Efficient Hidden Trajectory Reconstruction from Sparse Data

Yang, Ning; Yu, Philip S.

doi:10.1145/2983323.2983796

Cited by 4 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Banerjee et al [44] infer uncertain trajectories from network-constrained partial observations by summarizing all probable routes in a holistic manner. Yang et al [45] investigate the problem of reconstructing hidden trajectories from a collection of separate spatial-temporal points where trajectory links are unknown. However, these methods require historical trajectories as input, which cannot be applied to recovering routes in our problem.…”

Section: Related Workmentioning

confidence: 99%

Citywide Traffic Volume Inference with Surveillance Camera Records

Tang

Yao

et al. 2021

IEEE Trans. Big Data

View full text Add to dashboard Cite

Real-time traffic monitoring becomes an essential part of an intelligent city. In recent years, the adoption of surveillance cameras is rapidly growing because they are helpful to manage and control the traffic. However, it is impossible to install cameras on every road in a city due to the high costs of deployment and maintenance. Given the information from limited surveillance cameras, can we infer the citywide traffic volume accurately? This is a challenging question because we have no historical data on the roads without cameras. It requires us to design a method that goes beyond the inference using nearby traffic data. Moreover, a nice property of surveillance camera data is that these AI-equipped cameras can recognize individual vehicles. So we can recover incomplete trajectories for vehicles using plate numbers in surveillance camera records. However, for road segments without cameras, we do not know whether those vehicles pass through them or not. How can such incomplete trajectories be effectively used to help citywide traffic inference? In this paper, we propose a framework named CityVolInf to infer citywide traffic volume based on surveillance camera records. Our framework combines a semi-supervised learning-based similarity module with a novel simulation module to address the above challenges. While the similarity module focuses on spatiotemporal correlations of traffic volume between road segments, the simulation module utilizes incomplete trajectories to model transitions of traffic volume between adjacent road segments. Our framework bridges the conventional data-driven approach and transportation domain knowledge from the simulator. We conduct extensive experiments on a real-world dataset, containing 405, 370, 631 camera records collected from 1, 704 surveillance cameras over a period of 31 days in a provincial capital in China. The experimental results demonstrate the effectiveness of CityVolInf compared with existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Citywide Traffic Volume Inference with Surveillance Camera Records

Tang

Yao

et al. 2021

IEEE Trans. Big Data

View full text Add to dashboard Cite

show abstract

“…We first estimate the missing portions of incomplete trajectories by using rich spatiotemporal movement patterns. Unlike the existing methods [4,14,37,45], our solution relies on a traffic simulator [11], which naturally observes road network constraints (e.g., no turn on red at some intersections) and the global consistency of traffic in the road network. It also captures the influence of vehicle interactions.…”

Section: Trajectory Recovery Viamentioning

confidence: 99%

Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference

Tang

Gong

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

Real-time traffic volume inference is key to an intelligent city. It is a challenging task because accurate traffic volumes on the roads can only be measured at certain locations where sensors are installed. Moreover, the traffic evolves over time due to the influences of weather, events, holidays, etc. Existing solutions to the traffic volume inference problem often rely on dense GPS trajectories, which inevitably fail to account for the vehicles which carry no GPS devices or have them turned off. Consequently, the results are biased to taxicabs because they are almost always online for GPS tracking. In this paper, we propose a novel framework for the citywide traffic volume inference using both dense GPS trajectories and incomplete trajectories captured by camera surveillance systems. Our approach employs a high-fidelity traffic simulator and deep reinforcement learning to recover full vehicle movements from the incomplete trajectories. In order to jointly model the recovered trajectories and dense GPS trajectories, we construct spatiotemporal graphs and use multi-view graph embedding to encode the multi-hop correlations between road segments into real-valued vectors. Finally, we infer the citywide traffic volumes by propagating the traffic values of monitored road segments to the unmonitored ones through masked pairwise similarities. Extensive experiments with two big regions in a provincial capital city in China verify the effectiveness of our approach.

show abstract

“…The spatial-temporal tasks could be easily linked and analyzed by the platform to recover the trajectories of this vehicle according to the tasks accepted by the vehicle. There are pieces of evidence that are Privacy-friendly spatial crowdsourcing in vehicular networks 61 likely to reconstruct the path even with sparse location data of vehicles [8] . Moreover, the reconstructed trajectories can be utilized to identify a particular smart vehicle even if it uses pseudonyms to hide its real identity.…”

Section: Figure 1 Spatial Crowdsourcing In Vehicular Networkmentioning

confidence: 99%

Privacy-friendly spatial crowdsourcing in vehicular networks

Huang

Zhu

2017

J. Commun. Inf. Netw.

View full text Add to dashboard Cite

With the evolution of conventional VANETs (Vehicle Ad-hoc Networks) into the IoV (Internet of Vehicles), vehicle-based spatial crowdsourcing has become a potential solution for crowdsourcing applications. In vehicular networks, a spatial-temporal task/question can be outsourced (i.e., task/question relating to a particular location and in a specific time period) to some suitable smart vehicles (also known as workers) and then these workers can help solve the task/question. However, an inevitable barrier to the widespread deployment of spatial crowdsourcing applications in vehicular networks is the concern of privacy. Hence, We propose a novel privacy-friendly spatial crowdsourcing scheme. Unlike the existing schemes, the proposed scheme considers the privacy issue from a new perspective according that the spatial-temporal tasks can be linked and analyzed to break the location privacy of workers. Specifically, to address the challenge, three privacy requirements (i.e. anonymity, untraceability, and unlinkability) are defined and the proposed scheme combines an efficient anonymous technique with a new composite privacy metric to protect against attackers. Detailed privacy analyses show that the proposed scheme is privacy-friendly. In addition, performance evaluations via extensive simulations are also conducted, and the results demonstrate the efficiency and effectiveness of the proposed scheme.

show abstract

Efficient Hidden Trajectory Reconstruction from Sparse Data

Cited by 4 publications

References 23 publications

Citywide Traffic Volume Inference with Surveillance Camera Records

Citywide Traffic Volume Inference with Surveillance Camera Records

Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference

Privacy-friendly spatial crowdsourcing in vehicular networks

Contact Info

Product

Resources

About