Traffic signs are integral elements of any transportation network; however, keeping records of those signs and their condition is a tedious, time-consuming, and labor-intensive process. As a result, many agencies worldwide have been working toward automating the process. One form of automation uses remote sensing techniques to extract traffic sign information. An algorithm is proposed that can automatically extract traffic signs from mobile light detection and ranging data. After the number of signs on a road segment has been determined, the coordinates of those signs are mapped onto the road segment. The sign extraction procedure involves applying multiple filters to the point cloud data and clustering the data into traffic signs. The proposed algorithm was tested on three highways located in different regions of the province of Alberta, Canada. The segments on which the algorithm was tested include a two-lane undivided rural road and four-lane divided highways. The highway geometry varied, as did vegetation and tree density. Success rates ranged from 93% to 100%, and the algorithm performed better on highways without overhead signs. Results indicate that the proposed method is simple but effective for creating an accurate inventory of traffic signs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.