Swarm-supported outdoor localization with sparse visual data

— The localization of mobile systems with video data is a challenging field in robotic vision research. Apart from artificial environmental support technologies like GPS localization, a selfsufficient visual system is desirable. In this work, we introduce a new heuristic approach to outdoor localization in a scenario where no odometry readings are available. In an earlier work, we employed SIFT features and a common particle filter method in the scenario. A modification of Particle Swarm Optimization, a popular optimization technique especially in dynamically changing environments, is developed and fit to the localization problem, including self-adaptive mechanisms. The new method obtains similar or better localization results in our experiments, while requiring a fraction of SIFT comparisons of the standard method, indicating an all-over speed-up by 25%.

• Type: Journal
• Year: 2010
• Where: RAS
• Authors: Marcel Kronfeld, Christian Weiss, Andreas Zell
• Keywords: Particle Swarm Optimization, Particle filter Method, RAS 2010, Robotic Vision Research