Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_331cd7e2dfc9d1dec82506ebc2afc4d9 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2218-12 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2218-08 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-047 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/G01N21-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2415 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N21-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 |
filingDate |
2021-09-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f2a391cf794f175a8ed11fe4005c4a9e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bf19badb0f87e823071d602aa7f8e850 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_72456f40ee4b1773acbd20c0dcd7a403 |
publicationDate |
2021-11-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-113591816-A |
titleOfInvention |
Hyperspectral anomaly detection method and system based on self-supervised guided coding network |
abstract |
Embodiments of the present invention provide a method and system for detecting hyperspectral anomalies based on a self-supervised guided coding network, which uses hyperspectral data of various items to synthesize hyperspectral data of normal target detection objects to generate artificial abnormal spectral data; and uses a self-coding network It is jointly optimized with the self-supervised classifier. The self-supervised classifier uses the encoded features obtained by the self-encoding network as input to classify normal features and artificial abnormal features, so that the self-supervised classifier can guide the self-encoding network. Anomaly detection with more meaningful low-dimensional features. Compared with the traditional auto-encoding reconstruction error method, this method can significantly improve the anomaly detection accuracy. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114445720-A |
priorityDate |
2021-09-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |