2D Livestock Mobility Scoring for Scalable Lameness Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing livestock monitoring solutions rely on manual intervention or specialized 3D cameras, which are non-scalable, prone to inconsistencies, and have limited operational range and illumination requirements, making them costly and inefficient for monitoring animal mobility and health.
Innovation Solution
A method and system using a 2D camera to capture video recordings, segment frames, detect reference points on animal bodies, and use a neural network to determine mobility scores based on relative position changes, enabling autonomous monitoring without specialized equipment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If specialized 3D camera equipment is used for monitoring animal mobility, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses 2D video recordings as a simplified copy or representation of the animal's movement, rather than requiring complex 3D camera systems. The 2D video data is processed through machine learning algorithms to extract mobility information, effectively replacing expensive specialized equipment with standard cameras and computational analysis.
Solution Approach 2:
The patent replaces the mechanical/optical complexity of 3D camera systems with a computational approach using 2D video analysis and neural networks. Instead of using specialized hardware to capture three-dimensional movement data, the system uses standard 2D cameras combined with AI algorithms to infer mobility metrics.
2Measurement precision
If manual sensor positioning on animals is used for monitoring, then measurement precision is improved, but ease of operation and scalability worsen
Solution Approach 1:
The system allows animals to move freely without requiring manual sensor attachment or positioning. The automated video capture and AI-based analysis performs the monitoring function autonomously, eliminating the need for human intervention in data collection and enabling scalable deployment across large herds.
Solution Approach 2:
The patent replaces manual sensor-based monitoring with an automated computer vision system. Instead of physically attaching sensors to each animal requiring human operation, the system uses overhead 2D cameras with machine learning algorithms to automatically track and analyze animal movement, dramatically improving scalability.
3Measurement precision
If existing image-based solutions with specialized cameras are used, then measurement precision is improved, but adaptability to different environments worsens
Solution Approach 1:
The patent employs a universal 2D camera system that can be deployed in various farm environments without requiring specialized configuration for each location. The machine learning model is trained to handle different lighting conditions and environments, making the system adaptable and versatile across multiple settings while maintaining acceptable measurement precision.
Solution Approach 2:
The system uses machine learning algorithms that can adapt to different environmental parameters such as lighting conditions, camera angles, and animal types. By training the neural network on diverse data, the system becomes flexible and adaptable to various farm environments without requiring specialized hardware configuration for each location.
4Device complexity
If overhead 2D video recording is used for monitoring, then device complexity and cost decrease, but measurement precision and reliability worsen
Solution Approach 1:
The patent replaces complex specialized camera hardware with simple 2D overhead video recording combined with advanced machine learning analysis. The computational intelligence in the neural network compensates for the limitations of 2D data, extracting accurate mobility information that would otherwise require complex 3D sensing systems.
Solution Approach 2:
The system uses standard 2D video cameras to capture animal movement, creating a simplified visual record that is then analyzed through AI algorithms. This approach copies the essential movement information needed for mobility assessment without requiring expensive specialized equipment, achieving cost-effective monitoring with acceptable precision.
Data Source
AI summary
The present invention provides a method and a system for monitoring the mobility levels of individual farm animals and accordingly determining their corresponding mobility score. The mobility score may be indicative of the health and/or welfare status of the animals. The present invention processes a 2D video recording obtained from an imaging device to detect the movement of individual animals through a space. The video recording is segmented over a set of individual frames and in each frame the individual instances of the animal appearing in the vide frame are detected. The detected instances of each animal over a number of frames are grouped together. From each detected instance of an individual animal a set of reference points are extracted. The reference points are associated with location on the animal body. The present invention determines the mobility score of each animal by monitoring the relative position between reference points in each frame and the relative position of each reference point across the set of individual frames associated with an animal.