視覺(jué)顯著性檢測(cè)模型研究及應(yīng)用
發(fā)布時(shí)間：2018-08-02 10:46
【摘要】：人類視覺(jué)系統(tǒng)在面對(duì)復(fù)雜自然場(chǎng)景時(shí),具有快速搜索感興趣目標(biāo)的能力,這種能力我們稱之為視覺(jué)注意。在人類生存與發(fā)展的過(guò)程中,視覺(jué)注意扮演著至關(guān)重要的角色。視覺(jué)注意和人類如何感知、處理視覺(jué)刺激緊密相關(guān),并且正在被包括認(rèn)知心理學(xué)、神經(jīng)生物學(xué)和計(jì)算機(jī)視覺(jué)在內(nèi)的多個(gè)學(xué)科進(jìn)行研究。隨著認(rèn)知心理學(xué)和神經(jīng)生物學(xué)的不斷發(fā)展,通過(guò)對(duì)視覺(jué)機(jī)理的研究發(fā)現(xiàn),人類視覺(jué)對(duì)場(chǎng)景中目標(biāo)的選擇性可分為兩個(gè)階段：一個(gè)快速的、無(wú)意識(shí)的、數(shù)據(jù)驅(qū)動(dòng)的、自底向上的階段和一個(gè)較慢的、有意識(shí)的、任務(wù)驅(qū)動(dòng)的、自頂向下的階段.而與視覺(jué)注意緊密相連的概念就是視覺(jué)顯著性,他是指導(dǎo)視覺(jué)注意的一個(gè)關(guān)鍵注意機(jī)制。圖像顯著性區(qū)域檢測(cè)研究的目的是快速定位顯著性區(qū)域并反映顯著性區(qū)域的顯著程度。視覺(jué)顯著性區(qū)域檢測(cè)在圖像處理中有著廣泛的應(yīng)用,包括圖像分割、目標(biāo)識(shí)別、自適應(yīng)壓縮、內(nèi)容敏感圖像編輯、圖像檢索、目標(biāo)檢測(cè)、目標(biāo)跟蹤、圖像質(zhì)量評(píng)價(jià)等。本文從視覺(jué)注意機(jī)制的研究出發(fā),對(duì)視覺(jué)顯著性檢測(cè)與應(yīng)用中的一些關(guān)鍵問(wèn)題進(jìn)行了較為深入的研究,提出了一些新的思想和算法。論文的主要工作與貢獻(xiàn)包括：(1)針對(duì)已有局部對(duì)比度和全局對(duì)比度建模方法存在的不足,本文提出了一種基于條件隨機(jī)場(chǎng)融合全局特征的顯著性區(qū)域檢測(cè)方法。該方法首先采用唯一性、顏色空間分布等全局特征計(jì)算相應(yīng)的顯著圖：其次在條件隨機(jī)場(chǎng)框架下融合多個(gè)顯著圖,通過(guò)顯著性區(qū)域與背景區(qū)域的區(qū)域標(biāo)注實(shí)現(xiàn)顯著性區(qū)域初步檢測(cè)；然后采用基于顯著性區(qū)域的高斯模型計(jì)算目標(biāo)先驗(yàn)圖,并對(duì)全局特征顯著圖進(jìn)行高斯濾波；最后再利用條件隨機(jī)場(chǎng)融合濾波之后的顯著圖來(lái)實(shí)現(xiàn)更加精確的顯著性檢測(cè)。實(shí)驗(yàn)結(jié)果表明該方法能均勻致密的凸顯顯著性區(qū)域,有效的抑制背景干擾,并具有較高的檢測(cè)準(zhǔn)確率與召回率。(2)基于視覺(jué)機(jī)制挖掘可應(yīng)用的更高層次的顯著性先驗(yàn)特征,本文提出了一種融合多級(jí)顯著性特征的顯著性目標(biāo)檢測(cè)方法。該方法融合了基于像素級(jí)的局部對(duì)比度、基于區(qū)域級(jí)的全局對(duì)比度以及基于目標(biāo)級(jí)的背景先驗(yàn)信息。該方法基于凸包檢測(cè)技術(shù)使用底層的視覺(jué)線索從背景分離顯著性目標(biāo)�；诔跫�(jí)的檢測(cè)結(jié)果提取背景模版,利用PCA計(jì)算背景先驗(yàn)信息。為了抑制背景干擾,該方法采用目標(biāo)中心先驗(yàn)信息精煉局部對(duì)比度特征和全局對(duì)比度特征。在公開(kāi)的數(shù)據(jù)集上的實(shí)驗(yàn)表明,該方法所得到的顯著圖能較好的凸顯顯著性目標(biāo).同時(shí)也證明Otsu自適應(yīng)閾值方法可以用來(lái)產(chǎn)生高質(zhì)量的目標(biāo)分割結(jié)果。(3)針對(duì)視覺(jué)顯著性在目標(biāo)跟蹤過(guò)程中的應(yīng)用研究,本文提出了一種基于視覺(jué)注意的目標(biāo)跟蹤算法。該算法首先采用基于背景先驗(yàn)的視覺(jué)顯著性檢測(cè)算法來(lái)提取目標(biāo)的顯著性特征,其次采用基于貝葉斯決策理論的前景背景分類方法來(lái)提取目標(biāo)的運(yùn)動(dòng)特征,然后利用顯著特征引導(dǎo)運(yùn)動(dòng)特征與顏色特征進(jìn)行目標(biāo)狀態(tài)估計(jì),最后結(jié)合自適應(yīng)粒子濾波形成目標(biāo)跟蹤算法。實(shí)驗(yàn)結(jié)果表明在復(fù)雜場(chǎng)景下,該算法相對(duì)于現(xiàn)有的目標(biāo)跟蹤算法具有較強(qiáng)的魯棒性,對(duì)光照變化、姿態(tài)變化、目標(biāo)遮擋、快速運(yùn)動(dòng)、復(fù)雜背景等具有較好的跟蹤效果。(4)針對(duì)槍球聯(lián)動(dòng)接力跟蹤過(guò)程中的目標(biāo)離開(kāi)槍機(jī)畫(huà)面后在球機(jī)中初始定位問(wèn)題,本文提出了一種基于視覺(jué)注意的槍球聯(lián)動(dòng)接力跟蹤方法。該方法采用網(wǎng)格結(jié)合插值算法實(shí)現(xiàn)在球機(jī)中的目標(biāo)放大跟蹤,當(dāng)目標(biāo)離開(kāi)槍機(jī)畫(huà)面時(shí),利用視覺(jué)顯著性檢測(cè)算法計(jì)算候選區(qū)域,利用槍機(jī)保存的目標(biāo)模版在候選區(qū)域中搜索匹配區(qū)域,確定目標(biāo)在球機(jī)場(chǎng)景中的位置,最后利用Mean Shift跟蹤算法實(shí)現(xiàn)球機(jī)的主動(dòng)跟蹤。實(shí)驗(yàn)結(jié)果表明本文提出的基于視覺(jué)注意的槍球聯(lián)動(dòng)接力跟蹤具有較好的實(shí)時(shí)跟蹤效果。
[Abstract]:In the face of complex natural scenes, the human visual system has the ability to quickly search for a target of interest, which we call visual attention. Visual attention plays a vital role in the process of human survival and development. Visual attention and human perception are closely related to visual stimuli, and are being included. The study of cognitive psychology, neurobiology and computer vision. With the continuous development of cognitive psychology and neurobiology, the study of visual mechanisms found that human vision can be divided into two stages: a fast, unconscious, data driven, bottom-up. The stage and a slow, conscious, task driven, top-down stage. The concept of close connection with visual attention is visual significance. He is a key attention mechanism to guide visual attention. The purpose of the image saliency region detection study is to quickly locate the significant region and reflect the significance of the significant region. Degree. Visual saliency region detection has a wide range of applications in image processing, including image segmentation, target recognition, adaptive compression, content sensitive image editing, image retrieval, target detection, target tracking, image quality evaluation and so on. This paper, starting from the research of visual attention mechanism, discusses some key points in visual significance detection and application. Some new ideas and algorithms are proposed. The main work and contributions of this paper are as follows: (1) in view of the shortcomings of the existing local contrast and the global contrast modeling method, a significant regional detection method based on the global characteristics of conditional random fields is proposed. We use the uniqueness, the color space distribution and other global characteristics