基于背景建模的運(yùn)動(dòng)目標(biāo)監(jiān)控視頻檢測(cè)算法
發(fā)布時(shí)間：2018-07-20 20:51
【摘要】：視頻監(jiān)控已廣泛應(yīng)用于水路航運(yùn),尤其對(duì)運(yùn)動(dòng)船舶尺寸、流量、速度以及異常事件分析的需求日益突出,運(yùn)動(dòng)目標(biāo)檢測(cè)作為視頻監(jiān)控系統(tǒng)的核心環(huán)節(jié),作用不言而喻。然而實(shí)際監(jiān)控場(chǎng)景復(fù)雜多變,變化的光線、搖晃的樹(shù)葉、水面的波紋等,對(duì)運(yùn)動(dòng)目標(biāo)檢測(cè)的準(zhǔn)確性產(chǎn)生了巨大影響,有必要專題研究復(fù)雜場(chǎng)景下的運(yùn)動(dòng)目標(biāo)檢測(cè)算法。論文源自船聯(lián)網(wǎng)國(guó)家重大專項(xiàng)《船舶實(shí)時(shí)視頻圖像監(jiān)測(cè)識(shí)別系統(tǒng)關(guān)鍵技術(shù)研究及應(yīng)用》和江蘇省海事局科研項(xiàng)目《船舶超限檢測(cè)系統(tǒng)》,結(jié)合項(xiàng)目中遇到的難點(diǎn)和挑戰(zhàn),諸如水面波紋、船尾拖紋、相機(jī)抖動(dòng)、船舶運(yùn)動(dòng)速度過(guò)慢等問(wèn)題,分析了國(guó)內(nèi)外現(xiàn)有的背景建模算法,找出了算法誤檢的原因,針對(duì)算法缺陷提出了優(yōu)化方案,并加以實(shí)驗(yàn)驗(yàn)證。論文闡述了國(guó)內(nèi)外視頻監(jiān)控系統(tǒng)的研究現(xiàn)狀,解析了背景建模算法在運(yùn)動(dòng)目標(biāo)檢測(cè)中的作用和地位,對(duì)比分析了經(jīng)典背景建模算法的檢測(cè)性能,提出了基于改進(jìn)VIBE的運(yùn)動(dòng)目標(biāo)檢測(cè)算法,優(yōu)化了基于像素運(yùn)動(dòng)特征的MOG算法,給出了基于三維圖像的運(yùn)動(dòng)船舶超限監(jiān)測(cè)算法。論文研究了背景建模算法理論,對(duì)比分析了六種經(jīng)典背景建模算法的優(yōu)勢(shì)與不足,通過(guò)實(shí)驗(yàn)驗(yàn)證了各個(gè)算法的適用場(chǎng)景和檢測(cè)效果。論文分析了VIBE算法的優(yōu)點(diǎn)與缺陷,針對(duì)動(dòng)態(tài)背景問(wèn)題,從背景模型初始化、模型匹配和模型更新三個(gè)階段,采用多幀連續(xù)圖像初始化背景模型,削弱了“鬼影”對(duì)后續(xù)檢測(cè)的干擾；根據(jù)背景動(dòng)態(tài)程度自適應(yīng)調(diào)整匹配閾值,減少了動(dòng)態(tài)背景誤檢；計(jì)算背景樣本離散度尋找最優(yōu)替換樣本,結(jié)合空間一致性原理和模糊理論,提高了背景模型準(zhǔn)確性,降低了誤檢率。論文分析了相機(jī)抖動(dòng)下背景像素的運(yùn)動(dòng)信息分布,提取像素運(yùn)動(dòng)特征,二次分辨MOG算法提取的運(yùn)動(dòng)前景,剔除相機(jī)抖動(dòng)產(chǎn)生的誤檢,并自適應(yīng)優(yōu)化了算法的學(xué)習(xí)速率,在前景區(qū)域和背景區(qū)域設(shè)置不同的更新速率,解決了動(dòng)態(tài)背景誤檢和真實(shí)前景漏檢之間的矛盾,提高了算法的魯棒性。論文研究了三維圖像運(yùn)動(dòng)船舶超限監(jiān)測(cè)算法,采用三臺(tái)掃描儀采集三維點(diǎn)云,運(yùn)用PCA方法分類點(diǎn)云數(shù)據(jù),測(cè)量出運(yùn)動(dòng)船舶的三維尺寸。論文創(chuàng)新點(diǎn)如下：●提出基于改進(jìn)VIBE的運(yùn)動(dòng)目標(biāo)檢測(cè)算法,采用多幀圖像初始化背景模型,根據(jù)背景動(dòng)態(tài)程度自適應(yīng)調(diào)整匹配閾值,計(jì)算樣本離散度實(shí)現(xiàn)最佳樣本替換,結(jié)合模糊理論,提高了背景模型準(zhǔn)確性,降低了動(dòng)態(tài)背景對(duì)運(yùn)動(dòng)目標(biāo)檢測(cè)的干擾；·優(yōu)化基于像素運(yùn)動(dòng)特征的MOG算法,提取像素運(yùn)動(dòng)特征用于運(yùn)動(dòng)前景二次分辨,并自適應(yīng)調(diào)整學(xué)習(xí)速率,抑制了抖動(dòng)誤檢,提高了算法的魯棒性�！そo出了基于三維圖像的運(yùn)動(dòng)船舶超限監(jiān)測(cè)算法,用于檢測(cè)運(yùn)動(dòng)船舶的三維尺寸,為監(jiān)測(cè)超限船舶提供依據(jù)。
[Abstract]:Video surveillance has been widely used in waterway shipping, especially for the size, flow, speed and abnormal event analysis of moving ships. As the core of video surveillance system, the role of moving target detection is self-evident. However, the complex and changeable scene, changing light, rocking leaves and ripples of water surface have a great influence on the accuracy of moving target detection. It is necessary to study the algorithm of moving target detection in complex scene. The thesis is derived from the key technology research and application of ship real-time video image monitoring and identification system, a major national project of ship networking, and the scientific research project of Jiangsu Marine Administration, "ship Over-limit Detection system", which combines the difficulties and challenges encountered in the project. Problems such as surface ripple, stern ripple, camera jitter and slow ship motion are analyzed. The existing background modeling algorithms at home and abroad are analyzed, and the reasons for the false detection of the