圖像視頻中運動估計和分析
發(fā)布時間：2018-11-16 18:16
【摘要】：隨著多媒體技術(shù)和傳感器技術(shù)的飛速發(fā)展,圖像和視頻作為記錄視覺的載體,對人們的生活、生產(chǎn)等產(chǎn)生越來越重要的影響。近十年來,在各個方面的記錄視覺信息的需求,產(chǎn)生了爆炸式的圖像和視頻。在這些數(shù)據(jù)中,運動信息在圖像和視頻的生成和記錄過程中都扮演著重要的角色,可以說覆蓋了圖像和視頻處理的各個領(lǐng)域,而在語義上也涵蓋了從低層的運動軌跡估計到高層的運動理解。具體來說,在圖像生成過程中,相機運動會帶來圖像的模糊,而使得圖像的信息熵增大,為了能夠恢復出清楚的尖銳的圖像,我們往往需要精確估計相機的運動。在圖像的記錄過程中,有可能因為物體或人的快速運動造成了圖像內(nèi)容的運動模糊。在記錄過程中產(chǎn)生的運動模糊往往比清楚圖像提供的信息更多因為其捕捉到了動態(tài)的物體疊加。視頻通�？梢钥醋魇菆D像在時序上的疊加,類似地,在視頻產(chǎn)生過程中,相機的運動往往會導致畫面的晃動和模糊,無論在圖像質(zhì)量上和視頻可觀賞性上都有一定的影響。而在視頻內(nèi)容記錄中,運動信息往往是視頻存在的理由,分析其運動往往更關(guān)注高層的語義。本課題以運動為核心,對圖像和視頻中的運動估計和分析展開了深入研究,具體包括:圖像生成過程中相機運動的建模和表征,模糊圖像中的相機運動估計和圖像復原,視頻內(nèi)容記錄中的運動的多層次表征學習以及運動的快速分析。本論文的主要工作和創(chuàng)新點可以總結(jié)為以下幾點:1.在圖像成像過程中對相機運動的深層分析,我們提出了對運動核進行分解并獨自優(yōu)化的模型。該分解模式能夠揭示相機成像的內(nèi)在特性,從而以一種全新的角度觀測經(jīng)典的圖像去模糊問題。為了展示該表征的優(yōu)勢,我們提出了軌跡隨機擾動算法來優(yōu)化運動核。在很多例子當中,我們發(fā)現(xiàn)現(xiàn)有的去模糊算法落入局部極值的時候,我們的算法通過獨立優(yōu)化相機軌跡能夠取得較好的去模糊效果以及正確的模糊核。2.在圖像成像過程中利用高亮區(qū)域能夠較準確地刻畫相機運動這一特點,我們針對夜景這一非常具有挑戰(zhàn)性的場景結(jié)合高亮區(qū)域把該問題變得可行。我們提出了一個全新的框架有機地把從高亮區(qū)域中推斷出的運動核和非高亮區(qū)域結(jié)合求解更準確的運動核,除此之外,我們提出了一個全新的函數(shù)化運動核表征從而較準確地從高亮區(qū)域推斷運動核,我們提出了一個新的能量最小化方程能夠自動地把提取的運動核分配給不同的區(qū)域以便進行非均勻去模糊。3.在視頻內(nèi)容記錄中,我們側(cè)重分析了視頻內(nèi)容中的重要的運動信息:摔倒動作檢測,為了適應視頻流場景下實時的運動分析,即實時的摔倒檢測,我們把視頻內(nèi)容中運動信息按照"難易程度"分層,通過級聯(lián)的方式進行動作檢測,不同于傳統(tǒng)的級聯(lián)框架,該級聯(lián)框架能夠支持不同復雜度的特征。通過這種混合特征的級聯(lián)框架,我們的系統(tǒng)在精確度和效率上能夠達到較好的折中。除此之外,我們精細地設計了我們采用的特征,支持特征復用以及增量式更新從而能夠?qū)σ曨l流場景具有較好地支持。最后,在摔倒動作檢測的基礎(chǔ)之上,我們進行了拓展從而能夠支持一般種類的動作檢測以及引入了更多種類的特征從而在精確度上有一個更好的提升。本文針對圖像生成過程中和視頻內(nèi)容記錄中的運動進行了深入的分析。大量的實驗結(jié)果表明了我們對相機運動建模的有效性以及對視頻內(nèi)容中運動分層而快速檢測的高效性。
[Abstract]:With the rapid development of multimedia technology and sensor technology, image and video, as the carrier of recording vision, have become more and more important to people's life, production and so on. In the last decade, the demand for recording visual information in various aspects has resulted in an explosive image and video. In these data, motion information plays an important role in both the generation and recording of images and videos, and can be said to cover various fields of image and video processing, and in the semanteme it also covers the motion understanding from the low-level motion track to the high-level motion. In particular, in the image generation process, the camera motion causes the blurring of the image, and the information entropy of the image is increased, and in order to be able to recover a clear sharp image, it is often necessary to accurately estimate the motion of the camera. during the recording of the image it is possible that the motion blur of the image content is caused by the rapid movement of the object or person. The motion blur generated in the recording process tends to be more information than the information provided by the clear image because it captures the dynamic object superposition. The video is generally considered to be a superposition of the images in time series, similarly, during the production of the video, the motion of the camera often results in the shaking and blurring of the picture, whether in the image quality and in the video. In the video content record, the motion information is often the reason of the existence of the video, and the analysis of its motion tends to pay more attention to the