本文選題：井下行人檢測　切入點：卷積神經(jīng)網(wǎng)絡(luò)　出處：《西安科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：煤炭在我國能源利用中占據(jù)著舉足輕重的地位,煤礦安全尤其是井下生產(chǎn)環(huán)境的安全則一直是煤礦行業(yè)的重中之重。目前煤礦企業(yè)對于井下工作人員的檢測主要依托于已裝備的井下人員定位系統(tǒng)等,這些技術(shù)的應(yīng)用可以有效地進(jìn)行人員的定位和識別,但是在使用過程當(dāng)中也出現(xiàn)替下、捎卡等情況,其精準(zhǔn)度不高,智能化水平較低,特別是當(dāng)監(jiān)控人員疏忽時,存在很大的安全隱患。基于這樣的背景,本文結(jié)合DCNN(深度卷積神經(jīng)網(wǎng)絡(luò))在視頻圖像識別領(lǐng)域中的應(yīng)用和井下裝備的工業(yè)視頻監(jiān)控系統(tǒng),提出了一種基于DCNN的礦井井下行人檢測技術(shù)。為提高檢測速度,采用了 YOLO目標(biāo)檢測系統(tǒng),并針對井下特殊環(huán)境的特點對其進(jìn)行了改進(jìn),最終利用Java Web技術(shù)對基于改進(jìn)YOLO的井下行人檢測系統(tǒng)進(jìn)行了簡單實現(xiàn)。本文以神經(jīng)網(wǎng)絡(luò)為基礎(chǔ),首先對卷積神經(jīng)網(wǎng)絡(luò)、深度學(xué)習(xí)網(wǎng)絡(luò)等的理論做了介紹與分析,在深度卷積神經(jīng)網(wǎng)絡(luò)的基礎(chǔ)上對YOLO目標(biāo)檢測系統(tǒng)的網(wǎng)絡(luò)結(jié)構(gòu)以及檢測過程等原理進(jìn)行了詳細(xì)的剖析,分析了 YOLO系統(tǒng)精確度不高的缺陷,針對礦井下的視頻質(zhì)量差、背景單調(diào)、檢測目標(biāo)單一等特點對原有的YOLO系統(tǒng)在數(shù)據(jù)集和網(wǎng)絡(luò)結(jié)構(gòu)上進(jìn)行了改進(jìn)。利用煤礦井下的監(jiān)控視頻重新制作了訓(xùn)練集,網(wǎng)絡(luò)結(jié)構(gòu)上利用淺層的表征信息與深層的語義信息相結(jié)合的思想將網(wǎng)絡(luò)中第八層的特征提取出來與最后層的輸出相加作為整個網(wǎng)絡(luò)最后的輸出,在提取第八層提取特征的基礎(chǔ)上提.提出了三種方案,分別為先卷積后采樣、先采樣后卷積、最后層輸出利用反卷積擴(kuò)大特征圖再與第八層相加。通過在Caffe框架上進(jìn)行實驗并分析結(jié)果,綜合考慮后選擇了第二種方案為最終改進(jìn)方案,證明.了改進(jìn)后的YOLO系統(tǒng)在井下特殊環(huán)境的行人檢測性能得到了提升。最后,利用Java EE技術(shù)構(gòu)建了關(guān)于Java Web的井下行人檢測系統(tǒng),該系統(tǒng)包含系統(tǒng)管理、權(quán)限管理、檢測管理、考勤信息、設(shè)備管理五個模塊,對DCNN的井下行人檢測系統(tǒng)進(jìn)行了測試分析及功能性驗證,說明了所設(shè)計系統(tǒng)的可行性。通過本文的實驗可以看出,改進(jìn)后的YOLO系統(tǒng)對井下特殊環(huán)境的檢測有比較好的檢測效果。
[Abstract]:Coal occupies a pivotal position in the utilization of energy in China. Coal mine safety, especially the safety of the underground production environment, has always been the top priority of the coal mining industry. At present, the inspection of underground workers by coal mining enterprises mainly depends on the positioning system of the underground personnel that has been equipped. The application of these technologies can effectively locate and identify the personnel, but in the process of use, there are replacement, cards, etc., their accuracy is not high, and the level of intelligence is low, especially when the monitoring personnel are negligent. Based on this background, this paper combines the application of DCNN (depth convolution neural network) in the field of video image recognition and the industrial video surveillance system of underground equipment. This paper presents a kind of underground pedestrian detection technology based on DCNN. In order to improve the detection speed, the YOLO target detection system is adopted, and it is improved according to the characteristics of the special underground environment. Finally, using Java Web technology, a simple realization of underground pedestrian detection system based on improved YOLO is carried out. Firstly, the theory of convolution neural network and depth learning network is introduced and analyzed based on neural network. On the basis of deep convolution neural network, the network structure and detection process of YOLO target detection system are analyzed in detail, and the defects of low accuracy of YOLO system are analyzed. The video quality under mine is poor and the background is monotonous. The original YOLO system has been improved in data set and network structure with the characteristics of single detection target, and the training set has been remade by using the monitoring video of underground coal mine. In the network structure, the feature of the eighth layer in the network is extracted and the output of the last layer is added as the final output of the whole network by the idea of combining the shallow representation information with the deep semantic information. On the basis of extracting features from the eighth layer, three schemes are proposed, which are first convolution and then sampling, first sampling and then convolution. The final layer output uses deconvolution expanded feature map to add to the eighth layer. Through the experiment on the Caffe framework and the analysis of the results, the second scheme is selected as the final improvement scheme. It is proved that the improved YOLO system has improved the performance of pedestrian detection in the special underground environment. Finally, the underground pedestrian detection system about Java Web is constructed by using Java EE technology. The system includes system management, authority management, detection management, etc. Five modules of attendance information and equipment management are used to test and analyze the underground pedestrian detection system of DCNN and verify the function of the system. The feasibility of the designed system is demonstrated by the experiment in this paper. The improved YOLO system has a good effect on the detection of underground special environment.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TD76;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王超;;基于卷積神經(jīng)網(wǎng)絡(luò)的圖像分類技術(shù)研究與實現(xiàn)[J];電腦知識與技術(shù);2016年35期

