Summary
Processing sonar data like images can be slow and complicated for autonomous systems. The authors suggest using a simpler format, CSV, to handle sonar signals more efficiently. Their approach greatly reduces the time needed for processing while improving how well machine learning can identify objects. It also enhances the quality of the signals used for detection.
What this means in practice
- •For autonomous system engineers: Process sonar data faster on-board using CSV formats, enabling quicker object detection with improved accuracy.
- •For marine survey teams: Enhance object identification in underwater remote sensing by using alternative signal processing methods that boost signal quality.
Authors
Logan Luna, Sirio Jansen-Sánchez, Ilteris Demirkiran, Leo Ghelarducci
Abstract
The dominant method of processing sonar data is using image-based representations, requiring the preprocessing of image data on autonomous systems. We propose an alternative data processing method for remote sensing applications via the use of data in Comma-Seperated Value format. Experimentation on our alternative approach shows a reduction of processing time by 91.18%, an improvement in accurate object detection by Machine Learning, and an increase in SNR (Signal-to-noise ratio), PSNR (Peak signal-to-noise ratio), and other evaluation metrics.