Principal Orientation and Generalized Vanish Point Based Road Detection

Abstract

With the development of road detection related applications, higher performance is required on the accuracy, robustness and time efficiency. Road detection algorithm based on vanishing point estimation has been paid lots attention on for its adaptability when processing complicated situations. However, the existing algorithms based on vanishing point estimation have two shortcomings: 1) unable to handling images with no internal vanishing point, 2) high computational complexity. This paper proposes an improved road detection algorithm based on principal orientation and generalized vanishing point estimation. Proposed method reduce amount of calculation by select effective voting pixels with the principal orientation constraint, and improved the algorithm robustness by handling cases that vanishing point located external of images with the concept of generalized vanishing point. Quantitative and qualitative experiment results donate that the proposed method is both accurate and efficient in road detection. KeywordsRoad Detection; Vanishing Point Estimation; Generalized Vanishing Point; Principal Orientation; Multidimensional Voting Strategy