Real-time road information plays a crucial role in enabling intelligent transportation systems (ITS) applications. With sufficient road information, the map of road topography can be built and updated more easily. Furthermore, many appealing ITS applications can be enabled accordingly. Aiming at improving the quality and update rate of road information, a hot topic today is how to mine information from global positioning systems (GPS) trajectories by the clustering-based methods. Such schemes, however, encounter two challenges: 1) GPS noise and 2) low sampling rate of GPS traces data. As a result, it is difficult to infer road information from these irregular clusters. To tackle the above issues, we directly mine useful road information, heading, and width of roads, for ITS applications from GPS point cloud, i.e., a set of GPS points. First, the distribution of GPS points is discussed and the least squares method (LSM) is demonstrated to be outstanding for mining the heading of the road under a huge number of GPS points. Second, the weighted approximation least squares method is proposed to improve the accuracy of the LSM. Furthermore, combining with relevant distribution features in GPS points, the data distribution variance-road width discrete model is proposed to mine road width from GPS point cloud. Finally, using real-world datasets, we demonstrate that these proposed methods can achieve satisfactory performance in practice.
INDEX TERMSIntelligent transportation systems, road information, GPS data, data mining.The associate editor coordinating the review of this manuscript and approving it for publication was Zhong-Ke Gao.
Chen et al.[10] apply a clustering-based method to mine road information from GPS data, aiming to reconstruct accurate digital maps for autonomous driving. Therefore, aiming to popularize intelligent transportation systems, it is necessary to improve data accuracy and timeliness of road information.Traditionally, this crucial road information is obtained through ground measurement [11]. It means moving devices equipped with sensors and visual systems are used to collect original information of road segments. This ground measurement is regarded as a time-consuming and expensive method. Recent years, with the research on ad hoc network, various individual mobile devices, such as unmanned aerial vehicles and robots [12], can collect road information simultaneously and share it with each other in this network. This way is effective to improve the collection rate for road information.
