本文選題：顯著性物體檢測 + 顯著性偏置��； 參考：《中國科學(xué)技術(shù)大學(xué)》2016年博士論文

【摘要】：近年來,圖像的數(shù)量隨著移動互聯(lián)網(wǎng)的發(fā)展呈現(xiàn)爆發(fā)式的增長。為了從海量圖像數(shù)據(jù)中尋找自己所需的信息,人們迫切需要快速、準(zhǔn)確的圖像處理技術(shù)。人類視覺系統(tǒng)為了解決大腦處理能力有限的問題,在接收場景信息時會選擇重要的視覺信息進(jìn)行優(yōu)先處理。這種選擇性注意機(jī)制使人類能夠快速適應(yīng)外界的變化。受此機(jī)制的啟發(fā),研究人員提出了視覺顯著性檢測方法來模擬人類的視覺注意機(jī)制。顯著性檢測算法能夠定位圖像中吸引人注意力的區(qū)域,非常適合用于排除圖像中無關(guān)內(nèi)容的干擾,從而大大加快傳統(tǒng)圖像處理的速度。顯著性檢測目前已經(jīng)成為計(jì)算機(jī)視覺的熱門研究方向,并廣泛應(yīng)用在多個計(jì)算機(jī)視覺領(lǐng)域中,如目標(biāo)分割、物體識別和目標(biāo)跟蹤等。人類視覺系統(tǒng)在觀察環(huán)境時可以分為快速的、與任務(wù)無關(guān)的自底向上的方式和慢速的、由任務(wù)驅(qū)動的自頂向下的方式。由于自底向上的方式不需要高層知識的引導(dǎo),因此大多數(shù)研究關(guān)注自底向上的顯著性檢測。本文主要針對自底向上的顯著性物體檢測展開研究,通過分析已有的顯著性算法的缺點(diǎn),并結(jié)合顯著性的生物學(xué)原理,提出了兩種新穎的顯著性物體檢測算法,并成功應(yīng)用在目標(biāo)分割等計(jì)算機(jī)視覺應(yīng)用中。本文的主要研究工作和貢獻(xiàn)可概括如下：1)基于人類視覺系統(tǒng)的顯著性物體選擇機(jī)制,提出了基于顯著性偏置的顯著性物體檢測算法,將區(qū)域顯著性計(jì)算和物體性計(jì)算明確區(qū)分開。該方法首先計(jì)算每個區(qū)域?qū)儆谖矬w的概率(即物體性)來定位圖像中所有可能的物體區(qū)域,然后基于對比度計(jì)算每個區(qū)域的顯著性,最后通過非線性融合的方式實(shí)現(xiàn)區(qū)域顯著性對物體性的偏置,得到顯著性物體區(qū)域。為了解決同類區(qū)域顯著值不一致的問題,提出了基于顯著性擴(kuò)散的優(yōu)化方法,從初始顯著圖中選擇種子點(diǎn),并利用區(qū)域特征學(xué)習(xí)區(qū)域間相似度,然后根據(jù)其他區(qū)域與種子點(diǎn)的相似性關(guān)系優(yōu)化每個區(qū)域的顯著值,得到更加一致的顯著性檢測結(jié)果。實(shí)驗(yàn)結(jié)果驗(yàn)證了所提算法的有效性。2)基于區(qū)域顯著性產(chǎn)生的生物學(xué)原理,提出了背景驅(qū)動的顯著性檢測算法。通過分析已有的基于局部或全局對比度的顯著性檢測方法的局限性,發(fā)現(xiàn)背景在對比度計(jì)算中的重要作用,并從背景圖中分割出背景區(qū)域作為對比度計(jì)算參考區(qū)域。背景圖可以利用任何背景先驗(yàn)得到,我們特別提出了基于卷積神經(jīng)網(wǎng)絡(luò)的背景學(xué)習(xí)模型來預(yù)測每個區(qū)域?qū)儆诒尘暗母怕省Ｓ?jì)算區(qū)域?qū)Ρ榷葧r采用顏色和紋理特征,并且根據(jù)特征的分布情況動態(tài)確定兩者的權(quán)重。為了提高顯著性物體的完整性,提出了基于增強(qiáng)圖模型的優(yōu)化方法,在傳統(tǒng)的k-正則圖中嵌入背景先驗(yàn),并添加特征空間中的非局部連接,然后利用節(jié)點(diǎn)間相似度在圖上傳播并優(yōu)化顯著值。在多個典型數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果證明了所提算法的有效性。3)為了驗(yàn)證顯著性物體檢測的應(yīng)用價值,將所提出的檢測算法應(yīng)用于目標(biāo)分割和物體分類中。在目標(biāo)分割中,探討了顯著圖的自適應(yīng)分割、基于GrabCut的分割和基于用戶交互的分割方法,對比實(shí)驗(yàn)結(jié)果表明顯著性檢測可以促進(jìn)目標(biāo)分割的效果。在物體分類中,為了排除背景區(qū)域特征的干擾,在顯著圖分割出的前景區(qū)域中提取特征并進(jìn)行分類。通過比較不同顯著性檢測算法對分類性能的影響,表明顯著性檢測可以增強(qiáng)物體分類的性能,并且檢測效果越好,分類性能也越強(qiáng)�？偨Y(jié)起來,本文針對顯著性物體檢測方法進(jìn)行了深入研究,以顯著性產(chǎn)生的相關(guān)生物學(xué)原理為指導(dǎo),提出了兩種顯著性物體檢測方法,即基于顯著性偏置和擴(kuò)散的方法和背景驅(qū)動的方法,在提高檢測物體的顯著性和完整性方面取得了領(lǐng)先的效果。在顯著性檢測應(yīng)用中,探討了顯著性物體檢測在目標(biāo)分割和物體分類中的應(yīng)用,展示了其應(yīng)用價值。
[Abstract]:In recent years, the number of images has been increasing with the development of mobile Internet. In order to find out the information needed from the massive image data, people urgently need fast and accurate image processing technology. In order to solve the problem of limited brain processing ability, human visual system will choose important information in receiving scene information. Based on this mechanism, the researchers have proposed a visual significance detection method to simulate human visual attention mechanism. In addition to the interference of unrelated content in the image, the speed of traditional image processing is greatly accelerated. Significant detection has become a hot research direction in computer vision and is widely used in the field of multiple computer vision, such as target segmentation, object recognition and target tracking. Fast, bottom-up and slow, task driven, top-down, task driven, top-down way. Most studies focus on bottom-up saliency detection because of the bottom-up approach. Therefore, this paper focuses on bottom-up significant object detection. With the shortcomings of some significant algorithms, and combining with the biological principles of significance, two novel detection algorithms for significant objects are proposed and applied to computer vision applications such as target segmentation. The main research work and contributions of this paper are summarized as follows: 1) the significant object selection mechanism based