Adaptive UAV Field Monitoring for Anomaly-Targeted Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aerial monitoring systems for agriculture are costly, labor-intensive, and impractical for frequent field monitoring due to high capital and labor costs, and they fail to deliver actionable information in a timely and cost-effective manner, requiring agronomists to revisit fields for verification.
Innovation Solution
An adaptive cyber-physical system using multi-stage flight planning algorithms and computationally efficient image processing techniques allows for real-time identification of high-priority areas in fields, enabling unmanned aerial vehicles (UAVs) to autonomously capture high-resolution images without cloud connectivity, and learns from user feedback to improve image acquisition and presentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If current aerial monitoring systems are used, then field monitoring coverage is improved, but cost and labor requirements increase significantly
Solution Approach 1:
The patent segments the field monitoring task into two distinct phases: a first flight path for broad area coverage and a second flight path for focused high-resolution imaging of specific regions of interest. This segmentation allows the system to achieve comprehensive field coverage while avoiding the need for continuous high-cost high-resolution monitoring of entire fields, thereby reducing overall operational costs and labor requirements.
Solution Approach 2:
The system applies local quality by using high-resolution imaging only for specific regions of interest identified during the first flight phase, rather than uniformly applying high-resolution monitoring across the entire field. This approach maintains monitoring quality where needed while reducing resource consumption in areas where broad coverage suffices, effectively resolving the contradiction between coverage and cost.
2Measurement precision
If high-resolution images are captured across the entire field, then monitoring accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The patent extracts and processes only the most critical data by first identifying regions of interest through broad-area imaging, then capturing high-resolution images solely for those specific areas. This extraction approach eliminates the need to process vast amounts of high-resolution data from entire fields, significantly reducing computational time and resource requirements while maintaining monitoring accuracy for the most important areas.
Solution Approach 2:
The system performs preliminary identification of regions of interest through the first flight path before committing resources to high-resolution imaging. This preliminary action allows the system to pre-filter areas requiring detailed inspection, ensuring that high computational resources are allocated only to areas where they will provide maximum value, thereby reducing overall processing time.
3Reliability
If frequent field monitoring is conducted, then early problem detection is improved, but operational costs increase
Solution Approach 1:
The patent implements a dynamic monitoring strategy where the system adapts its resource allocation based on identified needs. By using the two-stage flight approach, the system can frequently monitor fields for early problem detection while dynamically adjusting the level of detail and resource investment based on what regions of interest are actually detected, thereby maintaining reliability without incurring excessive operational costs.
Data Source
AI summary
The present disclosure provides a system for monitoring unstructured environments. A predetermined path can be determined according to an assignment of geolocations to one or more agronomically anomalous target areas, where the one or more agronomically anomalous target areas are determined according to an analysis of a plurality of first images that automatically identifies a target area that deviates from a determination of an average of the plurality of first images that represents an anomalous place within a predetermined area, where the plurality of first images of the predetermined area are captured by a camera during a flight over the predetermined area. A camera of an unmanned vehicle can capture at least one second image of the one or more agronomically anomalous target areas as the unmanned vehicle travels along the predetermined path.