基于多特征结合的损毁建筑物检测

针对震后高分辨率遥感图像的建筑物损毁区域,提出一种基于多特征结合的损毁建筑物检测方法。首先使用形态学属性剖面(MAP)与局部二值模式(LBP)算子提取图像中的几何特征与纹理特征;然后使用随机森林(RF)分类器提取损毁的建筑物,形成初步结果;最后针对分割的对象,根据对象损毁像元所占的比例获取最终的损毁建筑物区域。采用空间分辨率为0.1 m的玉树震后航空遥感图像进行实验。结果表明,该方法的总体精度比基于形态学剖面(MP)的方法提高了12%,能够有效检测高分辨率震后遥感图像中的损毁建筑物区域。

Building-damage detection based on combination of multi-features

To detect building-damage areas in post-seismic high-resolution remote sensing images, a building-damage detection method based on multi-features was proposed. Firstly, Morphological Attribute Profile (MAP) and Local Binary Pattern (LBP) operator were used to extract geometric features and texture features. Then, Random Forest (RF) classifier was applied to extract damaged building regions so as to form the preliminary results. At last, for segmented objects, the ultimate building-damage area was obtained by computing the damaged ratio of each object. Experiments were carried out on Yushu post-seismic aerial remote sensing images whose spatial resolution was 0.1 m. Results show that this method improves overall accuracy by 12% compared with Morphological Profile (MP)-based method. The results indicate that the proposed method can effectively detect building-damage areas with high accuracy in post-seismic high-resolution images.