發(fā)布時間：2018-04-18 01:01

  本文選題：場景分類 + 直播視頻��； 參考：《北京交通大學(xué)》2017年碩士論文

【摘要】：網(wǎng)絡(luò)直播是繼傳統(tǒng)廣播電視后的新視頻文化,至今共經(jīng)歷了三個發(fā)展階段。從優(yōu)酷等網(wǎng)站上傳個人視頻,到Y(jié)Y等網(wǎng)頁端的"秀場"直播,再到如今的"隨走、隨看、隨播"的移動視頻直播時代,共經(jīng)歷六年,而二、三階段僅經(jīng)歷三年不到卻占據(jù)現(xiàn)今直播的主流市場。據(jù)不完全統(tǒng)計,目前全國在線直播平臺數(shù)量超過200家,在方正證券的預(yù)測中,2020年網(wǎng)絡(luò)直播市場規(guī)模將達(dá)到600億元,直播將是微博、微信之后的第三波移動互聯(lián)網(wǎng)流量中心。由于缺少高端設(shè)備和后期制作的支持,畫面質(zhì)量問題一直是網(wǎng)絡(luò)直播關(guān)注的重要問題之一。目前如百度云直播、阿里云直播等平臺都向用戶提供了針對不同錄制場景的畫質(zhì)優(yōu)化方案,但是針對同一個視頻流,直播平臺一般都使用同一個優(yōu)化算法進行優(yōu)化,這也就意味著在直播過程中更換場景后對應(yīng)使用的視頻流優(yōu)化算法并不是最合適的。因此,本項目提出了基于Spark的直播視頻場景分類系統(tǒng)對視頻流進行實時分類從而為實現(xiàn)畫質(zhì)優(yōu)化方案的動態(tài)變化提供依據(jù)。本項目結(jié)合任務(wù)消息隊列的思想在Spark核心框架上使用Spark Streaming流式計算框架對多個視頻流進行并行實時處理與分類。視頻的處理包括視頻流數(shù)據(jù)轉(zhuǎn)圖像幀數(shù)據(jù),對圖像幀進行轉(zhuǎn)灰度處理、直方圖均衡化處理、HOG特征提取處理以及光流特征提取處理。同時,本項目基于AlexNet模型改進并建立了接收多路輸入的深度卷積神經(jīng)網(wǎng)絡(luò)分類模型,多路AlexNet(Multi-Stream AlexNet,MSAN)模型。本項目使用該模型對視頻的圖像數(shù)據(jù)進行場景分類,并且按照視頻推流的最小單元對連續(xù)圖像幀進行分組,統(tǒng)計組內(nèi)分類記票以確定該組視頻數(shù)據(jù)的場景類別從而實現(xiàn)直播視頻的實時分類。目前項目已經(jīng)訓(xùn)練得到分類準(zhǔn)確率平均為98%的MSAN模型,場景分類系統(tǒng)也在集群上部署實現(xiàn),并且完成了系統(tǒng)的單元測試與系統(tǒng)測試。
[Abstract]:Webcast is a new video culture after traditional radio and television, which has experienced three stages of development.From websites such as Youku uploading personal videos, to the "show" live broadcast at the end of the YY web page, and to the mobile video broadcasting era of "follow, watch and broadcast" now, a total of six years, and two,Three stages only experienced less than three years but occupied the current mainstream market of live broadcast.According to incomplete statistics, there are more than 200 online live broadcasting platforms in the country at present. In the forecast of Fang Zheng Securities, the market scale of live webcast will reach 60 billion yuan in 2020, and live broadcast will be the third wave of mobile Internet traffic center after Weibo and WeChat.Due to the lack of high-end equipment and post-production support, picture quality has been one of the most important issues in webcast.At present, such platforms as Baidu Cloud Live and Ali Cloud Live provide users with the optimization scheme for different recorded scenes, but for the same video stream, the live broadcast platform generally uses the same optimization algorithm to optimize.This means that the corresponding video stream optimization algorithm is not the most suitable after changing the scene during the live broadcast.Therefore, this project proposes a live video scene classification system based on Spark to classify video streams in real time so as to provide the basis for the dynamic change of image quality optimization scheme.Based on the idea of task message queue, this project uses Spark Streaming streaming computing framework to process and classify multiple video streams in parallel and real-time on the Spark core framework.Video processing includes video stream data to image frame data, image frame to gray processing, histogram equalization processing to hog feature extraction and optical flow feature extraction processing.At the same time, based on the AlexNet model, the classification model of the deep convolution neural network for receiving multiple inputs, the multichannel AlexNet(Multi-Stream AlexNet MSAN model, is established.The project uses the model to classify the scene of the video image data, and groups the continuous image frames according to the smallest unit of the video push stream.In order to determine the scene classification of the video data, the real-time classification of live video can be realized.At present, the project has been trained to get the MSAN model with an average classification accuracy of 98%, and the scene classification system has been deployed and implemented on the cluster, and the unit test and system test of the system have been completed.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前3條

1 胡聰叢;胡桓;;深度神經(jīng)網(wǎng)絡(luò)的發(fā)展現(xiàn)狀[J];電子技術(shù)與軟件工程;2017年04期

2 李學(xué)龍;史建華;董永生;陶大程;;場景圖像分類技術(shù)綜述[J];中國科學(xué):信息科學(xué);2015年07期

3 石大明,劉海濤,舒文豪;結(jié)合進化計算的神經(jīng)認(rèn)知機[J];計算機學(xué)報;2001年05期

，

本文編號：1766075