本文關(guān)鍵詞：基于RGA的快速光學(xué)遙感圖像艦船目標(biāo)檢測(cè)算法研究　出處：《西南交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 姿態(tài)回歸 位置關(guān)系 輪廓完整性 先驗(yàn)信息 感興趣區(qū)域

【摘要】：遙感技術(shù)具有偵查范圍廣,全天候,不受地理限制等優(yōu)點(diǎn),應(yīng)用前景廣闊。基于遙感圖像的目標(biāo)檢測(cè)作為遙感圖像應(yīng)用中重要的一環(huán),其對(duì)于資源調(diào)查、災(zāi)害檢測(cè)以及軍用偵查都具有重要的研究意義。由于遙感圖像的復(fù)雜多樣性,目標(biāo)檢測(cè)需要解決顏色紋理、旋轉(zhuǎn)尺度變化、形似干擾物等一系列難點(diǎn)問(wèn)題;同時(shí)隨著遙感技術(shù)的發(fā)展,遙感信息數(shù)據(jù)的快速增長(zhǎng),依靠人工判別不能滿足實(shí)時(shí)性的要求,這些都對(duì)遙感圖像目標(biāo)的檢測(cè)提出了新的挑戰(zhàn)。復(fù)雜背景下兼顧目標(biāo)檢測(cè)的精度和速度對(duì)于實(shí)時(shí)性應(yīng)用具有非常重要的意義和價(jià)值。本文以光學(xué)遙感圖像艦船目標(biāo)為研究對(duì)象,圍繞復(fù)雜背景下的目標(biāo)檢測(cè)算法的精度和效率進(jìn)行研究。針對(duì)復(fù)雜背景下目標(biāo)輪廓附近的噪聲干擾、形似干擾物及目標(biāo)部分遮擋等影響的問(wèn)題,本文在RGA姿態(tài)一致性算法的基礎(chǔ)上,設(shè)計(jì)了一種基于姿態(tài)回歸的艦船檢測(cè)方法。方法主要包括三個(gè)部分:(1)根據(jù)艦船模板輪廓點(diǎn)之間的位置關(guān)系和RGA分布,得到每個(gè)輪廓點(diǎn)及其鄰域同姿態(tài)點(diǎn),對(duì)被檢目標(biāo)輪廓點(diǎn)姿態(tài)估計(jì)時(shí),將其與模板輪廓點(diǎn)及近鄰?fù)藨B(tài)點(diǎn)校驗(yàn),抑制噪聲點(diǎn)對(duì)目標(biāo)中心的投票;(2)采用艦船局部連接結(jié)構(gòu)加權(quán)的方法,提升具有艦船目標(biāo)特征的整體投票比重,以增加V型設(shè)施、矩形等形似干擾物和目標(biāo)之間的區(qū)分度;(3)在現(xiàn)有方法的基礎(chǔ)上重新定義了輪廓命中率和最大非連續(xù)因子,對(duì)檢測(cè)目標(biāo)采用艦船模板輪廓命中率和最大連續(xù)丟失率進(jìn)行修正,并對(duì)最后檢測(cè)結(jié)果與回歸的模板輪廓完整性進(jìn)行綜合判別,去除虛警。實(shí)驗(yàn)證明,本章的方法對(duì)目標(biāo)輪廓附近的噪聲具有良好的適應(yīng)性,并且可以較好區(qū)分形似干擾物。在復(fù)雜背景下較目前最好的方法檢測(cè)準(zhǔn)確率提高了 8%左右。針對(duì)姿態(tài)回歸艦船檢測(cè)算法的時(shí)間復(fù)雜度過(guò)高問(wèn)題,本文設(shè)計(jì)了一種基于顯著性的快速艦船目標(biāo)檢測(cè)算法。首先,選用以超像素作為基本計(jì)算單位的對(duì)比度顯著性檢測(cè)方法,通過(guò)結(jié)合各超像素的顏色和空間距離差異得到對(duì)比度先驗(yàn)圖,突出目標(biāo)區(qū)域和背景區(qū)域的差異;其次,為了得到更準(zhǔn)確的目標(biāo)中心位置,使用超像素之間的差異值作為局部特征構(gòu)建凸包確定目標(biāo)的大致位置,對(duì)不同位置的超像素使用高斯模型賦予不同權(quán)重,得到中心先驗(yàn)圖;同時(shí)為進(jìn)一步抑制邊界背景,在對(duì)比度先驗(yàn)圖和中心先驗(yàn)圖的基礎(chǔ)上融合了邊界背景先驗(yàn)圖,通過(guò)三種先驗(yàn)信息融合的顯著性檢測(cè)方法快速精準(zhǔn)的提取目標(biāo)感興趣區(qū)域,最后采用姿態(tài)回歸的方法在感興趣區(qū)域進(jìn)行艦船目標(biāo)檢測(cè)。實(shí)驗(yàn)證明,復(fù)雜背景下本文算法有效快速去除背景區(qū)域的同時(shí),檢測(cè)準(zhǔn)確率也得到一定提升。相比于RGA方法和姿態(tài)回歸方法,該算法檢測(cè)準(zhǔn)確率分別提高了 12.9%和4.8%,檢測(cè)時(shí)間降低了72%和78%。
[Abstract]:Remote sensing technology has the advantages of wide range of detection, all-weather, no geographical restrictions, and so on. As an important part of remote sensing image application, target detection based on remote sensing image is an important part of resource investigation. Disaster detection and military investigation are of great significance. Because of the complexity and diversity of remote sensing images, target detection needs to solve a series of difficult problems, such as color texture, rotation scale change, shape like interference object, etc. At the same time, with the development of remote sensing technology, the rapid growth of remote sensing information data, relying on manual discrimination can not meet the requirements of real-time. All of these put forward new challenges to target detection in remote sensing image. It is very important and valuable for real-time application to take into account the accuracy and speed of target detection in complex background. In this paper, the object of ship in optical remote sensing image is considered. Marked as the object of study. Focusing on the accuracy and efficiency of the target detection algorithm