發(fā)布時(shí)間：2018-09-13 15:55

【摘要】：隨著科技的發(fā)展,時(shí)代不斷的進(jìn)步,計(jì)算機(jī)視覺(jué)技術(shù)、高速的網(wǎng)絡(luò)通信技術(shù)和電子技術(shù)也在不斷向前發(fā)展。智能交通系統(tǒng)(Intelligent Transportation System,簡(jiǎn)稱ITS)在城市交通的合理規(guī)劃和管理中發(fā)揮著越來(lái)越強(qiáng)大的作用。在基于視頻幀的序列圖像中,運(yùn)動(dòng)車輛目標(biāo)的定位、識(shí)別、測(cè)速、跟蹤是智能交通系統(tǒng)研究的重點(diǎn)之處。智能交通系統(tǒng)要解決的首要問(wèn)題是進(jìn)行運(yùn)動(dòng)車輛檢測(cè),檢測(cè)的結(jié)果會(huì)直接影響車輛的后續(xù)處理。通常所使用的目標(biāo)檢測(cè)算法,很容易將陰影部分當(dāng)成前景檢測(cè)出來(lái)。所以,能否成功地去除陰影,會(huì)直接影響到車輛的檢測(cè)結(jié)果的準(zhǔn)確度。本文通過(guò)分析陰影的形成原理和顏色屬性的特性,提出了一種基于顏色屬性的陰影去除方法。由于,光線一般都是平行的直線,離車越近的地方遮擋越大,陰影也就越深,離車遠(yuǎn)的地方,遮擋相對(duì)較小,陰影較輕。顏色屬性(即顏色名)是從現(xiàn)實(shí)的生活世界中學(xué)習(xí)得到的。通過(guò)Google圖像搜索引擎為每個(gè)顏色名搜索一定數(shù)量的圖像數(shù)據(jù)集,然而,這些數(shù)據(jù)集中存在著許多錯(cuò)誤的正樣本。因此,采用概率潛在語(yǔ)義分析模型(PLSA)學(xué)習(xí)顏色名。該方法利用了顏色屬性可以將一張圖像映射成邊界清晰、顏色分明、不存在漸變像素點(diǎn)的圖像,且圖像能夠很好地保證原有圖像的完整性。根據(jù)這一特性,可以將較深的陰影部分與車輛映射成不同的顏色塊。同時(shí),將映射后的圖像進(jìn)行二值化處理,以達(dá)到去除較深的陰影目的。由于,顏色屬性是對(duì)整幅圖像進(jìn)行處理,會(huì)將周圍的環(huán)境也映射成前景區(qū)域。從而很難確定目標(biāo)所在的位置,以及無(wú)法將陰影完全去除。所以,本文結(jié)合了基于高斯模型的背景差分。首先,檢測(cè)出運(yùn)動(dòng)車輛,以極大地減小要處理的前景區(qū)域。同時(shí),對(duì)背景差分的結(jié)果進(jìn)行了形態(tài)學(xué)上的腐蝕操作,以減少前景邊緣部分的噪聲。將背景差分與幀問(wèn)差分結(jié)果進(jìn)行邏輯與操作,在保證車輛目標(biāo)完整性的前提下,去除周圍環(huán)境噪聲的影響。同時(shí),為了較少內(nèi)部和邊緣孤立的噪聲,采用腐蝕操作將其去除,為了減少內(nèi)部的空洞現(xiàn)象,采用形態(tài)學(xué)上的膨脹操作。最后,根據(jù)陰影區(qū)域具有連通性的特性,對(duì)車輛區(qū)域進(jìn)行填充,以得到更加精確的車輛目標(biāo)。
[Abstract]:With the development of science and technology, computer vision technology, high speed network communication technology and electronic technology are developing. Intelligent Transportation system (Intelligent Transportation System,) is playing a more and more powerful role in the rational planning and management of urban traffic. In the sequence image based on video frame, the location, recognition, speed measurement and tracking of moving vehicle targets are the key points of the research of intelligent transportation system (its). The most important problem of Intelligent Transportation system (its) is to detect moving vehicles, and the result of detection will directly affect the subsequent processing of vehicles. Usually the target detection algorithm is used, it is easy to detect the shadow as foreground. Therefore, whether the shadow can be successfully removed will directly affect the accuracy of vehicle detection results. By analyzing the principle of shadow formation and the characteristics of color attributes, a shadow removal method based on color attributes is proposed in this paper. Because the light is usually a parallel straight line, the closer it is to the vehicle, the bigger the shadow is, and the deeper the shadow is, the smaller the shade is and the lighter the shadow is. Color attributes, or color names, are learned from the real world of life. A certain number of image data sets are searched for each color name by Google image search engine. However, there are many wrong positive samples in these datasets. Therefore, the probabilistic latent semantic analysis model (PLSA) is used to learn color names. The method uses color attributes to map an image into an image with clear boundary, clear color and no gradual pixels, and the image can ensure the integrity of the original image. Based on this feature, darker shaded parts can be mapped to different color blocks from vehicles. At the same time, the mapped images are binarized to remove deeper shadows. Because the color attribute processes the whole image, the surrounding environment is mapped to the foreground area. It is difficult to locate the target and to remove the shadow completely. Therefore, this paper combines the background difference based on Gao Si model. First, the moving vehicle is detected to greatly reduce the foreground area to be processed. At the same time, the result of background difference is corroded morphologically to reduce the noise of foreground edge. The background differential and frame differential results are logically and operationally operated to remove the influence of ambient noise on the premise of ensuring the integrity of the vehicle target. At the same time, in order to reduce the internal and edge isolated noise, the corrosion operation is used to remove it, and the morphological expansion operation is used to reduce the internal cavity phenomenon. Finally, according to the connectivity of the shadow region, the vehicle area is filled to obtain more accurate vehicle targets.
【學(xué)位授予單位】：安徽大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：U495;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 陸化普;李瑞敏;;城市智能交通系統(tǒng)的發(fā)展現(xiàn)狀與趨勢(shì)[J];工程研究-跨學(xué)科視野中的工程;2014年01期

