發(fā)布時間：2018-06-23 01:39

  本文選題：圖像拼接 + 統(tǒng)一計算設備架構��； 參考：《長春理工大學》2016年博士論文

【摘要】：無論是民用領域的礦產(chǎn)資源勘查、土地規(guī)劃利用、環(huán)境監(jiān)測、海洋開發(fā)、氣象預報及地理信息服務還是軍事領域偵察監(jiān)視、精確制導、超視距攻防對抗等都需要有足夠?qū)挼囊晥龊妥銐蚋叩姆直媛室酝瓿蓪δ繕说膹V域范圍監(jiān)測、搜索和跟蹤。對基于寬視場高分辨成像系統(tǒng)海量圖像數(shù)據(jù)的處理、分析和利用是該類系統(tǒng)建構的核心價值所在。其中,高分辨率傳感器拼接成像過程中將涉及到對海量數(shù)據(jù)的實時處理,計算過程有著極高的復雜度,因此,圖像拼接算法的準確性和實時性將成為影響系統(tǒng)性能的主要因素之一。此外,對于寬視場高分辨場景下動態(tài)目標的跟蹤技術也成為后期圖像分析的研究熱點。同時,由于這類系統(tǒng)應用的環(huán)境自身的復雜性(背景變化、光照變化、陰影變化等)和動態(tài)目標固有的一些特性(非剛體、姿態(tài)多變等),使得可實用的目標跟蹤技術仍然非常具有挑戰(zhàn)性。針對以上需求,本文圍繞寬視場成像系統(tǒng)的圖像拼接和目標跟蹤問題開展研究,主要研究工作如下:本文采用了一種將先驗信息和統(tǒng)一計算設備架構(CUDA)相結合的自適應并行加速算法用于提高大視場全景拼接成像的實時性。在圖像拼接之前,先利用高精度標定平臺對各成像單元的重疊區(qū)域進行預標定。標定之后,利用基于CUDA的快速魯棒特征檢測方法提取參考圖像與待配準圖像的候選特征點集,再利用基于隨機KD-Tree索引的近似最近鄰搜索算法選取參考圖像與待配準圖像的初始匹配點對,本文還采用了基本線性代數(shù)運算子程序用于加速算法搜索速度。對于參考圖像與待配準圖像誤匹配點對的刪除和空間變換矩陣的參數(shù)估計,本文采用的是一種在傳統(tǒng)的漸近式抽樣一致性算法基礎上改進的基于CUDA的并行算法。實驗結果表明本文采用的算法極大地提高了圖像拼接速度,可以滿足圖像拼接實時性的工程應用要求。為了對場景中動態(tài)飛行目標進行識別,提出一種基于混沌雙種群進化策略的圖像分割方法。利用進化策略能從選定的初始解出發(fā),通過逐代迭代進化逐步改進當前解,直至最后收斂于最優(yōu)解或滿意解的特點和優(yōu)勢,將其用于圖像分割閾值最優(yōu)解的求解上。為了克服傳統(tǒng)基于閾值的圖像分割方法的缺點,例如較高的復雜度和早熟問題,本文提出了一個高效的基于進化策略的圖像分割算法,它通過使用多種群進化策略來計算閾值。在進化過程中同時存在局部種群和全局種群兩個群體,進而確保算法的全局和局部搜索能力。該算法的每一步迭代過程中,首先,基于混沌理論生成若干個初始個體,并將這些個體分別加入局部種群和全局種群,計算這些個體的適應度函數(shù)值。然后,將選擇、重組、變異等進化操作算子作用于局部種群和全局種群,進行迭代進化,進化后的個體集合中選擇最好的若干個體放入局部種群,其余放入全局種群,直至收斂。最后,種群中的最優(yōu)個體即為所求的解。實驗結果表明,本文提出的方法比傳統(tǒng)的遺傳算法有著更快的收斂速度。種群多樣性信息能有效指導進化策略的進化過程,因此本文又提出了改進的混沌雙種群進化策略算法,采用了多動機強化學習算法設定初始種群和本地種群數(shù)值,動態(tài)學習種群比例,以使進化策略的局部搜索能力和全局搜索能力進一步均衡化。動機層的引入為先驗知識和領域知識的引入提供了條件,由此可以加速強化學習的學習進程。本文根據(jù)圖像分割問題實際,定義了動機集合,采用了MMQ投票(MMQ-voting)方法用于指導智能體動作的選擇策略。經(jīng)過實驗驗證,本文采用的多動機強化學習方法能使強化學習以較快的速度收斂于最優(yōu)動作策略,從而使種群個體多樣性保持在一個合適的狀態(tài),有助于進一步提高圖像最優(yōu)分割閾值的搜索效率。為了對場景中動態(tài)飛行目標進行跟蹤,提出一種基于強化學習的動態(tài)目標跟蹤方法,將目標跟蹤問題建模成強化學習問題,并提出了一個兩階段強化學習算法用于圖像中的目標跟蹤。我們設置了多個追蹤智能體來跟蹤圖像中的目標,在算法的每一步中,首先對每個追蹤智能體進行動態(tài)子任務分配,即先是給每個追蹤智能體動態(tài)分配一個子目標,之后每個追蹤智能體根據(jù)其當前的子目標選擇其行動。學習算法將學習過程劃分為兩個部分,一個是學習任務分配的策略,另一個是學習動作選擇的策略,每個追蹤智能體通過共享Q函數(shù)來共享所學知識、提高學習效率。實驗結果驗證了該方法的有效性。
[Abstract]:Whether it is the mineral exploration in the civil field, land planning and utilization, environmental monitoring, marine development, weather forecast and geographic information service or military field surveillance and surveillance, precision guidance, and over the horizon attack and defense confrontation need to have wide field of view and high enough resolution to complete the wide range monitoring, search and tracking of the target. The analysis and utilization of massive image data based on wide field of view high-resolution imaging system is the core value of this kind of system construction. Among them, high resolution sensor splicing will involve real-time processing of mass data and high complexity in the calculation process. Therefore, the accuracy and reality of the image mosaic algorithm will be true. Time character will be one of the main factors that affect the performance of the system. In addition, the tracking technology for dynamic targets in the wide field of view high resolution scene has also become a hot topic in the later image analysis. At the same time, due to the complexity of the environment itself (background change, illumination change, shadow change, etc.) and some inherent characteristics of the dynamic target, the application of this kind of system The practical target tracking technology is still very challenging. Aiming at the above requirements, this paper focuses on the problem of image mosaic and target tracking in the wide field of view imaging system. The main research work is as follows: a combination of prior information and unified computing device architecture (CUDA) is used in this paper. The adaptive parallel acceleration algorithm is used to improve the real-time performance of the panoramic mosaic imaging in large field. Before the image splicing, the high precision calibration platform is used to pre calibrate the overlapped regions of the imaging units. After calibration, the CUDA based fast robust feature detection method is used to extract the candidate feature points of the reference image and the image to be registered. Set, and then use the approximate nearest neighbor search algorithm based on random KD-Tree index to select the initial