光谱特征分析的城市道路提取

道路是城市中典型的人造地物。利用高分辨率影像进行城市道路提取，对城市规划、交通发展具有重要意义。由于地物光谱的混淆性和异质性，利用传统基于光谱的分类方法很难将道路与其他城市地物区分开。针对这一问题，提出了一种利用道路边缘结构信息进行分类的方法，边缘作为光谱衍生信息对线性地物(如，道路等)识别具有明显的意义。首先，根据全色光谱波段纹理信息，利用改进的自适应Mean Shift算法进行边缘检测，最大限度减少噪声与伪边缘;然后，对边缘图像中的线段进行编组，利用统计模型依次对边缘线段求取统计特征，并将该统计特征与多光谱特征结合作为总分类特征;最后，利用监督学习方法对城市道路样本进行学习并对整个实验区域进行分类。结果表明将光谱信息与边缘统计特征融合对道路的识别精度为93%，相比传统方法78%的精度有显著的提高，因此，该方法是一种有效、可行的高分辨率遥感图像城市道路提取方法。

Road Extraction in Remote Sensing Images Based on Spectral and Edge Analysis

Roads are typically man-made objects in urban areas. Road extraction from high-resolution images has important applications for urban planning and transportation development. However, due to the confusion of spectral characteristic, it is difficult to distinguish roads from other objects by merely using traditional classification methods that mainly depend on spectral information. Edge is an important feature for the identification of linear objects (e. g., roads). The distribution patterns of edges vary greatly among different objects. It is crucial to merge edge statistical information into spectral ones. In this study, a new method that combines spectral information and edge statistical features has been proposed. First, edge detection is conducted by using self-adaptive mean-shift algorithm on the panchromatic band, which can greatly reduce pseudo-edges and noise effects. Then, edge statistical features are obtained from the edge statistical model, which measures the length and angle distribution of edges. Finally, by integrating the spectral and edge statistical features, SVM algorithm is used to classify the image and roads are ultimately extracted. A series of experiments are conducted and the results show that the overall accuracy of proposed method is 93% comparing with only 78% overall accuracy of the traditional. The results demonstrate that the proposed method is efficient and valuable for road extraction, especially on high-resolution images.