Spatio-temporal traffic video data archiving and retrieval system

Yue, Hang; Rilett, Laurence R.; Révész, Péter

doi:10.1007/s10707-015-0231-0

Cited by 17 publications

(7 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further research may develop verification platforms or methods for the development of T-CPSs with different road or intersection geometrical features and more complicate traffic simulation situations. Also, it would be useful for dynamic information optimisation and traffic delay analysis via the integration of CSTPNs, advanced traffic event data collection techniques [33], advanced traffic data models [34] and spatiotemporal transportation databases [35]. Fig.…”

Section: Discussionmentioning

confidence: 99%

Using CSTPNs to model traffic control CPS

et al. 2017

Self Cite

View full text Add to dashboard Cite

Transportation cyber-physical system (T-CPS) is a spatiotemporal discrete-continuous hybrid system. However, the hybrid T-CPSs have some analysis and modelling problems, especially the problems related to the spatiotemporal characteristics. Existing coloured Petri net approaches of traffic control cannot effectively analyse dynamic changes of cyber systems and physical entities in space and time. Moreover, some problems, related to the state space explosion and the large complex T-CPSs, have not been well solved. This study develops the innovative methods for T-CPS design and modelling via the development and application of coloured spatiotemporal Petri nets (CSTPNs). The proposed research ideas involve the CSTPN theory creation, the development of traffic intersection coordination control system using CSTPNs, the traffic simulation analysis and the implementation of T-CPS-based CSTPNs. The experimental results show that the new spatiotemporal theories and approaches of the traffic coordination control based on CSTPNs have excellent potentials to address the issues related to the spatiotemporal discrete-continuous characteristics of T-CPS. Moreover, these innovative methods with a good validity can be easily applied into practise for the development of T-CPS.

show abstract

Section: Discussionmentioning

confidence: 99%

Using CSTPNs to model traffic control CPS

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Image databases (see Chapter 8 in [23]) are ubiquitously used in numerous applications from recognizing text in images [10][11][12], affine invariant image retrieval [9], facial recognition systems and traffic monitoring [39]. Images in image databases can be represented by pixels, vectors, or constraints [14].…”

Section: The Dataset Usedmentioning

confidence: 99%

Data Mining Ancient Script Image Data Using Convolutional Neural Networks

Daggumati

Révész

2018

Proceedings of the 22nd International Database Engineering &Amp; Applications Symposium on - IDEAS 2018

Self Cite

View full text Add to dashboard Cite

The recent surge in ancient scripts has resulted in huge image libraries of ancient texts. Data mining of the collected images enables the study of the evolution of these ancient scripts. In particular, the origin of the Indus Valley script is highly debated. We use convolutional neural networks to test which Phoenician alphabet letters and Brahmi symbols are closest to the Indus Valley script symbols. Surprisingly, our analysis shows that overall the Phoenician alphabet is much closer than the Brahmi script to the Indus Valley script symbols. CCS CONCEPTS • Computing methodologies → Machine learning; Machine learning approaches;

show abstract

“…Based on GPS probe vehicles, Kong et al [14] presented the curve-fitting-based method and the vehicletracking-based method for the traffic state estimation. H. Yue et al [15][16] use video data to archiving and retrieval. Shi et al [17] proposed a method whose location-amended GPS data are dynamically fitted with the adaptive traffic flow, and it can estimate the state of the traffic flow along rolling time periods.…”

Section: Related Workmentioning

confidence: 99%

“…Because of the huge calculation and complex computation, we use stochastic gradient descent (SGD) as our optimization method, and ε as the condition of convergence. SGD is sensitive to the initialized value [15]. Therefore, we set the initialized W following the investigation of urban traffic and the experts' experience, to make sure the W can present the importance of each properties.…”

Section: ) Determination Of Weights In Congestion Estimationmentioning

confidence: 99%

Efficient traffic congestion estimation using multiple spatio-temporal properties

Yang

Han

et al. 2017

Neurocomputing

View full text Add to dashboard Cite

Abstract-Traffic estimation is an important issue to analyze the traffic congestion in large-scale urban traffic situations.Recently, many researchers have used GPS data to estimate traffic congestion. However, how to fuse the multiple data reasonably and guarantee the accuracy and efficiency of these methods are still challenging problems. In this paper, we propose a novel method Multiple Data Estimation (MDE) to estimate the congestion status in urban environment with GPS trajectory data efficiently, where we estimate the congestion status of the area through utilizing multiple properties, including density, velocity, inflow and previous status. Among them, traffic inflow and previous status (combination of time and space factors) are not both used in other existing methods. In order to ensure the accuracy and efficiency, we apply dynamic weights of data and parameters in MDE method. To evaluate our methods, we apply it on large-scale taxi GPS data of Beijing and Shanghai. Extensive experiments on these two real-world datasets demonstrate the significant improvements of our method over several state-ofthe-art methods.

show abstract

Spatio-temporal traffic video data archiving and retrieval system

Cited by 17 publications

References 51 publications

Using CSTPNs to model traffic control CPS

Using CSTPNs to model traffic control CPS

Data Mining Ancient Script Image Data Using Convolutional Neural Networks

Efficient traffic congestion estimation using multiple spatio-temporal properties

Contact Info

Product

Resources

About