Ing. Junhee Youn
Senior Researcher
Korea Institute of Construction
Korea

Biography
Junhee Youn is working at Korea Institute of Construction Technology from 2011. He was in Samsung SDS between 2007-2011. He got a Ph.D degree in Purdue University, US. His main research areas are feature extraction from various sensors, and disaster management with spatial information.

Abstract
Automatic Extraction of Direction Information in Road Sign Imagery Obtained by Mobile Mapping System

Road signs are important infrastructures for safe and smooth traffic, since they provide useful information for drivers. For systematic managing the road signs, constructing road sign database and implementing road sign managing system are essential for local government. In this paper, we deals with automatic extraction of direction information in road sign imagery obtained by MMS (Mobile Mapping System). Our approach starts from image pre-processing and binarization. Next, arrow areas are extracted by proposed four-direction consecutive cell measures. From the arrow area, corner points are detected by using good feature to track algorithm, which is extended Newton-Rhapson method. Clearly, some of the detected corner points compose arrow head. Therefore, LSM (Least Square Matching) algorithm is applied to the corner points to extract the direction information. For the LSM algorithm, four direction arrow head shaped templates are used. As a result, we can confirm the possibility of automatic extraction of direction information in road sign imagery.