30 April 2018 Recognizing objects in 3D data with distinctive self-similarity features
Author Affiliations +
Abstract
Local features with invariant descriptions are important for many tasks in image processing and computer vision. This paper presents a new local feature descriptor for 3D object and scene representation. The new descriptor, named 3DSSIM, explores the internal geometric property of layout similarity of 3D objects to produce efficient feature representation. The 3D-SSIM is highly distinctive, quick to compute, and shows superior advantages in terms of robustness to noises, invariance to viewpoints, and tolerance to geometric distortions. We extensively evaluated performance of the new descriptor with various datasets.
Conference Presentation
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Suya You, Suya You, Jing Huang, Jing Huang, "Recognizing objects in 3D data with distinctive self-similarity features", Proc. SPIE 10648, Automatic Target Recognition XXVIII, 106480D (30 April 2018); doi: 10.1117/12.2305110; https://doi.org/10.1117/12.2305110
PROCEEDINGS
9 PAGES + PRESENTATION

SHARE
RELATED CONTENT

Moment Invariants Of Perspective Transformation
Proceedings of SPIE (March 26 1989)
Geometric features in images of polyhedra
Proceedings of SPIE (October 02 1995)
The Vision By Pattern Aggregation - V.P.A.- System
Proceedings of SPIE (December 10 1985)
Object recognition based on reflectance and geometry
Proceedings of SPIE (June 22 1993)

Back to Top