A Novel SDASS Descriptor for Fully Encoding the Information of 3D Local Surface
share
Local feature description is a fundamental yet challenging task in 3D computer vision. This paper proposes a novel descriptor, named Statistic of Deviation Angles on Subdivided Space (SDASS), for comprehensive encoding geometrical and spatial in-formation of local surface on Local Reference Axis (LRA). The SDASS descriptor is generated by one geometrical feature and two spatial features. Considering that surface normals, which are usually used for encoding geometrical information of local surface, are vulnerable to various nuisances, we propose a robust geometrical attribute, called Local Principal Axis (LPA), to replace the normals for generating the geometrical feature of our SDASS descriptor. For accurately encoding spatial information, we use two spatial features for fully encoding the spatial information of a local surface based on LRA. Besides, an improved LRA is proposed for increasing the robustness of our SDASS to noise and varying mesh resolutions. The performance of the SDASS descriptor is rigorously tested on several popular datasets. Results show that our descriptor has a high descriptiveness and strong robustness, and its performance outperform existing algorithms by a large margin. Finally, the proposed descriptor is applied to 3D registration. The accurate result further confirms the effectiveness of the SDASS method.
READ FULL TEXT