摘要
针对航拍图像中水上桥梁目标的自动识别问题,提出了基于区域特征的水上桥梁自动识别算法。首先对航拍图像进行基于梯度均方差的图像二值化;再进行基于像素密度的二值图像去噪;然后进行基于像素的二值图像连通区域标记,区域标记算法采用6邻域连通规则进行标识,能够有效获取水域的区域特征;最后进行桥梁的精确提取。实验结果表明,该算法能够有效地识别低对比度、低空侧拍等复杂航拍图像中的水上桥梁目标。
Addressing the automatic recognition problem of a bridge above water in aerial im- ages, an automatic recognition algorithm for a bridge above water in aerial image based on regional features is proposed. Firstly, aerial image binarization is executed based on the gra- dient mean square variance. The image noises are then removed based on pixel density. Next, the connective regions are labeled according to the pixels in binary image with a six neighborhood connection rule to obtain the water regional feature. Finally, the bridge is ex- tracted. Experiments show this algorithm is effective for automatic recognition of a bridge a- bove water in low-contrast aerial images taken at low altitudes.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2013年第9期1073-1077,共5页
Geomatics and Information Science of Wuhan University
基金
湖北省自然科学基金资助项目(2011CDC023)
关键词
航拍图像
桥梁识别
区域分割
区域标记
梯度均方差
aerial image
bridge recognition~ region segmentation~ region labeling~ gradientmean square variance
