基于水平集演化和支持向量机分类的高分辨率遥感图像自动变化检测

Automatic Change Detection of High Resolution Remote Sensing Images Based on Level Set Evolution and Support Vector Machine Classification

提出了基于水平集演化和支持向量机(SVM)分类的高分辨率遥感图像变化检测方法,该方法将像素级的和对象级的变化检测方法相结合,运用了像素特征和对象特征以提高变化类和非变化类的准确率。在像素级上,变化检测问题转化为水平集演化的图像分割问题。在对象级上,本文可以从分割结果中为SVM分类器自动地选择潜在的训练样本。最终将基于像素级的变化和基于对象级的变化相结合得到最终的变化结果。所提出的方法的主要优势在于可以自动选择合适的样本进行SVM分类器训练。此外,提出的方法可以有效的提高精确度和自动化水平。通过SPOT5图像和航空图像进行实验,结果表明该方法是有效的。

We propose a method for change detection in high-resolution remote sensing images by means of level set evolution and Support Vector Machine(SVM)classification,which combined both pixel-level method and object-level method.Both pixel-based change features and object-based ones are extracted to improve the discriminability between the changed class and the unchanged class.At the pixel-level,the change detection problem is formulated as a segmentation issue using level set evolution in the difference image.At the object-level,potential training samples are selectedfrom the segmentation results without manual intervention into SVM classifier.Thereafter,the final changes are obtained by combining the pixel-based changes and the object-based changes.A chief advantage of our approach is being able to select appropriate samples for SVM classifier training.Furthermore,our proposed method helps improving the accuracy and the degree of automation.We systematically evaluated it with a variety of SPOT5 images and aerial images.Experimental results demonstrated the accuracy of our proposed method.