matching points of the reference image and the image to be registered. This paper also uses the basic linear algebra operation subroutine to speed up the search speed. It is estimated that this paper uses an improved CUDA based parallel algorithm based on the traditional asymptotic sampling consistency algorithm. The experimental results show that the algorithm used in this paper can greatly improve the speed of image stitching, and can meet the engineering application requirements of the real-time image splicing. An image segmentation method based on chaotic dual population evolution strategy is proposed. Using the evolutionary strategy, it can gradually improve the current solution by iterative evolution from the selected initial solution, and finally converge to the characteristics and advantages of the optimal solution or satisfactory solution, and apply it to the solution of the threshold optimal solution of the image segmentation. The shortcoming of threshold image segmentation methods, such as high complexity and precocious problem, presents an efficient image segmentation algorithm based on evolutionary strategy. It uses a variety of cluster evolution strategies to calculate threshold. In the process of evolution, there are two groups of local population and whole local population, which can ensure the overall situation of the algorithm. In each iteration of the algorithm, first of all, a number of initial individuals are generated based on the chaos theory, and these individuals are added to the local population and the global population to calculate the fitness function values of these individuals. Then, the evolutionary operators such as selection, reorganization and mutation are used to act on the local population and the global population. The optimal individual is placed in the local population and the rest is placed in the global population to converge. Finally, the optimal individual in the population is the solution. The experimental results show that the proposed method has a faster convergence rate than the traditional genetic algorithm. The population diversity information can be effective. In order to guide the evolutionary process of evolutionary strategy, this paper also proposes an improved chaotic dual population evolution strategy algorithm, which uses a multi motivation reinforcement learning algorithm to set the initial population and local population values and dynamically learn the population proportion, so that the local search ability and the overall search ability of the evolutionary strategy are further balanced. The introduction of motivation layer is introduced. It provides the conditions for the introduction of prior knowledge and domain knowledge, which can accelerate the learning process of intensive learning. Based on the reality of the image segmentation, this paper defines the set of motivation and uses the MMQ voting (MMQ-voting) method to guide the selection strategy of the action of the agent. The method can make the reinforcement learning converge to the optimal action strategy at a faster speed, so that the individual diversity of the population is kept in a suitable state and helps to further improve the search efficiency of the optimal segmentation threshold of the image. In order to track the dynamic flight targets in the scene, a dynamic target tracking method based on reinforcement learning is proposed. The target tracking problem is modeled as a reinforcement learning problem, and a two stage reinforcement learning algorithm is proposed for target tracking in the image. We set up multiple tracking agents to track the target in the image. In each step of the algorithm, we first assign each tracking agent into the action state sub task, that is, each tracking intelligence first is given to each tracking intelligence. The learning algorithm divides the learning process into two parts, one is the strategy of learning task allocation and the other is the strategy of learning action selection. Each tracking intelligent body shares the learned knowledge by sharing the Q function, and improves the learning process. Learning efficiency. Experimental results verify the effectiveness of the method.
【學位授予單位】：長春理工大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41

