本文選題：輸電線提取　切入點(diǎn)：防震錘檢測　出處：《北京交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：在智能電網(wǎng)系統(tǒng)中,輸電線路的智能巡檢是極其重要的組成部分。輸電線路上的防震錘是一種為了減少輸電線因風(fēng)力扯起振動(dòng)而安裝的設(shè)備,它是保障電力正常運(yùn)輸?shù)闹匾画h(huán)。因此,對輸電線路圖像上防震錘檢測的研究就彰顯出重要的價(jià)值。傳統(tǒng)的輸電線路的巡檢工作基本上采用人工巡檢的方式,這種作業(yè)方式勞動(dòng)強(qiáng)度大、危險(xiǎn)系數(shù)高并且效率低。近年來,無人機(jī)航拍的巡檢方式被部分電力公司使用。然而,無人機(jī)采集到的圖像視野遼闊、背景復(fù)雜、視角、目標(biāo)分辨率也不盡相同,這些都給防震錘檢測帶來了極大的挑戰(zhàn)。本論文正是基于這一背景下,調(diào)研國內(nèi)外相關(guān)工作,對輸電線路上防震錘的檢測定位算法展開研究,以解決復(fù)雜背景中魯棒的檢測防震錘的問題,為防震錘的缺陷診斷做準(zhǔn)備。本文的主要工作有:(1)基于AdaBoost算法的防震錘檢測。針對現(xiàn)有的基于隨機(jī)霍夫變換、基于模板匹配的方法檢測,只適用于特定場景、特定角度的防震錘檢測,并不適用于本數(shù)據(jù)集的問題。本文提出了一種基于AdaBoost算法的防震錘檢測方法。在訓(xùn)練階段,我們使用了針對防震錘的Haar特征然后結(jié)合AdaBoost分類器進(jìn)行訓(xùn)練。在檢測階段,由于防震錘與輸電線的依附關(guān)系,我們首先對輸電線進(jìn)行提取,候選出帶有防震錘的感興趣區(qū)域,然后通過滑動(dòng)窗口結(jié)合分類器在此區(qū)域進(jìn)行防震錘的檢測。最后我們比較分析了不同的特征選取、不同的參數(shù)設(shè)置對實(shí)驗(yàn)結(jié)果的影響,并從準(zhǔn)確率和計(jì)算效率兩方面對實(shí)驗(yàn)結(jié)果進(jìn)行評(píng)價(jià)與分析。在無人機(jī)采集的野外的輸電線路圖像中,我們收集整理了二千五百幅包含防震錘的圖像,建立了防震錘數(shù)據(jù)集,并手工標(biāo)注防震錘Ground Truth,最后在此數(shù)據(jù)集中的檢測圖像上進(jìn)行了防震錘檢測,達(dá)到了 93%的準(zhǔn)確率。(2)針對漏檢防震錘情況,我們提出基于多視角匹配的方法對防震錘漏檢情況進(jìn)行補(bǔ)充,從而達(dá)到優(yōu)化檢測結(jié)果的目的。(3)基于深度學(xué)習(xí)的防震錘檢測。針對本課題中無人機(jī)采集到的圖像具有復(fù)雜場景,我們提出基于深度學(xué)習(xí)SSD模型的防震錘檢測方法,并且設(shè)計(jì)了檢測模型。最后對實(shí)驗(yàn)結(jié)果進(jìn)行了分析。在我們構(gòu)建的數(shù)據(jù)集上,SSD模型達(dá)到了 98%的準(zhǔn)確率。
[Abstract]:In smart grid systems, intelligent inspection of transmission lines is an extremely important part. It is an important link to ensure the normal transportation of electric power. Therefore, the research on the detection of seismic hammer on the transmission line image shows the important value. The traditional inspection work of transmission line basically adopts the way of manual inspection. In recent years, unmanned aerial photography has been used by some power companies. However, the images captured by unmanned aerial vehicles have a wide field of view, complex background and perspective. The target resolution is not the same, which brings great challenge to the detection of earthquake hammer. Based on this background, this paper studies the detection and location algorithm of the shock hammer on transmission line by investigating the related work at home and abroad. In order to solve the problem of robust detection of anti-shock hammer in complex background and prepare for the fault diagnosis of anti-shock hammer, the main work of this paper is: 1) the detection of anti-shock hammer based on AdaBoost algorithm. The method based on template matching is only suitable for the detection of shock proof hammer with specific scene and angle, but not for the problem of this data set. This paper presents a method of detecting earthquake hammer based on AdaBoost algorithm. We used the Haar feature of the shock hammer and then trained it with the AdaBoost classifier. In the detection phase, because of the dependency between the hammer and the transmission line, we first extracted the transmission line and candidate the region of interest with the hammer. Finally, we compare and analyze the effects of different feature selection and different parameter settings on the experimental results. The experimental results are evaluated and analyzed from two aspects of accuracy and computational efficiency. In the field transmission line images collected by UAV, 2,500 images containing shock proof hammer are collected and arranged, and the seismic hammer data set is established. And manually annotate the shock hammer Ground Truth.Finally, the anti-shock hammer detection is carried out on the detection image of this data set, and the accuracy rate of 93% is reached. In order to optimize the detection results, we propose a method based on multi-angle matching to supplement the detection of earthquake proof hammer, which is based on depth learning. The images collected by UAV in this subject have complex scenes. We propose a method for detecting earthquake hammer based on depth learning SSD model, and design a detection model. Finally, the experimental results are analyzed. The accuracy of the model is 98% on our data set.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TM755

