Multisensor poly information fusion technology and its application

Traffic congestion state identification is one of the most important tasks of ITS. Traffic flow is a nonlinear complicated system. Traffic congestion state is affected by many factors, such as road channelization, weather condition, drivers' different driving behavior and so on. It is difficult to collect all necessary traffic information. Traffic congestion auto identification result based on incomplete traffic information exists uncertain. Little work has been done to analyze the uncertainty. Possibility theory introduced by Zadeh is an efficient means to present incomplete knowledge. Possibility distribution determination is an important task of possibility theory. In this paper, possibility theory is used to describe the uncertainty of traffic state. The possibility distribution of traffic state is determined according to the probability distribution of traffic flow parameters, such as volume, speed and occupancy and so on. The multi-variable distribution of traffic flow parameters is determined with large-scale traffic flow data. Large-scale traffic congestion samples are generated with parallel k-mean clustering method. Traffic congestion forecasting is based on the forecasting of traffic flow parameters with SVM (Support Vector Machines). At last, a practical example is analyzed with the proposed method.

show abstract

“…It has been widely studied [1]. Currently, traffic congestion identification is performed mainly through three means, i.e.…”

Section: Introductionmentioning

confidence: 99%

Traffic Congestion Forecasting Based on Possibility Theory

Sun

Zhao

2014

Int. J. ITS Res.

View full text Add to dashboard Cite

show abstract

“…Aerial detection technologies show great potential in the road traffic information acquisition applications [1]. Although satellites are initially considered for traffic surveillance purposes, their applications in transportation are limited not only by the transitory nature of satellite orbits which lead to be difficult to obtain the right imagery to address continuous problems such as traffic tracking, but also by the bad image quality caused by the cloud covers [2].…”

Section: Introductionmentioning

confidence: 99%

Traffic Flow Registraton for Unmanned Aerial Vehicle Detection

Xiao¹,

Du²

2014

Proceedings of the 2015 International Conference on Material Science and Applications

View full text Add to dashboard Cite

Abstract. Registration of detection data is to ensure the time-space consistency and effective fusion of air-ground traffic detection data. In this paper, we aim to propose a space-time registration method for the vehicle detection data of unmanned aerial vehicle (UAV). Considering temporal and spatial distribution characteristics of UAV detection, we define time effectiveness and two evaluation indicators for UAV data registration, namely absolute and relative effective times. These two indicators are used to characterize the quality of UAV detection data. Based on time effectiveness of UAV detection, space and time registration methods are developed. Data verification is conducted by Matlab programming with the holographic vehicle trajectory data of I-80 highway. Results of the case study show that, registration largely improves the data accuracy of UAV traffic flow detection data from 68.4% to 88.8%.

show abstract

“…Many scholars have been studying on the topic and many forecasting models have been developed. Commonly used methods include average method, ARMA, linear regression, nonparametric regression, and neural networks [1][2][3]. The forecasting precisions of these methods usually can't meet with the practical requirement.…”

Section: Introductionmentioning

confidence: 99%

Traffic Flow Forecasting Based on Combination of Multidimensional Scaling and SVM

Sun

Fox

2013

Int. J. ITS Res.

View full text Add to dashboard Cite

Abstract:Traffic flow forecasting is a popular research topic of Intelligent Transportation Systems (ITS). With the development of information technology, lots of history electronic traffic flow data are collected. How to take full use of the history traffic flow data to improve the traffic flow forecasting precision is an important issue. More history data are considered, more computation cost should be taken. In traffic flow forecasting, many traffic parameters can be chosen to forecast traffic flow. Traffic flow forecasting is a real-time problem, how to improve the computation speed is a very important problem. Feature extraction is an efficient means to improve computation speed. Some feature extraction methods have been proposed, such as PCA, SOM network, and Multidimensional Scaling (MDS) and so on. But PCA can only measure the linear correlation between variables. The computation cost of SOM network is very expensive. In this paper, MDS is used to decrease the dimension of traffic parameters, interpolation MDS is used to increase computation speed. It is combined with nonlinear regression Support Vector Machines (SVM) to forecast traffic flow. The efficiency of the method is illustrated through analyzing the traffic data of Jinan urban transportation.

show abstract

Multisensor poly information fusion technology and its application

Cited by 9 publications

References 0 publications

Traffic Congestion Forecasting Based on Possibility Theory

Traffic Congestion Forecasting Based on Possibility Theory

Traffic Flow Registraton for Unmanned Aerial Vehicle Detection

Traffic Flow Forecasting Based on Combination of Multidimensional Scaling and SVM

Contact Info

Product

Resources

About