本文選題：受電弓　切入點(diǎn)：接觸網(wǎng)　出處：《西南交通大學(xué)》2017年碩士論文

【摘要】：當(dāng)前我國(guó)高速鐵路事業(yè)正在快速發(fā)展,"四橫四縱"網(wǎng)絡(luò)已基本形成,運(yùn)行車次和速度都在不斷增加,鐵路的安全運(yùn)行也越來(lái)越受到重視,而供電系統(tǒng)的安全在這中間扮演著關(guān)鍵角色。為了滿足不斷提高的對(duì)鐵路供電系統(tǒng)安全檢測(cè)和監(jiān)測(cè)的要求,緩解人工檢測(cè)壓力,實(shí)現(xiàn)自動(dòng)化、智能化的弓網(wǎng)系統(tǒng)安全巡檢,基于圖像處理技術(shù)的檢測(cè)和監(jiān)測(cè)手段越來(lái)越得到關(guān)注。本文的研究工作是按照6C系統(tǒng)中的接觸網(wǎng)安全巡檢裝置和受電弓滑板監(jiān)測(cè)裝置的技術(shù)規(guī)范來(lái)展開的。本文算法以動(dòng)車組車頂圖像和接觸網(wǎng)巡檢圖像為實(shí)驗(yàn)數(shù)據(jù),利用圖像處理和機(jī)器學(xué)習(xí)的方法實(shí)現(xiàn)了對(duì)圖像中的目標(biāo)設(shè)備的智能檢測(cè)提取,最后通過(guò)實(shí)驗(yàn)測(cè)試也驗(yàn)證了本文所提出的算法的有效性。本文的主要工作及創(chuàng)新內(nèi)容包括以下幾個(gè)方面:在對(duì)圖像的預(yù)處理過(guò)程中,首先研究采用受限對(duì)比度自適應(yīng)直方圖均衡化算法(Contrast Limited Adaptive Histogram Equalization,CLAHE)對(duì)存在霧氣影響、對(duì)比度不明顯的圖像進(jìn)行圖像增強(qiáng)處理。然后,結(jié)合Hough變換和Canny算法對(duì)車頂圖像進(jìn)行傾角檢測(cè),再用透視變換進(jìn)行圖像矯正。最后,利用旋轉(zhuǎn)投影法對(duì)接觸網(wǎng)巡檢圖像進(jìn)行傾角檢測(cè),再用仿射變換進(jìn)行接觸網(wǎng)圖像矯正。在受電弓檢測(cè)中,本文采用Sobel算子和形態(tài)學(xué)操作對(duì)受電弓區(qū)域進(jìn)行粗提取。然后,利用Paralleled-Gabor變換提取受電弓區(qū)域的方向性特征。最后研究利用多個(gè)支持向量機(jī)(Support Vector Machine,SVM)分類器的決策融合方法實(shí)現(xiàn)受電弓區(qū)域的精確檢測(cè)提取。在接觸網(wǎng)支柱檢測(cè)中,研究了采用檢測(cè)圖像滅點(diǎn)的方式得到接觸網(wǎng)圖像的透視信息。然后,根據(jù)鐵軌與支柱的相對(duì)位置關(guān)系,利用透視信息得到支柱區(qū)域位置并采樣得到支柱疑似區(qū)域圖像。最后采用卷積神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)對(duì)巡檢圖像中接觸網(wǎng)支柱區(qū)域的檢測(cè)提取。本文對(duì)現(xiàn)有動(dòng)車組車頂圖像和接觸網(wǎng)巡檢圖像數(shù)據(jù)集進(jìn)行了實(shí)驗(yàn)測(cè)試。結(jié)果表明,本文算法具有較好的適用性,得到了理想的識(shí)別率,驗(yàn)證了本文算法具有一定的工程應(yīng)用價(jià)值。
[Abstract]:At present, high speed railway is developing rapidly in our country. The network of "four horizontal and four vertical" has been basically formed, the number of trains and the speed are increasing, and the safe operation of railway has been paid more and more attention. The safety of the power supply system plays a key role in this process. In order to meet the increasing requirements for the safety detection and monitoring of the railway power supply system, relieve the pressure of manual inspection, and realize automatic and intelligent safety inspection of the pantograph and catenary system, More and more attention has been paid to the detection and monitoring methods based on image processing technology. The research work in this paper is carried out according to the technical specifications of catenary safety inspection device and pantograph slide monitoring device in 6C system. The algorithm takes the roof image of the EMU and the patrol image of the catenary as the experimental data. The method of image processing and machine learning is used to realize the intelligent detection and extraction of the target equipment in the image. Finally, the effectiveness of the proposed algorithm is verified by experimental tests. The main work and innovations of this paper include the following aspects: in the process of image preprocessing, In this paper, the constrained contrast adaptive histogram equalization algorithm (Contrast Limited Adaptive Histogram equalization) is first studied to enhance the image with the influence of fog and the contrast is not obvious. Then, the inclination angle of the roof image is detected by combining the Hough transform and Canny algorithm. Finally, using the rotation projection method to detect the obliquity of the patrol image of the catenary, and then the affine transformation to correct the image of the catenary. In the pantograph detection, In this paper, Sobel operator and morphological operation are used to extract the pantograph region. Then, The directional feature of pantograph region is extracted by Paralleled-Gabor transform. Finally, a decision fusion method based on support vector machine (SVM) support Vector machine (SVM) classifier is proposed to detect and extract pantograph region accurately. The perspective information of the catenary image is obtained by detecting the vanishing point of the image. Then, according to the relative position relationship between the rail and the pillar, Using the perspective information to get the position of the pillar area and sampling the image of the suspected pillar area. Finally, using convolution neural network to realize the detection and extraction of the OCS pillar area in the patrol image. In this paper, the existing EMU roof map is presented. The image and catenary patrol image data sets are tested experimentally. The results show that, The algorithm in this paper has good applicability, and the ideal recognition rate is obtained, which verifies that this algorithm has certain engineering application value.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 楊衛(wèi)中;徐銀麗;喬曦;饒偉;李道亮;李振波;;基于對(duì)比度受限直方圖均衡化的水下海參圖像增強(qiáng)方法[J];農(nóng)業(yè)工程學(xué)報(bào);2016年06期

