Satellite image auxiliary based unmanned aerial vehicle image super-resolution reconstruction method and system
By constructing a UAV image-satellite image pair dataset and designing a deep learning fusion network model, the problem of insufficient utilization of satellite images in UAV image super-resolution reconstruction was solved, achieving high-resolution image reconstruction and improving the accuracy of image analysis and detail recognition capabilities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HANGZHOU DIANZI UNIV
- Filing Date
- 2026-05-27
- Publication Date
- 2026-07-17
AI Technical Summary
Existing UAV image super-resolution reconstruction technology cannot effectively utilize satellite image information, resulting in poor reconstruction quality, especially when the UAV image resolution is low, making it difficult to meet the requirements of high-precision analysis.
We constructed a dataset of UAV image-satellite image pairs and designed a deep learning-based multi-input image fusion network model. Through feature extraction, matching, and decoding, we achieved feature fusion of images from different perspectives to reconstruct high-resolution images.
By effectively utilizing satellite imagery information, the resolution of UAV images can be improved, image detail information can be enhanced, and the accuracy of image analysis and the ability to identify small targets can be increased.
Smart Images
Figure CN122415336A_ABST