红外与毫米波学报, 2017, 36 (5): 554, 网络出版: 2017-11-21  

巡线LiDAR多通道光谱图像异常识别技术

LiDAR multichannel spectral abnormal image recognition technology for transmission lines
作者单位
1 长春理工大学 理学院, 吉林 长春 130022
2 吉林建筑大学 电气与计算机学院, 吉林 长春 130000
3 中国大唐集团技术经济研究院,北京 101401
摘要
联合GPS、ISN、LiDAR、测距机等, 构建超POS信息;计算最小视场分辨率、像元数、焦距等选择相机;将POS采集系统与相机组合成LiDAR多通道光谱图像异常识别系统.采用多通道匹配融合法融合紫、红外、彩色图片, 基于Hough变换, 通过同族容器归纳法确定疑似故障点.运用Hough变换、免疫遗传Snake、最小二乘法解析椭圆形貌, 解决绝缘子异常识别问题.工程实验表明, 该系统平均探测精度是82.4%, 优于直升机与人工平均值24.05%, 是一种高效率的智能电网巡线排查手段.
Abstract
The position and orientation system (POS) information of a target can be obtained through airborne laser radar (LiDAR) technology combined with the Global Positioning System, an inertial navigation system, and a laser range finder. The camera is chosen by calculating the minimum field of view resolution, pixel number, focal length, and other parameters. The LiDAR multichannel spectrum image recognition system is composed of the POS information acquisition system and the multispectral camera. The multichannel matching fusion method can produce ultraviolet, infrared, and color pictures. The elliptical shape can be fitted and parsed using the Hough transform method, the immune genetic snake model algorithm, and the least squares method, which can solve anomaly recognition problem in the insulator. The average failure detection resolution of LiDAR multi-channel spectral image anomaly recognition system is 82.4%, and it is higher than the average for copter and manual detection of 2405%. The proposed system is a highly efficient smart grid patrol screening method.

任天宇, 端木庆铎, 吴博琦, 姜会林, 许金凯, 邱进财. 巡线LiDAR多通道光谱图像异常识别技术[J]. 红外与毫米波学报, 2017, 36(5): 554. REN Tian-Yu, DUANMU Qing-Duo, WU Bo-Qi, JIANG Hui-Lin, XU Jin-Kai, QIU Jin-Cai. LiDAR multichannel spectral abnormal image recognition technology for transmission lines[J]. Journal of Infrared and Millimeter Waves, 2017, 36(5): 554.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!