An edge and cloud collaborative analysis learning method and system for a drone view

By dynamically packaging view data on the drone end and extracting and associating features at edge nodes, combined with cloud-based adaptive optimization, the problems of fragmentation and lack of linkage in drone view processing are solved, achieving efficient and stable collaborative analysis.

CN122244644APending Publication Date: 2026-06-19JIANGSU FENGPAN TECH CO LTD +1
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
JIANGSU FENGPAN TECH CO LTD
Filing Date
2026-05-19
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

Existing technologies for UAV view processing suffer from problems such as fragmentation, lack of linkage, and static parameters, resulting in computational redundancy and limited real-time performance. Cross-node feature association relies on cloud processing and lacks adaptability.

⚗Method used

The drone-based system dynamically packages view data into logical segments based on semantic and spatiotemporal information. Edge nodes are used for feature extraction and cross-node association to generate a virtual synthetic data stream. Through cloud-based online adaptive parameter optimization, a closed-loop adaptive collaborative analysis is formed.

🎯Benefits of technology

It effectively reduced the computational burden, improved system processing efficiency and stability, enhanced the accuracy and real-time performance of collaborative analysis, and realized an end-to-end optimization system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

This invention discloses an edge-cloud collaborative analysis learning method and system for UAV views, belonging to the field of collaborative analysis technology. This invention effectively avoids the problem of fragmented strongly correlated pixel blocks caused by traditional fixed segmentation, significantly reducing the computational burden of cross-segment feature association for edge nodes. Combining dynamic routing with semantic type labels and edge node load awareness, it achieves accurate matching of computational resources and view content, improving the overall processing efficiency and stability of the system. Furthermore, through master fusion node election, multi-view geometric correction, and pixel-level weighted fusion, it generates a high-quality virtual synthetic data stream. The cloud performs statistical analysis on the time alignment residual and pixel fusion residual, and adaptively adjusts the front-end segment clustering, feature matching, and fusion weight parameters online, forming an end-to-end closed-loop optimization system. This continuously improves the accuracy, real-time performance, and robustness of collaborative analysis in dynamic scenarios.
Need to check novelty before this filing date? Find Prior Art