Unloading Apparatus Positioning via Vertical Strip Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for controlling the filling of crop materials in agricultural harvesting machines using image data are complex, lacking robustness, accuracy, and speed due to the need for comprehensive image recognition algorithms.
Innovation Solution
A method that analyzes a limited portion of the image, specifically vertical strips, to derive relative position data between the unloading apparatus and the container, allowing for efficient and simplified control by filtering distance data and using derivatives to determine border positions, enabling precise positioning of the unloading apparatus.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If comprehensive image recognition algorithms are used to control spout position and container filling, then the control coverage is complete, but the system complexity increases and processing speed decreases
Solution Approach 1:
The patent divides the image processing task into segments by selecting only specific vertical strips from the image that contain relevant information about the container borders and crop level. This segmentation approach processes only necessary portions of the image rather than the entire image, reducing computational complexity while maintaining control reliability.
Solution Approach 2:
The patent extracts only the essential distance data from the image that is needed for control decisions - specifically distance values related to container borders and crop surface. By taking out only the relevant information and discarding unnecessary image data, the system achieves reliable control with simpler processing.
2Measurement precision
If comprehensive image recognition algorithms are used to analyze the entire container filling area, then the measurement completeness is high, but the processing speed decreases
Solution Approach 1:
The image is segmented into multiple vertical strips, and only the strips containing container border information are processed in detail. This segmentation allows the system to maintain measurement precision for critical features while significantly reducing the overall processing volume and increasing processing speed.
Solution Approach 2:
Different processing quality is applied to different regions of the image. High-precision processing is applied only to vertical strips containing container borders and relevant features, while other regions receive minimal or no processing. This local quality approach maintains necessary measurement precision while improving overall processing speed.
3Productivity
If the unloading apparatus directs crop to positions above the near upper border or below the remote upper border, then the container filling efficiency increases, but crop piling occurs
Solution Approach 1:
The system continuously measures the distance to container borders and crop surface using the camera, and uses this feedback information to dynamically adjust the unloading apparatus position. This closed-loop feedback control ensures that crop is directed to optimal positions within the container, maximizing filling efficiency while preventing crop piling by maintaining proper spatial relationships.
Data Source
Figure 1
Figure 2
Figure 3A~3F
AI summary
The present invention relates to a method for directing a movable unloading apparatus (1 ) of an agricultural harvesting machine to a container (4) driven adjacent the harvesting machine, the container comprising - as seen from the harvesting machine - near and remote upper borders (6,8). An image of the container is taken by a 3-D camera, in the form of an array of pixels, wherein the camera also generates for each pixel a value of the distance between the camera and the object in the image. The image is analysed by selecting a number of vertical strips (21,22,23) in the image, determining the filtered distance values for each vertical position along the strips, and determining from these distance values the positions of the near and remote upper borders (6,8). On the basis of these data, the unloading apparatus (1 ) is moved towards a predetermined position relative to the container, said predetermined relative position being a position wherein the unloading apparatus directs the harvested crop (3) to a position above said near upper border (6) and/or below said remote upper border (8), respectively.