One of the bottlenecks of loading and unloading a container is that it is a hard job for a driver to park the container truck appropriately and quickly under the quayside container crane. It depends on the experience and eyeballing of the driver to adjust the parking position of the truck. This adjusting process undoubtedly delays the loading and unloading procedure, and thus degrades the efficiency. A method using monocular vision technology is proposed here to detect the position and speed of a moving container truck so that reasonably information can be shown to the driver to help him park the truck quickly and accurately. Thus, time is saved and efficiency is upgraded. In this paper, feasibility of using monocular vision technology in this application is firstly demonstrated. Then, the mathematical model of this method is established. Based on this model, we analyze the speed and accuracy of the detecting method. Finally, the simulation result of the analysis is delivered to demonstrate that the method is a simple and feasible way to solve this kind of problem.
[1]
P. Hosmer.
The use of laser scanning technology for perimeter protection
,
2003,
IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings..
[2]
Pentti Mattila,et al.
Integrated robotic vehicle control system for outdoor container handling
,
1997,
Other Conferences.
[3]
S. Katahara,et al.
Location detection system by an on-board slit camera imaging road surface marks and its application
,
2002,
Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.
[4]
Antonio Criminisi,et al.
Accurate Visual Metrology from Single and Multiple Uncalibrated Images
,
2001,
Distinguished Dissertations.