EXTRACTION OF HORIZONTAL VANISHING LINE USING SHAPES AND STATISTICAL ERROR PROPAGATION

In this paper we address the problem of estimating the horizontal vanishing line, making use of motion statistics derived from a video sequence. The computation requires the satisfying of a number of corresponding object's height measurement; and in our approach these are extracted using motion statistics. These easy-to-compute statistics enable accurate determination of average shape of every point in the image. Thanks to the use of motion statistics and error propagation formulas in the intermediate steps, our approach gives robust results. The outcomes show that our approach gives accurate results in the context of different environments.