基于超椭圆拟合的水下小目标分类
|
摘要
水下小目标分类技术在海底探测、水下考古等方面应用广泛。在实际的水下声图像中,小目标投影产生的阴影区域通常在形状和尺寸方面显著于目标本身产生的亮区,故阴影分析算法对于目标的检测、识别和分类均有重要的研究意义。该文采用超椭圆曲线拟合算法拟合目标阴影区域,通过控制超椭圆函数的几个参数变化,实现不同的超椭圆曲线拟合不同的目标阴影形状,并将控制超椭圆曲线尺寸、形状和位置的参数作为特征向量输入到分类器,通过对比多个分类器得出分类结果,证明了以拟合参数为特征的分类方法有效。
Underwater small target classification technology is widely used in seabed detection, archaeology and so on. In the actual underwater acoustic image, the shape and size of shadow area, which produced by underwater small target, are usually more significant than bright area generated by the target itself, so shadow analysis algorithms have important research value in detection, identification and classification of target. In this paper, the superellipse fitting algorithm is used to fit the shadow area of the target. By controlling several parameters of superellipse function, different superellipse curves can be used to fit different target shadow shape. The parameters controlling the size, shape and position of superellipse curve are input into the classifier as feature vectors. By comparing the classification results of several classifiers, it is demonstrated that the classification method characterized by fitting parameters is effective.
Underwater small target classification technology is widely used in seabed detection, archaeology and so on. In the actual underwater acoustic image, the shape and size of shadow area, which produced by underwater small target, are usually more significant than bright area generated by the target itself, so shadow analysis algorithms have important research value in detection, identification and classification of target. In this paper, the superellipse fitting algorithm is used to fit the shadow area of the target. By controlling several parameters of superellipse function, different superellipse curves can be used to fit different target shadow shape. The parameters controlling the size, shape and position of superellipse curve are input into the classifier as feature vectors. By comparing the classification results of several classifiers, it is demonstrated that the classification method characterized by fitting parameters is effective.
引文
[1]Kim S D,Lee J H,Kim J K.A new chain-coding algorithm for binary images using run-length codes[J].Computer Vision,Graphics,and Image Processing,1988,41(1):114-128.
[2]Belkasim S O,Shridhar M,Ahmadi M.Pattern recognition with moment invariants:a comparative study and new results[J].Pattern Recognition,1991,24(12):1117-1138.
[3]Barr A H.Superquadrics and angle-preserving transformations[J].IEEE Computer Graphics and Applications,1981,1(1):11-23.
[4]Pentland A P.Perceptual organization and the representation of natural form[J].Artificial Intelligence,1986,28(3):293-331.
[5]Peak P.Mathematical games-The superellipse:a curve that lies between the ellipse and the rectangle,scientific american by martin gardner[J].Mathematics Teacher,1966,59(5):473.
[6]陈京,袁保宗,文富荣.一种基于曲率约束的不完整超二次曲线拟合[C]//第十二届全国信号处理学术年会(CCSP-2005)论文集,2005:367-370.
[7]Rosin P L.Fitting superellipses[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2000,22(7):726-732.
[8]Ahn S J,Rauh W,Cho S H,et al.Orthogonal distance fitting of implicit curves and surfaces[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2002,24(5):620-638.
[9]Voss K,Suesse H.A new one-parametric fitting method for planar objects[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1999,21(7):646-651.
[10]Rosin P L,West G A W.Curve segmentation and representation by superellipses[J].IEE Proceedings-Vision,Image and Signal Processing,1995,142(5):280-288.
[11]Fitzgibbon A,Pilu M,Fisher R B.Direct least square fitting of ellipses[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):476-480.
[12]Nelder J A,Mead R.A simplex method for function minimization[J].Compute Journal,1965,7(4):308-331.
[13]Mignotte M,Collet C,Pérez P,et al.Three-class Markovian segmentation of high-resolution sonar images[J].Computer Vision and Image Understanding,1999,76(3):191-204.
[14]Kim S D,Lee J H,Kim J K.A new chain-coding algorithm for binary images using run-length codes[J].Computer Vision,Graphics,and Image Processing,1988,41(1):114-128.
[15]Cutler A,Cutler D R,Stevens J R.Random forests[J].Machine Learning,2004,45(1):157-176.
[16]Zhao Q,Principe J C.Support vector machines for SARautomatic target recognition[J].IEEE Transactions on Aerospace&Electronic Systems,2001,37(2):643-654.
[2]Belkasim S O,Shridhar M,Ahmadi M.Pattern recognition with moment invariants:a comparative study and new results[J].Pattern Recognition,1991,24(12):1117-1138.
[3]Barr A H.Superquadrics and angle-preserving transformations[J].IEEE Computer Graphics and Applications,1981,1(1):11-23.
[4]Pentland A P.Perceptual organization and the representation of natural form[J].Artificial Intelligence,1986,28(3):293-331.
[5]Peak P.Mathematical games-The superellipse:a curve that lies between the ellipse and the rectangle,scientific american by martin gardner[J].Mathematics Teacher,1966,59(5):473.
[6]陈京,袁保宗,文富荣.一种基于曲率约束的不完整超二次曲线拟合[C]//第十二届全国信号处理学术年会(CCSP-2005)论文集,2005:367-370.
[7]Rosin P L.Fitting superellipses[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2000,22(7):726-732.
[8]Ahn S J,Rauh W,Cho S H,et al.Orthogonal distance fitting of implicit curves and surfaces[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2002,24(5):620-638.
[9]Voss K,Suesse H.A new one-parametric fitting method for planar objects[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1999,21(7):646-651.
[10]Rosin P L,West G A W.Curve segmentation and representation by superellipses[J].IEE Proceedings-Vision,Image and Signal Processing,1995,142(5):280-288.
[11]Fitzgibbon A,Pilu M,Fisher R B.Direct least square fitting of ellipses[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):476-480.
[12]Nelder J A,Mead R.A simplex method for function minimization[J].Compute Journal,1965,7(4):308-331.
[13]Mignotte M,Collet C,Pérez P,et al.Three-class Markovian segmentation of high-resolution sonar images[J].Computer Vision and Image Understanding,1999,76(3):191-204.
[14]Kim S D,Lee J H,Kim J K.A new chain-coding algorithm for binary images using run-length codes[J].Computer Vision,Graphics,and Image Processing,1988,41(1):114-128.
[15]Cutler A,Cutler D R,Stevens J R.Random forests[J].Machine Learning,2004,45(1):157-176.
[16]Zhao Q,Principe J C.Support vector machines for SARautomatic target recognition[J].IEEE Transactions on Aerospace&Electronic Systems,2001,37(2):643-654.