Underwater Creature Size Estimation via Directional Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating the size of underwater creatures, such as fish, face challenges in achieving high accuracy when fish bodies are facing various directions in captured images, as disclosed in Patent Literature 1.
Innovation Solution
A size estimation device and method that utilize a learning model to estimate feature points on fish bodies facing specific directions, using stereo cameras to capture images from different angles and align fish directions for accurate size calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a rectangular region method is used to specify fish body in captured images, then the measurement process is simplified, but measurement precision deteriorates when fish bodies face various directions
Solution Approach 1:
The system performs preliminary action by sorting and selecting only images where fish bodies face a predetermined direction before进行 size estimation. This pre-filtering step ensures that subsequent measurements are performed on properly oriented fish, resolving the contradiction by maintaining simplicity while improving accuracy through selective processing
Solution Approach 2:
The system applies local quality by directing attention to specific directional characteristics of fish bodies in images. By identifying and processing only those images where fish face the predetermined direction, the system locally optimizes measurement conditions without complicating the overall measurement framework
2Productivity
If images with fish facing various directions are processed together, then processing efficiency is maintained, but measurement precision deteriorates
Solution Approach 1:
The system segments the image processing workflow into distinct stages: first sorting images by fish direction, then selecting predetermined-direction images, and finally performing size estimation. This segmentation allows efficient batch processing while ensuring accuracy through directional filtering, resolving the contradiction between productivity and precision
3Adaptability or versatility
If feature points are specified on fish bodies facing various directions, then adaptability to different fish orientations is improved, but measurement precision deteriorates
Solution Approach 1:
The system extracts and processes only the subset of images where fish face the predetermined direction, separating these from the broader set of images with various orientations. This extraction approach maintains adaptability by accepting all orientations as input while improving precision by focusing analysis on properly oriented specimens
Data Source
AI summary
The size estimation device 5 is provided with an estimation unit 51 and a calculation unit 52. The estimation unit 51 estimates, on the basis of a learning model which learns the feature of a first underwater creature body that faces one direction in an image captured in the water, a first feature point that indicates one end in a one direction side of a second underwater creature body that faces a one direction included in an image captured outside and a second feature point that indicates the other end. The calculation unit 52 calculates information indicating the size of the second underwater creature body on the basis of information including the first feature point and the second feature point.