Aggregation of binary feature descriptors for compact scene model representation in large scale structure-from-motion applications
This addresses memory efficiency for incremental structure-from-motion and SLAM applications, though it appears incremental as it builds on existing descriptor aggregation techniques.
The paper tackles the problem of high memory usage in large-scale structure-from-motion by aggregating binary feature descriptors into compact real-valued prototypes, resulting in significant memory reduction and enabling faster matching with approximate nearest neighbor search methods like FLANN.
In this paper we present an efficient method for aggregating binary feature descriptors to allow compact representation of 3D scene model in incremental structure-from-motion and SLAM applications. All feature descriptors linked with one 3D scene point or landmark are represented by a single low-dimensional real-valued vector called a \emph{prototype}. The method allows significant reduction of memory required to store and process feature descriptors in large-scale structure-from-motion applications. An efficient approximate nearest neighbours search methods suited for real-valued descriptors, such as FLANN, can be used on the resulting prototypes to speed up matching processed frames.