基于众源轨迹数据的行人路网提取

目前,导航位置服务应用提供的路线大多基于机动车道路网数据,难以满足行人导航的需求,有无完备的行人道路网络成为制约行人导航应用的重要因素,因此,本文提出了一种基于莫尔斯理论的行人路网提取方法.首先对轨迹进行预处理,清除轨迹数据中的冗余和噪声,并对原始轨迹进行合理分割,形成清晰的轨迹集合;然后利用莫尔斯理论,对步行轨迹密度...

Pedestrian road network extraction based on crowdsourcing trajectory data

At present,the routes provided by the navigation location service application are mostly based on the data of the vehicle road network,which is difficult to meet the needs of pedestrian navigation. The complete pedestrian network has become an important factor restricting the application of pedestrian navigation. Therefore,this paper proposes a pedestrian network extraction method based on Morse theory. First,the trajectory is preprocessed to remove redundancy and noise in the trajectory data,and the original trajectory is divided reasonably to form a clear trajectory set. Secondly,Morse theory is used to extract the"ridgeline"in the density map of walking track and reconstruct the pedestrian network. The experimental analysis uses the walking GPS track data of Shenzhen university campus to extract the pedestrian network. By qualitative and quantitative comparison of the extracted pedestrian network results with Open Street Map( OSM) data,the effectiveness of the method in this paper is verified. At the same time,compared with the current typical road network extraction methods,the proposed method can extract high quality pedestrian network.