Underwater mapping finds litter faster with camera and sonar combined
Active Mapping of Underwater Litter Using Camera-Sonar Fusion
Robotics
Summary
Marine litter harms underwater life, but finding this litter is hard because cameras don’t work well in murky water and sonar gives fuzzy images. The authors created a method that uses both a camera and sonar together, combining their information in a smart map that guesses where litter might be. A computer then chooses where to look next to find trash faster than searching in a fixed pattern. Their tests in a realistic underwater simulation showed this combined approach locates trash more quickly than using just one sensor or sweeping the area evenly.
What this means in practice
- •For marine survey teams: Conduct underwater litter surveys more efficiently by actively selecting sensor viewpoints using combined camera and sonar data.
- •For environmental monitoring operators: Improve autonomous underwater debris detection systems by integrating sonar and camera data for faster and more reliable identification of litter.
Authors
David Rete, Patrick Boros, Lucian Busoniu
Abstract
Marine litter is a growing threat to the underwater ecosystem, driving demand for autonomous survey methods that can locate debris efficiently over large areas. Existing survey methods typically follow predefined paths or operate with a single sensing modality, typically a camera (with image quality suffering in poor-visibility conditions) or sonar (usually noisy and low-resolution). We present an active mapping framework in which a forward-looking sonar and a camera both feed into a shared Bayesian occupancy map, and an optimization problem is solved at each step to decide on the next best view. Candidate viewpoints are scored by a two-term utility that balances exploration of uncertain regions via voxel entropy against exploitation of likely objects. Each sensor is characterized by range- and bearing-dependent detection and false-alarm probability tables determined from data. We evaluate the approach in a realistic underwater simulator, demonstrating that active mapping finds objects faster than a lawnmower coverage pattern, and that the dual-sensor approach works better than using either of the individual sensors.