Distributed and Consistent Multi-Image Feature Matching via QuickMatch
This work addresses the multi-image feature matching problem for applications like SLAM and object detection, but it is incremental as it builds on an existing centralized algorithm.
The authors tackled the multi-image feature matching problem by extending the centralized QuickMatch algorithm to a distributed version that preserves match quality while minimizing communication between agents. They demonstrated that QuickMatch matches features across many images more accurately and in larger numbers than standard techniques.
In this work we consider the multi-image object matching problem, extend a centralized solution of the problem to a distributed solution, and present an experimental application of the centralized solution. Multi-image feature matching is a keystone of many applications, including simultaneous localization and mapping, homography, object detection, and structure from motion. We first review the QuickMatch algorithm for multi-image feature matching. We then present a scheme for distributing sets of features across computational units (agents) that largely preserves feature match quality and minimizes communication between agents (avoiding, in particular, the need of flooding all data to all agents). Finally, we show how QuickMatch performs on an object matching test with low quality images. The centralized QuickMatch algorithm is compared to other standard matching algorithms, while the Distributed QuickMatch algorithm is compared to the centralized algorithm in terms of preservation of match consistency. The presented experiment shows that QuickMatch matches features across a large number of images and features in larger numbers and more accurately than standard techniques.