本文關(guān)鍵詞： 遙感圖像 敏感對象識別 三角網(wǎng)格 魚眼變換 圖像縮放　出處：《北方工業(yè)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著航空航天技術(shù)的進(jìn)步,如何能夠?qū)b感圖像中的敏感區(qū)域進(jìn)行無失真的有效縮放成了現(xiàn)在很重要的研究熱點(diǎn)。機(jī)場和橋梁在交通運(yùn)輸方面具有重要的作用且一直是國防軍事打擊的重要目標(biāo)。如何能夠做到從全局的角度重點(diǎn)觀察遙感圖像中這兩種對象的細(xì)節(jié)信息是軍事打擊以及研究的重要基礎(chǔ)。本文提出一種提取對象敏感度特征并結(jié)合對象一般特性對多光譜圖像中的敏感對象進(jìn)行識別的算法;提出一種三角網(wǎng)格與魚眼變換相結(jié)合的遙感圖像縮放算法,以實(shí)現(xiàn)敏感區(qū)域的最優(yōu)縮放。多光譜圖像因其不同的采集方式,使其本身具有很多分類特征,對這些特征的提取可以有效的識別出圖像中不同的對象區(qū)域。本文提出的一種基于敏感度的敏感區(qū)域識別算法,在對提取出的敏感對象潛在區(qū)域提取紋理特征、顏色矩特征、面積特征之后又結(jié)合各潛在區(qū)域在原始圖像中的上下文信息提取了對象區(qū)域敏感度特征,最后,通過基于AdaBoost的SVM分類器對各潛在區(qū)域進(jìn)行分類,確定敏感區(qū)域的具體位置,并在原圖像中標(biāo)識出來。將該算法應(yīng)用于多光譜圖像機(jī)場、橋梁敏感目標(biāo)的識別上,實(shí)驗(yàn)表明該算法較以機(jī)場跑道直線特征為主要檢測依據(jù)的機(jī)場識別算法和以橋梁與水體的光譜差異性為識別依據(jù)的橋梁識別算法的平均準(zhǔn)確率有了明顯提高,機(jī)場識別平均識別準(zhǔn)確率達(dá)到92%,橋梁平均識別準(zhǔn)確率達(dá)到了 90%。目前針對遙感圖像縮放技術(shù)的研究非常少。本文提出的一種三角網(wǎng)格與魚眼變換相結(jié)合的圖像縮放算法針對已識別出的多光譜圖像中的敏感區(qū)域,對區(qū)域內(nèi)部進(jìn)行三角網(wǎng)格劃分,并對區(qū)域內(nèi)部實(shí)現(xiàn)基于三角網(wǎng)格的縮放,保持區(qū)域內(nèi)部敏感對象部分的信息內(nèi)容不變。整幅圖像除敏感區(qū)域之外的部分,做與敏感區(qū)域縮放過程產(chǎn)生的變化有關(guān)的基于魚眼變換算法的壓縮。實(shí)驗(yàn)結(jié)果表明,圖像在縮放過程中產(chǎn)生的絕大部分失真畸變都發(fā)生在敏感區(qū)域以外的部分,敏感區(qū)域內(nèi)部失真很小,縮放效果較現(xiàn)有的線裁剪縮放方法、三角網(wǎng)格縮放方法以及魚眼變換內(nèi)容感知縮放算法有明顯改善。
[Abstract]:With the advance of aerospace technology. How to effectively scale sensitive areas in remote sensing images without distortion has become an important research hotspot. Airports and bridges play an important role in transportation and have always been important for national defense and military strike. How to observe the details of the two objects in remote sensing images from a global perspective is an important basis for military attack and research. In this paper, we propose a method to extract sensitivity features of objects and combine them with objects. The algorithm for the recognition of sensitive objects in multispectral images with general characteristics; A remote sensing image scaling algorithm based on triangular mesh and fish-eye transform is proposed to realize the optimal scaling of sensitive region. Multi-spectral images have many classification characteristics because of their different acquisition methods. The extraction of these features can effectively identify different object areas in the image. A sensitive region recognition algorithm based on sensitivity is proposed to extract texture features from the potential areas of the extracted sensitive objects. Color moment feature, area feature and the contextual information of each potential region in the original image are used to extract the sensitivity feature of the object region. The potential regions are classified by SVM classifier based on AdaBoost to determine the specific location of the sensitive regions and identify them in the original image. The algorithm is applied to the multi-spectral image field. Bridge sensitive target recognition. The experimental results show that the average accuracy of the algorithm is significantly improved compared with the airport recognition algorithm based on the linear features of the airport runway and the bridge recognition algorithm based on the spectral difference between the bridge and the water body. The average recognition accuracy of airport recognition is 92%. The average accuracy of bridge recognition has been achieved. At present, there is very little research on remote sensing image scaling technology. In this paper, a new image scaling algorithm based on triangle mesh and fish-eye transform is proposed for the sensitive areas in the identified multi-spectral images. Triangulation is carried out within the region, and the region is scaled based on the triangular mesh to keep the information content of the sensitive object in the region unchanged. The whole image is except the sensitive area. The experiment results show that most of the distortion in the process of image zooming occurs outside the sensitive region. The internal distortion of sensitive area is very small, and the scaling effect is obviously improved compared with the existing line clipping method, triangular mesh scaling method and fish-eye transform content sensing scaling algorithm.
【學(xué)位授予單位】：北方工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 孫艷麗;周偉;鐘佩琳;;一種針對多光譜遙感圖像的橋梁快速識別算法[J];海軍航空工程學(xué)院學(xué)報(bào);2016年04期