algorithm are found out, and the optimization scheme is proposed for the defects of the algorithm. It is verified by experiments. This paper describes the research status of video surveillance system at home and abroad, analyzes the role and status of background modeling algorithm in moving target detection, and compares the detection performance of classical background modeling algorithm. A moving target detection algorithm based on improved vibe is proposed, and a Mog algorithm based on pixel motion features is optimized. This paper studies the theory of background modeling algorithm, compares and analyzes the advantages and disadvantages of six classical background modeling algorithms, and verifies the applicable scene and detection effect of each algorithm through experiments. This paper analyzes the advantages and disadvantages of VIBE algorithm. Aiming at the dynamic background problem, the background model is initialized from three stages: background model initialization, model matching and model updating, and multi-frame continuous image is used to initialize the background model. It weakens the interference of "ghost" to the subsequent detection; adaptively adjusts the matching threshold according to the dynamic degree of background, reduces the false detection of dynamic background; calculates the dispersion of background samples to find the optimal replacement samples, and combines the spatial consistency principle and fuzzy theory. The accuracy of the background model is improved and the false detection rate is reduced. In this paper, the motion information distribution of background pixels under camera jitter is analyzed, the motion feature of pixels is extracted, the motion foreground is extracted by second resolution Mog algorithm, the false detection caused by camera jitter is eliminated, and the learning rate of the algorithm is optimized adaptively. Different update rates are set in the foreground region and background area, which solves the contradiction between dynamic background false detection and real foreground missed detection, and improves the robustness of the algorithm. In this paper, we study the algorithm of detecting the moving ship in 3D image. Three scanners are used to collect the 3D point cloud, and PCA method is used to classify the point cloud data to measure the 3D size of the moving ship. The innovations of this paper are as follows: a moving target detection algorithm based on improved vibe is proposed. The background model is initialized by multi-frame images and the matching threshold is adjusted adaptively according to the dynamic degree of background. The sample dispersion is calculated to achieve the best sample replacement. Combined with fuzzy theory, the accuracy of background model is improved, the interference of dynamic background to moving target detection is reduced, and the Mog algorithm based on pixel motion feature is optimized to extract pixel motion feature for the second resolution of motion foreground. It adaptively adjusts the learning rate, restrains the jitter error detection, and improves the robustness of the algorithm. An algorithm based on 3D image is presented to detect the 3D size of the moving ship, which provides the basis for monitoring the ship in excess of the limit.
