Homography‐Based Vision Algorithm for Traffic Sign Attribute Computation

Abstract

Listen

Translate article

Abstract: Traffic signs are transportation assets important for roadway safety. Traffic sign attributes are typically collected manually in the field, which is time‐consuming, costly, and dangerous. This article proposes an algorithm to extract traffic sign attributes, including height, tilted angle, location, and sign‐to‐camera distance, from video log images. The article makes two contributions. First, the article develops an algorithm that computes traffic sign attributes by applying a homography‐based computation model. The algorithm has four main steps: homography computation, camera calibration, sign pose calculation, and computation of traffic sign attributes. Second, the article uses three‐coordinate systems to solve out‐of‐view and occlusion problems; sign attributes can be computed when the bottom of a sign is occluded by objects like grass or is not available in the image due to the camera's angle of view. Simulation data was first used to test the algorithm performance with different noise levels, sign‐to‐camera distances, and calibration errors, which are difficult to obtain from real data. A typical 60 cm × 75 cm rectangular speed limit sign, 3 m high and with a 6° tilted angle, was created for the simulation. Under a typical 8 m measurement distance and 0.5 pixel noise level, the computed sign angle has an error of 0.4 ° with a standard deviation of 4.0 °. The means and standard deviations for the errors of the height and sign‐to‐camera distance are 10 cm, 18 cm, and 1 cm, 4 cm, respectively. In the real image test, the algorithm was further validated by the images collected from the Georgia Tech campus and by using the actual video log images taken from Georgia State Route 10 and provided by the Georgia Department of Transportation (GDOT). The experiments show that the algorithm could work well for traffic signs with different types and shapes. Future research is also discussed.