Adaptive UAS Flight Planning for Targeted Agronomic Anomaly Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aerial monitoring systems for agriculture are costly, labor-intensive, and inefficient, requiring high-bandwidth connectivity and trained personnel, and often fail to provide actionable information in a timely manner, leading to suboptimal field monitoring and yield losses.
Innovation Solution
A cyber-physical system using adaptive multi-stage flight planning algorithms and computationally efficient image processing techniques allows for autonomous identification of high-priority areas in fields using UAS, enabling rapid, actionable insights 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 system segments the field into multiple zones and uses multiple UAS vehicles to monitor different areas simultaneously. Each UAS captures images of a specific zone, which are then stitched together to form a complete field map, achieving comprehensive coverage while distributing the system cost across multiple simpler units.
Solution Approach 2:
The system uses consumer-grade UAS vehicles with standard cameras instead of expensive specialized aerial monitoring equipment. By copying the functionality across multiple inexpensive units rather than relying on a single complex system, the patent achieves comprehensive field coverage at reduced cost.
2Measurement precision
If high-resolution images are captured across the entire field, then detection precision is improved, but data processing time and computational resources increase
Solution Approach 1:
The system applies different processing quality levels to different field zones based on anomaly risk. High-resolution processing is applied only to zones flagged as potentially problematic, while other areas receive standard processing. This maintains detection precision for critical areas while reducing overall computational burden and processing time.
Solution Approach 2:
Instead of processing all captured images at maximum resolution, the system performs initial processing at standard resolution and only applies high-resolution processing to specific regions where anomalies are detected. This partial application of excessive processing maintains precision where needed while minimizing overall processing time.
3Productivity
If autonomous anomaly detection is implemented, then agronomist productivity is improved, but algorithm complexity and false positive rates increase
Solution Approach 1:
The system performs preliminary filtering and preprocessing of images before applying complex anomaly detection algorithms. Basic features such as color thresholds, texture patterns, and geometric properties are pre-calculated and used to quickly eliminate normal areas, allowing the more complex algorithms to focus only on suspicious regions and reducing false positives.
Solution Approach 2:
The system introduces intermediate processing layers between image capture and final anomaly detection. These intermediate layers include feature extraction, region proposal generation, and confidence scoring that simplify the task for the final detection algorithm, reducing its complexity while maintaining productivity benefits.
4Productivity
If multi-stage flight planning is used, then image acquisition efficiency is improved, but flight coordination complexity increases
Solution Approach 1:
The flight planning system divides the field into multiple zones and assigns different UAS vehicles to specific zones. Each vehicle executes a simplified flight plan for its assigned area, reducing individual flight coordination complexity. The overall system achieves high image acquisition efficiency through parallel operation of multiple simplified flight plans rather than one complex coordinated plan.
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.