《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (5): 1583-1590.DOI: 10.11772/j.issn.1001-9081.2021030493

• 多媒体计算与计算机仿真 • 上一篇    下一篇

基于Order-Aware网络内点筛选网络的电力巡线航拍图像拼接

回立川, 李万禹(), 陈艺琳   

  1. 辽宁工程技术大学 电气与控制工程学院,辽宁 葫芦岛 125105
  • 收稿日期:2021-04-01 修回日期:2021-05-18 接受日期:2021-05-18 发布日期:2022-06-11 出版日期:2022-05-10
  • 通讯作者: 李万禹
  • 作者简介:回立川(1980—),男,河北邢台人,副教授,博士,主要研究方向:电力系统运行监测
    李万禹(1993—),男,辽宁大连人,硕士研究生,主要研究方向:电力系统运行监测 670252229@qq.com
    陈艺琳(1994—),女,河北阜城人,硕士研究生,主要研究方向:电力系统运行监测。
  • 基金资助:
    辽宁省教育厅科学研究项目(LJ2017QL009)

Power line inspection aerial image stitching based on Order-Aware network internal point screening network

Lichuan HUI, Wanyu LI(), Yilin CHEN   

  1. Faculty of Electrical and Control Engineering,Liaoning Technical University,Huludao Liaoning 125105,China
  • Received:2021-04-01 Revised:2021-05-18 Accepted:2021-05-18 Online:2022-06-11 Published:2022-05-10
  • Contact: Wanyu LI
  • About author:HUI Lichuan, born in 1980,Ph. D.,associate professor. Hisresearch interests include power system operation monitoring.
    LI Wanyu, born in 1993,M. S. candidate. His research interestsinclude power system operation monitoring.
    CHEN Yilin, born in 1994,M. S. candidate. Her research interestsinclude power system operation monitoring.
  • Supported by:
    Scientific Research Project of Educational Department of Liaoning Province(LJ2017QL009)

摘要:

电力巡线图像纹理复杂且具有视差变化,针对传统算法获取成对匹配点数量较少、配准精度较低,严重影响电力巡线无人机图像拼接效果等问题,提出了一种基于改进OANet的图像拼接算法。首先,借助加速“风”(AKAZE)算法对待拼接电力巡线图像进行粗匹配;其次,对OANet中Order-Aware模块添加挤压和激励网络(SENet),从而增强网络对局部和全局上下文信息的抓取能力,得到更精确的成对匹配点;然后,通过MPA算法配准待拼接图像;最后,借助内容压缩感知算法计算重叠区域的最佳缝合线以完成图像拼接。改进OANet相较原OANet的正确匹配点数量增加了10%左右,耗时平均增加了10 ms;与APAP算法、AANAP算法、MPA算法等配准拼接算法相比,所提算法的拼接质量最好,其待拼接图像的重叠区域的均方根误差为0,非重叠区域未发生畸变。实验结果表明,所提算法可快速、稳定地拼接电力巡线航拍图像。

关键词: 电力巡线, 图像拼接, OANet, 挤压和激励网络, MPA算法, 内容压缩感知算法

Abstract:

The texture of power line inspection images with parallax variation is complex, the number of paired matching points obtained by traditional algorithms is less and the registration accuracy is low, which seriously affect the stitching effect of power line inspection unmanned aerial vehicle image. In order to solve the problems, a new image stitching method based on improved Order-Aware Network (OANet) was proposed. Firstly, the Accelerated KAZE (AKAZE) algorithm was adopted to match the power line inspection images to be stitched roughly. Secondly, the Squeeze-and-Excitation Networks (SENet) was added to the Order-Aware module in OANet, which helped to enhance the grasping ability of the network for both the local and global context information, and more accurate paired matching points were obtained. Then, the Mesh-based Photometric Alignment (MPA) algorithm was used to register the images to be stitched. Finally, the optimal suture line in the overlapping area was calculated by the content compressed sensing algorithm to complete image stitching. The number of correct matching points of the improved OANet network is about 10% higher than that of the original OANet network with time consumption increased by 10 ms on average. Compared with the registration stitching algorithms such as As-Projective-As-Possible (APAP) algorithm, Adaptive As-Natural-As-Possible (AANAP) algorithm and MPA algorithm, the proposed algorithm has the highest stitching quality with the root mean square error of the overlapping area of the images to be stitched is 0 and no distortion in the non-overlapping area. Experimental results show that, the proposed algorithm can stitch the aerial images of power line inspection quickly and stably.

Key words: power line, inspection image stitching, Order-Aware Network (OANet), Squeeze-and-Excitation Network (SENet), Mesh-based Photometric Alignment (MPA) algorithm, content compressed sensing algorithm

中图分类号: