A Progressive Extended Kalman Filter Method for Freeway Traffic State Estimation Integrating Multisource Data

Abstract

Variable techniques have been used to collect traffic data and estimate traffic conditions. In most cases, more than one technology is available. A legitimate need for research and application is how to use the heterogeneous data from multiple sources and provide reliable and consistent results. This paper aims to integrate the traffic features extracted from the wireless communication records and the measurements from the microwave sensors for the state estimation. A state-space model and a Progressive Extended Kalman Filter (PEKF) method are proposed. The results from the field test exhibit that the proposed method efficiently fuses the heterogeneous multisource data and adaptively tracks the variation of traffic conditions. The proposed method is satisfactory and promising for future development and implementation.

Review of Data Fusion Methods for Real-Time and Multi-Sensor Traffic Flow Analysis

“…A combination of features entails making a more realistic condition. Liu et al [86] use speed and density features to come out with freeway state estimation. Mehrannia et al [49] combine features from different sensor systems for traffic incident detection.…”

“…Liu et al [86] implement a progressive extended KF (PEKF) to produce traffic conditions estimation on heterogeneous data from multi-sensor. The sensors are microwave and wireless communication, which provide data of different characteristics.…”

FCG-ASpredictor: An Approach for the Prediction of Average Speed of Road Segments with Floating Car GPS Data

“…To overcome this issue, an extended Kalman filter (EKF) that is suitable for nonlinear traffic prediction is implemented with the KF algorithm, which linearizes the nonlinear state space model. Liu et al [18] proposed a state-space model and a progressive EKF method. It fuses heterogeneous data and tracks the variation in traffic dynamics.…”

Investigating and modelling the relationship between traffic volume and extracts from cellphone activity data

“…For instance, fixed sensors such as loop detectors have to deal with the limited spatial coverage and high cost; comparatively, the probe methods like GPS‐based probes have some problems in probe penetration. Therefore, researchers are still working to find a better data collection and mining method [2]. With this background, this research aims to further explore traffic information from the cellphone‐based probe data.…”

“…These activities are recorded by the cellular towers, which are called as the communication activity (CA) data. A new method presented in the previous works applied these whole communication data to extracting two traffic features; and then, estimated the traffic speeds and density [2, 14]. In summary, these methods could help obtain satisfactory speed, in spite of their immaturity in traffic volume or density collection.…”