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 馮亦東;孫躍;;基于SURF特征提取和FLANN搜索的圖像匹配算法[J];圖學(xué)學(xué)報(bào);2015年04期

2 趙志剛;梁利輝;;直升機(jī)作業(yè)在超高壓輸電線路巡視與帶電檢修中的應(yīng)用[J];河北電力技術(shù);2013年04期

3 曹文明;王耀南;印峰;伍錫如;繆思怡;;高壓輸電線路除冰機(jī)器人障礙物識(shí)別方法研究[J];儀器儀表學(xué)報(bào);2011年09期

4 文學(xué)志;方巍;鄭鈺輝;;一種基于類Haar特征和改進(jìn)AdaBoost分類器的車輛識(shí)別算法[J];電子學(xué)報(bào);2011年05期

5 繆思怡;孫煒;張海霞;;基于小波矩的高壓輸電線路除冰機(jī)器人障礙智能視覺識(shí)別方法[J];機(jī)器人;2010年03期

6 陳曉娟;吳英石;趙亮;;基于隨機(jī)Hough變換的OPGW防震錘識(shí)別[J];黑龍江電力;2010年01期

7 張銳娟;張建奇;楊翠;;基于SURF的圖像配準(zhǔn)方法研究[J];紅外與激光工程;2009年01期

8 胡彩石;吳功平;曹珩;蔣國偉;;高壓輸電線路巡線機(jī)器人障礙物視覺檢測識(shí)別研究[J];傳感技術(shù)學(xué)報(bào);2008年12期

9 陳蓋凱;;基于Hough變換的直線檢測[J];西安航空技術(shù)高等專科學(xué)校學(xué)報(bào);2007年03期

10 張運(yùn)楚;梁自澤;傅思遙;譚民;吳功平;;基于結(jié)構(gòu)約束的架空輸電線路巡線機(jī)器人障礙識(shí)別[J];機(jī)器人;2007年01期

相關(guān)碩士學(xué)位論文 前3條

1 王海地;基于顯著性檢測和分類器訓(xùn)練的航拍圖像車輛檢測[D];北京交通大學(xué);2015年

2 周峰;基于尺度不變特征變換（SIFT）的圖像配準(zhǔn)技術(shù)研究[D];昆明理工大學(xué);2010年

3 馬帥營;直升機(jī)巡檢輸電線路中絕緣子圖像的分割方法[D];大連海事大學(xué);2009年

，

本文編號(hào)：1633093