What is it about?
Sensor and Data Fusion for Intelligent Transportation Systems introduces readers to the roles of the data fusion processes defined by the Joint Directors of Laboratories (JDL) data fusion model and the Data Fusion Information Group (DFIG) enhancements, data fusion algorithms, and noteworthy applications of data fusion to intelligent transportation systems (ITS). Additionally, the monograph offers detailed descriptions of three of the widely applied data fusion techniques and their relevance to ITS (namely, Bayesian inference, Dempster‒Shafer evidential reasoning, and Kalman filtering), and indicates directions for future research in the area of data fusion. The focus is on data fusion algorithms rather than on sensor and data fusion architectures, although the book does summarize factors that influence the selection of a fusion architecture and several architecture frameworks.
Featured Image
Why is it important?
Sensor and Data Fusion for Intelligent Transportation Systems was prepared to give undergraduate and graduate students and traffic management professionals a multidisciplinary description of sensor and data fusion and the benefits it brings to the transportation community, especially for Intelligent Transportation Systems. Although sensor and data fusion processes are introduced through the lens of the military-oriented U.S. Joint Directors of Laboratories (JDL) data fusion model, analogous language for its application to traffic management is afforded at each data fusion processing level. The JDL model was selected because of its ability to expose all of the generally acknowledged facets of data fusion.
Perspectives
The book focuses on data fusion functions and data processing algorithms. Sensor fusion architectures, although discussed, are not treated in as much detail. The discussions explore techniques that enhance the interpretation of information gathered from a diverse mixture of sensors and other data sources (for instance, floating cars, connected and cooperative vehicles, self-driving vehicles, mobile devices such as cell phones accessible through Bluetooth® communications, and automatic license plate and toll-tag readers) that help characterize the traffic environment. Its often-complex nature is exacerbated by a mix of different types of vehicles, changes in traffic flow characteristics, appearance of unexpected objects such as pedestrians darting across a roadway, inclement weather, vehicles changing lanes, and roadside structures or poor visibility conditions that interfere with the normal observation of traffic patterns and the gathering of needed data.
Dr Lawrence A Klein
University of California Los Angeles
Read the Original
This page is a summary of: Sensor and Data Fusion for Intelligent Transportation Systems, June 2019, SPIE,
DOI: 10.1117/3.2525400.
You can read the full text:
Resources
Contributors
The following have contributed to this page
