A Novel Method of Straight-Line Extraction Based on Wallis Filtering for the Close-Range Building

摘要

3D reconstruction based on high-level features, such as line and plane, is an important development trend in Digital Photogrammetry and Computer Vision. A novel method for extracting stratight line is presented, which can be illustrated as follows. Firstly, image is preprocessed by Wallis filtering that is used to enhance the image contrast and reduce the noise, so it is easy to extract more lines. Secondly, Laplacian of Gaussian operator (LOG) algorithm is implemented to locate the edge by detecting discontinuity variation in image. Thirdly, feature grouping (perceptual organization) and line fitting with hypothesis testing are utilized for combining and fitting fractured short line segments into a whole line, which not only can overcome the deficiency of Hough transform but also can avoid misconnecting grouped collinear lines. Lastly, the least square template matching algorithm (LSTM) is done to get higher precise located lines. The experimental results show that the proposed algorithm by us is more efficient and reliable, which can get richer and higher accurate (sub-pixel) straight line information, especially for the close-range image of building.