Redirigiendo al acceso original de articulo en 21 segundos...
ARTÍCULO
TITULO

Road Intersection Recognition via Combining Classification Model and Clustering Algorithm Based on GPS Data

Yizhi Liu    
Rutian Qing    
Yijiang Zhao and Zhuhua Liao    

Resumen

Road intersections are essential to road networks. How to precisely recognize road intersections based on GPS data is still challenging in intelligent transportation systems. Road intersection recognition involves detecting intersections and recognizing its scope. There are few works on intersections? scope recognition. The existing methods always focus on road intersection detection. It includes two parts: one is selecting turning points from GPS data and extracting their geometric features, another is clustering them into center coordinates of road intersections. However, the accuracy of road intersection detection still has improvement room due to two drawbacks: (1) Besides geometric features, spatial features explored from GPS data and the interactions among all features are also important to represent intersections? semantics more accurately, and (2) How to capture the points around intersections for clustering has great impact on the accuracy of intersection detection. To solve the preceding problems, we propose a novel approach for road intersection recognition via combining a classification model and clustering algorithm based on GPS data, which involves detecting the center coordinate and computing the radius of the intersection. Firstly, we distil geometric features and spatial features from historical GPS points. These features are inputted into the Extreme Deep Factorization Machine (xDeepFM) model which is applied for capturing the GPS points nearby road intersections. Secondly, the preceding points are clustered into center coordinates of road intersections by the Density-Based Spatial Clustering of Applications with Noise algorithm (DBSCAN). Thirdly, we present a new method of radius computing by integrating Delaunay triangulation with circle shape structure. Experiments are carried out on the GPS data of Chengdu, China. Compared with some state-of-the-art methods, our approach achieves higher accuracy on road intersection recognition based on GPS data. The precision, recall, and f-measure of our proposed center coordinates detection method are respectively 99.0%, 92.7%, and 95.8% when the matching area?s radius is 30 m. Moreover, the error of the proposed radius calculation method is less than 26.5%.

 Artículos similares

       
 
Lin Qu, Yue Zhou, Jiangxin Li, Qiong Yu and Xinguo Jiang    
Map matching of trajectory data has wide applications in path planning, traffic flow analysis, and intelligent driving. The process of map matching involves matching GPS trajectory points to roads in a roadway network, thereby converting a trajectory seq... ver más

 
Jianing Ding, Xin Jin and Zhiheng Li    
The Time-Period-Based Most Frequent Path (TPMFP) problem has been a hot topic in traffic studies for many years. The TPMFP problem involves finding the most frequent path between two locations by observing the travelling behaviors of drivers in a specifi... ver más

 
Surya Michrandi Nasution, Emir Husni, Kuspriyanto Kuspriyanto and Rahadian Yusuf    
Indonesia has the third highest number of motorcycles, which means the traffic flow in Indonesia is heterogeneous. Traffic flow can specify its condition, whether it is a free flow or very heavy traffic. Traffic condition is the most important criterion ... ver más

 
Abdelmajid Erramaline, Thierry Badard, Marie-Pier Côté, Thierry Duchesne and Olivier Mercier    
GPS trajectories collected from automotive telematics for insurance purposes go beyond being a collection of points on the map. They are in fact a powerful data source that we can use to extract map and road network properties. While the location of road... ver más

 
Calimanut-Ionut Cira, Martin Kada, Miguel-Ángel Manso-Callejo, Ramón Alcarria and Borja Bordel Sanchez    
The road surface area extraction task is generally carried out via semantic segmentation over remotely-sensed imagery. However, this supervised learning task is often costly as it requires remote sensing images labelled at the pixel level, and the result... ver más