2 郭麗麗;丁世飛;;深度學(xué)習(xí)研究進(jìn)展[J];計算機(jī)科學(xué);2015年05期

3 費建超;芮挺;周怞;方虎生;朱會杰;;基于梯度的多輸入卷積神經(jīng)網(wǎng)絡(luò)[J];光電工程;2015年03期

4 許曉帆;王毅;王永泉;;基于自適應(yīng)非極大值抑制的SIFT改進(jìn)算法[J];電子設(shè)計工程;2014年18期

5 楊運(yùn)平;吳智俊;;Apache Shiro安全框架在技術(shù)轉(zhuǎn)移服務(wù)系統(tǒng)中的應(yīng)用[J];計算機(jī)與現(xiàn)代化;2014年03期

6 鄭胤;陳權(quán)崎;章毓晉;;深度學(xué)習(xí)及其在目標(biāo)和行為識別中的新進(jìn)展[J];中國圖象圖形學(xué)報;2014年02期

7 蘇松志;李紹滋;陳淑媛;蔡國榕;吳云東;;行人檢測技術(shù)綜述[J];電子學(xué)報;2012年04期

8 薛峰;梁鋒;徐書勛;王彪任;;基于Spring MVC框架的Web研究與應(yīng)用[J];合肥工業(yè)大學(xué)學(xué)報(自然科學(xué)版);2012年03期

9 劉進(jìn)鋒;郭雷;;神經(jīng)網(wǎng)絡(luò)前向傳播在GPU上的實現(xiàn)[J];微型機(jī)與應(yīng)用;2011年18期

10 胡啟敏;薛錦云;鐘林輝;;基于Spring框架的輕量級J2EE架構(gòu)與應(yīng)用[J];計算機(jī)工程與應(yīng)用;2008年05期

相關(guān)碩士學(xué)位論文 前4條

1 史秋瑩;基于深度學(xué)習(xí)和遷移學(xué)習(xí)的環(huán)境聲音識別[D];哈爾濱工業(yè)大學(xué);2016年

2 楊楠;基于Caffe深度學(xué)習(xí)框架的卷積神經(jīng)網(wǎng)絡(luò)研究[D];河北師范大學(xué);2016年

3 郭麗;Izhikevich神經(jīng)網(wǎng)絡(luò)多態(tài)同步組信息傳輸特性研究[D];南京師范大學(xué);2015年

4 許可;卷積神經(jīng)網(wǎng)絡(luò)在圖像識別上的應(yīng)用的研究[D];浙江大學(xué);2012年

，

本文編號：1650104