面向矢量路网的自适应紧凑二维图像表达方法

Compact 2D Image Representation Method for Urban Road Networks

矢量路网的二维图像表达旨在建立道路到图像的转化关系,对于道路交通流预测等实际问题具有重要研究价值。针对目前研究存在的空间拓扑关系丢失和图像分辨率不易确定等问题,提出了一种矢量路网的自适应二维图像表达方法。该方法能够自适应不同路网结构,在最大维持矢量路网拓扑关系的前提下,将道路路段一一映射到像素单元上,从而生成矢量路网的紧凑二维图像。选取国内外数百个城市不同类型的矢量路网对算法的性能进行验证,通过与随机编码和顺序编码的结果进行对比,证明了该方法的有效性与合理性。

The 2D image representation of road network aims to establish a road-to-image transformation relationship,which is valuable for many transportation prediction problems such as road traffic flow prediction. However, current studies to represent road network can be affected by the topological relationship loss problem and the spatial resolution problem.Thus, a 2D image representation method for road network is proposed. The method can be adapted to road networks with different spatial structures and can derive a compact 2D image from the road network by mapping the individual road segments into the corresponding image pixels in terms of maintaining their topological relationships in a large extent.Experiments are conducted to evaluate the performance of the method in hundreds of urban road networks at home and abroad, and the results suggest the effectiveness and superiority of the proposed method by comparing with random coding and sequential coding.