一种低照度宽视场视频图像变化检测方法及装置
By employing extreme value average ratio operator, Laplacian pyramid adaptive fusion, and improved adaptive median filtering, the problem of decreased video image quality in eagle-eye cameras under low illumination conditions is solved, achieving efficient video image change detection. This method is suitable for security monitoring of large-area ordinary cameras.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XINJIANG UNIVERSITY
- Filing Date
- 2024-04-17
- Publication Date
- 2026-07-17
AI Technical Summary
Under low light conditions, the video image quality of the eagle eye camera deteriorates, resulting in reduced image clarity and difficulty in detecting small targets. Existing algorithms are not effective in detecting changes in video images under wide field of view and low light conditions, and the detection time is relatively long.
The difference map is generated by the extreme value average ratio operator, and the Laplacian pyramid adaptive fusion and TVL1 dual method are combined to denoise the image. Improved adaptive median filtering and K-means clustering are used to enhance image contrast and suppress noise. The final detection result is obtained by threshold segmentation and K-means clustering.
It significantly shortens detection time, improves detection accuracy, reduces false alarms, lowers costs, reduces waste of human resources, and is suitable for large-scale deployment of ordinary cameras.
Smart Images
Figure CN118279829B_ABST