TrajCompressor: An Online Map-matching-based Trajectory Compression Framework Leveraging Vehicle Heading Direction and Change

Chao Chen, Yan Ding, Xuefeng Xie, Shu Zhang, Zhu Wang, Liang Feng

科研成果: 期刊稿件文章同行评审

87 引用 (Scopus)

摘要

Massive and redundant vehicle trajectory data are continuously sent to the data center via vehicle-mounted GPS devices, causing a number of sustainable issues, such as storage, communication, and computation. Online trajectory compression becomes a promising way to alleviate these issues. In this paper, we present an online trajectory compression framework running under the mobile environment. The framework consists of two phases, i.e., online trajectory mapping and trajectory compression. In the phase of online trajectory mapping, we develop a light-weighted yet efficient map matcher, namely, Spatial-Directional Matching (SD-Matching), to align the noisy and sparse GPS points upon the underlying road network, which fully explores the usage of vehicle heading direction collected from the GPS trajectory data. In the phase of online trajectory compression, we propose a novel compressor based on the heading change at intersections, namely, Heading Change Compression (HCC), aiming at finding a concise and compact trajectory representation. Finally, we conduct experiments to evaluate the effectiveness and efficiency of the proposed framework using real-world datasets in the city of Beijing, China. We further deploy the system in the real world in the city of Chongqing, China. The experimental results demonstrate that: 1) the SD-Matching algorithm achieves a higher mean accuracy but consumes less time than the state-of-the-art algorithm, namely, Spatial-Temporal Matching (ST-Matching) and 2) the HCC algorithm also outperforms baselines in trading-off compression ratio and computation time.

源语言英语
文章编号8697124
页(从-至)2012-2028
页数17
期刊IEEE Transactions on Intelligent Transportation Systems
21
5
DOI
出版状态已出版 - 5月 2020

指纹

探究 'TrajCompressor: An Online Map-matching-based Trajectory Compression Framework Leveraging Vehicle Heading Direction and Change' 的科研主题。它们共同构成独一无二的指纹。

引用此