In this paper we develop a novel classification method for multibeam sonar images based on the Weyl transform. The texture descriptor based on Weyl coefficients describes effectively the multiscale correlation feature...
详细信息
ISBN:
(纸本)9783030312541;9783030312534
In this paper we develop a novel classification method for multibeam sonar images based on the Weyl transform. The texture descriptor based on Weyl coefficients describes effectively the multiscale correlation features appearing in the sonar images. Our classification approach combines the Weyl coefficients with statistical features that are commonly used in the analysis of seabed sonar images and captures the morphological variation and geoacoustic characteristics of the seafloor. We employ a neural network as a classifier. The proposed combined feature extraction method demonstrates better performance than the commonly used statistical methods in this application.
The Ocean Mapping Group has been collecting data in the Arctic since 2003 and there are approximately 2,000 basemaps. In the current online storage format used by the OMG, it is difficult to view the data and users ca...
详细信息
The Ocean Mapping Group has been collecting data in the Arctic since 2003 and there are approximately 2,000 basemaps. In the current online storage format used by the OMG, it is difficult to view the data and users cannot easily pan and zoom. The purpose of this research is to investigate the advantages of the use of Google Maps, to display the OMG's Arctic data. The map should should load the large Artic dataset in a reasonable time. The bathymetric images were created using software in Linux written by the OMG, and a step-by-step process was used to create images from the multibeamdata collected by the OMG in the Arctic. The website was also created using Linux operating system. The projection needed to be changed from Lambert Conformal Conic (useful at higher Latitudes) to Mercator (used by Google Maps) and the data needed to have a common colour scheme. After creating and testing a prototype website using Google Ground overlay and Tile overlay, it was determined that the high resolution images (10m) were loading very slowly and the ground overlay method would not be useful for displaying the entire dataset. Therefore the Tile overlays were selected to be used within Google Maps. Tile overlays used for this project proved to be useful for large datasets because they cut the image into many different tiles and load only the part of the image (tile) within the map window bounds.
暂无评论