Development of Differential Growth Method for Automated Vehicle Recognition

by Hirotaka Koike, Utsunomiya Univ, Utsunomiya, Japan,
Minoru Motohashi, Utsunomiya Univ, Utsunomiya, Japan,

Document Type: Proceeding Paper

Part of: Computing in Civil and Building Engineering


The purpose of this study is to improve a system which enables automatic recognition of vehicles from video images using image processing system. Basic methodology is a subtracting operation between two consecutive images, which leaves only the moving parts as residual images on the screen. Then the center of gravity of these residual images are computed. The problem with this method is the inaccuracy of computed center of gravity of a vehicle when shadow exists, or when a number of vehicles are closely positioned one another. In the current study, a new approach was developed to improve the accuracy of automatic recognition of vehicles using a procedure which is named as the differential growth method. Using this procedure, much more accurate movement of vehicles is automatically recognized. A case study at an intersection demonstrated vehicle movements in the intersection fairly accurately. The application of this method seems promising in various traffic engineering survey areas.

Subject Headings: Vehicles | Automation and robotics | Traffic surveys | Traffic engineering | Computer vision and image processing | Computing in civil engineering | Case studies | Management methods

Services: Buy this book/Buy this article


Return to search