彩色扫描地图中线目标的矢量化方法

Vectorization of Linear Features on Color Scanned Topographic Maps

地图要素的矢量化是从扫描地图中获取地理信息的重要问题之一.通过分析彩色扫描地图的颜色特征,提出了一种线目标半自动矢量化的方法.该方法通过在用户选择的线目标上加一个滑动窗,采用颜色空间转换、K-均值聚类和区域生长相结合的方法对窗口内的当前线目标进行自适应分割;再通过不断地沿前进方向移动窗口和对窗口内的线目标进行分割、细化及序贯跟踪,来完成线目标的矢量化.实验结果表明,文中方法快速、准确、适应性强,对于低对比度、低信噪比的彩色扫描地图尤为有效.

Cartographic feature vectorization is one of the most salient problems in the acquisition of geographic information from scanned topographic maps. This paper presents a novel semi-automatic approach to linear feature vectorization based on the analysis of color scanned topographic map features. By the approach, a sliding window is added on a user-given linear feature, and the current linear feature in the window is segmented self-adaptively by using color space conversion, K-means clustering and region growing. The linear feature is vectorized through moving the window continuously along the forward direction, image segment, thinning and sequential tracking. Experimental results show that linear features can be vectorized rapidly and accurately by using the proposed approach, and good robustness can be obtained, especially for color scanned topographic maps with lower contrast and lower SNR.