An integrated low-cost system for object detection in underwater environments

Abstract

We propose a novel low-cost integrated system prototype able to recognize objects/lifeforms in underwater environments. The system has been applied to detect unexploded ordnance materials in shallow waters. Indeed, small and agile remotely controlled vehicles with cameras can be used to detect unexploded bombs in shallow waters, more effectively and freely than complex, costly and heavy equipment, requiring several human operators and support boats. Moreover, visual techniques can be easily combined with the traditional use of magnetometers and scanning imaging sonars, to improve the effectiveness of the survey. The proposed system can be easily adapted to other scenarios (e.g., underwater archeology or visual inspection of underwater pipelines and implants), by simply replacing the Convolutional Neural Network devoted to the visual identification task. As a final outcome of our work we provide a large dataset of images of explosive materials: it can be used to compare different visual techniques on a common basis.