to calculate the corresponding significant graphs. Secondly, multiple significant graphs are fused under the conditional random field framework, and the significant region detection is realized through the regional annotation of the significant region and the background region. Then the Gauss model based on the saliency region is used to calculate the prior map of the target, and the whole area is calculated. The characteristic salient image of the bureau is used to carry out Gauss filtering; finally, a more accurate detection is achieved by using the salient graph following the fusion filter of the airport. The experimental results show that the method can highlight the significant region, effectively suppress the background interference, and have high detection accuracy and recall. (2) the visual machine is based on the visual machine. This method combines the local contrast based on the pixel level, the global contrast based on the regional level and the backview prior information based on the target level. This method is based on the convex packet detection technique. The underlying visual cues are used to separate the significant targets from the background. The background template is extracted based on the primary detection results and the background information is calculated using the PCA. In order to suppress the background interference, the method uses the target center prior information to refine the local contrast characteristics and the global contrast characteristics. The experiment on the open data set shows that this method is used to extract the background information. The remarkable graph obtained by the method can better highlight the significant target. It also proves that the Otsu adaptive threshold method can be used to produce high quality target segmentation results. (3) aiming at the application of visual significance in target tracking, a target tracking algorithm based on visual attention is proposed in this paper. The visual saliency detection algorithm of background prior is used to extract the significant feature of the target. Secondly, the foreground background classification method based on Bayesian decision theory is used to extract the motion features of the target, and then the target state is estimated by using the significant feature to guide the motion feature and color feature. Finally, the adaptive particle filter is combined to form the target state. The experimental results show that in the complex scene, the algorithm has strong robustness against the existing target tracking algorithm, and has good tracking effect on illumination change, attitude change, target occlusion, fast motion, complex background and so on. (4) in the course of the gun ball linkage relay tracking, the target leaves the gun frame. In this paper, the problem of initial positioning in the ball machine is presented. This paper proposes a method of tracking the joint force of the gun ball based on visual attention. This method uses the mesh and interpolation algorithm to achieve the target amplification and tracking in the ball machine. When the target leaves the gun, the candidate region is calculated by the visual significance detection algorithm, and the target template saved by the gun is used. In the candidate region, the matching area is searched, the location of the target in the ball scene is determined, and the Mean Shift tracking algorithm is used to achieve the active tracking of the ball machine. The experimental results show that the tracking of the gun ball joint relay based on visual attention has good real-time tracking effect.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41
，
本文編號(hào)：2159180
[Abstract]:In the face of complex natural scenes, the human visual system has the ability to quickly search for a target of interest, which we call visual attention. Visual attention plays a vital role in the process of human survival and development. Visual attention and human perception are closely related to visual stimuli, and are being included. The study of cognitive psychology, neurobiology and computer vision. With the continuous development of cognitive psychology and neurobiology, the study of visual mechanisms found that human vision can be divided into two stages: a fast, unconscious, data driven, bottom-up. The stage and a slow, conscious, task driven, top-down stage. The concept of close connection with visual attention is visual significance. He is a key attention mechanism to guide visual attention. The purpose of the image saliency region detection study is to quickly locate the significant region and reflect the significance