| 面向无人机前端轻量级应用的输电线路鸟巢智能检测 |
| |
| 引用本文： | 陈 杰,朱仕焜,孙 嫱,林财德,江 灏.面向无人机前端轻量级应用的输电线路鸟巢智能检测[J].福州大学学报(自然科学版),2023,51(4):539-546. |
| |
| 作者姓名： | 陈 杰 朱仕焜 孙 嫱 林财德 江 灏 |
| |
| 作者单位： | 国网福建省电力有限公司漳州供电公司,国网福建省电力有限公司平和县供电公司,国网福建省电力有限公司漳州供电公司,国网福建省电力有限公司漳州供电公司,福州大学电气工程与自动化学院 |
| |
| 基金项目： | 国网福建省电力有限公司科技资助项目（521350210034）；福建省高校产学研合作资助项目（2019H600） |
| |
| 摘 要： | 为有效治理鸟害，保障线路安全稳定运行，本研究根据巡检拍摄的鸟巢图像具有位置、角度的不确定性和图像背景复杂等特点，利用鸟巢色彩单一的性质，提出一种结合YOLOX与颜色空间的鸟巢检测方法。在前端设备Jetson Xavier NX 里，采用经过调优训练的YOLOX目标检测网络对鸟巢图像检测并截取区域子图；根据颜色空间分布过滤非鸟巢区域，实现鸟巢的精筛。实验结果表明，采用上述方法对测试集中的鸟巢图像进行检测，准确率可达97.20%。
|
| 关 键 词： | 鸟巢检测 电力巡检 深度学习 颜色空间 |
| 收稿时间： | 2022/5/5 0:00:00 |
| 修稿时间： | 2022/9/26 0:00:00 |
Bird's nest intelligent detection on transmission lines for UAV front-end lightweight application |
| |
| CHEN Jie,ZHU Shikun,SUN Qiang,LIN Caide,JIANG Hao.Bird's nest intelligent detection on transmission lines for UAV front-end lightweight application[J].Journal of Fuzhou University(Natural Science Edition),2023,51(4):539-546. |
| |
| Authors: | CHEN Jie ZHU Shikun SUN Qiang LIN Caide JIANG Hao |
| |
| Affiliation: | State Grid Fujian Electric Power Co,Ltd Zhangzhou Power Supply Company,State Grid Fujian Electric Power Co,Ltd Pinghe County Power Supply Company,State Grid Fujian Electric Power Co,Ltd Zhangzhou Power Supply Company,State Grid Fujian Electric Power Co,Ltd Zhangzhou Power Supply Company,School of Electrical Engineering and Automation,Fuzhou University |
| |
| Abstract: | In order to effectively control bird damage and ensure the safe and stable operation of the line. we propose a bird nest detection method combining YOLOX and color space for bird nest images taken by inspection with uncertainty of position and angle and complex background of images, and use the characteristics of bird nest color singularity. In the front-end device Jetson Xavier NX, a tuned and trained YOLOX target detection network is used to detect the bird nest images and intercept the region sub-maps; the non-nest regions are filtered according to the color space distribution to achieve the fine screening of bird nests. The experimental results show that the detection of bird nest images in the test set using the above method can reach an accuracy of 97.20%. |
| |
| Keywords: | |
|
| 点击此处可从《福州大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《福州大学学报(自然科学版)》下载全文 |
|
