本文選題：魚眼攝像頭 + 全景圖像　； 參考：《中國農(nóng)業(yè)大學》2017年博士論文

【摘要】：基于全景視覺的汽車行駛環(huán)境監(jiān)測系統(tǒng)可以為駕駛員提供全景成像和目標檢測兩大駕駛輔助功能,是主動安全領域的重要技術,具有重要的應用價值�，F(xiàn)有的目標檢測功能主要基于雷達或普通攝像頭實現(xiàn),其檢測算法對于大視場、大畸變的魚眼攝像頭并不適用。本文首先對全景成像系統(tǒng)的標定方法進行改進從而快速獲得精確的系統(tǒng)參數(shù),然后對基于全景視覺的行人檢測算法進行研究。主要研究內(nèi)容包括:分析了全景成像系統(tǒng)的標定原理。通過對比實驗選擇折反射模型作為魚眼攝像頭的成像模型,以此為基礎進行攝像頭的標定和全景成像系統(tǒng)的標定。為魚眼攝像頭設計一種由三個相互垂直的標定板組成的立體標定板,使標定時角點完全覆蓋攝像頭,從而充分利用魚眼圖像邊緣部分以獲得更精確的攝像頭參數(shù)。在全景系統(tǒng)標定板上添加定位塊,保證系統(tǒng)標定的穩(wěn)定性。對魚眼圖像進行前視圖投影和直方圖均衡化,完成預處理。建立歸一化的行人樣本庫。分別對常用的行人描述特征和機器學習算法進行分析,包括Haar特征結合AdaBoost算法,HOG特征結合SVM算法,以及卷積神經(jīng)網(wǎng)絡進行分類器訓練實驗,對所得分類器和訓練過程進行評價,總結各自的特點。對行人局部HOG特征與整體HOG特征進行對比,提出基于ROI-HOG特征訓練SVM分類器;設計卷積神經(jīng)網(wǎng)絡行人檢測分類器,優(yōu)化網(wǎng)絡結構參數(shù),并結合無監(jiān)督CNN提取特征與線性SVM分類器監(jiān)督學習形成組合分類器,實現(xiàn)快速準確的行人檢測。為充分利用魚眼圖像的大視場,研究如何克服圖像邊緣的大幅度變形。提出了多橫擺角前視投影的方法,將一幅魚眼圖像展開為不同橫擺角的前視投影圖,然后進行行人檢測。圖像任意位置的行人在某一范圍內(nèi)的虛擬橫擺角下的前視圖中,都可去除仿射變形恢復正常人體比例,方便后續(xù)進行行人檢測。通過實驗總結前視圖橫擺角設置規(guī)則,盡量減少一幅魚眼圖像的展開數(shù),減少檢測耗時。進行實車全景系統(tǒng)標定實驗,結果表明系統(tǒng)具有較高的標定精度和標定穩(wěn)定性。采集行車視頻數(shù)據(jù),逐幀標記行人形成測試集,在PC上設計評估軟件,運行行人檢測程序,評估行人檢測算法性能,結果表明在一定距離范圍內(nèi)本文算法可以實現(xiàn)較高的行人檢測率。
[Abstract]:The vehicle driving environment monitoring system based on panoramic vision can provide driving assistant functions of panoramic imaging and target detection. It is an important technology in active safety field and has important application value. The existing target detection function is mainly based on radar or ordinary camera, and its detection algorithm is not suitable for large field of view and large distortion fish-eye camera. In this paper, the calibration method of panoramic imaging system is improved to obtain the accurate system parameters quickly, and then the pedestrian detection algorithm based on panoramic vision is studied. The main contents are as follows: the calibration principle of panoramic imaging system is analyzed. The refraction model is chosen as the imaging model of fish-eye camera by contrast experiment, and the camera and panoramic imaging system are calibrated based on the model. A stereo calibration board composed of three vertical calibration boards is designed for the fish-eye camera, which can cover the camera completely when the corners are calibrated, thus making full use of the edge part of the fish-eye image to obtain more accurate camera parameters. A positioning block is added to the panoramic system calibration board to ensure the stability of the system calibration. The front view projection and histogram equalization are used to preprocess the fish eye image. A normalized pedestrian sample bank is established. The common pedestrian description features and machine learning algorithms are analyzed respectively, including Haar feature and AdaBoost algorithm combined with SVM algorithm, and convolution neural network for classifier training experiment. The classifier and training process are evaluated. Summarize their own characteristics. By comparing the local HOG features of pedestrians with the overall HOG features, a SVM classifier based on ROI-HOG feature training is proposed, and a pedestrian detection classifier based on convolution neural network is designed to optimize the network structure parameters. Combined with unsupervised CNN feature extraction and linear SVM classifier supervised learning, a combined classifier is formed to realize fast and accurate pedestrian detection. In order to make full use of the large field of view of the fish-eye image, this paper studies how to overcome the large deformation of the image edge. A method of forward projection with multiple yaw angles is proposed. A fish-eye image is expanded into a forward projection image with different yaw angles, and then pedestrian detection is carried out. In the front view of a virtual yaw angle in any position of the image, the affine deformation can be removed to restore the normal proportion of the human body, and it is convenient to carry out pedestrian detection. The rules of yaw angle setting in front view are summarized by experiments to reduce the expansion number of a fish-eye image and the detection time. The calibration experiment of real vehicle panoramic system shows that the system has high calibration accuracy and stability. Collect the video data of the vehicle, mark the pedestrian to form the test set frame by frame, design the evaluation software on the PC, run the pedestrian detection program, evaluate the performance of the pedestrian detection algorithm, The results show that the proposed algorithm can achieve high pedestrian detection rate within a certain range of distances.
【學位授予單位】：中國農(nóng)業(yè)大學
【學位級別】：博士
【學位授予年份】：2017
【分類號】：U463.6