of the significant region. Degree. Visual saliency region detection has a wide range of applications in image processing, including image segmentation, target recognition, adaptive compression, content sensitive image editing, image retrieval, target detection, target tracking, image quality evaluation and so on. This paper, starting from the research of visual attention mechanism, discusses some key points in visual significance detection and application. Some new ideas and algorithms are proposed. The main work and contributions of this paper are as follows: (1) in view of the shortcomings of the existing local contrast and the global contrast modeling method, a significant regional detection method based on the global characteristics of conditional random fields is proposed. We use the uniqueness, the color space distribution and other global characteristics to calculate the corresponding significant graphs. Secondly, multiple significant graphs are fused under the conditional random field framework, and the significant region detection is realized through the regional annotation of the significant region and the background region. Then the Gauss model based on the saliency region is used to calculate the prior map of the target, and the whole area is calculated. The characteristic salient image of the bureau is used to carry out Gauss filtering; finally, a more accurate detection is achieved by using the salient graph following the fusion filter of the airport. The experimental results show that the method can highlight the significant region, effectively suppress the background interference, and have high detection accuracy and recall. (2) the visual machine is based on the visual machine. This method combines the local contrast based on the pixel level, the global contrast based on the regional level and the backview prior information based on the target level. This method is based on the convex packet detection technique. The underlying visual cues are used to separate the significant targets from the background. The background template is extracted based on the primary detection results and the background information is calculated using the PCA. In order to suppress the background interference, the method uses the target center prior information to refine the local contrast characteristics and the global contrast characteristics. The experiment on the open data set shows that this method is used to extract the background information. The remarkable graph obtained by the method can better highlight the significant target. It also proves that the Otsu adaptive threshold method can be used to produce high quality target segmentation results. (3) aiming at the application of visual significance in target tracking, a target tracking algorithm based on visual attention is proposed in this paper. The visual saliency detection algorithm of background prior is used to extract the significant feature of the target. Secondly, the foreground background classification method based on Bayesian decision theory is used to extract the motion features of the target, and then the target state is estimated by using the significant feature to guide the motion feature and color feature. Finally, the adaptive particle filter is combined to form the target state. The experimental results show that in the complex scene, the algorithm has strong robustness against the existing target tracking algorithm, and has good tracking effect on illumination change, attitude change, target occlusion, fast motion, complex background and so on. (4) in the course of the gun ball linkage relay tracking, the target leaves the gun frame. In this paper, the problem of initial positioning in the ball machine is presented. This paper proposes a method of tracking the joint force of the gun ball based on visual attention. This method uses the mesh and interpolation algorithm to achieve the target amplification and tracking in the ball machine. When the target leaves the gun, the candidate region is calculated by the visual significance detection algorithm, and the target template saved by the gun is used. In the candidate region, the matching area is searched, the location of the target in the ball scene is determined, and the Mean Shift tracking algorithm is used to achieve the active tracking of the ball machine. The experimental results show that the tracking of the gun ball joint relay based on visual attention has good real-time tracking effect.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41
，
本文編號(hào)：2159180
本文鏈接：http://www.lk138.cn/shoufeilunwen/xxkjbs/2159180.html
最近更新
教材專著
