1P1-D14 海底の地形及び画像情報によるサツマハオリムシ領域の自動抽出手法 : AUVの観測結果の全自動処理に向けて

概要

論文の詳細を見る
Although the vast amount of information provided by AUVs brings significant benefits, too much information to analyze causes a problem of information explosion. Automatic data processing and analysis are key technologies necessary to cope with this problem. We propose a robust, automated scheme for detection and volume determination of tubeworm colonies using visual and geometric features obtained by underwater robotic surveys, on condition that the position of the sensors are provided. Tubeworm is a characteristic benthos of hydrothermal vent fields. The proposed method achieves robustness against sensor noise by utilizing different kind of characteristics, imagery and geometry. Firstly, the tubeworm candidates are obtained as a three-dimensional region between practical bathymetry mesh and a mesh representing estimated seafloor without tubeworms. Then, the tubeworm candidates are verified through frequency analysis of corresponding images. The performance of this method was verified using a data set obtained by an AUV at Tagiri vent field, Kagoshima bay in Japan.
一般社団法人日本機械学会の論文