Impact Assessing of Traffic Lights via GPS Vehicle Trajectories

Liao, Zhuhua; Xiao, H.; Liu, Silin; Liu, Yizhi; Yi, Aiping

doi:10.3390/ijgi10110769

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

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%

“…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%

See 1 more Smart Citation

Recognition of Intersection Traffic Regulations from Crowdsourced Data

Zourlidou

Sester

2022

IJGI

View full text Add to dashboard Cite

In this paper, a new method is proposed to detect traffic regulations at intersections using GPS traces. The knowledge of traffic rules for regulated locations can help various location-based applications in the context of Smart Cities, such as the accurate estimation of travel time and fuel consumption from a starting point to a destination. Traffic regulations as map features, however, are surprisingly still largely absent from maps, although they do affect traffic flow which, in turn, affects vehicle idling time at intersections, fuel consumption, CO2 emissions, and arrival time. In addition, mapping them using surveying equipment is costly and any update process has severe time constraints. This fact is precisely the motivation for this study. Therefore, its objective is to propose an automatic, fast, scalable, and inexpensive way to identify the type of intersection control (e.g., traffic lights, stop signs). A new method based on summarizing the collective behavior of vehicle crossing intersections is proposed. A modification of a well-known clustering algorithm is used to detect stopping and deceleration episodes. These episodes are then used to categorize vehicle crossing of intersections into four possible traffic categories (p1: free flow, p2: deceleration without stopping events, p3: only one stopping event, p4: more than one stopping event). The percentages of crossings of each class per intersection arm, together with other speed/stop/deceleration features, extracted from trajectories, are then used as features to classify the intersection arms according to their traffic control type (dynamic model). The classification results of the dynamic model are compared with those of the static model, where the classification features are extracted from OpenStreetMap. Finally, a hybrid model is also tested, where a combination of dynamic and static features is used, which outperforms the other two models. For each of the three models, two variants of the feature vector are tested: one where only features associated with a single intersection arm are used (one-arm model) and another where features also from neighboring intersection arms of the same intersection are used to classify an arm (all-arm model). The methodology was tested on three datasets and the results show that all-arm models perform better than single-arm models with an accuracy of 95% to 97%.

show abstract

Section: Existing Workmentioning

confidence: 99%

Section: Existing Workmentioning

confidence: 99%

Recognition of Intersection Traffic Regulations from Crowdsourced Data

Zourlidou

Sester

2022

IJGI

View full text Add to dashboard Cite

show abstract

“…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%

Fusing Spatio-Temporal Contexts into DeepFM for Taxi Pick-Up Area Recommendation

Liu¹,

Qing²,

Zhao³

et al. 2023

Computer Systems Science and Engineering

Self Cite

View full text Add to dashboard Cite

Short-term GPS data based taxi pick-up area recommendation can improve the efficiency and reduce the overheads. But how to alleviate sparsity and further enhance accuracy is still challenging. Addressing at these issues, we propose to fuse spatio-temporal contexts into deep factorization machine (STC_DeepFM) offline for pick-up area recommendation, and within the area to recommend pick-up points online using factorization machine (FM). Firstly, we divide the urban area into several grids with equal size. Spatio-temporal contexts are destilled from pick-up points or points-of-interest (POIs) belonged to the preceding grids. Secondly, the contexts are integrated into deep factorization machine (DeepFM) to mine high-order interaction relationships from grids. And a novel algorithm named STC_DeepFM is presented for offline pick-up area recommendation. Thirdly, we devise the architecture of offline-to-online (O2O) recommendation respectively based on DeepFM and FM model in order to tradeoff the accuracy and efficiency. Some experiments are designed on the DiDi dataset to evaluate step by step the performance of spatio-temporal contexts, different recommendation models, and the O2O architecture. The results show that the proposed STC_DeepFM algorithm exceeds several state-of-the-art methods, and the O2O architecture achieves excellent real-time performance.

show abstract

“…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%

Recognition of Intersection Traffic Regulations From Crowdsourced Data

Zourlidou¹,

Sester²,

Hu³

2022

Preprint

View full text Add to dashboard Cite

In this paper, a new method is proposed to detect traffic regulations at intersections using GPS traces. The knowledge of traffic rules of regulated locations can help various location-based applications in the context of Smart Cities, such as the accurate estimation of travel time and fuel consumption from a starting point to a destination. Traffic regulations as map features, however, are surprisingly still largely absent from maps, although they do affect traffic flow which in turn affects vehicle idling time at intersections, fuel consumption, CO_2 emissions and arrival time. In addition, mapping them using surveying equipment is costly and any update process has severe time constraints. This fact is precisely the motivation for this study. Therefore, its objective is to propose an automatic, fast, scalable and inexpensive way to identify the type of intersection control (e.g. traffic lights, stop signs). A new method based on summarizing the collective behavior of vehicles crossing intersections is proposed. A modification of a well-known clustering algorithm for detecting stopping and decelerating events is presented. These detected events are then used to categorize vehicle crossing of intersections into four possible traffic categories (p1: free flow, p2: deceleration without stopping events, p3: only one stopping event, p4: more than one stopping event). The percentages of crossings of each class per junction arm, together with other speed/stop/deceleration features, extracted from trajectories, are then used as features to classify the junction arms according to their traffic control type dynamic model). The classification results of the dynamic model are compared with those of the static model, where the classification features are extracted from OpenStreetMap. Finally, a hybrid model is also tested, where a combination of dynamic and static features is used, which outperforms the other two models. For each of the three models, two variants of the feature vector are tested: one where only features associated with a single junction arm are used (one-arm model) and another where features also from neighbouring junction arms of the same junction are used to classify an arm (all-arm model). The methodology was tested on three datasets and the results show that all-arm models perform better than single-arm models with an accuracy of 94\% to 97\%.

show abstract

Impact Assessing of Traffic Lights via GPS Vehicle Trajectories

Cited by 7 publications

References 14 publications

Recognition of Intersection Traffic Regulations from Crowdsourced Data

Recognition of Intersection Traffic Regulations from Crowdsourced Data

Fusing Spatio-Temporal Contexts into DeepFM for Taxi Pick-Up Area Recommendation

Recognition of Intersection Traffic Regulations From Crowdsourced Data

Contact Info

Product

Resources

About