Abstract
The road-network matching method is an effective tool for map integration, fusion, and update. Due to the complexity of road networks in the real world, matching methods often contain a series of complicated processes to identify homonymous roads and deal with their intricate relationship. However, traditional road-network matching algorithms, which are mainly central processing unit (CPU)-based approaches, may have performance bottleneck problems when facing big data. We developed a particle-swarm optimization (PSO)-based parallel road-network matching method on graphics-processing unit (GPU). Based on the characteristics of the two main stages (similarity computation and matching-relationship identification), data-partition and task-partition strategies were utilized, respectively, to fully use GPU threads. Experiments were conducted on datasets with 14 different scales. Results indicate that the parallel PSO-based matching algorithm (PSOM) could correctly identify most matching relationships with an average accuracy of 84.44%, which was at the same level as the accuracy of a benchmark—the probability-relaxation-matching (PRM) method. The PSOM approach significantly reduced the road-network matching time in dealing with large amounts of data in comparison with the PRM method. This paper provides a common parallel algorithm framework for road-network matching algorithms and contributes to integration and update of large-scale road-networks.
Highlights
To perform the road-network matching in an effective and efficient manner, a parallel matching strategy using graphics-processing unit (GPU) architecture is developed in this paper, and particle-swarm optimization (PSO) is introduced for the global optimization of the matching process
Parameter settings of particle and thread are discussed in Section 5.2; algorithm accuracies are analyzed in Section 5.3; and Section 5.4 examines the speed-up ratio of PSO-based matching algorithm (PSOM) under the GPU environment, comparing with another global optimization strategy, the probability-relaxation algorithm (PRM)
This study developed a parallel PSO-based road-network matching algorithm (PSOM) on graphics-processing units (GPU), which can be used to conquer the bottleneck problem of traditional road-network matching algorithms when facing big data
Summary
Road-network matching is a key technology of vector road-map integration, fusion, and update [1]. The core of the road-network matching method is evaluating the similarity of two node/road features and determining the corresponding relationship of matching pairs. Some studies pay more attention to the structural information of the road network and shift the matching unit to a larger scale, such as junction/segment clusters, for global optimization [3,10]. It makes the similarity measures more comprehensive but more complicated. Dealing with a larger scale of road-network data requires a higher time cost, because the number of objects that need to be computed increases. From a data perspective, dividing the data into smaller units can offer a potential for accelerating matching efficiency by parallel computation [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
