發(fā)布時(shí)間：2018-03-27 07:07

  本文選題：運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤　切入點(diǎn)：高斯混合模型　出處：《長春工業(yè)大學(xué)》2017年碩士論文

【摘要】：視頻序列中運(yùn)動(dòng)目標(biāo)的檢測(cè)與跟蹤一直是計(jì)算機(jī)視覺領(lǐng)域研究中倍受關(guān)注的熱門課題,并被廣泛應(yīng)用于精確武器制導(dǎo)、智能監(jiān)控、人機(jī)交互、智能機(jī)器人等軍事和日常生活中。這一課題不僅涉及了多個(gè)學(xué)科領(lǐng)域,而且其應(yīng)用的實(shí)際場(chǎng)景也是不盡相同。雖然人們針對(duì)這一課題進(jìn)行了大量的研究工作,但是還是存在著一些重要問題尚未解決。本論文不僅對(duì)前人的檢測(cè)和跟蹤算法進(jìn)行了深入的分析和研究,而且在某些方面給出了自己的改進(jìn)算法,使其更趨于完善。在運(yùn)動(dòng)目標(biāo)檢測(cè)方面,本論文分析了三種常用的運(yùn)動(dòng)目標(biāo)檢測(cè)方法,即:光流法、幀間差分法、背景減除法。著重對(duì)基于高斯混合模型的背景減除法做了分析和研究,此方法主要包括前景檢測(cè)、像素級(jí)后處理、區(qū)域分析、區(qū)域級(jí)后處理、特征提取五個(gè)環(huán)節(jié)。通過分析和研究發(fā)現(xiàn)傳統(tǒng)的基于高斯混合模型的背景減除法,在前景檢測(cè)環(huán)節(jié)中存在著缺陷,算法收斂速度慢,并且算法需要大量的存儲(chǔ)空間。于是在前景檢測(cè)算法的基礎(chǔ)上,對(duì)于該算法的具體實(shí)現(xiàn)步驟進(jìn)行了改進(jìn),給出了一種新的高斯混合模型初始化方法,利用在線K-均值聚類的方法對(duì)高斯混合模型進(jìn)行初始化,同時(shí)對(duì)模型更新方法做了進(jìn)一步改進(jìn)和優(yōu)化,對(duì)匹配準(zhǔn)則和新高斯分布生成準(zhǔn)則做了改進(jìn)。通過前景檢測(cè)的仿真實(shí)驗(yàn)發(fā)現(xiàn)改進(jìn)算法不但提高了檢測(cè)算法的收斂速度,而且具有很好的穩(wěn)定性,此外,從算法運(yùn)行時(shí)所占用的存儲(chǔ)空間上比較,實(shí)驗(yàn)證明節(jié)約了近一半的存儲(chǔ)空間。在運(yùn)動(dòng)目標(biāo)跟蹤方面,本論文對(duì)基于Kalman濾波的運(yùn)動(dòng)目標(biāo)跟蹤算法和采用顏色直方圖作為跟蹤特征的Camshift跟蹤算法做了深入的研究和分析。通過分析發(fā)現(xiàn),當(dāng)運(yùn)動(dòng)目標(biāo)周圍存在著與其具有相似顏色特征的大面積干擾物時(shí),Camshift跟蹤算法不能準(zhǔn)確的跟蹤運(yùn)動(dòng)目標(biāo)。針對(duì)這一問題,本文給出了一種將Camshift跟蹤算法和基于Kalman濾波的跟蹤算法兩者相結(jié)合的新的運(yùn)動(dòng)目標(biāo)跟蹤算法,通過實(shí)驗(yàn)證明,給出的新算法能夠有效的解決大面積顏色干擾的問題。
[Abstract]:Detection and tracking of moving targets in video sequences has been a hot topic in the field of computer vision, and has been widely used in precision weapon guidance, intelligent monitoring, human-computer interaction. In military and daily life, such as intelligent robots, this subject not only involves many disciplines, but also has different application scenarios. Although people have done a lot of research on this subject, However, there are still some important problems that remain unsolved. This paper not only analyzes and studies the previous detection and tracking algorithms, but also gives its own improved algorithm in some aspects. In the aspect of moving target detection, this paper analyzes three common moving target detection methods, namely: optical flow method, inter-frame difference method, Background subtraction method. The background subtraction method based on Gao Si's mixed model is analyzed and studied. This method mainly includes foreground detection, pixel level post processing, region analysis, region level post processing, Through analysis and research, it is found that the traditional background subtraction method based on Gao Si's mixed model has some defects in foreground detection, and the convergence speed of the algorithm is slow. And the algorithm needs a lot of storage space. Therefore, based on the foreground detection algorithm, the implementation steps of the algorithm are improved, and a new initialization method of Gao Si hybrid model is proposed. The online K-means clustering method is used to initialize Gao Si's mixed model, and the model updating method is further improved and optimized. The matching criterion and the new Gao Si distribution generation criterion are improved. The simulation results of foreground detection show that the improved algorithm not only improves the convergence speed of the detection algorithm, but also has good stability. Compared with the storage space occupied by the algorithm, the experimental results show that nearly half of the storage space is saved. In this paper, the moving target tracking algorithm based on Kalman filter and the Camshift tracking algorithm based on color histogram are studied and analyzed. The Camshift tracking algorithm can not track moving targets accurately when there is a large area of disturbance with similar color characteristics around the moving target. In this paper, a new moving target tracking algorithm which combines Camshift tracking algorithm and Kalman filter tracking algorithm is presented. The experimental results show that the new algorithm can effectively solve the problem of large area color interference.
【學(xué)位授予單位】：長春工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 周鑫;錢秋朦;葉永強(qiáng);王從慶;;改進(jìn)后的TLD視頻目標(biāo)跟蹤方法[J];中國圖象圖形學(xué)報(bào);2013年09期

2 姜明新;王洪玉;劉曉凱;;基于多相機(jī)的多目標(biāo)跟蹤算法[J];自動(dòng)化學(xué)報(bào);2012年04期

3 謝之宇;蔣曉瑜;汪熙;裴闖;;改進(jìn)的幀差法在目標(biāo)匹配中的應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2011年34期

4 蔣馨;;淺析國外智能視頻監(jiān)控技術(shù)的發(fā)展及應(yīng)用[J];中國安防;2011年10期

5 張娟;毛曉波;陳鐵軍;;運(yùn)動(dòng)目標(biāo)跟蹤算法研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2009年12期

6 成琳;陳俊杰;相潔;;圖像顏色征提取技術(shù)的研究與應(yīng)用[J];計(jì)算機(jī)工程與設(shè)計(jì);2009年14期

7 孫凱;劉士榮;;多目標(biāo)跟蹤的改進(jìn)Camshift/卡爾曼濾波組合算法[J];信息與控制;2009年01期

8 苑穎;羅青山;曾貴華;;視頻監(jiān)控系統(tǒng)中陰影去除方法的研究[J];計(jì)算機(jī)工程與應(yīng)用;2008年36期

9 吳成東;郭利鋒;張?jiān)浦?劉o，

本文編號(hào)：1670510