【學(xué)位授予單位】：南京大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.41;TN948.6
本文編號(hào)：2134739
[Abstract]:Video surveillance has been widely used in waterway shipping, especially for the size, flow, speed and abnormal event analysis of moving ships. As the core of video surveillance system, the role of moving target detection is self-evident. However, the complex and changeable scene, changing light, rocking leaves and ripples of water surface have a great influence on the accuracy of moving target detection. It is necessary to study the algorithm of moving target detection in complex scene. The thesis is derived from the key technology research and application of ship real-time video image monitoring and identification system, a major national project of ship networking, and the scientific research project of Jiangsu Marine Administration, "ship Over-limit Detection system", which combines the difficulties and challenges encountered in the project. Problems such as surface ripple, stern ripple, camera jitter and slow ship motion are analyzed. The existing background modeling algorithms at home and abroad are analyzed, and the reasons for the false detection of the algorithm are found out, and the optimization scheme is proposed for the defects of the algorithm. It is verified by experiments. This paper describes the research status of video surveillance system at home and abroad, analyzes the role and status of background modeling algorithm in moving target detection, and compares the detection performance of classical background modeling algorithm. A moving target detection algorithm based on improved vibe is proposed, and a Mog algorithm based on pixel motion features is optimized. This paper studies the theory of background modeling algorithm, compares and analyzes the advantages and disadvantages of six classical background modeling algorithms, and verifies the applicable scene and detection effect of each algorithm through experiments. This paper analyzes the advantages and disadvantages of VIBE algorithm. Aiming at the dynamic background problem, the background model is initialized from three stages: background model initialization, model matching and model updating, and multi-frame continuous image is used to initialize the background model. It weakens the interference of "ghost" to the subsequent detection; adaptively adjusts the matching threshold according to the dynamic degree of background, reduces the false detection of dynamic background; calculates the dispersion of background samples to find the optimal replacement samples, and combines the spatial consistency principle and fuzzy theory. The accuracy of the background model is improved and the false detection rate is reduced. In this paper, the motion information distribution of background pixels under camera jitter is analyzed, the motion feature of pixels is extracted, the motion foreground is extracted by second resolution Mog algorithm, the false detection caused by camera jitter is eliminated, and the learning rate of the algorithm is optimized adaptively. Different update rates are set in the foreground region and background area, which solves the contradiction between dynamic background false detection and real foreground missed detection, and improves the robustness of the algorithm. In this paper, we study the algorithm of detecting the moving ship in 3D image. Three scanners are used to collect the 3D point cloud, and PCA method is used to classify the point cloud data to measure the 3D size of the moving ship. The innovations of this paper are as follows: a moving target detection algorithm based on improved vibe is proposed. The background model is initialized by multi-frame images and the matching threshold is adjusted adaptively according to the dynamic degree of background. The sample dispersion is calculated to achieve the best sample replacement. Combined with fuzzy theory, the accuracy of background model is improved, the interference of dynamic background to moving target detection is reduced, and the Mog algorithm based on pixel motion feature is optimized to extract pixel motion feature for the second resolution of motion foreground. It adaptively adjusts the learning rate, restrains the jitter error detection, and improves the robustness of the algorithm. An algorithm based on 3D image is presented to detect the 3D size of the moving ship, which provides the basis for monitoring the ship in excess of the limit.
【學(xué)位授予單位】：南京大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.41;TN948.6
【共引文獻(xiàn)】
相關(guān)期刊論文 前2條
1 周曉;趙鋒;朱艷林;;基于ViBe的室外動(dòng)態(tài)背景閃爍像素噪聲消除方法[J];計(jì)算機(jī)應(yīng)用;2015年06期
2 何廣達(dá);王洪順;李強(qiáng);;基于計(jì)算機(jī)視覺(jué)的激光檢測(cè)系統(tǒng)研究[J];激光雜志;2015年09期
相關(guān)博士學(xué)位論文 前1條
1 畢國(guó)玲;智能視頻監(jiān)控系統(tǒng)中若干關(guān)鍵技術(shù)研究[D];中國(guó)科學(xué)院研究生院(長(zhǎng)春光學(xué)精密機(jī)械與物理研究所);2015年
，本文編號(hào)：2134739
本文鏈接：http://sikaile.net/kejilunwen/wltx/2134739.html
最近更新
教材專著