【相似文獻】

相關期刊論文 前10條

1 唐偉力;龍建忠;;一種基于降雨模型的圖像分割方法在礫巖圖像分割中的應用[J];成都信息工程學院學報;2007年02期

2 黃曉莉;曾黃麟;王秀碧;劉永春;;基于脈沖耦合神經(jīng)網(wǎng)絡的圖像分割[J];信息技術;2008年09期

3 肖飛;綦星光;;圖像分割方法綜述[J];可編程控制器與工廠自動化;2009年11期

4 汪一休;;一種交互式圖像分割的修正優(yōu)化方法[J];中國科學技術大學學報;2010年02期

5 李丹;;圖像分割方法及其應用研究[J];科技信息;2010年36期

6 龔永義;黃輝;于繼明;關履泰;;基于熵的兩區(qū)域圖像分割[J];中國圖象圖形學報;2011年05期

7 張甫;李興來;陳佳君;;淺談圖像分割方法的研究運用[J];科技創(chuàng)新與應用;2012年04期

8 汪梅;何高明;賀杰;;常見圖像分割的技術分析與比較[J];計算機光盤軟件與應用;2013年06期

9 魏慶;盧照敢;邵超;;基于復雜性指數(shù)的圖像分割必要性判別技術[J];計算機工程與應用;2013年16期

10 陳曉丹;李思明;;圖像分割研究進展[J];現(xiàn)代計算機(專業(yè)版);2013年33期

相關會議論文 前10條

1 楊魁;趙志剛;;圖像分割技術綜述[A];2008年中國高校通信類院系學術研討會論文集（下冊）[C];2009年

2 楊暄;郭成安;李建華;;改進的脈沖耦合神經(jīng)網(wǎng)絡及其在圖像分割中的應用[A];第十屆全國信號處理學術年會（CCSP-2001）論文集[C];2001年

3 楊生友;;圖像分割在醫(yī)學圖像中應用現(xiàn)狀綜述[A];2009中華醫(yī)學會影像技術分會第十七次全國學術大會論文集[C];2009年

4 閆平昆;;基于模型的圖像分割技術及其醫(yī)學應用[A];第十五屆全國圖象圖形學學術會議論文集[C];2010年

5 高嵐;胡友為;潘峰;盧凌;;基于小生境遺傳算法的SAR圖像分割[A];可持續(xù)發(fā)展的中國交通——2005全國博士生學術論壇（交通運輸工程學科）論文集（下冊）[C];2005年

6 孫莉;張艷寧;胡伏原;趙榮椿;;基于Gaussian-Hermite矩的SAR圖像分割[A];第十三屆全國圖象圖形學學術會議論文集[C];2006年

7 李盛;;基于協(xié)同聚類的圖像分割[A];第十四屆全國圖象圖形學學術會議論文集[C];2008年

8 張利;許家佗;;舌象圖像分割技術的研究與應用進展[A];中華中醫(yī)藥學會中醫(yī)診斷學分會第十次學術研討會論文集[C];2009年

9 秦昆;李振宇;李輝;李德毅;;基于云模型和格網(wǎng)劃分的圖像分割方法[A];《測繪通報》測繪科學前沿技術論壇摘要集[C];2008年

10 高惠琳;竇麗華;陳文頡;謝剛;;圖像分割技術在醫(yī)學CT中的應用[A];中國自動化學會控制理論專業(yè)委員會A卷[C];2011年

相關博士學位論文 前10條

1 白雪飛;基于視覺顯著性的圖像分割方法研究[D];山西大學;2014年

2 黃萬里;基于高分衛(wèi)星數(shù)據(jù)多尺度圖像分割方法的天山森林小班邊界提取研究[D];福建師范大學;2015年

3 王輝;圖像分割的最優(yōu)化和水平集方法研究[D];電子科技大學;2014年

4 高婧婧;腦部MR圖像分割理論研究[D];電子科技大學;2014年

5 潘改;偏微分方程在圖像分割中的應用研究[D];東北大學;2013年

6 馮籍瀾;高分辨率SAR圖像分割與分類方法研究[D];電子科技大學;2015年

7 李偉斌;圖像分割中的變分模型與快速算法研究[D];國防科學技術大學;2014年

8 鄧曉政;基于免疫克隆選擇優(yōu)化和譜聚類的復雜圖像分割[D];西安電子科技大學;2014年

9 帥永e，

本文編號：2055155