A BASIC STUDY ON TRAFFIC CENSUS USING GENERIC DEEP LEARNING

Abstract

 Road administrators perform traffic censuses for road maintenance and management. In these censuses, surveyors visually count the number of passing vehicles, labor-saving method is necessary because the surveyors must count in many places and it is time-consuming. Mechanical surveys have been introduced as a countermeasure. However, considering the growth of ICT, further development in survey technology is expected. In the field of urban transportation, various technologies are suggested to recognize vehicles from video data using deep learning. For putting it to practical use and spreading some methods widely, it is necessary to survey the practicality of technologies and proper conditions of photographing based on the existing studies. In this research, we developed a technology of recognizing vehicles based on existing methods and took videos under various conditions. By analyzing them using the present technology, we clarified the usefulness of deep learning in the proper conditions of photographing.