2 莫圣陽(yáng);謝慶華;駱少明;譚志忠;呂文閣;;基于3D視覺(jué)技術(shù)的受電弓磨耗檢測(cè)系統(tǒng)設(shè)計(jì)[J];機(jī)電工程技術(shù);2015年09期

3 葉珍;何明一;;PCA與移動(dòng)窗小波變換的高光譜決策融合分類[J];中國(guó)圖象圖形學(xué)報(bào);2015年01期

4 吳迪;朱青松;;圖像去霧的最新研究進(jìn)展[J];自動(dòng)化學(xué)報(bào);2015年02期

5 ;基于雙目視覺(jué)的受電弓碳滑板磨耗檢測(cè)[J];電子技術(shù);2013年12期

6 韓志偉;劉志剛;張桂南;楊紅梅;;非接觸式弓網(wǎng)圖像檢測(cè)技術(shù)研究綜述[J];鐵道學(xué)報(bào);2013年06期

7 雷蕾;王曉丹;邢雅瓊;畢凱;;結(jié)合SVM和DS證據(jù)理論的多極化HRRP分類研究[J];控制與決策;2013年06期

8 雷蕾;王曉丹;;結(jié)合SVM與DS證據(jù)理論的信息融合分類方法[J];計(jì)算機(jī)工程與應(yīng)用;2013年11期

9 陳維榮;馮倩;張健;于國(guó)旺;李哲;;受電弓滑板狀態(tài)監(jiān)測(cè)的圖像目標(biāo)提取[J];西南交通大學(xué)學(xué)報(bào);2010年01期

10 王蘭;吳謹(jǐn);;一種改進(jìn)的Canny邊緣檢測(cè)算法[J];微計(jì)算機(jī)信息;2010年02期

，

本文編號(hào)：1663109