变电站双目视觉隐患行为告警方法、系统、设备及介质
By using binocular cameras and a 3D sparse point cloud ranging algorithm, the problem of quantifying the distance between potential hazards and equipment in substations was solved, enabling differentiated alarms for potential hazards in substations and improving the intelligence and response efficiency of safety monitoring.
CN122135505BActive Publication Date: 2026-07-17HUAYAN INTELLIGENT TECH (GRP) CO LTD +3
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUAYAN INTELLIGENT TECH (GRP) CO LTD
- Filing Date
- 2026-04-30
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies cannot accurately measure the distance between potential hazards in substations and power equipment, making it impossible to precisely control the degree of harm caused by these hazards to the equipment.
Method used
Images of key nodes of the equipment are acquired using binocular cameras to construct spatial relationships. Combined with personnel behavior detection and entity segmentation models, the distance between personnel and equipment is calculated using a 3D sparse point cloud ranging algorithm, and the hazard alarm level is determined based on the distance.
Benefits of technology
It enables differentiated alarms for potential hazards in substations, improving the intelligence level and response efficiency of operational safety monitoring.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122135505B_ABST
Abstract
本发明公开了一种变电站双目视觉隐患行为告警方法、系统、设备及介质，涉及行为告警技术领域。该方法包括：通过双目相机采集设备关键节点双目图像，进而构造设备关键节点的空间关系；通过间隔采样变电站双目视觉图像，检测出双目隐患行为矩形框，进而采集实时变电站双目视觉图像；通过实时变电站双目视觉图像，检测出双目隐患行为矩形框，进而利用双目人体分割与关键点匹配，构造人体关键节点的空间关系；基于人体关键节点的空间关系与设备关键节点的空间关系，采用稀疏点云测距算法计算人员与设备距离，并据此进行不同隐患告警等级的差异化告警。这样，通过量化隐患行为与变电设备之间的距离，实现了变电站隐患行为的差异化告警。
Need to check novelty before this filing date? Find Prior Art