一种用于视频监控的AI分析告警平台及方法
By combining negative space and depth discriminators, the problems of high false alarm rate and poor adaptability of existing video surveillance systems in complex scenarios are solved, and alarm response with high accuracy and timeliness is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YUNXIDE TECH (JIANGSU) CO LTD
- Filing Date
- 2025-10-16
- Publication Date
- 2026-07-17
AI Technical Summary
Existing AI analysis and alarm platforms for video surveillance systems rely on positive sample training, which makes it difficult to adapt to dynamic and complex scenarios, resulting in high false alarm rates and poor adaptability, affecting the accuracy and timeliness of video surveillance analysis and alarms.
A negative space based on absolutely normal data is constructed as a priori threshold. Combined with a depth discriminator and a multi-channel directional alarm response, anomaly alarm management is achieved through data entropy change judgment and feature causal processing, including direct alarm and depth verification.
It improves the accuracy and timeliness of video surveillance analysis and alarms, reduces the false alarm rate, and enables precise response to complex scenarios.
Smart Images
Figure CN121305824B_ABST
Abstract
Citation Information
Patent Citations
Semantic region segmentation-based traffic congestion early warning method
CN105894815A
Sample space fault diagnosis method based on multistage high dimension characteristic
CN108052954A