SALINA: Towards Sustainable Live Sonar Analytics in Wild Ecosystems
Open Access
- 4 November 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 68-81
Abstract
Sonar radar captures visual representations of underwater objects and structures using sound wave reflections, making it essential for exploration, mapping, and continuous surveillance in wild ecosystems. Real-time analysis of sonar data is crucial for time-sensitive applications, including environmental anomaly detection and in-season fishery management, where rapid decision-making is needed. However, the lack of both relevant datasets andpre-trained DNN models, coupled with resource limitations in wild environments, hinders the effective deployment and continuous operation of live sonar analytics. We present SALINA, a sustainable live sonar analytics system designed to address these challenges. SALINA enables real-time processing of acoustic sonar data with spatial and temporal adaptations, and features energy-efficient operation through a robust energy management module. Deployed for six months at two inland rivers in British Columbia, Canada, SALINA provided continuous 24/7 underwater monitoring, supporting fishery stewardship and wildlife restoration efforts. Through extensive real-world testing, SALINA demonstrated an up to 9.5% improvement in average precision and a 10.1% increase in tracking metrics. The energy management module successfully handled extreme weather, preventing outages and reducing contingency costs. These results offer valuable insights for long-term deployment of acoustic data systems in the wild.Keywords
All Related Versions
Funding Information
- NSERC Discovery Grant (RGPIN/4040Discovey RGPIN/4040-2019)
- British Columbia Salmon Recovery and Innovation Fund (BCSRIF_2022_401)
- Mitacs Accelerate Cluster Grant (IT39788)
This publication has 31 references indexed in Scilit:
- Survey on deep learning based computer vision for sonar imageryEngineering Applications of Artificial Intelligence, 2022
- High‐resolution multibeam sonar bathymetry of the deepest place in each oceanGeoscience Data Journal, 2021
- End-to-End Object Detection with Transformers2020
- HOTA: A Higher Order Metric for Evaluating Multi-object TrackingInternational Journal of Computer Vision, 2020
- PV power output prediction from sky images using convolutional neural network: The comparison of sky-condition-specific sub-models and an end-to-end modelJournal of Renewable and Sustainable Energy, 2020
- Counting Fish in Sonar Images2018
- Fully Automated and Highly Accurate Dense Correspondence for Facial Surfaces2016
- SSD: Single Shot MultiBox Detector2016
- Improved adaptive Gaussian mixture model for background subtraction2004
- Adaptive background mixture models for real-time tracking2003