Road signage has an ultimate role; as a communication and information tools to secure smooth road traffic flow and provide safe and easy driving environments for drivers. Nowadays, road sign management should go beyond than just providing direction information. There is a need for an intelligent transportation system (ITS) to provide timely, accurate and automatic management of road signs and to equip the drivers or traffic users with the relevant real-time information, thus a lot of money and time can be saved.
Road signs are communicating information to secure smooth road traffic flow, and provide safe and easy driving environments for drivers. The signs, that provide information to drivers, include road signs and traffic signs. The main role of traffic signs is to warn/regulate/direct traffic or to provide information on road conditions. The main role of road signs is to provide information for the correct movement of drivers and for smooth traffic flow. Redundant implementation or incorrect placement of road signs must be minimized, because road signs have to provide relevant real-time information to drivers.
In current road sign management system, content modification and renewal works are typically carried out manually, thus a lot of time and money being wasted due to inefficiency in the operating system. There is an urgent need to integrate and manage this works automatically for timely and accurate management of road signs. In addition, inaccurate direction information can cause great confusion for the driver heading to an unfamiliar destination.
An automatic technique for road signage is an important component of the base technique for constructing an intelligent transportation system (ITS) with automatic recognition of number plates and traffic signs using image processing and computer vision techniques. These automatic techniques can be divided into automatic panel detection methods and automatic recognition of sign information. Road signs express the directional information by using colors, shapes, symbols, and text. Consequently, it is difficult to apply recognition techniques directly to road signs because the information included in signs takes many different forms. However, informational road sign recognition and related research results are still mostly at a more fundamental level than traffic sign recognition research.
The automation of content updates and modifications for the management of road sign information can be divided into two fields: automatic recognition of text information in the road sign and automatic recognition of graphic direction information. The automatic recognition of text information in a road sign applies a method of continuous form including segmentation, boundary detection, color analysis, and character outline analysis.
Since direction information is formatted according to a certain standard, detection of direction information in an image was done with an image matching method by converting the direction information using a detection template that conforms to a domestic road sign manufacturing standards database. Furthermore, it describes a faster effective image matching method by applying a characteristic extraction algorithm and a line-scan-form direction information field detection algorithm.
Road Sign Direction Information Automatic Recognition Method
The images taken on the road are not only the road signs but also include various details and backgrounds along the roads. In order to extract panel including road signs from the imagery captured by MMS, one can use color information in the imagery. However, this method may be affected by background images such as billboards, so criteria based on the size and form of the extracted surface relative to the MMS direction are required. Moreover, a hybrid method that applies these criteria by extracting information from horizontal surfaces perpendicular to the direction of travel based on MMS and ground LiDAR can be applied. In this research, only the image processing step was conducted, assuming that only the road sign panel was extracted from the road imagery captured by MMS. The automatic extraction of direction information from the imagery applied in this paper is divided into three stages: input image generation (preprocessing), arrow region extraction, and direction recognition through image matching.
Figure 1 shows the algorithm process for the automatic extraction of direction information applied in this study.
(a) Row line scan for detecting contiguous cells in the row direction
(b) Column line scan for detecting contiguous cells in the column direction
.
.(c) Intersection of row line scan result and column line scan result
Fig. 2. Line scan method for extracting the seed area of an arrow region.
In the direction recognition phase, the template matching technique is used to extract the direction information from the detected arrow regions. In addition, the effectiveness of image matching algorithm is increased by extracting the corner points around the arrow regions. In order to extract the corner points, “good features to track” algorithm is applied. The good features to track algorithm is an object-tracking algorithm for which the Newton–Raphson method was extended based on the similarity transformation of the image. Usually road signs are generated based on the standard, the templates, which expresses the head of the arrow is used for template matching.
The arrow-head templates are presented in Fig. 3.
Direction Information Automatic Recognition Algorithm Construction and Recognition Experiment Result
To show the feasibility of the proposed algorithm, the pilot system using the C++ language-based Open CV Library has been implemented which included image enhancement, image binarization, vertical and horizontal contiguous pixel detection, image composition, field extension, corner point extraction, template image matching, and matching result extraction function. The images used in the experiment were the same as those in Fig. 5(a) and were sized 479 × 286 pixels. Figure 4 shows the results of the direction information recognition experiment for road signs by applying the method suggested in this study.
The results of applying this algorithm to other images are shown in Figs. 5–7.
Figs. 5
Fig. 6
Figs. 7
Conclusion
This paper attempted to extract direction information automatically from road sign imagery by applying various computer vision techniques. The algorithm was implemented using the C++ language-based Open CV Library, and direction information was automatically extracted from road sign images through processes such as image conversion, vertical and horizontal contiguous pixel detection, image combination, field extension, corner extraction, and template matching method. However, in this study, the possibility for automatic direction information extraction from images was proved only under relatively ideal conditions. For accurate extraction of direction information from road sign images obtained under inferior conditions likes damaged signs, backlit reflective signs, or signs with nonstandard figures or markings, an improved algorithm with better image binarization, direction information field extraction, and image matching is required
