An Intelligent Road Waterlogging Sensor for Traffic Safety: Principle and Algorithm
- 6 Downloads
Road waterlogging affects the behavior of driver-vehicle unit, thus road waterlogging perception technique is highly important to traffic safety. In this work, a pressure-guiding waterlogging perception method is introduced, and this sensor is modeled based on the principle of differential pressure to realize the real-time measurement of the road waterlogging level. In order to decrease non-linear measurement error of this waterlogging sensor under complex road environment, this paper proposed an adaptive correction algorithm according to the principle of data fusion. The experimental results show that this proposed method has much higher stability and measurement accuracy than typical measurement methods of the road waterlogging level.
KeywordsRoad waterlogging Level measurement Error compensation Data fusion
This work was supported by a grant from Anhui Province Foreign Science and Technology Cooperation Project.
- 2.Huang Z, Wang S (2013) Based on the water depth sensor network highway measurement system design. Comput Meas Control 21(2):352–354Google Scholar
- 3.Xu Z, Feng J, Chang H (2017) Research survey of road-water depth measurements. Electron Meas TechnolGoogle Scholar
- 4.Iwahashi M, Udomsiri S, Imai Y, et al (2007) Water level detection for functionally layered video coding. In: IEEE international conference on image processing. IEEE, pp II-321–II-324Google Scholar
- 6.Mousa M, Claudel C (2014) Water level estimation in urban ultrasonic/passive infrared flash flood sensor networks using supervised learning. In: IPSN-14 proceedings of the 13th international symposium on information processing in sensor networks. IEEE, pp 277–278Google Scholar
- 7.Xu H, Liu L (2010) Application of electronic water gauge in monitoring system for urban road waterlogging. Water Resour Informatization 3:015Google Scholar
- 8.Xia Z (2013) Design of monitoring and alarm system for city stagnant water. Electron Test 5:030Google Scholar
- 9.Zhang X, Yu S, Zhang J (2016) Lead pressure formula fluviograph:, CN 205561978 U [P]Google Scholar
- 11.Hecht-Nielsen R (1992) Theory of the backpropagation neural network. In: Neural networks for perception. pp 65–93Google Scholar
- 12.Xia S, Zhao L (2015) Research of multi-sensor information fusion based on BP neural networks. Comput Meas ControlGoogle Scholar