本文選題：混合高斯模型 + 陰影消除　； 參考：《南京航空航天大學(xué)》2014年碩士論文

【摘要】：在目前的智能交通系統(tǒng)中，對(duì)車(chē)輛的識(shí)別和跟蹤一直是一個(gè)核心的環(huán)節(jié)，它能夠提供各種動(dòng)態(tài)的交通環(huán)境信息，便于統(tǒng)一管理和調(diào)度，緩解交通擁擠和減少交通事故，因此對(duì)車(chē)輛的準(zhǔn)確識(shí)別和長(zhǎng)期跟蹤一直是智能交通監(jiān)控的研究熱點(diǎn)。本文重點(diǎn)研究了車(chē)輛的識(shí)別和跟蹤理論，從四個(gè)步驟重點(diǎn)論述了車(chē)輛的檢測(cè)、識(shí)別和跟蹤方法，并用具體的實(shí)驗(yàn)證明了本文算法的可靠性和有效性。具體的工作如下： （1）提出了一種基于改進(jìn)的混合高斯模型的動(dòng)目標(biāo)檢測(cè)算法，，該算法通過(guò)幀間匹配度信息反饋改變了傳統(tǒng)方法的學(xué)習(xí)規(guī)則，克服了車(chē)輛檢測(cè)斷裂或分離的缺陷，排除了車(chē)輛和環(huán)境對(duì)背景學(xué)習(xí)的干擾。實(shí)驗(yàn)表明，該方法對(duì)于提取動(dòng)目標(biāo)區(qū)域較經(jīng)典方法更加準(zhǔn)確。 （2）提出了一種基于HSV色彩空間法和混合高斯模型的陰影檢測(cè)算法，該算法通過(guò)人工采集方法和HSV色彩空間法來(lái)獲得陰影樣本，并利用期望最大法對(duì)陰影訓(xùn)練樣本估計(jì)模型參數(shù)，獲得的混合高斯模型用來(lái)區(qū)分車(chē)輛和陰影。實(shí)驗(yàn)結(jié)果表明該方法可以有效分離車(chē)輛和陰影。 （3）采用了7個(gè)Hu不變距、分散度、長(zhǎng)寬比和緊湊度組成10維的形狀特征向量以及三層BP神經(jīng)網(wǎng)絡(luò)對(duì)行人、大車(chē)、小車(chē)、自行車(chē)或者摩托車(chē)這四類(lèi)目標(biāo)進(jìn)行分類(lèi)，實(shí)驗(yàn)結(jié)果表明通過(guò)樣本訓(xùn)練出來(lái)的神經(jīng)網(wǎng)絡(luò)分類(lèi)器可以對(duì)這四類(lèi)目標(biāo)有效分類(lèi)。 （4）提出了一種改進(jìn)的TLD跟蹤算法，該算法結(jié)合原來(lái)的單分類(lèi)器，加入了基于Haar特征和在線(xiàn)Adaboost方法的分類(lèi)器，構(gòu)成了一種半監(jiān)督協(xié)同訓(xùn)練的分類(lèi)器，提高了分類(lèi)器的泛化能力，實(shí)驗(yàn)結(jié)果表明該方法可以進(jìn)一步提高跟蹤效果。
[Abstract]:In the current intelligent transportation system, the identification and tracking of vehicles is always a core link. It can provide a variety of dynamic traffic environment information, facilitate unified management and scheduling, alleviate traffic congestion and reduce traffic accidents. Therefore, the accurate identification and long-term tracking of vehicles has always been the research hotspot of intelligent traffic monitoring. This paper focuses on the theory of vehicle recognition and tracking, discusses the detection, recognition and tracking methods of vehicles from four steps, and proves the reliability and effectiveness of this algorithm by experiments. The specific work is as follows: (1) A moving target detection algorithm based on the improved hybrid Gao Si model is proposed. The algorithm changes the learning rules of the traditional methods through the information feedback of the matching degree between frames, and overcomes the defect of vehicle detection breaking or separation. The interference of vehicle and environment to background learning is eliminated. Experiments show that the proposed method is more accurate than the classical method in extracting moving target regions. (2) A shadow detection algorithm based on HSV color space method and hybrid Gao Si model is proposed. The shadow sample is obtained by artificial acquisition and HSV color space method, and the model parameters are estimated by the expected maximum method. The hybrid Gao Si model is obtained to distinguish vehicles from shadows. The experimental results show that this method can effectively separate vehicle from shadow. Using seven Hu invariants, dispersion, aspect ratio and compactness, a 10-dimensional shape feature vector and a three-layer BP neural network are used to classify pedestrian, cart, car, bicycle or motorcycle. The experimental results show that the neural network classifier trained by the samples can effectively classify the four kinds of targets. In this paper, an improved TLD tracking algorithm is proposed, which combines the original single classifier and adds a classifier based on Haar features and online Adaboost method. It constitutes a semi-supervised cooperative training classifier and improves the generalization ability of the classifier. Experimental results show that this method can further improve the tracking effect.
【學(xué)位授予單位】：南京航空航天大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：U495

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 黃信想;劉秉瀚;;基于HSV色彩空間的云模型車(chē)輛陰影檢測(cè)[J];福州大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年06期

2 吳小強(qiáng),李鵬,曲衛(wèi)民;智能交通系統(tǒng)研究回顧與展望[J];國(guó)外公路;2000年04期

3 顏佳;吳敏淵;;遮擋環(huán)境下采用在線(xiàn)Boosting的目標(biāo)跟蹤[J];光學(xué)精密工程;2012年02期

4 朱峰;羅立民;宋余慶;陳健美;左欣;;基于自適應(yīng)空間鄰域信息高斯混合模型的圖像分割[J];計(jì)算機(jī)研究與發(fā)展;2011年11期

5 郁梅,蔣剛毅,郁伯康;智能交通系統(tǒng)中的計(jì)算機(jī)視覺(jué)技術(shù)應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2001年10期

6 張運(yùn)楚;李貽斌;張建濱;;高斯混合背景模型的方差估計(jì)研究[J];計(jì)算機(jī)工程與應(yīng)用;2012年04期

7 劉勃,魏銘旭,周荷琴;交通場(chǎng)景中分塊陰影檢測(cè)算法研究[J];計(jì)算機(jī)工程;2005年11期

8 黃英杰;盧湖川;;一種改進(jìn)的運(yùn)動(dòng)目標(biāo)檢測(cè)和陰影消除算法[J];計(jì)算機(jī)工程;2008年06期

9 盧s

本文編號(hào)：1961725