semantics of the higher layer. This paper studies the motion estimation and analysis of the image and video with the motion as the core, including: the modeling and characterization of the camera motion in the process of image generation, the motion estimation of the camera in the blurred image, and the image restoration. The multi-level representation of the motion in the video content record and the rapid analysis of the motion. The main work and innovation points of this paper can be summarized as follows: 1. In the process of image imaging, the deep analysis of the motion of the camera is carried out, and the model of the motion kernel is decomposed and optimized by itself. The decomposition model can reveal the intrinsic characteristics of the camera imaging, so as to observe the classical image de-blurring problem with a brand-new angle. In order to demonstrate the advantages of the characterization, we propose a trajectory random perturbation algorithm to optimize the motion kernel. In many examples, when we find that the existing deblurring algorithm falls into the local extreme value, our algorithm can obtain better de-blurring effect and correct blur kernel by independently optimizing the camera track. This feature of the camera motion can be more accurately described by using the high-bright area in the image-forming process, and it becomes feasible to combine the problem with the high-bright area for the very challenging scene of the night scene. In addition, we put forward a new frame that organically combines the motion kernel and the non-high bright region inferred from the high bright region to find a more accurate motion kernel. In addition, we propose a new functional motion kernel representation to accurately infer the motion kernel from the high bright region, We propose a new energy minimization equation that can automatically assign the extracted motion kernel to different areas for non-uniform deblurring. In the video content record, we focus on the analysis of the important motion information in the video content: the fall motion detection, in order to adapt to the real-time motion analysis in the video stream scene, that is, the real-time fall detection, we divide the motion information in the video content according to the "degree of difficulty", The action detection is carried out in a cascade manner, which is different from the traditional cascade framework, which can support the characteristics of different complexity. Through the cascading frame of this kind of mixing characteristic, our system can achieve a good compromise on the accuracy and efficiency. In addition, we designed the features we adopted, support the feature multiplexing and incremental updating, so that the video stream scene can be well supported. Finally, on the basis of the detection of the fall motion, we have developed so as to be able to support the general kinds of motion detection and to introduce more kinds of features so as to have a better improvement in the accuracy. This paper makes an in-depth analysis of the motion in the process of image generation and in the video content record. A large number of experiments show the effectiveness of the motion modeling of the camera and the high efficiency of rapid detection of motion layering in the video content.
