Real-time Container Truck Speed Measurement at Container Port Gates Based on the Binocular Vision Technology

Abstract

Jiang, J.; Mi, C.; Wu, M.; Zhang, Z.; Feng, Y., and Mi, W., 2019. Real-time container truck speed measurement at container port gates based on the binocular vision technology. In: Guido-Aldana, P.A. and Mulahasan, S. (eds.), Advances in Water Resources and Exploration. Journal of Coastal Research, Special Issue No. 93, pp. 998–1005. Coconut Creek (Florida), ISSN 0749-0208.With the development of intelligent gates in the container ports, more and more attention has been paid to the real-time container truck speed measurement. Current solutions to measuring vehicle speed commonly use coil, laser or radar. These methods can obtain results with high precision but they are limited in some way, such as low stability, high costs, and high computation requirements. This paper proposed a method to measure real-time container truck speed at container port gates based on binocular videos. Firstly, the feature points from the time-series images of the moving container truck are obtained. Secondly, the correlation of these feature points in time and space is analyzed to obtain the homonymous coordinates. Finally, the container truck speed is calculated according to the homonymous coordinates. Experiments on container truck speed measurement based on binocular vision were carried out at the gates of Taicang Container Port. The results showed that when the container truck speed was less than 30 km/h, the algorithm was highly accurate in speed measurement and the error percentage was under 10%. In addition, the calculation took about 120 ms, which can satisfy the real-time requirements of automatic container truck speed measurement at a lower cost.