A family of globally optimal branch-and-bound algorithms for 2D–3D correspondence-free registration. (September 2019)

• Record Type: Journal Article
• Authors: Brown, Mark; Windridge, David; Guillemaut, Jean-Yves
• Is Part Of: Pattern recognition. Volume 93(2019:Sep.)
• Page Start: 36
• Page End: 54
• Publication Date: 2019-09
• Subjects: 2D–3D registration -- Multi-modal registration -- Branch-and-bound -- Global optimisation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.04.002
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: First globally optimal solution to the correspondence-free 2D-3D registration problem. The proposed branch-and-bound formulation provides intrinsic guarantees on optimality. Scene primitives invariance allowing registration from both point and line features. Deterministic and probabilistic procedures are introduced to speed-up convergence. The approach enables a significant increase in accuracy and robustness to outliers. Abstract: We present a family of methods for 2D–3D registration spanning both deterministic and non-deterministic branch-and-bound approaches. Critically, the methods exhibit invariance to the underlying scene primitives, enabling e.g. points and lines to be treated on an equivalent basis, potentially enabling a broader range of problems to be tackled while maximising available scene information, all scene primitives being simultaneously considered. Being a branch-and-bound based approach, the method furthermore enjoys intrinsic guarantees of global optimality; while branch-and-bound approaches have been employed in a number of computer vision contexts, the proposed method represents the first time that this strategy has been applied to the 2D–3D correspondence-free registration problem from points and lines. Within the proposed procedure, deterministic and probabilistic procedures serve to speed up the nested branch-and-bound search while maintaining optimality. Experimental evaluation with synthetic and real data indicates that the proposed approach significantly increases both accuracy and robustness compared to the state of the art.