Superellipse Fitting for the Recovery and Classification of Mine-Like Shapes in Sidescan Sonar Images

Inst. of Robot., Univ. de Valencia, Valencia
IEEE Journal of Oceanic Engineering (Impact Factor: 1.18). 11/2008; 33(4):434 - 444. DOI: 10.1109/JOE.2008.2002962
Source: IEEE Xplore


Mine-like object classification from sidescan sonar images is of great interest for mine counter measure (MCM) operations. Because the shadow cast by an object is often the most distinct feature of a sidescan image, a standard procedure is to perform classification based on features extracted from the shadow. The classification can then be performed by extracting features from the shadow and comparing this to training data to determine the object. In this paper, a superellipse fitting approach to classifying mine-like objects in sidescan sonar images is presented. Superellipses provide a compact and efficient way of representing different mine-like shapes. Through variation of a simple parameter of the superellipse function different shapes such as ellipses, rhomboids, and rectangles can be easily generated. This paper proposes a classification of the shape based directly on a parameter of the superellipse known as the squareness parameter. The first step in this procedure extracts the contour of the shadow given by an unsupervised Markovian segmentation algorithm. Afterwards, a superellipse is fitted by minimizing the Euclidean distance between points on the shadow contour and the superellipse. As the term being minimized is nonlinear, a closed-form solution is not available. Hence, the parameters of the superellipse are estimated by the Nelder-Mead simplex technique. The method was then applied to sidescan data to assess its ability to recover and classify objects. This resulted in a recovery rate of 70% (34 of the 48 mine-like objects) and a classification rate of better than 80% (39 of the 48 mine-like objects).

Download full-text


Available from: Esther Dura, Oct 01, 2015
1 Follower
78 Reads
  • Source
    • "The results will be assessed by using the extracted superellipse parameters for a classification. The best version is afterwards compared with the method by [24] where the segmentation and superellipse fitting is divided into two steps, i.e. the image is first divided into shadow and non-shadow areas with an algorithm that does not take into account the superellipse a-priori knowledge. "
    ICRA 2015, Seattle, Washington, USA; 05/2015
  • Source
    • "나 Superelipse Fitting [4] "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, underwater acoustic image classification of a cylindrical object using the Hough transformation is proposed. Hough transformation is often used to classify a cylindrical object in the optical systems. However, it is difficult to apply to the underwater acoustic image system because of lower resolution and noisier underwater environments. Thus, the cylindrical object was modeled and its geometric depth(GD) pixels were restored in order to make them suitable for the Hough transformation by using moving average filter and a polynomial interpolation method. As a result, restored GD pixels are similar to original ones and test results show high performance in classification.
    02/2013; 50(2). DOI:10.5573/ieek.2013.50.2.193
  • Source
    • "The Lamé curve is extended by one skew factor and expressed in a parametric form as x1,Lc(t) = a cos ǫ t, x2,Lc(t) = b sin ǫ t + m x1,Lc(t), (3) where a and b are the x1-and x2-intercepts, t ∈ R, ǫ is known as the squareness of the Lamé curve, which controls curve deformations at the corners and m denotes the skew in x2-direction. In [9] Lamé curves are considered in a similar context to be fitted to extracted contours, where only symmetric objects are allowed. Our new approach accomplishes for each quadrant an independent fit, which allows also non-symmetric objects to appear, like more complicated objects or non-symmetric shapes occurred due to environmental effects (e.g. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a new level set segmentation method which is guided by a parametric prior force based on Lamé curves. The use of prior knowledge is advantageous in order to improve the segmentation results in terms of matching expected object types because one can in general state that for different applications some shapes are more likely than others. By avoiding complex shape training processes the level set idea is extended with a parametric prior shape which forces the level set evolution to propagate towards the desired objects by not overpowering the image properties. Also a cross talk evolution is discussed for ternary images to handle correlations between adjacent or correlated objects.
    19th IEEE International Conference on Image Processing (ICIP), Orlando, Florida; 01/2012
Show more