Abstract
When resurveying a geographic area of the seafloor during sidescan change detection operations, an automated method to match bottom objects imaged previously with objects imaged in the resurvey can increase efficiency and accuracy. The geographic position of a new object relative to a historical object is a good indicator of a match. However, due to position error within either survey, there may be more than one spatially-close object in the new imagery. To complicate matters further, the reflected energy from the new object may be significantly different given a different incidence angle in the resurvey or the partial burial of the object. In addition, the resurveyed object image may be below the threshold set for automatic recognition and falsely eliminated. This presentation will address these problems and suggest possible methods for matching “constellations” of bottom objects by Dijkstra's minimum cost - maximum flow algorithm, control point matching, and the data-association procedure.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
