面向对象的投影互分割道路变化检测

Road Change Detection Using Object-oriented Projective Interactive Partition

通过实验提出了面向对象的投影互分割城市道路变化检测方法。选用不同时相的QuickBird图像,根据地物影像的光谱、形状及纹理等特征进行多尺度分割和层次分类,提取城市道路目标;建立检测层,将不同时相的图像分类结果投影到检测层的相应对象层上,并进行互分割,通过判断某一位置地物类别的一致性,实现道路变化检测的目的。实验表明,面向对象的投影互分割道路变化检测能得到较好的检测效果。

In this paper the authors present an object - oriented change detection method which uses projective interactive partition to detect the change of the urban road. The QuickBird images acquired in different years were used in the experiment, on which multi - scale segmentation and hierarchical classification were carried out for urban road extraction according to the spectrum, shape and texture features. Then the object layers were established in the same detection, and they were the projection layers taking over the classification results of asynchrony images. Interactive partition was also realized on these layers. Finally the change detection results were achieved after judging the consistency of land feature categories. The experiment results show that the method of object - oriented change detection using projective interactive partition can extract and detect the urban road effectively.