并对其标注。实验结果表明,提出的方法在粘连遮挡、目标类别多样等复杂交通场景中有较好的识别率和实时性。For Jintelligent transportation systems, vehicle recognition in complex traffic scenes is a key issue. In this article, a novel scheme using （HOG） features and sparse representation target recognition for vehicle recognition in complex traffic scenes is proposed. Our method uses the HOG to extract features from samples and candidate targets, and then wses trained samples as an overcomplete dictionary based on sparse representation. Finally, candidate targets are recognized by computing sparsity and reconstruction residuals in the dictionary. Experiment results show that the proposed scheme provides, higher recognition preciseness in real time, even in complex traffic scenes such containing occlusion and a large variety of target classes.

关 键 词：稀疏表示 方向梯度直方图 车辆识别 智能交通 压缩感知 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]