Accepted Papers

  • A Novel Method for Waterline Extraction From Remote Sensing Image based on Quad-tree and Multiple Active Contour Model
    Zhengzhou Institute of Surveying and Mapping, Zhengzhou 450052, China

    After the characteristics of geodesic active contour model (GAC), Chan-Vese model (CV) and local binary fitting model (LBF) are analyzed, and the active contour model based on regions and edges is combined with image segmentation method based on quad-tree, a waterline extraction method based on quad-tree and multiple active contour model is proposed in this paper. Firstly , the method provides an initial contour according to quad-tree segmentation; secondly, a new signed pressure force (SPF) function based on global image statistics information of CV model and local image statistics information of LBF model has been defined, and then, the edge stopping function(ESF) is replaced by the proposed SPF function, which solves the problem such as evolution stopped in advance and excessive evolution; finally, the Selective Binary and Gaussian Filtering Level Set method is used to avoid reinitializing and regularization to improve the evolution efficiency. The experimental results show that this method can effectively extract the weak edges and serious concave edges, and owns some properties such as sub-pixel accuracy, high efficiency and reliability for waterline extraction.

  • Astronomical Objects Detection in Celestial Bodies using Computer Vision Algorithm
    Turkish-German University, Turkey

    Computer vision, astronomy, and astrophysics function quite productively together to the point where they are completely logical for each other. Out of computer vision algorithms the progress of astronomy and astrophysics would have slowed down to reasonably a deadlock. The new researches and calculations can lead to more information as well as higher quality of data. Thus an organized view on planetary surfaces can change all in the long run. A new discovery would be a puzzling complexity or a possible branching of paths, yet the quest to know more about the celestial bodies by dint of computer vision algorithms will continue. The detection of astronomical objects in celestial bodies is a challenging task. This paper presents an implementation of how to detect astronomical objects in celestial bodies using computer vision algorithm with satisfactory performance. It also puts forward some observations linked among computer vision, astronomy, and astrophysics.

  • Radar Target Classiftcation With Rbf Neural Networks
    Department of Electrical & Computer Engineering, Ben-Gurion University of the Negev,Beer-Sheva, Israel

    This paper introduces a new method for classification of ground moving targets detected by Ground Moving Target Indication (GMTI) radar systems,based on artificial neural networks. The direct information provided by GMTI radars does not include any information regarding the type of vehicles which are detected. On the other hand, the ability of using GMTI radar measurements to classify ground moving targets, even roughly, is of great interest. The main approach suggested is based on Radial Basis Function (RBF) neural networks. The data used as features for classification is composed of Radar Cross Section (RCS)values of thetarget obtained in varying aspect angles. The proposed classifier was tested on diverse simulative cases and yielded over 90% correct estimation in classification for three groups of size, and over 85% correct estimation in classification for five groups.

Copyright ® ISPR 2017