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 support technologies like a GPS, a self-sufficient visual system is desirable. We introduce a new heuristic approach to outdoor localization in a scenario with sparse visual data and without odometry readings. Localization is interpreted as an optimization problem, and a swarm-based optimization method is adapted and applied, remaining independent of the specific visual feature type. The new method obtains similar or better localization results in our experiments while requiring only two-thirds of the number of image comparisons, indicating an overall speed-up by 25%.