3D Animal Weight Estimation Using Curve-Fit Regression

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing animal weight estimation methods, such as weight scales and 2D imaging, are costly, cumbersome, and limited in accuracy, while 3D imaging systems often require model generation and are not efficient for concurrent animal measurement.

Innovation Solution

A 3D imaging system using a 3D TOF camera captures animal data, extracts 3D pixel samples, fits curves to derive parameters, and applies regression algorithms to estimate weight without model comparison, enabling accurate and concurrent weight estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If 3D imaging systems use model generation and comparison for weight estimation, then measurement accuracy is improved, but device complexity and operational costs increase

Engineering Contradiction:
Improveweight estimation accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential geometric features (length, width, height) from the 3D point cloud data of animals, eliminating the need for complex model generation and comparison. By focusing on basic dimensional measurements rather than full model matching, the system achieves weight estimation without the computational overhead of complex 3D models.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the mechanical/model-based approach with a direct geometric measurement approach using regression algorithms. Instead of comparing animals to pre-defined 3D models, the system directly correlates measured dimensions (length, width, height) with weight through statistical regression, substituting complex model matching with simpler mathematical relationships.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If weight scales are installed on the floor of pens, then weight measurement accuracy is improved, but ease of operation and installation complexity worsen

Engineering Contradiction:
Improveweight measurement accuracyVSAvoidoperational convenience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces mechanical weight scales with an optical imaging system that estimates weight from 3D geometric measurements. This substitution eliminates the need for animals to physically interact with scales, allowing remote, non-contact weight estimation that is easier to operate and requires no animal handling.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces 3D imaging and geometric measurement as an intermediary between the animal and weight measurement. Instead of directly measuring weight through physical contact, the system uses intermediate geometric parameters (length, width, height) captured by imaging to infer weight, providing a convenient non-contact measurement method.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Device complexity

If 2D imaging is used for weight estimation, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoidweight estimation accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent transitions from 2D imaging to 3D point cloud data acquisition, adding the depth dimension to the measurements. This dimensional enhancement provides accurate length, width, and height measurements that capture the true three-dimensional geometry of animals, significantly improving weight estimation accuracy while maintaining relatively simple system architecture.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

4Productivity

If multiple animals are measured concurrently, then productivity is improved, but measurement precision may deteriorate due to alignment requirements

Engineering Contradiction:
Improvemeasurement throughputVSAvoidweight estimation accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the point cloud data to identify and measure individual animals independently within the scene. By separating and processing each animal's geometric data individually through curve fitting and dimension extraction, the system maintains high measurement precision even when multiple animals are present and measured simultaneously.

Inventive Principle:
Principle #1Segmentation

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system provides precise and efficient weight estimation for multiple animals without direct camera alignment, reducing installation complexity and operational costs, and improving measurement accuracy.

Implementation Method 1

A 3D image of a target region for one or more animals is recorded

Methodology Applied
Scientific EffectTime of flight: Time of Flight

Data Source

PatentEP3646287B1Regression-based animal weight estimation
Publication Date: 2026.04.08 THE GSI GRP LLC
  • EP3646287B1 patent drawingFigure 1
  • EP3646287B1 patent drawingFigure 2A~2B
  • EP3646287B1 patent drawingFigure 3

AI summary

In one embodiment, a method executed by a computing system, comprising: receiving pixel samples from three-dimensional (3D) data corresponding to one or more images comprising one or more animals; fitting curves for the received pixel samples; deriving parameters from the curves; determining measurements based on variations in the parameters; and estimating a weight of the one or more animals by applying one or more regression algorithms to the measurements.