3D Machine Vision for Automated Sow Estrus Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current estrus detection methods in swine farming are labor-intensive, inaccurate, and time-consuming, leading to low farrowing rates and increased economic losses due to missed insemination opportunities and high replacement rates of sows.
Innovation Solution
A robotic system using a 3D measurement device and deep learning models to automatically detect vulva volume changes in sows, incorporating a motorized movable mechanism and a control unit to analyze images and determine estrus status.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual estrus detection methods are used, then labor costs are high and detection accuracy is low, but automation introduces device complexity
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated imaging system using cameras and machine learning algorithms. The system captures images of the sow's vulva region and uses deep learning models to automatically detect estrus status, eliminating the need for manual physical examination while improving detection accuracy and consistency.
Solution Approach 2:
The system enables self-detection by allowing the imaging device to automatically capture and analyze vulva images without requiring human intervention. The machine learning model processes the images autonomously to determine estrus status, making the detection process self-sufficient and reducing labor dependency.
2Loss of time
If frequent manual inspection is performed, then detection timeliness improves, but labor time and costs increase significantly
Solution Approach 1:
The imaging system operates continuously or at scheduled intervals to monitor vulva changes without interruption. Multiple images are captured over time to track the development of estrus symptoms, ensuring continuous monitoring while eliminating the need for repeated manual inspections and optimizing the detection timeline.
Solution Approach 2:
The system performs preliminary detection by capturing early signs of vulva swelling and color changes before full estrus manifestation. This allows for advance identification of potential estrus cases, enabling timely intervention and reducing non-productive days by detecting changes at their earliest stages.
3Productivity
If automated imaging systems are deployed, then labor costs decrease, but measurement precision requirements increase
Solution Approach 1:
The system transitions from two-dimensional visual inspection to three-dimensional volumetric analysis of the vulva. By capturing depth information and calculating volume changes, the system provides more precise quantitative measurements that are more reliable for detecting estrus than traditional 2D visual assessment, thereby meeting the higher precision requirements of automated detection.
Solution Approach 2:
The system changes the measurement parameter from subjective visual assessment to objective quantitative metrics such as vulva volume, surface area, and color intensity. These measurable parameters provide precise, numerical data that can be consistently analyzed by machine learning algorithms, ensuring high measurement precision in automated detection.
Data Source
AI summary
Accurate estrus detection of sows is critical to achieving a high farrowing rate and maintaining good reproductive performance. However, the conventional method of estrus detection uses a back pressure test by farmers, which is time-consuming and labor-intensive with a significant degree of error. This disclosure is of an automated estrus detection method by monitoring the change in vulva swelling around the estrus using a three-dimensional measurement device, e.g., LiDAR camera, which includes an RGB camera and a depth camera. This sow estrus detection improves accuracy and efficiency, reduces labor and cost, and improves the sustainability of swine production using a data-driven decision-making system based on a robotic cyber-physical system (CPS) that can utilize deep learning detection based on a deep learning model.