2021
DOI: 10.3390/ijgi10110769
|View full text |Cite
|
Sign up to set email alerts
|

Impact Assessing of Traffic Lights via GPS Vehicle Trajectories

Abstract: The adaptability of traffic lights in the control of vehicle traffic heavily affects the trafficability of vehicles and the travel efficiency of traffic participants in busy urban areas. Existing studies mainly have focused on the presence of traffic lights, but rarely evaluate the impact of traffic lights by analyzing traffic data, thus there is no solution for practicably and precisely self-regulating traffic lights. To address these issues, we propose a low-cost and fast traffic signal detection and impact … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
3
1
1

Relationship

1
4

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 14 publications
0
4
0
Order By: Relevance
“…Furthermore, Liao et al [30] described a traffic-light detection (binary classification problem) and impact assessing framework that can detect the presence of traffic signals and estimate the influence range of traffic lights (in space and time) using speed time series extracted from GPS trajectories and intersection-related features, such as intersection type (connects arterial roads, connects secondary roads, connects arterial and secondary roads), road type (according to two speed limits) and traffic flow information. A distributed long short-term memory (DLSTM) neural network is used in the proposed framework, which treats discrete and sequential features separately and achieves an AUC value under the ROC curve of 0.95.…”
Section: Existing Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Furthermore, Liao et al [30] described a traffic-light detection (binary classification problem) and impact assessing framework that can detect the presence of traffic signals and estimate the influence range of traffic lights (in space and time) using speed time series extracted from GPS trajectories and intersection-related features, such as intersection type (connects arterial roads, connects secondary roads, connects arterial and secondary roads), road type (according to two speed limits) and traffic flow information. A distributed long short-term memory (DLSTM) neural network is used in the proposed framework, which treats discrete and sequential features separately and achieves an AUC value under the ROC curve of 0.95.…”
Section: Existing Workmentioning
confidence: 99%
“…Reference datasets (benchmarks) would facilitate direct comparisons between different TRR methods. Moreover, it seems that hybrid methods, such as that of [26], that combine static and dynamic features perform better than those using only static or dynamic features, and given that this idea is only addressed in two articles [26,30], it may be an interesting methodological direction to explore further.…”
Section: Existing Workmentioning
confidence: 99%
“…Spatio-temporal context plays an important role except some recent works [20,31,32,44]. Liu et al mined candidate pick-up points based on GPS data by spatio-temporal analysis, and created personalized hot spots by integrating a probabilistic optimization model with project-based collaborative filtering method [33].…”
Section: Spatio-temperal Contextsmentioning
confidence: 99%
“…Liao et al [22] described a traffic light detection (binary classification problem) and impact assessing framework that can detect the presence of traffic signals and estimate the influence range of traffic lights (in space and time) using speed time series extracted from GPS trajectories and intersection-related features such as intersection type (connects arterial roads, connects secondary roads, connects arterial and secondary roads), road type (according to two speed limits) and traffic flow information. A distributed long short-term memory (DLSTM) neural network is used in the proposed framework, which treats discrete and sequential features separately and achieves an AUC value under the ROC curve of 0.95.…”
Section: Introductionmentioning
confidence: 99%