on human visual system is proposed. A significant object detection algorithm based on significant bias, which separates the regional saliency calculation from the object calculation. This method first calculates the probability of each area belonging to the object (i.e. the object) to locate all the possible object regions in the image, then calculates the saliency of each region based on the contrast, and finally passes the nonlinearity. In order to solve the problem of congenialization, an optimization method based on significant diffusion is proposed to select the seed points from the initial significant map, and to learn the similarity between the regions and then according to the other regions and species. The similarity relation of the subpoints optimizes the significant values of each region and obtains a more consistent significance detection result. The experimental results verify the validity of the proposed algorithm.2) based on the biological principle generated by the regional significance, the background driven significance detection algorithm is proposed. The limitations of the method of sex detection, find the important role of the background in the contrast calculation, and divide the background area into the contrast calculation reference area from the background map. The background map can be obtained by any background prior. We specially propose a backview learning model based on the convolution neural network to predict the background of each region. In order to improve the integrity of the significant objects, an optimization method based on the enhancement graph model is proposed to embed the background pre test in the traditional k- regular graph and add the non local connection in the feature space. The experimental results on multiple typical datasets prove the validity of the proposed algorithm.3). In order to verify the application value of the significant object detection, the proposed detection algorithm is applied to the target segmentation and object classification. The segmentation, GrabCut based segmentation and the user interaction based segmentation method, the experimental results show that significant detection can promote the effect of target segmentation. In object classification, in order to eliminate the interference of the background region features, the features are extracted and classified in the foreground region divided by the significant graph. By comparing the different saliency of the object classification. The effect of detection algorithm on classification performance shows that significant detection can enhance the performance of object classification, and the better the detection effect, the better the classification performance. In this paper, this paper has carried out a thorough study on the detection methods of significant objects, guided by the principle of significant related biological science, and proposed two kinds of significant physical examination. The method, which is based on the method of significant bias and diffusion and the method of background driven, has achieved the leading effect in improving the significance and integrity of the object detection. In the application of significant detection, the application of significant object detection in target segmentation and object classification is discussed, and its application value is demonstrated.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 呂建勇;唐振民;;一種基于圖的流形排序的顯著性目標(biāo)檢測改進(jìn)方法[J];電子與信息學(xué)報(bào);2015年11期

2 蔣寓文;譚樂怡;王守覺;;選擇性背景優(yōu)先的顯著性檢測模型[J];電子與信息學(xué)報(bào);2015年01期

3 錢生;陳宗海;林名強(qiáng);張陳斌;;基于條件隨機(jī)場和圖像分割的顯著性檢測[J];自動化學(xué)報(bào);2015年04期

4 徐丹;唐振民;徐威;;融合顏色屬性和空間信息的顯著性物體檢測[J];中國圖象圖形學(xué)報(bào);2014年04期

5 張巧榮;景麗;肖會敏;劉海波;;利用視覺顯著性的圖像分割方法[J];中國圖象圖形學(xué)報(bào);2011年05期

，

本文編號：1918022