基于3D塔架配准的绝缘子自爆缺陷检测

摘要/Abstract

摘要：

在航拍图像的绝缘子检测中，图像的拍摄条件会导致背景的复杂程度不同，如何保持在多样背景下的绝缘子检测效果成为急需解决的一个重要问题。提出一种自适应的绝缘子自爆缺陷检测方法，该方法利用3D模型定位，并将绝缘子自身的绝缘子片作为模板检测缺陷。首先利用每种塔架的3D模型图与其对应的标准图进行SIFT点匹配，再利用随机抽样一致性方法找到标准图到待检测图的转换矩阵，从而找到塔架上每个绝缘子的位置；然后将图像转为HSV模型后，利用小波变换处理H通道，再进行二值化；最后通过Radon变换确定二值化图像中绝缘子中轴的大致方向并转正，去掉噪声点，取第一片绝缘子片作为模板在中轴滑动，记录每片绝缘子位置的像素分布直方图，利用地球移动距离EMD方法判断分布是否存在异常，最后再显示出自爆绝缘子片的位置。测试结果表明，该方法的自爆缺陷检测效果良好，具有较高的正确率和鲁棒性。

关键词: 3D模型, 图像匹配, 随机抽样一致性, HSV模型, 滑动模板

Abstract:

The conditions under which pictures are taken incur varied background complexity in aerial images. How to maintain consistent detection results in diverse backgrounds becomes an important issue. In this paper we propose an adaptive method for insulator blew detection. It locates the insulator with a 3D model and detects defects using the template of the insulator sheet. Firstly, we match the 3D model with standard image by the sift feature and find the transformation matrix from the standard image to the image to be tested via the RANSAC algorithm so as to locate all the insulators. Secondly, we transform the image from RGB to HSV, deal the H-channel with wavelet transform, and make it a binary image. We determine the direction of the axis in the binary image and turn it vertical by the Radon transform. After noise removed, we take the first insulator sheet as a model, which slides over the axis to record the histogram of every position. We employ the Earth Mover’s Distance (EMD) method to judge whether the histogram is normal or not, and locate the self-destruction position. Experimental results indicate the proposal is highly accurate and robust.

Key words: 3D model, image matching, RANSC, HSV model, sliding model

翟荔婷1，张冰怡1，冯志勇1，徐超2. 基于3D塔架配准的绝缘子自爆缺陷检测[J]. 计算机工程与科学.

ZHAI Li-ting1，ZHANG Bing-yi1，FENG Zhi-yong1，XU Chao2. Insulator blew detection based on match of 3D tower [J]. Computer Engineering & Science.

