Ground Vehicle Camera Orthomosaic Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for generating orthomosaic agricultural field maps using satellite or aerial imagery face challenges such as cloud cover, limited flight times of unmanned aircraft, and high computational costs for processing, making it difficult for growers to obtain accurate and high-resolution 2D maps.
Innovation Solution
A system utilizing ground vehicle-mounted cameras to capture and process images, removing obstruction and shadow pixels, and reintroducing plant pixels to create clear, undistorted 2D orthomosaic maps, which can be stitched together in real-time or near-real-time, incorporating metadata for georeferencing and image enhancement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If satellite or aerial imagery is used to generate orthomosaic maps, then field coverage is achieved, but cloud cover and wind conditions prevent reliable image acquisition
Solution Approach 1:
Instead of using aerial or satellite imagery to map fields, the patent inverts the approach by mounting cameras on ground-based vehicles that travel through the field. This ground-level perspective avoids cloud cover interference entirely and eliminates wind-related flight restrictions, allowing reliable image acquisition during normal field operations regardless of aerial conditions.
Solution Approach 2:
The patent introduces ground-based vehicles as intermediaries between the imaging system and the field. These vehicles serve as stable platforms that carry cameras through the field, mediating the image collection process without being subject to aerial limitations like cloud cover or wind, thus ensuring reliable data acquisition.
2Duration of action of moving object
If aerial imagery is used, then field mapping is possible, but limited battery capacity restricts flight time
Solution Approach 1:
The patent replaces the aerial mechanical system (drones with limited battery capacity) with a ground-based mechanical system (vehicles with engine or electric power). This substitution eliminates the battery capacity constraint that limits flight time, as ground vehicles have substantially longer operational duration through alternative power sources.
3Measurement precision
If 3D models are generated using stereo cameras and perspective effects, then depth information is obtained, but computational processing becomes expensive
Solution Approach 1:
The patent extracts only the essential 2D mapping information needed for agricultural analysis, removing the computationally expensive 3D modeling step. By using a single camera or simplified imaging approach focused on capturing top-down field views rather than creating full 3D models, the system achieves necessary measurement precision while dramatically reducing computational energy requirements.
4Productivity
If aerial imagery operations are conducted, then field mapping is achieved, but additional time and labor are incurred beyond normal field operations
Solution Approach 1:
The patent merges the field mapping function with normal field operations by mounting cameras on vehicles already present in the field for agricultural work. This combination eliminates the need for separate aerial imagery operations, allowing map generation to occur during routine field activities without adding extra time or labor requirements.
Solution Approach 2:
The ground-based imaging system serves multiple functions simultaneously: it performs both normal field operations and field mapping activities with a single system. The vehicles and cameras are multi-functional, eliminating the need for dedicated aerial mapping operations and thereby reducing total time and labor investment.
Data Source
AI summary
A method for generating a 2D orthomosaic map including obtaining a series of images of a field from a camera located on a ground based vehicle, processing the series of images to mark pixels of the ground based vehicle and optionally an implement, identifying, marking, and removing pixels containing plants, stitching together the series of images into a single map, and reintroducing pixels containing plants into the single map.