一种视频图像去雾与低光照增强方法及系统
By combining ghost imaging and Fourier layered imaging techniques, along with pulse-coupled neural networks and capsule networks, the problem of uneven image enhancement in complex outdoor environments was solved, achieving clear and natural image processing results that meet the needs of digital twin systems.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING ZHIHUI YUNZHOU TECH CO LTD
- Filing Date
- 2026-01-05
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to distinguish the types and degrees of interference in different regions of an image under complex and variable outdoor environments, leading to uneven image enhancement processing and affecting the accuracy and stability of the digital twin system.
By acquiring video frame sequences and reference frames of the digital twin scene, the light intensity correlation value is calculated using a ghost imaging device, and the Fourier layered imaging method is used for reconstruction to generate a fused feature map. Then, pulse-coupled neural networks and capsule networks are used for region recognition and adaptive restoration to generate a clear image.
It achieves natural overall image enhancement with clear details and smooth regional transitions in dynamic scenes where fog, low light, and turbulence coexist, meeting the high-quality image input requirements of digital twin systems.
Smart Images
Figure CN121458562B_ABST