Title :
Detecting ripple patterns in mission videos
Author :
Olmos, Adriana ; Trucco, Manuel ; Lebart, Katia ; Lane, Dave
Author_Institution :
Dept. of Offshore Eng., Heriot-Watt Univ., Edinburgh, UK
Abstract :
Ripple patterns on the seafloor carry information of interest for marine geophysicists, but identifying sand-ripple segments in a long mission video can be very tedious. This work presents a comparison between two experimental algorithms: frequency based method and feature based method. Both pursue the automatic detection of sand ripples in videos of underwater scientific missions. The investigation looks at the robustness of the classifier with increased noise conditions and changes in rotation and spatial frequency of ripple patterns
Keywords :
feature extraction; geophysical signal processing; geophysical techniques; image classification; oceanographic techniques; pattern classification; sand; seafloor phenomena; algorithm; automatic detection; classifier; feature based method; feature extraction; frequency based method; geophysical measurement technique; image classification; image processing; marine sediment; measurement technique; mission video; ocean; pattern recognition; ripple pattern; sand ripple segment; seabed; seafloor geology; Detection algorithms; Fourier transforms; Frequency; Laboratories; Oceans; Remotely operated vehicles; Shape; Testing; Underwater tracking; Videos;
Conference_Titel :
OCEANS 2000 MTS/IEEE Conference and Exhibition
Conference_Location :
Providence, RI
Print_ISBN :
0-7803-6551-8
DOI :
10.1109/OCEANS.2000.881280
