Heterogeneous Stream Processing and Crowdsourcing for Traffic Monitoring: Highlights

Schnitzler, François; Artikis, Alexander; Weidlich, Matthias; Boutsis, Ioannis; Liebig, Thomas; Piatkowski, Nico; Bockermann, Christian; Morik, Katharina; Kalogeraki, Vana; Mareček, Jakub; Gal, Avigdor; Mannor, Shie; Kinane, Dermot; Gunopulos, Dimitrios

doi:10.1007/978-3-662-44845-8_49

Cited by 14 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective of TFP is to provide traffic flow information that has the potential to help road users make better decisions on traveling, improve traffic operation efficiency, alleviate traffic congestion and reduce carbon emissions [1]. With the rapid development and deployment of various sensor sources, such as inductive loops [2], radars [3], visual sensors [4], [5], mobile global positioning systems [6], crowd sourcing [7] and social media [8], traffic data are exploding. Actually we have entered the era of data driven traffic prediction.…”

Section: Introductionmentioning

confidence: 99%

Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Liu,

Ji,

Dai

2016

Preprint

View full text Add to dashboard Cite

In this paper, we describe work in progress towards a real-time vision-based traffic flow prediction (TFP) system. The proposed method consists of three elemental operators, that are dynamic texture model based motion segmentation, feature extraction and Gaussian process (GP) regression. The objective of motion segmentation is to recognize the target regions covering the moving vehicles in the sequence of visual processes. The feature extraction operator aims to extract useful features from the target regions. The extracted features are then mapped to the number of vehicles through the operator of GP regression. A training stage using historical visual data is required for determining the parameter values of the GP. Using a lowresolution visual data set, we performed preliminary evaluations on the performance of the proposed method. The results show that our method beats a benchmark solution based on Gaussian mixture model, and has the potential to be developed into qualified and practical solutions to real-time TFP.

show abstract

Section: Introductionmentioning

confidence: 99%

Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Liu,

Ji,

Dai

2016

Preprint

View full text Add to dashboard Cite

show abstract

“…With respect to crowdsourcing applications in the transport domain, Zambonelli (2011) highlighted that crowdsourcing initiatives can improve public transport systems. Following this idea, Schnitzler et al (2014) implemented a crowdsourcing approach to complement information from real-time urban sensors to resolve sensor disagreements about traffic congestions. Furthermore, crowdsourcing has been proposed as a mechanism to empower citizens in making decisions about public transport policies (Filippi et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Crowdsourcing information for knowledge-based design of routes for unscheduled public transport trips

Cairó

Salcedo

Gutiérrez-García

2015

Journal of Knowledge Management

View full text Add to dashboard Cite

Purpose – The purpose of this paper is to devise a crowdsourcing methodology for acquiring and exploiting knowledge to profile unscheduled transport networks for design of efficient routes for public transport trips. Design/methodology/approach – This paper analyzes daily travel itineraries within Mexico City provided by 610 public transport users. In addition, a statistical analysis of quality-of-service parameters of the public transport systems of Mexico City was also conducted. From the statistical analysis, a knowledge base was consolidated to characterize the unscheduled public transport network of Mexico City. Then, by using a heuristic search algorithm for finding routes, public transport users are provided with efficient routes for their trips. Findings – The findings of the paper are as follows. A crowdsourcing methodology can be used to characterize complex and unscheduled transport networks. In addition, the knowledge of the crowds can be used to devise efficient routes for trips (using public transport) within a city. Moreover, the design of routes for trips can be automated by SmartPaths, a mobile application for public transport navigation. Research limitations/implications – The data collected from the public transport users of Mexico City may vary through the year. Originality/value – The significance and novelty is that the present work is the earliest effort in making use of a crowdsourcing approach for profiling unscheduled public transport networks to design efficient routes for public transport trips.

show abstract

Online Analysis of High-Volume Data Streams in Astroparticle Physics

Bockermann

Brügge

Buß

et al. 2015

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

Heterogeneous Stream Processing and Crowdsourcing for Traffic Monitoring: Highlights

Cited by 14 publications

References 4 publications

Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process

Crowdsourcing information for knowledge-based design of routes for unscheduled public transport trips

Online Analysis of High-Volume Data Streams in Astroparticle Physics

Contact Info

Product

Resources

About