Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e4463c01a3ae0fffbe8002848c98ac9b |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate |
2021-06-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2b31fe819fb52f3b6923581e011ac781 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e5e5bfb6f37e6b2418c3a21462ca62c4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b473fb77045066e7b2a33473dc881718 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f6ab7442ba2c67398ba556c3456df03b http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e3071657ea9b3291ac8869cc1ae089c1 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f4e72ff2fcc7e2d6034b66dbc1c2e22c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8f8fdde2b14c55f152256e9ef7502d57 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_714c6f35e3ad2951ecdb8ac8b4a0ff6f |
publicationDate |
2021-09-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-113435284-A |
titleOfInvention |
Post-disaster road extraction method based on dynamic filtering and multi-directional attention fusion |
abstract |
The invention relates to the technical field of road extraction from remote sensing images, in particular to a post-disaster road extraction method based on dynamic filtering and multi-directional attention fusion. Including collecting remote sensing image data of the study area; inputting the remote sensing influence data into the pre-trained DCCA network model; The data is processed to obtain a dataset containing images and labeled images; the CCA network model and the RCCA network model are used to pay attention to the direction information of the image features, and the output direction attention information energy and network extraction result output respectively; The model and the RCCA network model are trained; based on the CCA network model and the RCCA network model, the direction of the respective output of the image features focuses on the information energy and the network extraction result output, and the CCA network model and the RCCA network model are integrated to obtain the DCCA network model. |
priorityDate |
2021-06-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |