基于图像识别的嵌入式架空线路监测系统

Embedded Monitoring System for High-Voltage Transmission Line Based on Image Recognition

异物入侵所导致的架空线路跳闸严重影响电网安全。提出一种基于双目立体视觉算法进行高压输电线路异物入侵检测的方法,实现了基于嵌入式的前端在线异物入侵检测系统。相对于传统基于单目相机检测的方法,指出该方法的主要优点是对于场景内目标空间位置的估计更加准确,从而能提高异物入侵报警准确率。同时,基于前端嵌入式的系统实现方式可以减少对系统网络带宽的占用并降低系统整体功耗。实验结果表明,研究所实现的系统能够有效地实现对高压输电线路异物入侵的在线自动检测。

The safety of power grid will be seriously affect by overhead line tripping caused by foreign invasion. There-fore, this paper proposes a detection method based on binocular stereo vision algorithm, and realizes the on-line for-eign invasion detection system based on embedded front-end. Compared with the traditional method based on monocu- lar camera detection, this method is superior in more accurately estimating the position of the target within the scene, which can improve the foreign invasion alarming accuracy. At the same time, the system, based on the embedded front-end, can reduce the system network bandwidth utilization and the overall system power consumption. The exper-imental results show that the presented system can effectively achieve the on-line foreign invasion automatic detection for high-voltage transmission lines.