發(fā)布時間：2018-03-06 07:33

  本文選題：卷積神經(jīng)網(wǎng)絡　切入點：目標檢測　出處：《浙江大學》2017年碩士論文　論文類型：學位論文

【摘要】：隨著電子信息技術不斷發(fā)展,機房的設備在不斷更新和增加。如果機房設備出現(xiàn)故障,就將會直接影響整個系統(tǒng)的正常運行。本文針對無人值守機房的情況,設計了機房設備監(jiān)控平臺,該平臺通過實時分析機房現(xiàn)場的圖片來實時監(jiān)控機房設備的運行狀況。本文任務的核心是目標檢測,檢測出機房現(xiàn)場圖片里的指定目標。目標檢測在人工智能領域已經(jīng)得到了深入地研究,并且在工業(yè)上得到了廣大的應用。隨著目標檢測地被廣泛應用,目標檢測也存在很多的挑戰(zhàn)和問題。傳統(tǒng)的目標檢測算法采用形態(tài)學、統(tǒng)計學的算法,由于需要根據(jù)環(huán)境設定算法參數(shù),導致算法適應性不好。如果使用選擇搜索來提取圖片感興趣區(qū)域,這需要對圖片進行全局搜索,提取速度非常慢。因此本文采用卷積神經(jīng)網(wǎng)絡來進行目標檢測的任務。為了解決上面這些問題,本文設計合適的卷積神經(jīng)網(wǎng)絡來提取感興趣區(qū)域,然后設計卷積神經(jīng)網(wǎng)絡來對感興趣區(qū)域內(nèi)的目標物體進行識別。本文設計類別誤差函數(shù)來更新整個網(wǎng)絡權重,提高分類的準確率;此外設計位置坐標誤差函數(shù),在訓練的時候不斷更新網(wǎng)絡權重,進行線性位置回歸,從而提高位置預測的準確率。通過實驗可以驗證這種方法準確率和檢測速度都能滿足本文的要求。此外,本文初步討論了卷積神經(jīng)網(wǎng)絡的改進方式,發(fā)現(xiàn)卷積神經(jīng)網(wǎng)絡的前幾層卷積層具有相位對稱特性,因此可以將前幾層卷積層的輸出特征圖減少一半,另一半由這個鏡像得到。通過上面的方式,可以減少網(wǎng)絡的權重數(shù)量,這樣可以提高訓練、測試速度。
[Abstract]:With the development of electronic information technology, the equipment of the computer room is constantly updated and increased. If the equipment of the computer room fails, it will directly affect the normal operation of the whole system. The monitoring platform of computer room equipment is designed. The platform can real-time monitor the running condition of the equipment by analyzing the pictures of the computer room in real time. The core of the task of this paper is the target detection. Detection of designated targets in field pictures of computer rooms. Target detection has been deeply studied in artificial intelligence field and has been widely used in industry. With the wide application of target detection, There are also many challenges and problems in target detection. The traditional target detection algorithms use morphological and statistical algorithms, because of the need to set the algorithm parameters according to the environment. This result in poor adaptability of the algorithm. If you use selective search to extract the region of interest of the picture, this requires a global search of the image. The speed of extraction is very slow. Therefore, the task of target detection is based on convolution neural network. In order to solve these problems, this paper designs an appropriate convolutional neural network to extract the region of interest. Then the convolutional neural network is designed to identify the object in the region of interest. In this paper, the class error function is designed to update the weight of the whole network to improve the classification accuracy; in addition, the position coordinate error function is designed. During training, network weights are updated and linear position regression is carried out to improve the accuracy of location prediction. The experimental results show that the accuracy of this method and the speed of detection can meet the requirements of this paper. In this paper, the improved method of convolution neural network is discussed. It is found that the first several layers of the convolution neural network have phase symmetry, so the output characteristic map of the first several layers can be reduced by half. The other half is obtained by this mirror image. In this way, the weight of the network can be reduced, which can improve the training and testing speed.
【學位授予單位】：浙江大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP308;TP277

【參考文獻】

相關期刊論文 前10條

1 陳耀丹;王連明;;基于卷積神經(jīng)網(wǎng)絡的人臉識別方法[J];東北師大學報(自然科學版);2016年02期

2 鄧高登;王曉曄;袁聞;韓淼;楊星;謝曉U，

本文編號：1573917