Single and Cross-Dimensional Feature Detection and Description: An Evaluation
This work addresses a gap in object registration and recognition for researchers by evaluating cross-dimensional methods, but it is incremental as it builds on existing single-dimensional evaluations.
The paper tackled the problem of evaluating cross-dimensional (mixed 2D and 3D) feature detection and description methods, which had not been previously investigated, and demonstrated that cross-dimensional schemes outperform single-dimensional ones on several 3D datasets.
Three-dimensional local feature detection and description techniques are widely used for object registration and recognition applications. Although several evaluations of 3D local feature detection and description methods have already been published, these are constrained in a single dimensional scheme, i.e. either 3D or 2D methods that are applied onto multiple projections of the 3D data. However, cross-dimensional (mixed 2D and 3D) feature detection and description has yet to be investigated. Here, we evaluated the performance of both single and cross-dimensional feature detection and description methods on several 3D datasets and demonstrated the superiority of cross-dimensional over single-dimensional schemes.