2 秦鐘;;基于圖像不變矩特征和BP神經(jīng)網(wǎng)絡(luò)的車型分類[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年02期

3 孫正興 ,馮桂煥 ,周若鴻;基于草圖的人機(jī)交互技術(shù)研究進(jìn)展[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2005年09期

4 周麗;朱宏;;基于二重差分法的光流場(chǎng)運(yùn)動(dòng)檢測(cè)[J];計(jì)算機(jī)仿真;2009年12期

5 張紅穎;李鴻;孫毅剛;;基于混合高斯模型的陰影去除算法[J];計(jì)算機(jī)應(yīng)用;2013年01期

6 甘新勝;趙書(shū)斌;;基于背景差的運(yùn)動(dòng)目標(biāo)檢測(cè)方法比較分析[J];指揮控制與仿真;2008年03期

7 侯云山,劉宏兵;三次樣條函數(shù)的計(jì)算機(jī)求解[J];中州大學(xué)學(xué)報(bào);2004年03期

8 王滿剛;;淺談網(wǎng)絡(luò)視頻監(jiān)控系統(tǒng)在港口生產(chǎn)中的應(yīng)用[J];信息系統(tǒng)工程;2013年02期

相關(guān)碩士學(xué)位論文 前4條

1 單春芝;基于形態(tài)學(xué)策略的高分辨率遙感影像道路提取方法研究[D];山東科技大學(xué);2011年

2 趙俊;智能視頻監(jiān)控系統(tǒng)關(guān)鍵技術(shù)研究[D];西安電子科技大學(xué);2007年

3 李麗;基于視頻對(duì)象的壓縮編碼研究[D];山東大學(xué);2009年

4 陳爽;基于圖像處理的模具自動(dòng)識(shí)別與定位技術(shù)研究[D];東北大學(xué)　;2009年

，

本文編號(hào)：2241640