Abstract
This paper describes a technique for automatic fast orientation estimation and recognition of man-made objects present in underwater acoustic images. A method able (a) to estimate the orientation of the object principal axis, and (b) to recognize the object itself by using information about boundary segments and their angular relations, is presented. This method is based on a simple voting approach applied directly to the edge discontinuities of an image. Often, in underwater acoustic images some undesired effects are present, such as halos around objects, speckle that creates discontinuities, and distortion. Voting approach is very robust with respect to these effects, so allowing good results also when images have a very poor quality. A sequence of real acoustic images is shown for testing the proposed technique validity.
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.
