Optical Teat Positioning via 2D Contour and 3D Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the spatial position and orientation of dairy animal teats are inefficient due to variations in teat shape, size, and arrangement, and require precise and real-time data, especially when animals are in motion, which existing technologies struggle to achieve with high accuracy using conventional 2D and 3D imaging techniques.
Innovation Solution
A method that combines 2D and 3D information from images taken by at least one camera, where 2D contour information is used to extract relevant areas and select a subset of 3D information for precise determination of teat position and orientation, utilizing stereoscopic evaluation and pattern projection for accurate spatial analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional 2D imaging techniques are used to determine teat position, then the device complexity is low, but the measurement precision is insufficient due to variations in teat shape, size, and arrangement
Solution Approach 1:
The patent combines 2D contour information extraction with 3D information processing to determine teat position and orientation. The 2D image data provides contour information that, when merged with 3D spatial data, enables accurate determination of teat coordinates without requiring complex dedicated 3D imaging equipment alone.
Solution Approach 2:
The patent transitions from 2D image analysis to 3D spatial determination by processing images from multiple cameras at different positions. This dimensional enhancement allows accurate teat localization despite variations in teat shape, size, and animal movement, resolving the precision limitation of conventional 2D techniques.
2Productivity
If real-time teat position determination is implemented for moving animals, then the productivity is improved, but the measurement precision deteriorates due to animal movement and breathing
Solution Approach 1:
The system captures images from multiple cameras simultaneously before processing, freezing the momentary position of moving teats. This preliminary capture of spatial data from multiple angles allows subsequent processing to accurately determine teat coordinates even during animal movement, breathing, or chewing activities.
Solution Approach 2:
The patent implements a feedback mechanism where the determined teat position and orientation information is used to control the milking robot's attachment process. This closed-loop control enables real-time adaptation to animal movement, maintaining measurement precision while ensuring productive automated milking operations.
3Measurement precision
If sophisticated equipment like ultrasound or TOF measurements is used to achieve high accuracy, then the measurement precision is improved, but the device complexity and cost increase
Solution Approach 1:
The patent creates a 3D digital model (copy) of the teat and udder region by processing images from conventional cameras. This virtual 3D representation provides sufficient accuracy for milking robot control without requiring physical ultrasound or TOF measurement equipment, thereby reducing device complexity and cost while maintaining measurement precision.
Solution Approach 2:
The patent replaces sophisticated mechanical measurement systems (ultrasound transducers, TOF sensors) with an optical imaging and computational processing system. By substituting complex hardware with software-based 3D reconstruction from 2D images, the system achieves comparable measurement precision with simpler, more cost-effective equipment.
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
This approach allows for quick and precise determination of teat position and orientation in all spatial directions, achieving high accuracy with robust and inexpensive optical devices, suitable for real-time application in milking robots.
Implementation Method 1
At least one 2D image of the teat is captured and 2D contour information is extracted from the image
Implementation Method 2
the position of the teat ends in space can be determined using triangulation methods
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
The invention relates to a method for optically determining the position and/or orientation of an object in space on the basis of images from at least one camera (24a, 24b). At least one 2D image of the object is recorded; 2D contour information is extracted from the image. On the basis of the contour information, at least one area (40) of the object is determined. Furthermore, 3D information is obtained from the at least one 2D image or a further 2D image. A portion situated within the determined area (40) of the object is selected from this 3D information. The position and/or orientation of the object is then determined on the basis of the selected portion of the 3D information. The invention furthermore relates to a use of the method, a device for carrying out the method and a milking robot with such a device.