【參考文獻】

相關期刊論文 前10條

1 高秀麗;遲瑞娟;王建強;;采用立體標定板的魚眼相機快速標定方法[J];哈爾濱工程大學學報;2016年11期

2 孫銳;張廣海;高雋;;基于深度分層特征表示的行人識別方法[J];電子與信息學報;2016年06期

3 曾敏;周益龍;;基于深度學習模型的行人檢測研究與仿真[J];南京郵電大學學報(自然科學版);2015年06期

4 丁文秀;孫銳;閆曉星;;基于分層深度學習的魯棒行人分類[J];光電工程;2015年09期

5 芮挺;費建超;周怞;方虎生;朱經(jīng)緯;;基于深度卷積神經(jīng)網(wǎng)絡的行人檢測[J];計算機工程與應用;2016年13期

6 嚴春燕;;全景攝像機標定方法綜述[J];電腦知識與技術;2014年34期

7 遲瑞娟;趙木禎;王建強;張德兆;;一種基于折反射相機的客車全景環(huán)視系統(tǒng)[J];哈爾濱工程大學學報;2013年02期

8 江鐵;朱桂斌;孫奧;;全景圖像拼接技術研究現(xiàn)狀綜述[J];重慶工商大學學報(自然科學版);2012年12期

9 孫志軍;薛磊;許陽明;王正;;深度學習研究綜述[J];計算機應用研究;2012年08期

10 郭立君;劉曦;趙杰煜;史忠植;;結合運動信息與表觀特征的行人檢測方法[J];軟件學報;2012年02期

相關博士學位論文 前5條

1 賴世銘;全景凝視系統(tǒng)中的關鍵技術研究[D];國防科學技術大學;2014年

2 張陽;復雜交通場景中基于視頻的行人檢測與跟蹤若干關鍵問題研究[D];華南理工大學;2013年

3 馮為嘉;基于魚眼鏡頭的全方位視覺及全景立體球視覺研究[D];天津大學;2012年

4 汪中;面向變化場景的行人分類檢測方法研究[D];中國科學技術大學;2011年

5 郭烈;基于單目視覺的車輛前方行人檢測技術研究[D];吉林大學;2007年

，

本文編號：1862021