一种交通车站监控视频的图像压缩处理方法
By using the inter-frame difference method and the pose estimation key point algorithm, the importance values of different areas in the traffic station monitoring video are calculated, and an appropriate compression ratio is selected for compression. This solves the problems of low compression efficiency and loss of key information in the existing technology, and achieves efficient image compression and preservation of key information.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING HUNTER INFORMATION TECH CO LTD
- Filing Date
- 2025-12-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to improve compression efficiency while preserving important data when compressing surveillance videos at transportation stations, and existing methods may result in loss of visual quality in critical areas.
The inter-frame difference method and pose estimation keypoint algorithm are used to calculate the importance value of different regions in the image. Different compression ratios are selected according to the importance to compress the image, and the information of important regions is preserved.
By differentiating the compression ratios of important and unimportant regions in an image, compression efficiency is improved, storage space is saved, and the integrity of critical information is ensured at the same time.
Smart Images
Figure CN121771398B_ABST
Abstract
Citation Information
Patent Citations
Audio and video conjoint analysis-based fighting detection system and detection method thereof
CN102098492A
Fight behavior detection method based on spatio-temporal interest point
CN103279737A