Research and Application of Traffic Visualization Based on Vehicle GPS Big Data
GPS data of vehicle on the road can reflect the actual road status, its analysis can be help to urban road planning, but the multi-source, mass and high dimension features of GPS big data has restricted its application for road traffic. Aiming that, a GPS
- PDF / 469,329 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 38 Downloads / 215 Views
Abstract GPS data of vehicle on the road can reflect the actual road status, its analysis can be help to urban road planning, but the multi-source, mass and high dimension features of GPS big data has restricted its application for road traffic. Aiming that, a GPS big data visual computation architecture has been design in this paper, speed attribute and two-pass corner detection has been introduce to improve map matching and clustering analysis methods. Vehicle GPS data of Zibo city has been selected as the case, the relevant result shows that the improved methods can be effective and visual, and can get a better effect than flow map method for vehicle GPS big data processing. Keywords Visual analysis algorithm Traffic data
GPS big data Clustering analysis Map-matching
1 Introduction With the continuous development of urban traffic and positioning technology, the increasing of vehicle has leaded to a explosive growth of trajectory data, it is important that how to induce information and rules from these complex data in order to service urban transportation development [9]. Visualization method mentioned in this paper mainly is used to grasp the whole scene of the massive GPS trajectory data, help users to balance conflicts, and get the implicit knowledge data to improve road traffic planning. Tobler [8] has studied the flow map, finished population migration map based on the population data from 1965 and 1970. Kapler has exploited the development of visualization software called GeoTme [4], which can show each attribute of the trajectory data and track incidents involving a particular attribute, this method not X. Wang S. Zhao (&) L. Dong School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou, China e-mail: [email protected] © Springer Science+Business Media Singapore 2017 H. Lu (ed.), Proceedings of the Second International Conference on Intelligent Transportation, Smart Innovation, Systems and Technologies 53, DOI 10.1007/978-981-10-2398-9_27
293
294
X. Wang et al.
only can not break the trajectory space attribute features but also introduce the time attribute, this method makes utilizing trajectory data fully to be possible.
2 Visualization Algorithm Architecture 2.1
Map Matching
Vehicle GPS (Global Position System) trajectory data needs to be rebuilt and calibrated before its visualization [10], and then its attributes, such as space, time, and others can be visualized. Map matching is a kind of technology which can make use of network information to modify the original track data, the basic idea of this method aims to serialize vehicle position by comparing with the electronic position data of road network, and acquire the related location in the road electronic map. The process includes the trajectory data rebuilding, data cleaning, data saving, and so on. Generally vehicle GPS data acquired at first time have some features, such as poorer accuracy, serious loss signal, massive volume, and lower sampling rate. All these features makes it difficult to locate veh
Data Loading...
