高分辨率遥感影像中飞机识别研究
|
摘要
在目标识别领域,飞机是一种常被研究的对象,对飞机进行精确识别并定位,无论在军事打击和商业调查中都有重要意义。高分辨率图像中丰富的空间、光谱和上下文信息在带来更多有用细节信息的同时,也给飞机识别带来了更加复杂的背景干扰。主要研究应用面向对象的理念来实现对高分辨率遥感图像中飞机的识别。首先是图像预处理,即获得图像中的对象;然后是面向对象的图像识别,即提取图像对象的特征;并依据特征完成识别任务。利用的基本特征主要有图像对象的面积、长宽比、分散度、凸包缺陷。实验证明这种识别方法,对于不同朝向和大小的飞机都能取得较高的检出率。
The plane as a target is always used to study the field of target recognition. Accurately identification and location of the plane has important significance in both the military and commercial investigation. The rich space,spectrum and context information in high resolution image provides more useful information,but it brings about more complex background interference. Object-oriented method was applied to identify the plane in the high resolution remote sensing images. First step,image preprocessing,that is obtaining the objects in the images;second step, the object-oriented image recognition, that is getting the characteristic of image object and accomplishing recognition. The characteristic of image include area,length-width ratio,dispersity,ridge defect.The detection rate of the recognition algorithm is high in the experiment,although the planes are different in size and direction.
The plane as a target is always used to study the field of target recognition. Accurately identification and location of the plane has important significance in both the military and commercial investigation. The rich space,spectrum and context information in high resolution image provides more useful information,but it brings about more complex background interference. Object-oriented method was applied to identify the plane in the high resolution remote sensing images. First step,image preprocessing,that is obtaining the objects in the images;second step, the object-oriented image recognition, that is getting the characteristic of image object and accomplishing recognition. The characteristic of image include area,length-width ratio,dispersity,ridge defect.The detection rate of the recognition algorithm is high in the experiment,although the planes are different in size and direction.
引文
1 Hsieh J W,Chen J M,Chuang C H,et al.Novel aircraft type recognition with learning capabilities in satellite images.2004.2004International Conference on Image Processing.New York:IEEE,2004:1715—1718
2 Schowengerdt R A.Remote sensing:models and methods for image processing.Manhattan:Academic Press,2006
3 Richards J A.遥感数字图像分析导论.张钧萍,谷延锋,陈雨时,译.北京:电子工业出版社,2015Richards J A.Remote sensing digital image analysis:an introduction.Zhang J P,Gu Y F,Chen Y S,trans lated.Beijing:Electronic Industry Press,2015
4 Chen G,Hay G J,Castilla G,et al.A multiscale geographic objectbased image analysis to estimate lidar-measured forest canopy height using quickbird imagery.International Journal of Geographical Information Science,2011;25(6):877—893
5 徐大琦,倪国强,许廷发.中高分辨力遥感图像中飞机目标自动识别算法研究.光学技术,2006;32(6):855—858Xu D Q,Ni G Q,Xu T F.A study on automatic recognition algorithm of aircraft with mid-high resolution remote sensing image.Optical Technique,2006;32(6):855—858
6 于仕琪,刘瑞祯.学习Open CV(中文版).北京:清华大学出版社,2009Yu S Q,Liu R Z.Open CV study(Chinese edition).Beijing:Tsinghua University Press,2009
7 谢勰,王辉,张雪锋.图像阈值分割技术中的部分和算法综述.西安邮电学院学报,2011;16(3):1—5Xie S,Wang H,Zhang X F.Summary of the image threshold segmentation techniques and algorithms,Xi'an:Journal of Xi'an Institute of Posts and Telecommunications,2011;16(3):1—5
8 丁亮,张永平,张雪英.图像分割方法及性能评价综述.软件,2010;31(12):78—83Ding L,Zhang Y P,Zhang X Y.Summary of the method and evaluation on image segmentation.Journal of Software,2010;31(12):78—83
9 周丰乐,徐向民,肖跃,等.一种新的二值图像目标轮廓跟踪算法.微计算机信息,2007;23(6):259—261Zhou F L,Xu X M,Xiao Y,et al.A new binary image target contour tracking algorithm.Microcomputer Information,2007;23(6):259—261
10 冯伟兴,贺波,王臣业,等.Visual C++数字图像模式识别技术详解.北京:机械工业出版社,2013Feng W X,He B,Wang C Y,et al.Visual C++Digital image pattern recognition technology explanation.Beijing:China Machine Press,2013
11 韩现伟.大幅面可见光遥感图像典型目标识别关键技术研究.哈尔滨:哈尔滨工业大学,2013Han X W.Research on target identification key technology of large format optical remote sensing images.Harbin:Harbin Institute of Technology,2013
12 王慧燕,程翼宇.基于信息测度特征和Hausdorff距离的图像匹配策略.中国图像图形学报:,2004;9(11):1314—1319Wang H Y,Cheng Y Y.Image matching strategy based on the image characteristics and Hausdorff distance.Journal of Image and Graphics,2004;9(11):1314—1319
13 曾接贤,付俊,符祥.特征点和不变矩结合的遥感图像飞机目标识别.中国图像图形学报,2014;19(4):592—602Zeng J X,Fu J,Fu X.Remote sensing image aircraft target recognition based on Feature points and invariant moment.Journal of Image and Graphics,2014;19(4):592—602
14 才让卓玛,张名成.基于结构特征的飞机目标识别方法.计算机工程与应用,2013;49(4):174—177Cai R Z M,Zhang M C.Aircraft target recognition method based on structural characteristics.Computer Engineering and Applications,2013;49(4):174—177
15 黄丽华.基于灰度共生矩阵的纹理特征值提取.科技视界,2013;(22):47—47Huang L H.Eigenvalue extraction based on gray level co-occurrence matrix.Science&Technology Vision,2013;(22):47—47
16 蔡云骧,田振锡,毕道鵾.背景典型斑点特征的聚类分析.光电技术应用,2012;(3):69—73Cai Y X,Tian Z X,Bi D K.Cluster analysis of background typical spots characteristics.Electro-Optic Technology Application,2012;(3):69—73
17 刘光惠,陈传波.求解简单多边形和平面点集凸包的新算法.计算机科学,2007;(12):222—226Liu G H,Chen C B.A new algorithm for solving convex hull of simple polygon and point set.Computer Science,2007;(12):222 —226.
