Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308236554> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4308236554 abstract "Many fields are interested in mapping and monitoring the sea floor natural structure and biology, for environmental surveys, including identifying macro waste or detection of submerged artifacts such as cars, tires, wrecks, and even military applications, e.g., mine warfare whose detection depends heavily on the seabed structure. In this paper, we propose a new active learning method to improve seabed segmentation by deep learning. We perform segmentation of the sea floor using two data sources, sonar, and bathymetry. We train a network to fuse these two modalities and segment each sea floor pixel into nine fine ecological classes, then into three gross class sets, alive/not alive, and, in two different ways, whether mines can be hunted for or not. Once this training is done, a second stage involving a new active learning method based on network uncertainties greatly improves the performance." @default.
- W4308236554 created "2022-11-09" @default.
- W4308236554 creator A5012968147 @default.
- W4308236554 creator A5019447371 @default.
- W4308236554 creator A5027912077 @default.
- W4308236554 creator A5060579254 @default.
- W4308236554 date "2022-10-16" @default.
- W4308236554 modified "2023-10-17" @default.
- W4308236554 title "New Active Learning Approach for Seabed Segmentation" @default.
- W4308236554 cites W1978633512 @default.
- W4308236554 cites W1995875735 @default.
- W4308236554 cites W1998498767 @default.
- W4308236554 cites W2101927381 @default.
- W4308236554 cites W2113152670 @default.
- W4308236554 cites W2120576658 @default.
- W4308236554 cites W2130430899 @default.
- W4308236554 cites W2135293965 @default.
- W4308236554 cites W2139573966 @default.
- W4308236554 cites W2153744498 @default.
- W4308236554 cites W2194775991 @default.
- W4308236554 cites W2343514605 @default.
- W4308236554 cites W2527802235 @default.
- W4308236554 cites W2951911250 @default.
- W4308236554 cites W2956586819 @default.
- W4308236554 cites W2983238953 @default.
- W4308236554 cites W3048631361 @default.
- W4308236554 cites W3207200417 @default.
- W4308236554 cites W4206500946 @default.
- W4308236554 cites W4238404964 @default.
- W4308236554 doi "https://doi.org/10.1109/icip46576.2022.9897396" @default.
- W4308236554 hasPublicationYear "2022" @default.
- W4308236554 type Work @default.
- W4308236554 citedByCount "0" @default.
- W4308236554 crossrefType "proceedings-article" @default.
- W4308236554 hasAuthorship W4308236554A5012968147 @default.
- W4308236554 hasAuthorship W4308236554A5019447371 @default.
- W4308236554 hasAuthorship W4308236554A5027912077 @default.
- W4308236554 hasAuthorship W4308236554A5060579254 @default.
- W4308236554 hasConcept C111368507 @default.
- W4308236554 hasConcept C119599485 @default.
- W4308236554 hasConcept C124504099 @default.
- W4308236554 hasConcept C127313418 @default.
- W4308236554 hasConcept C127413603 @default.
- W4308236554 hasConcept C137184094 @default.
- W4308236554 hasConcept C141353440 @default.
- W4308236554 hasConcept C154945302 @default.
- W4308236554 hasConcept C174943157 @default.
- W4308236554 hasConcept C199104240 @default.
- W4308236554 hasConcept C2776355146 @default.
- W4308236554 hasConcept C31972630 @default.
- W4308236554 hasConcept C33613203 @default.
- W4308236554 hasConcept C41008148 @default.
- W4308236554 hasConcept C555745239 @default.
- W4308236554 hasConcept C77967617 @default.
- W4308236554 hasConcept C89600930 @default.
- W4308236554 hasConceptScore W4308236554C111368507 @default.
- W4308236554 hasConceptScore W4308236554C119599485 @default.
- W4308236554 hasConceptScore W4308236554C124504099 @default.
- W4308236554 hasConceptScore W4308236554C127313418 @default.
- W4308236554 hasConceptScore W4308236554C127413603 @default.
- W4308236554 hasConceptScore W4308236554C137184094 @default.
- W4308236554 hasConceptScore W4308236554C141353440 @default.
- W4308236554 hasConceptScore W4308236554C154945302 @default.
- W4308236554 hasConceptScore W4308236554C174943157 @default.
- W4308236554 hasConceptScore W4308236554C199104240 @default.
- W4308236554 hasConceptScore W4308236554C2776355146 @default.
- W4308236554 hasConceptScore W4308236554C31972630 @default.
- W4308236554 hasConceptScore W4308236554C33613203 @default.
- W4308236554 hasConceptScore W4308236554C41008148 @default.
- W4308236554 hasConceptScore W4308236554C555745239 @default.
- W4308236554 hasConceptScore W4308236554C77967617 @default.
- W4308236554 hasConceptScore W4308236554C89600930 @default.
- W4308236554 hasLocation W43082365541 @default.
- W4308236554 hasLocation W43082365542 @default.
- W4308236554 hasOpenAccess W4308236554 @default.
- W4308236554 hasPrimaryLocation W43082365541 @default.
- W4308236554 hasRelatedWork W1921505891 @default.
- W4308236554 hasRelatedWork W2016800904 @default.
- W4308236554 hasRelatedWork W2049105424 @default.
- W4308236554 hasRelatedWork W2114161718 @default.
- W4308236554 hasRelatedWork W2312941721 @default.
- W4308236554 hasRelatedWork W2362175816 @default.
- W4308236554 hasRelatedWork W2392611223 @default.
- W4308236554 hasRelatedWork W2888512610 @default.
- W4308236554 hasRelatedWork W2897910144 @default.
- W4308236554 hasRelatedWork W631245989 @default.
- W4308236554 isParatext "false" @default.
- W4308236554 isRetracted "false" @default.
- W4308236554 workType "article" @default.