彩色扫描地形图中等高线提取方法的研究

A Study of Contour Lines Extraction from Color Scanned Topographical Maps

提出了一种从彩色扫描地形图中提取等高线的方法,重点研究并解决等高线的断裂问题。其中,在地形图彩色分割方面,采用本征向量拟合算法计算各类地图符号(包括等高线)样本的颜色特征,以用于克服地形图在扫描过程中出现的颜色混淆和错误现象。在等高线断裂连接方面,提出了针对不同原因造成的断裂用不同的方法连接,并利用线状符号灰度分割结果来改善等高线彩色分割结果的方法。一方面对一些有代表性的地形图样本的提取结果进行了定性描述,另一方面则将该方法用于1∶5万国家标准地形图上等高线的提取,通过对结果的定量评价表明,该方法具有一定的实用性。

Contour lines are the most important features to characterize three-dimensional terrain on two-dimensional map sheets. Different from a well-conditioned map, aliasing and false colors in the scan of a common-conditioned map are so serious that when to segment contour lines from it, many gaps due to contour lines intersecting and overlapping with other features become more intricate. In this paper an effective method for extracting contour lines from color scanned topographical maps is proposed. It focuses on reconnecting gaps of contour lines. In topographical maps segmentation, an eigenvector-fitting algorithm is used for computing the color keys of map features（ include contour lines） and the phenomena of color-alias and color-misalignment are greatly reduced. In contour lines reconnection, linear features extracted from the gray version of the input color map are utilized to repair the contour lines segments extracted from the input color map. Unlike the existing methods, it introduces corresponding solutions for different cases of gaps in contour lines. Finally, some representative samples and national standard topographic maps with a scale of 1：50,000 are tested, and an evaluation scheme for the results is provided. The experiments indicate good applicability of this method in applications.