Aquaculture Sea Lice Detection via Image Quality Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring and counting external fish parasites like sea lice in aquaculture are manual, time-consuming, and prone to inaccuracies, leading to over-treatment or under-treatment, and are challenged by optical distortions and fish behavior in marine environments.
Innovation Solution
A system that captures and analyzes images of fish to distinguish between different classes of sea lice, calculates quality metrics for image sufficiency, and establishes separate detection rates for each class, using a camera and lighting rig with a ranging detector and posture sensing unit to minimize distortion and improve detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual counting methods are used to monitor sea lice on fish, then operators can directly observe and count parasites, but the process becomes extremely time-consuming and labor-intensive
Solution Approach 1:
The patent replaces manual mechanical counting with an automated optical imaging system that captures images of fish and uses image processing algorithms to automatically detect and count sea lice. The system uses a camera to capture images, processes them through software that identifies parasite characteristics, and automatically generates counts, eliminating the need for manual observation and counting while maintaining accuracy.
2Productivity
If manual counting of sea lice is performed on small samples, then the process remains quick, but the results lack validity when extrapolated to large fish populations
Solution Approach 1:
The automated imaging system enables rapid processing of large numbers of fish by capturing and analyzing images automatically. The system can process entire fish populations or large random samples quickly, generating statistically valid data for extrapolation to the entire population. The automated nature ensures consistent processing speed and reliability regardless of sample size.
3Extent of automation
If optical imaging is used to detect sea lice, then automated detection becomes possible, but optical distortions and fish behavior in marine environments reduce detection accuracy
Solution Approach 1:
The system incorporates feedback mechanisms where image quality metrics are continuously evaluated and used to adjust processing parameters. The software analyzes image quality indicators and adapts its detection algorithms accordingly, improving accuracy by compensating for environmental variations and optical distortions through iterative refinement based on actual image conditions.
Solution Approach 2:
The system adjusts various parameters including lighting conditions, camera focus, exposure time, and image processing thresholds to optimize detection accuracy under different marine environmental conditions. By dynamically changing these parameters based on actual imaging conditions, the system maintains high detection precision despite variations in water clarity, light availability, and fish movement.
4Measurement precision
If separate detection rates are established for different parasite classes, then more accurate infestation assessment is achieved, but the complexity of data processing increases
Solution Approach 1:
The system segments the parasite population into distinct classes (such as adult female, adult male, and juvenile sea lice) and establishes separate detection rates for each class. The image processing software automatically categorizes detected parasites based on their visual characteristics, allowing for differentiated infestation assessment. This segmentation enables more precise monitoring of different life stages and types of parasites while the automated classification algorithms manage the processing complexity.
Data Source
AI summary
A method for external fish parasites, such as sea lice, monitoring in aquaculture, comprising the steps of: —submerging a camera (52) in a sea pen (40) comprising fish (72, 74); —capturing images of the fish (72, 74) with the camera (52); and —identifying external fish parasites such as sea lice on the fish (72, 74) by analyzing the captured images, characterized by the steps of: —distinguishing between at least two different classes of external fish parasites such as sea lice which differ in the difficulty of recognizing the external fish parasites such as sea lice; —calculating quality metrics for each captured image, the quality metrics permitting to identify the classes of external fish parasites such as sea lice for which the quality of the image is sufficient for sea lice detection; and —establishing separate detection rates for each class of sea lice, each detection rate being based only on images the quality of which, as described by the quality metrics, was sufficient for detecting external fish parasites such as sea lice of that class.