本文選題：視頻圖像　切入點(diǎn)：目標(biāo)檢測(cè)　出處：《哈爾濱工程大學(xué)》2016年碩士論文

【摘要】：視頻圖像中目標(biāo)檢測(cè)與跟蹤屬于機(jī)器視覺中的前端處理部分,通過(guò)對(duì)視頻圖像信息進(jìn)行處理,實(shí)現(xiàn)計(jì)算機(jī)能夠代替人眼進(jìn)行目標(biāo)的識(shí)別與跟蹤功能,一直是機(jī)器視覺和計(jì)算機(jī)視覺的最終目的。如何從圖像序列中獲取有用的信息作為科研人員的研究方向已成為視頻圖像中目標(biāo)檢測(cè)與跟蹤的理論基礎(chǔ)。視頻圖像目標(biāo)檢測(cè)與跟蹤已大量應(yīng)用于現(xiàn)實(shí)生活中的各種場(chǎng)景,在這些方面都顯示出對(duì)視頻圖像信息處理的重要應(yīng)用價(jià)值。本課題主要關(guān)注視頻圖像中多目標(biāo)跟蹤與軌跡保持方法,對(duì)圖像序列進(jìn)行多目標(biāo)跟蹤與軌跡保持等方面研究。第一,在由檢測(cè)到跟蹤方法中,圖像目標(biāo)檢測(cè)是進(jìn)行目標(biāo)跟蹤的前提。使用基于圖像的顏色、梯度方向和梯度幅值等基本圖像特征的積分通道融合特征,結(jié)合基于boosting的決策樹分類器,生成目標(biāo)檢測(cè)器,實(shí)現(xiàn)對(duì)圖像目標(biāo)的準(zhǔn)確檢測(cè)。第二,以自頂向下的處理思路,闡述了基于貝葉斯濾波框架的目標(biāo)跟蹤原理。研究基于隨機(jī)有限集理論的概率假設(shè)密度濾波遞歸算法,對(duì)算法的兩種不同實(shí)現(xiàn)方式進(jìn)行對(duì)比仿真實(shí)驗(yàn),最終確定使用高斯混合PHD濾波算法來(lái)進(jìn)行圖像多目標(biāo)跟蹤。第三,結(jié)合圖像目標(biāo)表觀模型特點(diǎn)和高斯混合PHD算法的應(yīng)用條件,提出適合用于圖像多目標(biāo)跟蹤的高斯混合PHD自適應(yīng)新生目標(biāo)算法,通過(guò)在標(biāo)準(zhǔn)行人檢測(cè)數(shù)據(jù)集上實(shí)驗(yàn),驗(yàn)證跟蹤算法的性能。第四,針對(duì)PHD濾波處理并不能實(shí)現(xiàn)多目標(biāo)跟蹤運(yùn)動(dòng)軌跡情況,構(gòu)建圖像多目標(biāo)能量函數(shù),將視頻多目標(biāo)跟蹤問(wèn)題轉(zhuǎn)化為能量函數(shù)優(yōu)化求解問(wèn)題。把經(jīng)過(guò)跟蹤濾波算法處理的圖像序列作為輸入,進(jìn)行多次迭代,實(shí)現(xiàn)視頻圖像多目標(biāo)跟蹤軌跡。
[Abstract]:Object detection and tracking in video images is a part of front-end processing in machine vision. By processing the video image information, the computer can replace the human eyes to recognize and track the target. It has always been the ultimate goal of machine vision and computer vision. How to obtain useful information from image sequences as the research direction of researchers has become the theoretical basis of target detection and tracking in video images. Target detection and tracking have been widely used in various scenarios in real life. In these aspects, it shows the important application value to video image information processing. This subject mainly pays attention to the method of multi-target tracking and track keeping in video image, and carries on the multi-target tracking and trajectory keeping to the image sequence and so on. First, Image target detection is the premise of target tracking in the detection and tracking method. The integral channel fusion feature based on the basic image features such as color, gradient direction and gradient amplitude is used, and the decision tree classifier based on boosting is combined. Generation of target detector to achieve accurate detection of image targets. Second, to top-down processing ideas, This paper introduces the principle of target tracking based on Bayesian filtering framework, studies the recursive algorithm of probability hypothetical density filtering based on stochastic finite set theory, and makes a comparative simulation experiment on two different realization methods of the algorithm. Finally, Gao Si hybrid PHD filter algorithm is used for image multi-target tracking. Thirdly, considering the characteristics of the image target model and the application conditions of Gao Si hybrid PHD algorithm, Gao Si hybrid PHD adaptive newborn target algorithm suitable for image multi-target tracking is proposed. The performance of the tracking algorithm is verified by experiments on standard pedestrian detection data set. Fourth, In view of the fact that the PHD filter can not realize the multi-target tracking, the multi-target energy function is constructed. The video multi-target tracking problem is transformed into the energy function optimization problem, and the image sequence processed by the tracking filtering algorithm is taken as the input, and the multi-target tracking trajectory of the video image is realized through several iterations.
【學(xué)位授予單位】：哈爾濱工程大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 蔡強(qiáng);劉亞奇;曹健;毛典輝;牛群;;圖像目標(biāo)類別檢測(cè)綜述[J];計(jì)算機(jī)科學(xué)與探索;2015年03期

2 文學(xué)志;方巍;鄭鈺輝;;一種基于類Haar特征和改進(jìn)AdaBoost分類器的車輛識(shí)別算法[J];電子學(xué)報(bào);2011年05期

3 孫君頂;馬媛媛;;紋理特征研究綜述[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2010年06期

4 趙其杰;屠大維;高健;黃志華;;基于Kalman濾波的視覺預(yù)測(cè)目標(biāo)跟蹤及其應(yīng)用[J];光學(xué)精密工程;2008年05期

5 侯志強(qiáng);韓崇昭;;視覺跟蹤技術(shù)綜述[J];自動(dòng)化學(xué)報(bào);2006年04期

相關(guān)博士學(xué)位論文 前4條

1 呂敬欽;視頻行人檢測(cè)及跟蹤的關(guān)鍵技術(shù)研究[D];上海交通大學(xué);2013年

2 王守佳;基于圖像的人體檢測(cè)跟蹤和人臉識(shí)別的研究[D];吉林大學(xué);2013年

3 李彤;智能視頻監(jiān)控下的多目標(biāo)跟蹤技術(shù)研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2013年

4 張鶴冰;概率假設(shè)密度濾波算法及其在多目標(biāo)跟蹤中的應(yīng)用[D];哈爾濱工程大學(xué);2012年

相關(guān)碩士學(xué)位論文 前2條

1 胡威;基于Meanshift的視頻人體目標(biāo)跟蹤算法研究[D];上海交通大學(xué);2013年

2 趙欣;基于隨機(jī)集理論的被動(dòng)多傳感器多目標(biāo)跟蹤技術(shù)[D];西安電子科技大學(xué);2009年

，

本文編號(hào)：1695484