As salmon populations face unprecedented threats, a pioneering research project led by Assistant Professor Sara Beery is revolutionizing the way these iconic fish are monitored. By harnessing the power of computer vision and automation, the team aims to enhance oversight and inform data-driven conservation efforts.
Streamlining Data Collection for Improved Salmon Population Management
Assistant Professor Sara Beery is using automation to improve monitoring of migrating salmon in the Pacific Northwest.
The Importance of Accurate Salmon Monitoring
Salmon play a critical role in the health of their ecosystems, supporting a wide range of organisms and maintaining predator-prey relationships. Their migration not only sustains their own species but also contributes significantly to the local economy through commercial and recreational fisheries. For many Indigenous peoples in the Pacific Northwest, salmon hold ‘notable cultural value,’ as they have been central to their diets, traditions, and ceremonies.
The Challenges of Manual Salmon Monitoring
Historically, monitoring efforts relied on humans to manually count salmon from riverbanks using eyesight. In recent years, underwater sonar systems have been implemented to aid in counting the salmon. However, these systems still rely significantly on human effort and are an arduous and time-consuming process.
Automating Salmon Monitoring with Computer Vision
Assistant Professor Sara Beery is leading a research project that aims to streamline salmon monitoring using cutting-edge computer vision methods. The team has been collecting data in the form of videos from sonar cameras at different rivers, annotating a subset of the data to train the computer vision system to autonomously detect and count the fish as they migrate.
Overcoming Challenges with Automatic Adaptation
One challenge faced by the research team was the development of an efficient data infrastructure. To address this issue, the team has implemented a power-efficient computer, coined the ‘Fishbox,’ that can be used in the field to perform processing. The Fishbox consists of a small, lightweight computer with optimized software that fishery managers can plug into their existing laptops and sonar cameras.
Bringing Stakeholders Together
The team is also working to bring a community together around monitoring for salmon fisheries management in the Pacific Northwest. A workshop was organized in Seattle that convened nongovernmental organizations, tribes, and state and federal departments of fish and wildlife to discuss the use of automated sonar systems to monitor and manage salmon populations.
Salmon fisheries management involves regulating fishing activities to maintain healthy populations and conserve ecosystems.
The main goal is to balance human needs with environmental sustainability.
Key strategies include catch limits, closed seasons, and habitat protection.
In the US, the Pacific Salmon Treaty regulates fishing between 'Canada' and the US, while the Marine Stewardship Council certifies sustainable salmon fisheries worldwide.
Effective management requires close monitoring of fish stocks, ocean conditions, and fishing practices to ensure long-term viability.
Looking Forward
As the team continues to tune the computer vision system, refine their technology, and engage with diverse stakeholders — from Indigenous communities to fishery managers — the project is poised to make significant improvements to the efficiency and accuracy of salmon monitoring and management in the region. The Abdul Latif Jameel Water and Food Systems Lab (J-WAFS) seed grant is helping to support this important work.
