一种输电线工程车辆监控的误报抑制及重复告警消除方法及系统
By combining lightweight target detection and IOA algorithm, the problems of false alarms, duplicate alarms and missed alarms in the vehicle monitoring system of power transmission line engineering are solved, realizing efficient and real-time vehicle monitoring and adapting to the deployment of low computing power equipment along the power transmission line.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SICHUAN SHUJU INTELLIGENT MFG TECH CO LTD
- Filing Date
- 2026-05-09
- Publication Date
- 2026-07-17
AI Technical Summary
The existing monitoring system for power transmission line engineering vehicles suffers from problems such as high false alarm rate, frequent repeated alarms, high risk of missed alarms, and poor real-time performance. These problems are mainly caused by single-frame detection directly triggering alarms, the traditional IOU matching algorithm having low sensitivity to changes in the shape of engineering vehicles, and the lack of category constraints and specified type control.
A lightweight target detection model combined with the IOA algorithm is used for cross-frame tracking and ID allocation. Through confidence filtering and specified vehicle type verification, alarms are triggered only when the target first appears or its shape changes. The Pearson coefficient is used to determine target changes, achieving accurate tracking and alarm management.
Significantly reduces false alarm and missed alarm rates, reduces duplicate alarms, improves tracking accuracy, ensures system real-time performance, adapts to low-computing-power devices, reduces computing and storage overhead, and meets the real-time requirements of power operation and maintenance.
Smart Images
Figure CN122157173B_ABST