Geometric feature statistics histogram for both real-valued and binary feature representations of 3D local shape

• Published in: Image and vision computing 2022-01, Vol.117, p.104339, Article 104339
• Main Authors: Hao, Linbo, Wang, Huaming
• Format: Article
• Language: English
• Subjects: 3D point cloud; Binary extension; Feature matching; Local feature descriptor; Multiple geometric features
• ISSN: 0262-8856; 1872-8138
• DOI: 10.1016/j.imavis.2021.104339

3D local feature description is now at the core of many 3D vision technologies. However, most of the existing 3D feature descriptors can't strike a balance among descriptiveness, robustness, compactness, and efficiency. To overcome the challenges, we propose a real-valued 3D local feature descriptor named Geometric Feature Statistics Histogram (GFSH) and its binary extension descriptor named B-GFSH. A GFSH descriptor first constructs an improved-weighted covariance matrix to solve a stable and reliable Local Reference Frame (LRF), and then achieves a comprehensive description of the 3D local surface by performing statistics on multiple geometric distribution features, namely voxel density, voxel centroid, and projection density. A particular trait of our GFSH descriptor is its seamless extension to the binary representation to reduce storage consumption and accelerate feature matching. For each sub-feature of GFSH, B-GFSH respectively adopts the corresponding binarization strategy, i.e., improved Gray code quantization, thresholding based on coordinates, and neighbor comparison. Extensive experiments on six public datasets prove that both GFSH and B-GFSH have high descriptiveness, strong robustness, and fast real-time performance. In addition, B-GFSH further has the characteristics of fast matching speed, low memory footprint, and high compactness. Finally, we conduct 3D scene registration and 3D object recognition experiments to visually demonstrate the actual effectiveness of GFSH and B-GFSH. •We propose a real-valued 3D local feature descriptor named GFSH.•The reasonable construction algorithm develops the extensibility and flexibility of GFSH.•We seamlessly extend the real-valued GFSH descriptor to the binary representation named B-GFSH.•Across-dataset experiments and comparisons validate the superiority of GFSH and B-GFSH.