基于像斑异质度的矢量图与遥感影像变化检测

A change detection method for vector map and remote sensing imagery based on object heterogeneity

为实现矢量图与遥感影像的自动变化检测,提出一种基于像斑异质度的矢量图与遥感影像变化检测方法。以旧时期矢量图为约束,对新时期遥感影像采用标记分水岭算法进行影像分割获取像斑;提取兼顾光谱特征与纹理特征的像斑直方图作为像斑的特征,利用直方图相交距离构建像斑特征距离;利用新时期像斑与旧时期同类别像斑特征距离的平均值计算像斑的异质度,采用最大熵法自动获取各地物类别的异质度阈值;通过比较像斑异质度与矢量图所在时期对应类别的异质度阈值,实现像斑的变化/未变化判别。对QuickBird遥感影像的实验验证了所提方法的有效性,变化检测正确率达到了95%。

In order to realize the automatic change detection with vector map and remote sensing imagery,a change detection method based on the object heterogeneity for vector map and remote sensing imagery is proposed in the paper. Image segmentation under the constraint of vector map was employed to get image objects using marker-based watershed algorithm. The features of the object were extracted by histogram which describes both gray feature and texture feature. The histogram intersection distance was adopted to measure the feature distance. The object heterogeneity was built by the average of the distance between the object and the other objects with the same class in old period. Change/nochange label of the objects can be determined by comparison the object heterogeneity with the heterogeneity threshold of the class which was calculated by Maximum Entropy Principle automatically.Experiments on Quick Bird remote sensing images verified the effectiveness of the proposed method,and the correct rate of the change detection is up to 95%.