Deep learning-based seabed sediment analysis system for benthic ecological habitat classification

• Main Author: LIM MOON SOO
• Format: Patent
• Language: English; Korean
• Published: 25.02.2022
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; GYROSCOPIC INSTRUMENTS; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; MEASURING DISTANCES, LEVELS OR BEARINGS; NAVIGATION; PHOTOGRAMMETRY OR VIDEOGRAMMETRY; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; SURVEYING; TESTING

The present invention provides a deep learning-based marine sediment analysis system for benthic ecological habitat classification. The deep learning-based marine sediment analysis system comprises: an interface configured to receive and upload backscattered sound pressure data; a processor configured to select data to be classified among the uploaded sound pressure data and a learning model for classification, classify the data to be classified, generate a map from the classified data, and generate a benthic quality topographic map from the generated map; and a display configured to display the benthic quality topographic map on a map where the benthic quality topographic map can be displayed. According to the present invention, the analysis system can be utilized in a future ocean surveying project. 본 발명에 따른 저서생태 서식지 분류를 위한 딥러닝 기반 해저퇴적물 분석시스템이 제공된다. 상기 딥러닝 기반 해저퇴적물 분석시스템은 후방산란 음압데이터를 수신하여 업로드하도록 구성된 인터페이스; 상기 업로드된 음압데이터 중 분류할 데이터 및 분류를 위힌 학습모델을 선택하고 상기 분류할 데이터를 분류하고, 상기 분류된 데이터에서 맵(map)을 생성하고, 상기 생성된 맵으로부터 해저질 지형도를 생성하도록 구성된 프로세서; 및 상기 해저질 지형도를 상기 해저질 지형도가 표시될 수 있는 지도에 표시하도록 구성된 디스플레이를 포함한다.