Rigid blocks matching method based on contour curves and feature regions. Issue 1 (7th November 2017)

• Record Type: Journal Article
• Authors: Zhao, Fuqun; Zhou, Mingquan; Geng, Guohua; Zhu, Lipin
• Is Part Of: IET computer vision. Volume 12:Issue 1(2018)
• Page Start: 76
• Page End: 85
• Publication Date: 2017-11-07
• Subjects: image matching -- feature extraction -- iterative methods -- probability -- image segmentation; rigid block matching method -- contour curves -- feature regions -- coarse matching -- fine matching -- improved boundary growth method -- improved iterative closest point algorithm -- improved ICP algorithm -- rotation angle constraint -- dynamic iteration coefficient -- probability ICP algorithm -- feature extraction; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2016.0392
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : This study proposes a blocks matching method based on contour curves and feature regions that improve the matching precision and speed with which rigid blocks with a specified thickness in point clouds are matched. The method comprises two steps: coarse matching and fine matching. In the coarse matching step, the rigid blocks are first segmented into a series of surfaces and the fracture surfaces are distinguished. Then, the contour curves of the fracture surfaces are extracted using an improved boundary growth method and the rigid blocks are coarsely matched with them. In the fine matching step, feature regions are first extracted from the fracture surfaces. Then, the centroid of each feature region is calculated and the fine matching of rigid blocks with the centroid sets is completed using an improved iterative closest point (ICP) algorithm. The improved ICP algorithm integrates the rotation angle constraint and dynamic iteration coefficient into a probability ICP algorithm, which significantly improves matching precision and speed. Experiments conducted using public blocks and Terracotta Warriors blocks indicate that the proposed method carries out rigid blocks matching more accurately and rapidly than various conventional methods.