Topic Model-Based Road Network Inference from Massive Trajectories

Zheng, Renjie; Liu, Qin; Rao, Weixiong; Yuan, Mingxuan; Zeng, Jia; Jin, Zhongxiao

doi:10.1109/mdm.2017.41

Cited by 12 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, none of the existing work clearly illustrates the advantages of each type of solutions, and there is no research on how GPS data quality affects their performance. As plenty of new solutions [44,78,100,131,132,147,161] have emerged since the last survey [5] and many of them are not able to be classified into any of the existing categorisations, in our thesis, we review the existing map inference methods and propose a new categorisation based on their methodologies. More importantly, we focus on the influence of data quality issue in GPS trajectories to the map inference solutions.…”

Section: Map Inference Algorithmsmentioning

confidence: 99%

“…Therefore, the online/offline map-matching is also termed as incremental/global map-matching in some papers [50,74,135]. On the other hand, map inference on GPS trajectories has been studied for 20 years and is still a hot topic [24,78,161]. Intuitively, as all vehicles are running on the actual roads, their GPS records combined can somehow sketch the road network both topologically and geographically.…”

Section: Map-matchingmentioning

confidence: 99%

“…This method was first proposed in [17] and adopted in [4,5,59,82,116,161]. The main idea is to randomly extract a set of subgraphs from both the constructed and ground-truth maps and compare their similarity.…”

Section: Graph Sampling (Gs)mentioning

confidence: 99%

“…There are a few public datasets available, like the Chicago [4,17,70,100,116,132,161] and Berlin [38,132] which are widely adopted in existing map inference algorithms. However, they both suffer from severe trajectory disparity issues, as shown in Table 3…”

Section: Experimental Settings Datasetsmentioning

confidence: 99%

“…For example, as the essential preprocessing step of most trajectory-based applications, the map- On the other hand, the recent upsurge of research on map-matching [112,119], map inference [116,161] and map update [111,133] shows a strong need of comparing their own proposals to the previous baseline algorithms. Meanwhile, the frequent use of those data preprocessing procedures in practice requires a toolbox that supports those functionalities on different input formats, scales • In addition to the basic functionality, our proposed platform provides abundant toolkits for data conversion, data preprocessing, data visualisation and data quality evaluation for both GPS trajectories and maps.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Study on map-matching and map inference problems

Chao¹

View full text Add to dashboard Cite

The recent upsurge of GPS(Global Positioning System)-equipped devices has enabled the tracking of users'/vehicles' locations. Meanwhile, the emergence of various location-based services emphasises the crucial role of the underlying digital map. However, the intrinsic inaccuracy of both maps and GPS trajectories has been a major issue that hinders the development of location-based applications, like navigation, location-based recommendation and traffic analysis. Several techniques are proposed to deal with the data quality issues in maps and GPS trajectories, respectively: (1) To avoid the excessive cost of ground surveying for map construction, the map inference algorithm aims to construct a digital map from GPS trajectories automatically. (2) To ensure the recency of digital maps, the map update algorithm focusses on updating an existing map using recent GPS trajectories. (3) To get rid family), Dr.

show abstract