本文選題：隧道　切入點：行人檢測　出處：《昆明理工大學》2017年碩士論文　論文類型：學位論文

【摘要】：隧道區(qū)域是高速公路管理的重點區(qū)域,行人和非機動車輛違規(guī)進入高速公路隧道內會嚴重影響高速公路的正常運行,造成巨大的安全隱患。因此,針對隧道環(huán)境下視頻監(jiān)控中的行人檢測技術是高速公路正常運營的重要保障。隧道環(huán)境內,環(huán)境光照條件差,在圖像中產(chǎn)生大量噪聲,行人在隧道內目標小,像素低,給隧道環(huán)境下行人檢測帶來很大挑戰(zhàn)。本文主要研究了視頻檢測中的前景目標與背景目標的分割方法,使用了基于數(shù)學特征提取方法與卷積神經(jīng)網(wǎng)絡的行人目標檢測方法。并且針對提取特征訓練的分類器遍歷搜索慢,在隧道場景下采用運動信息縮小搜索范圍,節(jié)省了搜索時間。另外針對隧道環(huán)境下噪聲大行人特征提取困難的問題,利用卷積神經(jīng)網(wǎng)絡對特征提取的優(yōu)勢特點,訓練了端到端的隧道場景下行人檢測網(wǎng)絡。本文的主要研究內容如下:(1)一般的行人檢測分類器的訓練中通常采用單一的HOG特征,在隧道環(huán)境下檢測準確率偏低。本文通過引入一種局部二值模式(LBP)特征與梯度方向直方圖特征(HOG)串聯(lián)輸入到支持向量機的分類模型中,訓練得到的基于聯(lián)合特征行人檢測器大幅提升了隧道環(huán)境下行人檢測的準確率。(2)基于HOG特征與LBP特征串聯(lián)訓練的分類器一般采用滑動窗口遍歷搜索整個圖像的策略,這樣造成了巨大的時效性損失。在高速公路隧道中,監(jiān)控畫面出現(xiàn)在固定場景下。根據(jù)視頻監(jiān)控的這一特點,通過提取行人移動信息,將分類器檢測與一種改進的高斯混合背景差分方法相結合,提取圖像中運動區(qū)域,減少分類器對圖像的搜索次數(shù),大幅提升了算法系統(tǒng)對行人的識別效率。(3)針對高速公路隧道環(huán)境噪聲造成行人與環(huán)境輪廓邊界弱,傳統(tǒng)機器學習方法難以提取有效特征的問題,本文利用卷積神經(jīng)網(wǎng)絡高效的特征提取能力,通過改進候選框提取方法,使用RPN候選框提取網(wǎng)絡,在選用單幅圖片候選框少的情況下訓練出行人檢測的單一目標識別網(wǎng)絡。對候選框提取網(wǎng)絡與行人檢測網(wǎng)絡進行了訓練,得到端到端的行人檢測網(wǎng)絡。相對于特征設計的行人檢測模型,大幅度的提升隧道環(huán)境行人檢測的準確率,且在一定程度上提升基于RCNN算法框架下的行人檢測速度。針對高速公路隧道環(huán)境下行人檢測的要求,研究了基于特征提取的分類器模型對隧道應用場景的適應性,并提出相應的方法改進檢測模型。將區(qū)域卷積神經(jīng)網(wǎng)絡應用在氋速公路隧道場景下的行人檢測,同時訓練了端到端的深度行人檢測模型。提升了隧道監(jiān)控場景下行人檢測的準確率,對基于卷積神經(jīng)網(wǎng)絡的其他目標物識別工作具有一定的借鑒意義。
[Abstract]:Tunnel area is the key area of highway management. Illegal entry of pedestrians and non-motorized vehicles into expressway tunnel will seriously affect the normal operation of expressway and cause huge safety hazard. The pedestrian detection technology in video surveillance in tunnel environment is an important guarantee for the normal operation of highway. In the tunnel environment, the environment lighting conditions are poor, a lot of noise is produced in the image, the pedestrian in the tunnel has small targets and low pixels. It brings great challenge to pedestrian detection in tunnel environment. This paper mainly studies the segmentation method of foreground target and background object in video detection. The pedestrian target detection method based on mathematical feature extraction and convolution neural network is used. In addition, aiming at the difficult problem of extracting noisy pedestrian features in tunnel environment, we use convolutional neural network to extract features. The downlink detection network of end-to-end tunnel scene is trained. The main contents of this paper are as follows: 1) in the training of pedestrian detection classifier, a single HOG feature is usually used. In this paper, a local binary pattern (LBP) feature and gradient direction histogram feature (hog) are introduced into the classification model of support vector machine in series. The trained pedestrian detector based on joint feature greatly improves the accuracy of pedestrian detection in tunnel environment. (2) the classifier based on HOG feature and LBP feature series training generally uses sliding window traversal strategy to search the whole image. This results in a huge loss of timeliness. In highway tunnels, surveillance images appear in fixed scenes. According to this characteristic of video surveillance, by extracting pedestrian movement information, Combining the classifier detection with an improved Gao Si mixed background differential method, the moving region of the image is extracted, and the search times of the image are reduced. The efficiency of pedestrian recognition in the algorithm system is greatly improved. (3) aiming at the problem that the boundary between pedestrian and environment is weak due to the noise in highway tunnel environment, the traditional machine learning method is difficult to extract effective features. In this paper, we use convolutional neural network to extract features, improve the method of candidate extraction, and use RPN candidate to extract the network. The single target recognition network is trained under the condition of few single image candidate frames, and the candidate extraction network and pedestrian detection network are trained. Get the end to end pedestrian detection network. Compared with the feature designed pedestrian detection model, greatly improve the accuracy of pedestrian detection in tunnel environment. To some extent, the speed of pedestrian detection based on RCNN algorithm is improved. According to the requirement of pedestrian detection in highway tunnel environment, the adaptability of classifier model based on feature extraction to tunnel application scene is studied. The corresponding method is put forward to improve the detection model. The regional convolution neural network is applied to pedestrian detection in the scene of highway tunnel. At the same time, it trains the end-to-end depth pedestrian detection model, improves the accuracy of downlink detection of tunnel monitoring scene, and has some reference significance for other target recognition work based on convolution neural network.
【學位授予單位】：昆明理工大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：U458;TP391.41

【參考文獻】

相關期刊論文 前5條

1 張利平;邵宗凱;吳建德;;基于改進KSVD和極限學習機的車型識別方法研究[J];計算機與數(shù)字工程;2016年06期

2 劉操;鄭宏;黎曦;余典;;基于多通道融合HOG特征的全天候運動車輛檢測方法[J];武漢大學學報(信息科學版);2015年08期

3 汪成亮;周佳;黃晟;;基于高斯混合模型與PCA-HOG的快速運動人體檢測[J];計算機應用研究;2012年06期

4 王亮,胡衛(wèi)明,譚鐵牛;人運動的視覺分析綜述[J];計算機學報;2002年03期

5 徐一華,朱玉文,賈云得;一種人頭部實時跟蹤方法[J];中國圖象圖形學報;2002年01期

相關博士學位論文 前1條

1 趙明;二維視覺對象分割[D];浙江大學;2004年

相關碩士學位論文 前2條

1 魯寒凝;基于HOG特征的交通標志檢測與識別算法研究[D];長安大學;2015年

2 陳虹穎;隧道環(huán)境下行人目標視頻檢測技術研究[D];重慶大學;2013年

，

本文編號：1590244