参考文献

［1］Beumier C.3D face recognition［C］∥Proc of 2006 IEEE International Conference on Industrial Technology,2006: 369-374．
［2］Dorai C，Wang Gang，Jain A K,et al.Registration and integration of multiple object views for 3D model construction［J］ IEEE Transaction on Pattern Analysis and Machine Intelligence，1998,20(1):83-89．
［3］Li Bing-feng，Wu Deng-lu，Cong Yang.A method of insulator detection from video sequence［C］∥Proc of 2012 International Symposium on Information Science and Engineering，2012: 386-389．
［4］Zhang Xin-ye，An Ju-bai，Chen Fang-ming.A simple method of tempered glass insulator recognition from airborne image［C］∥Proc of 2010 International Conference on Optoelectronic and Image Processing，2010:127-130.
［5］Huang Xiao-ning，Zhang Zhen-liang.The extract algorithm of the helicopter patrol insulator images in aerial images［J］.Power System Technology，2010,34（1）:194-197.（in Chinese）
［6］Tong Wei-guo，Li Bao-shu，Pei Yu-long.Extraction and recognition of insulator based on aerial image［C］∥Proc of 2011 International Conference on Electric Information and Control Engineering，2011:4195-4198．
［7］Liao Sheng-long，An Ju-bai robust insulator detection algorithm based on local features and spatial orders for aerial image［J］.IEEE Geoscience and Remote Sensing Letters，2015，12（5）:963-967．
［8］Wu Qing-gang，An Ju-bai，Lin Bin.A texture segmentation algorithm based on PCA and global minimization active coutour model for aerial insulator images［J］.IEEE Journal of Selected Topic in Applied Earth Observations and Remote Sensing，2012，5（5）:1509-1518．
［9］Zhao Zhen-bing，Liu Ning. The recognition and localization of insulators adopting SURF and IFS based on correlation coefficient［J］.Optik-international Journal for Light and Electron Optics，2014，125（20）:6049-6052．
［10］Li Wei-guo，Ye Gao-sheng，Huang Feng.Recognition of insulator based on developed MPEG-7 texture feature［C］∥Proc of 2010 3rd International Congress on Image and Signal Processing,2010:265-268．
［11］Zhang Xin-ye，An Ju-bai，Chen Fang-ming. A method of insulator fault detection from airbone images［C］∥Proc of 2010 2nd WRI Global Congress on Intelligent Systems,2010:200-203．
［12］Lowe D G. Distinctive image features from scale-invariant keypoints［J］.International Journal of Computer Vision，2004，60（2）:91-110．
［13］Wang Wei，Hong Jun，Tang Yi-ping. Image matching for geomorphic measurement based on SIFT and RANSAC methods［C］∥Proc of 2008 International Conference on Computer Science and Software Engineering，2008:317-320．
［14］Solomon J，Rustamov R，Guibas L，et al.Earth mover’s distances on discrete surfaces［J］.ACM Transactions on Graphics，2014，33（67）:1-12．
［15］Pele O, Werman M. Fast and roubust earth mover’s dis-tances［C］∥Proc of 2009 IEEE 12th International Conference on Computer Vision,2009:460-467．
附中文参考文献：
［5］黄宵宁，张真良.直升机巡检航拍图像中绝缘子图像的提取算法［J］.电网技术，2010,34（1）:194-197．

[1]	谢聪, 郑洪清. 一种新型的樽海鞘群算法及其应用[J]. 计算机工程与科学, 2022, 44(01): 184-190.
[2]	严春满，郝有菲，张迪，陈佳辉. 混合特征下最优阈值预测的图像匹配[J]. 计算机工程与科学, 2019, 41(10): 1803-1808.
[3]	王岩全，孙博文. 基于单目摄像头的3D动态手势交互[J]. 计算机工程与科学, 2018, 40(09): 1662-1669.
[4]	鲍文霞1,2，余国芬1，胡根生1，阎少梅1. 基于最大池的谱特征匹配算法[J]. 计算机工程与科学, 2018, 40(03): 494-499.
[5]	唐秋虎，张志毅. 基于多视图像的摄像机自标定方法[J]. 计算机工程与科学, 2017, 39(04): 748-755.
[6]	李建华，刘柯. 基于SURF特征提取的双目测距在铝锭垛定位中的应用研究[J]. 计算机工程与科学, 2016, 38(10): 2121-2125.
[7]	杨凯达1，赵文杰2，李成2，李德军2. 基于改进快速鲁棒性特征的导弹视频特征匹配[J]. J4, 2016, 38(01): 148-155.
[8]	姜枫1，周莉莉2，李丛1. 基于二进制特征描述器的图像匹配算法[J]. J4, 2015, 37(08): 1551-1557.
[9]	陈丽芳，刘一鸣,刘渊. 一种结合SIFT和对应尺度LTP综合特征的图像匹配算法[J]. J4, 2015, 37(03): 582-588.
[10]	侯毅,周石琳,雷琳,赵键. 基于ORB的快速完全仿射不变图像匹配[J]. J4, 2014, 36(02): 303-310.
[11]	刘仲，邢彬朝，扈啸. 基于YHFT-QDSP的并行图像匹配算法[J]. J4, 2012, 34(4): 47-51.
[12]	黄俊杰,扈啸. 基于硬件加速器的高分辨率图像匹配算法及应用[J]. J4, 2012, 34(4): 71-76.
[13]	李欢欢，黄山，张洪斌. 基于Harris与SIFT算法的自动图像拼接[J]. J4, 2012, 34(11): 104-108.
[14]	王君本，卢选民，贺兆. 一种基于快速鲁棒特征的图像匹配算法[J]. J4, 2011, 33(2): 112-117.
[15]	熊文真,蔡光程,张宏举. 改进的Fourier-Mellin描述子在图像匹配中的应用[J]. J4, 2011, 33(2): 124-128.