Dynamic Edge Detection for GPS-Limited Tractor Row Guidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated vehicle operations face challenges due to unreliable GPS signals and limited processing power in embedded controllers, leading to inaccurate navigation and potential delays in farming vehicles.
Innovation Solution
A row vision system that uses camera images to detect edges between surfaces, incorporating operator input to enhance edge detection accuracy and reduce processing requirements by focusing on specific image areas, employing machine learning models to select the most accurate edge for modifying vehicle routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If GPS information is used for automated navigation, then wireless communication convenience is improved, but signal reliability deteriorates due to fading, shadowing, and interference
Solution Approach 1:
The patent introduces an intermediary system (computer vision system with camera and image processing) that mediates between the unreliable GPS wireless communication and the navigation function. Instead of relying solely on GPS signals, the system uses visual intermediaries (camera images) to detect edges and determine vehicle position, thereby resolving the contradiction by replacing the direct but unreliable wireless channel with an indirect but more reliable visual detection path.
2Measurement precision
If computer vision systems process entire images to identify edges, then edge detection accuracy is improved, but processing time and power consumption increase
Solution Approach 1:
The patent applies segmentation by dividing the image processing task into distinct stages: first identifying candidate edge regions using efficient algorithms, then applying more computationally intensive edge detection models only to those specific regions rather than the entire image. This segmentation allows the system to maintain high edge detection accuracy while significantly reducing overall processing time and power consumption.
Solution Approach 2:
The system performs partial action by applying full edge detection processing only to candidate regions identified as likely to contain relevant edges, rather than processing the entire image with the same level of detail. This selective approach maintains accuracy for critical areas while reducing unnecessary processing in other regions.
3Device complexity
If embedded controllers with limited processing power are used, then device simplicity is improved, but automated operation responsiveness deteriorates due to processing delays
Solution Approach 1:
The patent segments the processing workload between the embedded controller and external systems. The embedded controller handles simple tasks and communicates with external computers or servers that perform more intensive image processing and edge detection. This segmentation allows the embedded controller to remain simple while the system as a whole achieves high responsiveness through distributed processing.
Solution Approach 2:
The system introduces an intermediary processing layer (external computer or server) that mediates between the simple embedded controller and the complex image processing requirements. The embedded controller captures images and transmits them to the intermediary system for intensive processing, then receives results back for execution, thereby maintaining device simplicity while achieving high productivity.
4Power
If mobile devices are used for automated operation, then processing power is improved, but processing delays occur due to power constraints and resource limitations
Solution Approach 1:
The system performs partial processing on mobile devices by pre-identifying candidate regions and performing only necessary edge detection on those specific areas rather than processing entire images at full resolution. This selective approach reduces the computational burden on mobile devices, minimizing processing delays while maintaining adequate processing power utilization.
Data Source
AI summary
A row vision system modifies automated operation of a vehicle based on edges detected between surfaces in the environment in which the vehicle travels. The vehicle may be a farming vehicle (e.g., a tractor) that operates using automated steering to perform farming operations that track an edge formed by a row of field work completed next to the unworked field area. A row vision system may access images of the field ahead of the tractor and apply models that identify surface types and detect edges between the identified surfaces (e.g., between worked and unworked ground). Using the detected edges, the system determines navigation instructions that modify the automated steering (e.g., direction) to minimize the error between current and desired headings of the vehicle, enabling the tractor to track the row of crops, edge of field, or edge of field work completed.