GPS 신호와 다중 카메라를 이용한 도로표지 정보 인식 시스템

Abstract

Road sign is an important street furniture that gives some information such as road conditions. driving direction and driving condition to driver in a car. Thus, road sign is a major target of image recognition for self-driving car, the autonomous vehicle and intelligent driver assistance systems (ADAS), and intelligent transport systems(ITS). Automatic recognition scheme of road sign can tell a driver information of road sign through visual or audible signals. So this scheme is basic to self-driving car, ADAS and ITS. In the study of road and obstacle detection for ADAS, various schemes with vision composite sensor give the performance wanted by car industry. However, in the study of road sign recognition, the performance of recognition schemes has not reached the goal wanted by car industry yet. Therefore, to provide the road information for drivers and to create safe driving environment, the study for automatic road sign recognition is absolutely needed. In addition, street furniture smart management system for enhancing management uses mobile mapping system(MMS) that was equipped with a cameras, the complex sensors and GPS to collect road sign information automatically. in case of MMS, this vehicle system recognizes road sign information beside roadway using the composite sensors such as lasers and cameras and so on. However, in MMS, because of various type of the road sign and image resolution, it is difficult to implement road sign recognition in real time. Further more, to be equipped with sensors and control unit, MMS requires special design. And for the detailed scan, MMS needs high price and performance equipments. Therefore, to small scale local governments, MMS is financially demanding to administer huge size of road network in the local state. So, an enhanced recognition scheme is needed without high price sensors. In this paper, an enhanced road sign recognition system is proposed for MMS using the single and stereo camera, and GPS. For the proposed system, first, a road sign recognition scheme is proposed. this scheme is composed of detection and classification step. In the detection step, object candidate regions are extracted in image frames using hybrid road sign detection scheme that is based on color and shape features of road signs. And classification step, the area of candidate regions and road sign template is compared. Second, for a coordinate of road sign in single camera image, a position estimation scheme of road sign is proposed using the relationship between the pixel and object size in real world. In this scheme, coordinate value and direction are used getting coordinate value of road sign in images after estimating the equation related on pixel and real size of road sign. Third, a Geo-marking scheme for geo-content that is consist of road sign image and coordinate value is proposed. If the serious situation such as car accident is happened, this scheme can protect geographical information of road sign against illegal users. By experiments with test video set, in the three parts that are road sign recognition, coordinate value estimation and geo-marking, it is confirmed that proposed schemes can be used for MMS in commercial resign.