利用相似性比较提取车轮图像  

Similarity Based Picking Images Containing Whole Wheel

作　　者：周焰[1] 李德仁[1] 

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室

出　　处：《计算机辅助设计与图形学学报》2003年第12期1468-1471,1478,共5页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(4 0 10 10 19;40 0 2 3 0 0 4);测绘遥感信息工程国家重点实验室开放研究基金(WKL(0 0 ) 0 10 2 )资助

摘　　要：提出一种从大量的列车序列图像中提取包含完整车轮的清晰图像的方法 采用两级分析的方法 ,首先利用直方图交叉方法比较标准图像与候选图像之间的直方图相似度 ;然后用小波变换对图像进行多尺度分解 ,从小波系数中计算图像的各个方向边缘特征 ;最后将这两种特征结合起来 ,将那些满足阈值条件的图像选择出来 实验和实际应用表明 。Examining wheel images is needed for train's safe running Based on computation of image similarity, a method is introduced to pick a few available images for examination from a series of train's images, in which the whole and clear wheels are contained First, histogram is calculated and histogram intersection is adopted to evaluate the histogram similarity between the standard image and candidates, then a multi resolution decomposition using Haar wavelet is applied, several statistical features of wheel edge based on wavelet coefficients are obtained and similarity comparison on the features is undertaken These two kinds of similarity are combined to synthetically predict the similarity between two images Finally, those images satisfying threshold are picked for examination Experiments show useful wheel images can be acquired efficiently by this method

关 键 词：列车 安全运行 车轮图像 相似性 图像检测 边缘特征 图像提取 颜色特征 小波变换 

分 类 号：U292.4[交通运输工程—交通运输规划与管理] TP391.41[交通运输工程—道路与铁道工程]