Title :
Automatic Skid Number Evaluation Using Texture Laser Measurement
Author :
Xie, Jiabin ; Liu, Richard ; Michalk, Brian
Author_Institution :
Univ. of Houston, Houston
Abstract :
Skid resistance plays a very important role in highway construction, design, management, maintenance, road safety, and environment protection. In the past, evaluation of the skid resistance through the road texture on the highway and in the lab was not efficient, and traffic usually was disrupted. With the advent of the latest non-contact technologies of measurement, especially the use of laser, data acquisition can be performed real-time. The challenge is how to derive the skid resistance from the primitive data acquired from the road and effectively reduce the contribution of unwanted components introduced in the testing process, such as the vibration of the testing vehicle, noise from the environment, etc. A data or signal processing system was implemented to estimate the skid number; and, the architecture of multilayer feedforward neural network and the back propagation algorithm was used.
Keywords :
feedforward neural nets; roads; structural engineering computing; automatic skid number evaluation; backpropagation algorithm; highway construction; multilayer feedforward neural network; skid number estimation; skid resistance; testing vehicle vibration; texture laser measurement; Automated highways; Data acquisition; Electrical resistance measurement; Environmental management; Laser noise; Multi-layer neural network; Protection; Road safety; Signal processing algorithms; Testing;
Conference_Titel :
Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-1685-1
Electronic_ISBN :
978-1-4244-1686-8
DOI :
10.1109/ICNSC.2008.4525179