2 陳小娥;李慧敏;;多相同最小能量值線路下基于線裁剪的圖像縮放算法研究[J];長春工程學(xué)院學(xué)報(bào)(自然科學(xué)版);2016年02期

3 陳彥彤;徐偉;樸永杰;陳娟;;基于快速視網(wǎng)膜局部特征的遙感圖像目標(biāo)識別[J];儀器儀表學(xué)報(bào);2016年04期

4 尤磊;唐守正;宋新宇;;以優(yōu)先點(diǎn)為中心的Delaunay三角網(wǎng)生長算法[J];中國圖象圖形學(xué)報(bào);2016年01期

5 龐娜;趙啟林;芮挺;朱斌;;基于機(jī)器視覺的橋梁檢測技術(shù)現(xiàn)狀及發(fā)展[J];現(xiàn)代交通技術(shù);2015年06期

6 王民;周兆鎮(zhèn);李昌華;衛(wèi)銘斐;毛力;;基于像素點(diǎn)灰度差的Harris角點(diǎn)檢測算法[J];計(jì)算機(jī)工程;2015年06期

7 曾陽帆;趙擁軍;劉偉;陳建宏;;大幅場景高分辨率SAR圖像機(jī)場自動(dòng)檢測[J];測繪科學(xué)技術(shù)學(xué)報(bào);2015年03期

8 李鳳霞;劉詠梅;王曉哲;饒永輝;;一種基于映射法的散亂點(diǎn)云Delaunay三角剖分算法[J];計(jì)算機(jī)應(yīng)用研究;2015年03期

9 晉瑞錦;周偉;楊健;;大場景下的極化SAR機(jī)場檢測[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年12期

10 張麗霞;區(qū)兆明;宋鴻陟;;改進(jìn)魚眼變換技術(shù)的圖像適應(yīng)[J];中國圖象圖形學(xué)報(bào);2014年12期

相關(guān)博士學(xué)位論文 前1條

1 周文罡;基于局部特征的視覺上下文分析及其應(yīng)用[D];中國科學(xué)技術(shù)大學(xué);2011年

相關(guān)碩士學(xué)位論文 前5條

1 豐曉霞;基于深度學(xué)習(xí)的圖像識別算法研究[D];太原理工大學(xué);2015年

2 王瑋;幾種最新的圖像縮放方法的比較性研究[D];大連理工大學(xué);2013年

3 孫亦揚(yáng);基于Seam Carving方法的圖像縮放技術(shù)研究[D];西安電子科技大學(xué);2013年

4 徐國靖;基于形態(tài)學(xué)梯度的圖像邊緣檢測算法[D];西安電子科技大學(xué);2013年

5 王鵬;基于顏色特征的圖像檢索系統(tǒng)[D];西安電子科技大學(xué);2012年

，

本文編號：1475199