Vehicle detection based on information fusion of vehicle symmetrical contour and license plate position  

基于车辆轮廓对称与车牌定位信息融合的车辆检测方案(英文)

作　　者：连捷[1] 赵池航[1] 张百灵[2] 何杰[1] 党倩[1] 

机构地区：[1]东南大学交通学院,南京210096 [2]西交利物浦大学计算机与软件工程系,苏州215123

出　　处：《Journal of Southeast University(English Edition)》2012年第2期240-244,共5页东南大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No. 40804015,61101163)

摘　　要：An efficient vehicle detection approach is proposed for traffic surveillance images, which is based on information fusion of vehicle symmetrical contour and license plate position. The vertical symmetry axis of the vehicle contour in an image is. first detected, and then the vertical and the horizontal symmetry axes of the license plate are detected using the symmetry axis of the vehicle contour as a reference. The vehicle location in an image is determined using license plate symmetry axes and the vertical and the horizontal projection maps of the vehicle edge image. A dataset consisting of 450 images （15 classes of vehicles） is used to test the proposed method. The experimental results indicate that compared with the vehicle contour-based, the license plate location-based, the vehicle texture-based and the Gabor feature-based methods, the proposed method is the best with a detection accuracy of 90.7% and an elapsed time of 125 ms.为了有效地定位交通监控图像中的车辆区域,提出了一种基于车辆轮廓对称和车牌定位信息融合的车辆检测方法. 该方法首先检测图像中的车辆轮廓竖直对称轴,然后以车辆轮廓对称轴位置为基准检测车牌水平和竖直对称轴,最后根据车牌横纵对称轴和车辆轮廓图像的水平、竖直投影进行车辆区域定位. 以450 张 15 类车型的图片为测试集进行了基于对称特征融合的车辆区域检测,并与基于车辆边缘、车牌、车辆纹理特征和车辆图像 Gabor 特征的 4 种方法进行了对比,实验结果表明基于车辆轮廓对称与车牌对称特征融合的车辆区域检测方法最优,其检测率和检测时间分别为 90. 7%和 125 ms.

关 键 词：vehicle detection symmetrical contour license plate position information fusion 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]