Line segment detection based on probability map
Fei Wu, Sun Li, Bo Wang, Jinlei Ma · 2017
In this paper, a novel line segment detection method based on probability map is proposed. Firstly, the local gradient information is used to estimate if a pixel belongs to a line segment and a probability map is produced. The probability map combines gradient orientation with gradient magnitude information and can provide candidate points for edge chain extraction. Secondly, these candidate points are connected together to generate edge chains and then edge chains are split to candidate line segments by using least square line fitting method. At last, we apply Helmholtz principle to validate the detected line segments. Experimental results demonstrate that the proposed method outperforms other methods in term of visual comparison and quantitative assessment.