基于车型识别的卡口系统的研究和应用-电子与通信工程专业论文.docxVIP

Abstract A vehicle classification system is designed and implemented in the thesis. And the system includes two main steps: establishment of the sample library and vehicle classification. In the establishment of the sample library step, first, doing the image pre-processing, then using the time average image approach to get the background model, and then, in complex scene, using the background difference approach to detect and extract the outline of the moving vehicle, furthermore get the left, right and bottom edge of vehicle face according to the left, right and bottom edge of the outline, then, in the scene, select the same height threshold of the vehicle face and locate the vehicle face height. By processing the vehicle face image size normalized, the vehicle face image sample library is built. In the vehicle classification step, first, vehicle face images are extracted by the above ways, then calculates the vehicle face sift features and compare with the sift features of the sample library. When the matching values satisfy certain conditions the vehicles can be determined to be the same type of vehicle. The experimental platform is built with OpenCV and Visual C++, the vehicle face feature library is constructed by using 100 vehicles face in this thesis. In the experiment, adopting the size of 80*30 for vehicle face, the average time of one vehicle classification is about 150 ms in the system, when adopting the size of 160*60 and 320*120, the time is about 450 ms and 1400 ms respectively. The experimental results show the feasibility performance of the system, and in practical applications can get high recognition rate. Keywords: Vehicle Classification Vehicle Face Library Sift Feature 目录 第一章 绪论 1 1.1 课题研究的目的和意义 1 1.2 国内外研究现状 2 1.3 本文的主要研究内容 4 第二章 视频图像预处理 5 2.1 彩色图像的灰度化 5 2.2 图像噪声的减除 6 2.2.1 均值滤波器 6 2.2.2 高斯平滑滤波器 8 2.2.3 中值滤波器 8 2.3 灰度图像的二值化 9 2.4 基于数学形态学的图像处理技术 11 2.4.1 腐蚀与膨胀 11 2.4.2 开启与闭合 12 2.5 本章小结 12 第三章 运动目标检测与提取 13 3.1 引言 13 3.2 光流法 14