Animal In-Vivo Imaging Device Using 3D Scanner and Neural Network Focus
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing animal in-vivo imaging devices struggle to obtain optimal images due to difficulties in focusing on various subjects, such as mice and rats, with diverse types and sizes, and changing depth of field based on magnification ratios.
Innovation Solution
An animal in-vivo imaging device equipped with a camera, a three-dimensional scanner, and a neural network model that automatically adjusts the camera focus based on the type of animal, target organ, and three-dimensional shape information, ensuring accurate depth and position estimation of the target organ.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a set focus value or autofocus function is used, then the focusing process is simple, but optimal focus cannot be achieved for diverse animal subjects with different sizes and postures
Solution Approach 1:
The patent replaces traditional mechanical autofocus mechanisms with an AI-based estimation system. The estimation unit uses a trained neural network model to predict depth information of target organs, substituting complex mechanical focusing adjustments with intelligent algorithmic prediction based on animal type, organ type, and 3D shape information.
Solution Approach 2:
The system changes the focusing parameter from fixed or automatically detected values to dynamically predicted depth values. By varying the focus value based on estimated depth information from the neural network model, the system adapts to different animal subjects, organs, and 3D shapes, achieving optimal focus for each specific case.
2Adaptability or versatility
If the depth of field range is increased to accommodate diverse animal sizes, then various subjects can be captured, but the focus becomes less precise for specific target organs
Solution Approach 1:
The patent applies local quality by setting different focus values for different regions or targets. Instead of using a single depth of field setting for the entire image, the system predicts specific depth information for target organs and adjusts the focus value locally to match the predicted organ depth, ensuring precise focus on the target while accommodating diverse animal subjects.
3Measurement precision
If manual focus adjustment is performed to achieve optimal focus, then image quality improves, but the operation becomes complex and time-consuming
Solution Approach 1:
The system performs self-service by automatically estimating depth information and determining optimal focus values without user intervention. The estimation unit uses the neural network model to predict depth values, and the system automatically adjusts the focus, eliminating the need for manual focus adjustment while maintaining high image quality.
Solution Approach 2:
The system implements feedback by using 3D shape information measured by the scanner as input to the neural network model, which then predicts depth information that feeds back to the focus adjustment mechanism. This closed-loop feedback system continuously optimizes focus based on actual animal geometry and target organ position.
Data Source
AI summary
An animal in-vivo imaging device comprises: a camera for capturing an image of an animal and including a focus lens for adjusting a focus; a three-dimensional scanner for measuring three-dimensional shape information of the animal; an estimation unit configured to output depth information of a target organ by inputting the type of animal, the target organ, a preview image captured by the camera, and the three-dimensional shape information measured by the three-dimensional scanner into a trained neural network model; and a focus adjustment unit that adjusts a focus by controlling a focus driving motor that drives the focus lens according to the depth information.