18 Homma K,Takenaka E.An image processing method for feature extraction of space-occupying lesions.Journal of Nuclear Medicine:official publication.Society of Nuclear Medicine,1985;26(12):1472—1477
2 Schowengerdt R A.Remote sensing:models and methods for image processing.Manhattan:Academic Press,2006
3 Richards J A.遥感数字图像分析导论.张钧萍,谷延锋,陈雨时,译.北京:电子工业出版社,2015Richards J A.Remote sensing digital image analysis:an introduction.Zhang J P,Gu Y F,Chen Y S,trans lated.Beijing:Electronic Industry Press,2015
4 Chen G,Hay G J,Castilla G,et al.A multiscale geographic objectbased image analysis to estimate lidar-measured forest canopy height using quickbird imagery.International Journal of Geographical Information Science,2011;25(6):877—893
5 徐大琦,倪国强,许廷发.中高分辨力遥感图像中飞机目标自动识别算法研究.光学技术,2006;32(6):855—858Xu D Q,Ni G Q,Xu T F.A study on automatic recognition algorithm of aircraft with mid-high resolution remote sensing image.Optical Technique,2006;32(6):855—858
6 于仕琪,刘瑞祯.学习Open CV(中文版).北京:清华大学出版社,2009Yu S Q,Liu R Z.Open CV study(Chinese edition).Beijing:Tsinghua University Press,2009
7 谢勰,王辉,张雪锋.图像阈值分割技术中的部分和算法综述.西安邮电学院学报,2011;16(3):1—5Xie S,Wang H,Zhang X F.Summary of the image threshold segmentation techniques and algorithms,Xi'an:Journal of Xi'an Institute of Posts and Telecommunications,2011;16(3):1—5
8 丁亮,张永平,张雪英.图像分割方法及性能评价综述.软件,2010;31(12):78—83Ding L,Zhang Y P,Zhang X Y.Summary of the method and evaluation on image segmentation.Journal of Software,2010;31(12):78—83
9 周丰乐,徐向民,肖跃,等.一种新的二值图像目标轮廓跟踪算法.微计算机信息,2007;23(6):259—261Zhou F L,Xu X M,Xiao Y,et al.A new binary image target contour tracking algorithm.Microcomputer Information,2007;23(6):259—261
10 冯伟兴,贺波,王臣业,等.Visual C++数字图像模式识别技术详解.北京:机械工业出版社,2013Feng W X,He B,Wang C Y,et al.Visual C++Digital image pattern recognition technology explanation.Beijing:China Machine Press,2013
11 韩现伟.大幅面可见光遥感图像典型目标识别关键技术研究.哈尔滨:哈尔滨工业大学,2013Han X W.Research on target identification key technology of large format optical remote sensing images.Harbin:Harbin Institute of Technology,2013
12 王慧燕,程翼宇.基于信息测度特征和Hausdorff距离的图像匹配策略.中国图像图形学报:,2004;9(11):1314—1319Wang H Y,Cheng Y Y.Image matching strategy based on the image characteristics and Hausdorff distance.Journal of Image and Graphics,2004;9(11):1314—1319
13 曾接贤,付俊,符祥.特征点和不变矩结合的遥感图像飞机目标识别.中国图像图形学报,2014;19(4):592—602Zeng J X,Fu J,Fu X.Remote sensing image aircraft target recognition based on Feature points and invariant moment.Journal of Image and Graphics,2014;19(4):592—602
14 才让卓玛,张名成.基于结构特征的飞机目标识别方法.计算机工程与应用,2013;49(4):174—177Cai R Z M,Zhang M C.Aircraft target recognition method based on structural characteristics.Computer Engineering and Applications,2013;49(4):174—177
15 黄丽华.基于灰度共生矩阵的纹理特征值提取.科技视界,2013;(22):47—47Huang L H.Eigenvalue extraction based on gray level co-occurrence matrix.Science&Technology Vision,2013;(22):47—47
16 蔡云骧,田振锡,毕道鵾.背景典型斑点特征的聚类分析.光电技术应用,2012;(3):69—73Cai Y X,Tian Z X,Bi D K.Cluster analysis of background typical spots characteristics.Electro-Optic Technology Application,2012;(3):69—73
17 刘光惠,陈传波.求解简单多边形和平面点集凸包的新算法.计算机科学,2007;(12):222—226Liu G H,Chen C B.A new algorithm for solving convex hull of simple polygon and point set.Computer Science,2007;(12):222 —226.
18 Homma K,Takenaka E.An image processing method for feature extraction of space-occupying lesions.Journal of Nuclear Medicine:official publication.Society of Nuclear Medicine,1985;26(12):1472—1477