DEVELOPMENT OF TRAFFIC RESTRICTION SUPPORT SYSTEM USING OBJECT DETECTION BY DEEP LEARNING

Abstract

In the event of a disaster or accident, the road administrator needs to restrict traffic to endure safety. In recent years, disasters and aging deterioration of road structures have increased. Since the frequency of traffic restrictions may increase in the future, it is required to improve the efficiency of operations.

In this study, in order to improve the efficiency of traffic restriction work, we constructed a system to support traffic restriction by using an object detection method by deep learning. Furthermore, as an application example of this system, we took up the traffic restriction at Kaminoseki bridge and verified the effectiveness of the system.