No abstract

In this paper is proposed a traffic signs recognition prototype based on template matching approach of the 3D Registration technique in order to make use of the benefits provided by mobile augmented reality. The proposed solution finds speed traffic signs, extracted from a mobile device camera used in real environment, and uses them as AR markers to augment the virtual elements. This information is meant to help the driver during driving process by giving him various audio or visual indications via his mobile device. As one of the top three causes of road accidents is the distracted driving, usually caused by the driver talking on the mobile phone or sending a text message, including the audio component that gives signals when the road signs are not observed is useful. We proposed an ontology to attach some knowledge to each traffic sign, to guide its interpretation. Nevertheless, the performance of the prototype is affected by several factors, such as: video source, lighting conditions, occlusion, chaotic background and viewing angle, deterioration and deformations of the traffic signs etc. In order to reduce the negative effects of above factors is necessary to use the following methods: image resizing, grayscale transformation, median blur, Hough transformation. In the first part of the research we focused on describing the architecture of the prototype and the components of the OpenCV library, which are integrated in the current solution. In the second phase, we highlighted the most common issues that affect the performance of the application.