in complex background, aiming at the noise interference near the target contour, the shape of the jamming object and the partial occlusion of the target in the complex background, and so on. This paper is based on the RGA attitude consistency algorithm. A ship detection method based on attitude regression is designed. The method includes three parts: 1) according to the position relation and RGA distribution of ship template contour points. Each contour point and its neighborhood same attitude point are obtained. When the contour point attitude is estimated, it is checked with the template contour point and the nearest neighbor pose point to suppress the noise point voting on the target center. (2) the weighted method of local connection structure is used to increase the proportion of the whole voting with the characteristics of the ship's target, so as to increase the distinction between the V-shaped facilities, the rectangle and the object. 3) based on the existing methods, the contour hit ratio and maximum discontinuity factor are redefined, and the ship template contour hit ratio and the maximum continuous loss rate are corrected. Finally, the integrity of the final detection results and the regression template contour is comprehensively identified to remove false alarm. Experiments show that the method proposed in this chapter has a good adaptability to the noise near the target contour. Compared with the best method in complex background, the detection accuracy is improved by about 8%. Aiming at the problem of high time complexity of attitude regression ship detection algorithm. In this paper, we design a fast ship target detection algorithm based on saliency. Firstly, we choose the contrast significance detection method with super-pixel as the basic unit of calculation. By combining the color and spatial distance difference of each super-pixel, the contrast priori map is obtained to highlight the difference between the target region and the background area. Secondly, in order to get a more accurate target center position, the difference value between the super-pixels is used as the local feature to construct the convex hull to determine the approximate position of the target. Gao Si model is used to give different weights to superpixels in different positions, and a central prior map is obtained. At the same time, in order to further restrain the boundary background, the boundary background priori graph is fused on the basis of contrast prior graph and central prior graph. Through three priori information fusion salience detection methods quickly and accurately extract the region of interest of the target, and finally use the attitude regression method to detect the ship target in the region of interest. In the complex background, the algorithm can remove the background area effectively and quickly, and the detection accuracy is also improved, compared with the RGA method and attitude regression method. The detection accuracy of the algorithm is improved by 12.9% and 4.8, and the detection time is reduced by 72% and 78 respectively.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 安_g;王小非;夏學(xué)知;李琳;;海戰(zhàn)場(chǎng)光學(xué)遙感圖像艦船目標(biāo)檢測(cè)[J];武漢大學(xué)學(xué)報(bào)(工學(xué)版);2015年04期

