Title :
GIS for Manmade Object Contacts from Sidescan Sonar Images
Author :
Ma, Ning ; Chan, Weng Tat ; Raju, Durairaju Kumaran ; Natesan, Suresh ; Yeo, Keng Pong
Author_Institution :
DSO Nat. Lab., Singapore
Abstract :
Abstract -In this paper, we describe a in-house developed software system for manmade object detection and the geo-localization based on sidescan sonar image. The system contains the process of detecting objects in a sidescan sonar image, outlining the detected objects in a mosaic image which is formed by mosaicing several swathes of sonar images, and saving the detected objects in a geo-information data base. The automatic object detection algorithm is based on the reflection strength (highlights), shadows and their properties. Information on detected objects such as the estimated size, shape and their geo-locations are retrieved by the analysis. The localized objects and ancillary information are subsequently loaded into a Geographical Information System (GIS). This enhances the value of the information as they can then be viewed and queried in conjunction with other useful information like bathymetry, currents and seabed sediment types in an interactive map-based display over the Internet.
Keywords :
bathymetry; geographic information systems; image segmentation; object detection; oceanographic techniques; sediments; sonar detection; sonar imaging; GIS; Geographical Information System; Internet; automatic object detection algorithm; bathymetry; geolocalization; interactive map-based display; manmade object detection; mosaic image; ocean currents; reflection strength; seabed sediment types; shadows; sidescan sonar images; sonar image mosaicing; Geographic Information Systems; Information analysis; Information retrieval; Information systems; Object detection; Reflection; Sediments; Shape; Software systems; Sonar detection;
Conference_Titel :
OCEANS 2006 - Asia Pacific
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-0138-3
Electronic_ISBN :
978-1-4244-0138-3
DOI :
10.1109/OCEANSAP.2006.4393960