摘要
高压输电线路定期的巡逻检修是保障其安全可靠运行的重要手段。相比于传统的人工巡检,利用无人驾驶飞机搭载摄像机航拍的巡检方式具有速度快、人力成本低、人员风险小等优势。为了从海量的巡检图像中自动筛选出杆塔可能存在故障的图像,提出了一种融合多源信息的电力杆塔检测框架模型,主要包括摄像机标定、杆塔模型投影变换、杆塔模型聚类分析以及特征提取和匹配4个部分,并在实际的杆塔图像上进行了测试。结果表明,应用检测框架模型处理能够自动检测出图像中杆塔的精确位置,并判断杆塔是否存在杆件丢失等异常状态,验证了模型的有效性。
Regular inspection is key to operation safety and reliability of high-voltage transmission lines. Compared with the conventional manual inspection, inspection of UAV（unmanned aerial vehicle） with a cam- era for aerial photography is characterized by its fast speed, low labor cost, small personnel risk and so forth. In order to automatically select the images that may contain faulty power pylons from mass inspection images, the paper introduces a power pylon detection frame model that integrates multi-source information, including camera calibration, power pylon model projection transformation and cluster analysis as well as feature ex- traction and matching. Furthermore, the frame model is tested on actual pylon images. The results show that the frame model is able to automatically detect the precise power pylon location and determine abnormal sta- tus of power pylon such as member lost, which indicates the validity of the model.
出处
《浙江电力》
2016年第4期6-11,共6页
Zhejiang Electric Power
关键词
电力杆塔
无人机
输电线路
巡检
图像
power pylon
unmanned aerial vehicle （UAV）
transmission line
inspection
image
