A Heuristic Map-Matching Algorithm by Using Vector-Based Recognition

Abstract

The traditional map-matching algorithms mainly use two methods: the incremental method and the global method. Both of them have advantages and disadvantages of themselves: while the global map-matching algorithm produces better matching results, the incremental algorithm produces results of lower quality faster. All things considering the two traditional algorithms, this paper proposes a heuristic map-matching algorithm by using vector-based recognition. Firstly, the algorithm uses the heuristic search method which is similar to A* algorithm, and it makes use of geometric operation to form the restriction, and make the comparison between the vector formed with the vehicular GPS points and the special road network to heuristicly search and select the vehicular possible traveling routes. Secondly, it globally compares the vehicular every possible route by calculating the map-matching weight, and then chooses the optimal one. The result of testing demonstrates the efficiency of the algorithm both at accuracy and computational speed when handling the large-scale data of GPS tracking data even under the complex road network conditions.

An FCD Compensation Model Based on Traffic Condition Trends Matching

“…In HFCD, a lot of data do not reflect the real traffic condition of links as a result of the erratic driving and some special driving character [8] of floating cars, and the affect of traffic incident. This data is called abnormal data in this paper.…”

“…In this paper, compensating vacant information is performed to every road of road networks [8], in this section, some related definition about road and the VICM is given.…”

A heuristic path-estimating algorithm for large-scale real-time traffic information calculating

“…To improve the search efficiency, the heuristic search idea is introduced where the path search tree is defined as Ps-T. Ps-T=(U, A), (6) where U is non-empty sub-set of the V in the network topology G(R n )=(V, E), A is the relations between the edges in the U set. …”

“…Third, we compare the vectors consisting of the vehicular tracking points with the road network, use the geometric theory of the triangle as the restraint, adopt the heuristic graph search method to search the set of vehicular traveling route candidates, and improve the computing speed of the algorithm. Finally, the global optimization method is introduced for accuracy with a tree structure that saves all the route candidates meeting the vehicular trajectory, which compares the whole weight of every route, and selects one route nearest to the vehicular trajectory as the result [6] .…”

Curvedness feature constrained map matching for low-frequency probe vehicle data

“…In addition to distance, which was employed as a basic matching feature, other matching features have been synthesized into various map matching methods. Wu et al (2007) chose distance and direction of the vector of two neighboring track points to match track points onto road segments. Newson and Krumm (2009) introduced a hidden Markov model (HMM) map matching method, which adopted the distance of neighboring track points and the topology of their corresponding candidate road segments as matching features for searching matched subpaths and determining the global optimal matched paths.…”