2 肖志濤;王紅;張芳;耿磊;吳駿;李月龍;李峰;;復(fù)雜自然環(huán)境下感興趣區(qū)域檢測(cè)[J];中國(guó)圖象圖形學(xué)報(bào);2015年05期

3 況小琴;桑農(nóng);王潤(rùn)民;;基于Hough森林算法的遙感影像目標(biāo)檢測(cè)[J];測(cè)繪通報(bào);2014年S1期

4 魏龍生;羅大鵬;;基于視覺(jué)注意機(jī)制的遙感圖像顯著性目標(biāo)檢測(cè)[J];計(jì)算機(jī)工程與應(yīng)用;2014年19期

5 王彥情;馬雷;田原;;光學(xué)遙感圖像艦船目標(biāo)檢測(cè)與識(shí)別綜述[J];自動(dòng)化學(xué)報(bào);2011年09期

6 胡俊華;徐守時(shí);陳海林;張振;;基于局部自相似性的遙感圖像港口艦船檢測(cè)[J];中國(guó)圖象圖形學(xué)報(bào);2009年04期

7 田明輝;萬(wàn)壽紅;岳麗華;;遙感圖像中復(fù)雜海面背景下的海上艦船檢測(cè)[J];小型微型計(jì)算機(jī)系統(tǒng);2008年11期

8 隆剛;陳學(xué)Oz;;高分辨率遙感圖像港內(nèi)艦船的自動(dòng)檢測(cè)方法[J];計(jì)算機(jī)仿真;2007年05期

9 蔣李兵;王壯;胡衛(wèi)東;;一種基于可變夾角鏈碼的靠岸艦船目標(biāo)檢測(cè)方法[J];遙感技術(shù)與應(yīng)用;2007年01期

10 吳樊;王超;張紅;張波;張維勝;;基于知識(shí)的中高分辨率光學(xué)衛(wèi)星遙感影像橋梁目標(biāo)識(shí)別研究[J];電子與信息學(xué)報(bào);2006年04期

相關(guān)博士學(xué)位論文 前3條

1 康旭東;高光譜遙感影像空譜特征提取與分類方法研究[D];湖南大學(xué);2015年

2 陳霄;基于視覺(jué)顯著特征的目標(biāo)檢測(cè)方法研究[D];吉林大學(xué);2013年

3 魏昱;圖像顯著性區(qū)域檢測(cè)方法及應(yīng)用研究[D];山東大學(xué);2012年

相關(guān)碩士學(xué)位論文 前9條

1 劉冬華;基于視覺(jué)注意機(jī)制的高分影像變化檢測(cè)技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2015年

2 李一君;基于多先驗(yàn)和圖結(jié)構(gòu)的顯著性物體檢測(cè)[D];上海交通大學(xué);2015年

3 賈西西;圖像顯著性目標(biāo)檢測(cè)理論及其應(yīng)用[D];西安電子科技大學(xué);2014年

4 周國(guó)慶;基于視覺(jué)顯著性的圖像目標(biāo)檢測(cè)設(shè)計(jì)與實(shí)現(xiàn)[D];西安電子科技大學(xué);2014年

5 王飛;基于上下文和背景的視覺(jué)顯著性檢測(cè)[D];大連理工大學(xué);2013年

6 許軍毅;光學(xué)衛(wèi)星遙感圖像艦船目標(biāo)檢測(cè)技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2011年

7 施鵬;基于光學(xué)遙感圖像的艦船目標(biāo)自動(dòng)檢測(cè)技術(shù)[D];中國(guó)科學(xué)技術(shù)大學(xué);2010年

8 李文武;中低分辨率光學(xué)遙感圖像艦船目標(biāo)檢測(cè)算法研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2008年

9 蔣李兵;基于高分辨光學(xué)遙感圖像的艦船目標(biāo)檢測(cè)方法研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2006年

，

本文編號(hào)：1439933