基于阶段注意力机制的电力线提取算法
作者:
作者单位:

江苏师范大学电气工程及自动化学院, 徐州 221116

作者简介:

通讯作者:

基金项目:

国家自然科学基金(61503164,6180119)资助项目;江苏省自然科学基金(BK20181004)资助项目。


Power Line Extraction Algorithm Based on Stage Attention Mechanism
Author:
Affiliation:

School of Electrical Engineering & Automation, Jiangsu Normal University, Xuzhou 221116, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    电力系统维护是电力系统稳定运行的重要保障,应用智能算法的无人机电力巡检则为电力系统维护提供便捷。电力线提取是自主电力巡检以及保障飞行器低空飞行安全的关键技术,结合深度学习理论进行电力线提取是电力巡检的重要突破点。本文将深度学习方法用于电力线提取任务,结合电力线图像特点嵌入改进的图像输入策略和注意力模块,提出一种基于阶段注意力机制的电力线提取模型(SA-Unet)。本文提出的SA-Unet模型编码阶段采用阶段输入融合策略(Stage input fusion strategy, SIFS),充分利用图像的多尺度信息减少空间位置信息丢失。解码阶段通过嵌入阶段注意力模块(Stage attention module,SAM)聚焦电力线特征,从大量信息中快速筛选出高价值信息。实验结果表明,该方法在复杂背景的多场景中具有良好的性能。

    Abstract:

    The maintenance of power system is an important guarantee for the stable operation of power system. The power inspection based on intelligent algorithm provides convenience for the maintenance of power system. Extracting power line is a key technology for autonomous power inspection and ensures the safety of aircraft at low altitudes. At the same time, extracting power line using deep learning is an important breakthrough of power inspection. Based on these, deep learning is applied to extract power line. Combined with the characteristics of power line, the improved strategy of inputting image and attention module are embedded. The model of extracting power line based on stage attention mechanism (SA-Unet) is proposed. In the coding stage, the stage input fusion strategy (SIFS) is adopted to make full use of the multi-scale information of the image to reduce the loss of spatial information. In the decoding stage, the features of power line are focused by the embedded stage attention module (SAM), and high-value information is screened out from a large amount of information quickly. Experimental results show that the method has good performance in multiple scenes with complex backgrounds.

    表 2 对比实验结果Table 2 Results of comparative experiment
    表 1 消融实验结果Table 1 Results of ablation experiment
    图1 整体流程Fig.1 Overall process
    图2 SA-Unet模型Fig.2 Model of SA-Unet
    图3 阶段注意力模块Fig.3 Stage attention module
    图4 通道注意力模块Fig.4 Channel attention module
    图5 空间注意力模块Fig.5 Spatial attention module
    图6 金字塔注意力模块Fig.6 Pyramid attention module
    图7 电力线分割预测效果Fig.7 Prediction effect of power line segmentation
    参考文献
    相似文献
    引证文献
引用本文

姜振邦,邹宽胜.基于阶段注意力机制的电力线提取算法[J].数据采集与处理,2021,36(4):812-821

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2020-11-30
  • 最后修改日期:2021-02-28
  • 录用日期:
  • 在线发布日期: 2021-09-23