【學位授予單位】：中國科學技術(shù)大學
【學位級別】：博士
【學位授予年份】：2017
【分類號】：TP391.41
[Abstract]:With the rapid development of multimedia technology and sensor technology, image and video, as the carrier of recording vision, have become more and more important to people's life, production and so on. In the last decade, the demand for recording visual information in various aspects has resulted in an explosive image and video. In these data, motion information plays an important role in both the generation and recording of images and videos, and can be said to cover various fields of image and video processing, and in the semanteme it also covers the motion understanding from the low-level motion track to the high-level motion. In particular, in the image generation process, the camera motion causes the blurring of the image, and the information entropy of the image is increased, and in order to be able to recover a clear sharp image, it is often necessary to accurately estimate the motion of the camera. during the recording of the image it is possible that the motion blur of the image content is caused by the rapid movement of the object or person. The motion blur generated in the recording process tends to be more information than the information provided by the clear image because it captures the dynamic object superposition. The video is generally considered to be a superposition of the images in time series, similarly, during the production of the video, the motion of the camera often results in the shaking and blurring of the picture, whether in the image quality and in the video. In the video content record, the motion information is often the reason of the existence of the video, and the analysis of its motion tends to pay more attention to the semantics of the higher layer. This paper studies the motion estimation and analysis of the image and video with the motion as the core, including: the modeling and characterization of the camera motion in the process of image generation, the motion estimation of the camera in the blurred image, and the image restoration. The multi-level representation of the motion in the video content record and the rapid analysis of the motion. The main work and innovation points of this paper can be summarized as follows: 1. In the process of image imaging, the deep analysis of the motion of the camera is carried out, and the model of the motion kernel is decomposed and optimized by itself. The decomposition model can reveal the intrinsic characteristics of the camera imaging, so as to observe the classical image de-blurring problem with a brand-new angle. In order to demonstrate the advantages of the characterization, we propose a trajectory random perturbation algorithm to optimize the motion kernel. In many examples, when we find that the existing deblurring algorithm falls into the local extreme value, our algorithm can obtain better de-blurring effect and correct blur kernel by independently optimizing the camera track. This feature of the camera motion can be more accurately described by using the high-bright area in the image-forming process, and it becomes feasible to combine the problem with the high-bright area for the very challenging scene of the night scene. In addition, we put forward a new frame that organically combines the motion kernel and the non-high bright region inferred from the high bright region to find a more accurate motion kernel. In addition, we propose a new functional motion kernel representation to accurately infer the motion kernel from the high bright region, We propose a new energy minimization equation that can automatically assign the extracted motion kernel to different areas for non-uniform deblurring. In the video content record, we focus on the analysis of the important motion information in the video content: the fall motion detection, in order to adapt to the real-time motion analysis in the video stream scene, that is, the real-time fall detection, we divide the motion information in the video content according to the "degree of difficulty", The action detection is carried out in a cascade manner, which is different from the traditional cascade framework, which can support the characteristics of different complexity. Through the cascading frame of this kind of mixing characteristic, our system can achieve a good compromise on the accuracy and efficiency. In addition, we designed the features we adopted, support the feature multiplexing and incremental updating, so that the video stream scene can be well supported. Finally, on the basis of the detection of the fall motion, we have developed so as to be able to support the general kinds of motion detection and to introduce more kinds of features so as to have a better improvement in the accuracy. This paper makes an in-depth analysis of the motion in the process of image generation and in the video content record. A large number of experiments show the effectiveness of the motion modeling of the camera and the high efficiency of rapid detection of motion layering in the video content.
【學位授予單位】：中國科學技術(shù)大學
【學位級別】：博士
【學位授予年份】：2017
【分類號】：TP391.41
【相似文獻】
相關(guān)期刊論文 前10條
1 孫英皓;唐棣;;一種有效的交互式圖像局部內(nèi)容放大方法[J];計算機工程與應用;2012年12期
2 李瑞帥;余淑華;潘凱;王圓;;圖像特征金字塔快速計算方法[J];電子世界;2014年07期
3 曾喜良;王金娟;;指紋分割的塊圖像梯度因子聚類法[J];計算機與數(shù)字工程;2008年07期
4 劉陳;王欣欣;李鳳霞;趙相坤;;一種快速保邊的圖像對象分割方法[J];北京理工大學學報;2010年02期
5 朱薇;劉利剛;;圖像適應算法中非冗余顯著圖的計算[J];中國圖象圖形學報;2011年08期
6 柳有權(quán);吳宗勝;韓紅雷;吳恩華;;線條增強的建筑物圖像抽象畫生成[J];計算機輔助設計與圖形學學報;2013年09期
7 吳駿,唐紅梅,肖志濤,賈志成;一種基于相位信息的圖像對稱性檢測方法[J];信號處理;2004年01期
8 邵靜;高雋;趙瑩;張旭東;;一種基于圖像固有維度的感知物體檢測方法[J];儀器儀表學報;2008年04期
9 潘如如;高衛(wèi)東;;高緊度機織物圖像傾斜的自動糾正[J];紡織學報;2009年10期
10 劉貴喜,趙曙光,楊萬海;基于梯度塔形分解的多傳感器圖像融合[J];光電子·激光;2001年03期
相關(guān)會議論文 前5條
1 張一鳴;劉亞t，
本文編號：2336262
本文鏈接：http://sikaile.net/shoufeilunwen/xxkjbs/2336262.html
最近更新
教材專著
