http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112102394-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10032 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-62 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate | 2020-09-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2021-05-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2021-05-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-112102394-B |
titleOfInvention | An integrated extraction method of ship size from remote sensing images based on deep learning |
abstract | The invention discloses an integrated extraction method of remote sensing image ship size based on deep learning, constructing a remote sensing image ship size training set: acquiring remote sensing data and preprocessing, acquiring AIS ship data, and combining the two sets of data to establish Ship size training set in remote sensing images; build an integrated extraction model of remote sensing image ship size based on deep learning; model training: use the training set constructed in S1 to train the model constructed in S2, and apply the trained model to Ship size extraction from new remote sensing images. The invention simplifies the traditional way of extracting the length and width of ships, realizes the direct extraction of length and width information of ships from remote sensing images, improves the efficiency and accuracy of extracting ship length and width information from remote sensing images, and the extraction error is controlled within single pixel level. |
priorityDate | 2020-09-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID458431896 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID24857 |
Total number of triples: 19.