A fast physics-based, environmentally adaptive underwater object detection algorithm

David P. Williams, Johannes Groen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

21 Scopus citations

Abstract

A new algorithm for the detection of underwater man-made objects in sonar imagery is proposed. The algorithm is made extremely fast by employing a cascaded architecture and by exploiting integral-image representations. As a result, the method makes real-time detection of objects of interest in streaming sonar data collected by an autonomous underwater vehicle feasible. No training data is required because the proposed method is adaptively tailored to the environmental characteristics of the sensed data that is collected in situ. The flexible yet rigorous approach also addresses and overcomes five major limitations that plague the most popular detection algorithms that are in common use. The power and utility of the proposed approach is demonstrated on a large, challenging data set of synthetic aperture sonar imagery collected at sea.

Original languageEnglish (US)
Title of host publicationOCEANS 2011 IEEE - Spain
DOIs
StatePublished - 2011
EventOCEANS 2011 IEEE - Spain - Santander, Spain
Duration: Jun 6 2011Jun 9 2011

Publication series

NameOCEANS 2011 IEEE - Spain

Conference

ConferenceOCEANS 2011 IEEE - Spain
Country/TerritorySpain
CitySantander
Period6/6/116/9/11

All Science Journal Classification (ASJC) codes

  • Ocean Engineering

Fingerprint

Dive into the research topics of 'A fast physics-based, environmentally adaptive underwater object detection algorithm'. Together they form a unique fingerprint.

Cite this