Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_18086029ee284d70cc9ce46d117d4ff3 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4053 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4076 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4046 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T3-40 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate |
2021-04-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_68cf81e250176d5367631d116ea2b9b0 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5db7a10d4af5e2a675ac5abd7e5e4e10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0218d35606860ecab94749edc388b290 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c5a51f40845fdf6e7b8c76b0f1ec7410 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c51f24c0b8c61c43e03a646b146326ca http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e7aead4aab8d97dd4fa166095a7b2a1e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ed0864b4d2e617186b0c1b73571cc0ca |
publicationDate |
2021-05-14-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-112801881-A |
titleOfInvention |
A high-resolution hyperspectral computational imaging method, system and medium |
abstract |
The invention discloses a high-resolution hyperspectral computational imaging method, system and medium. The method comprises: performing spectral upsampling on an input RGB image Y to obtain an initial hyperspectral image X 0 ; inputting the initial hyperspectral image X 0 To the deep convolutional neural network guided by the pre-trained imaging model, the hyperspectral image X is obtained by iterative solution. The deep convolutional neural network is composed of multiple modules with the same structure cascaded, and each module is composed of a hyperspectral prior. The learning module HPL and the imaging model guidance module IMG are formed, and the hyperspectral prior learning module HPL is used to learn the prior features of the previous module or the upsampling result of the initial hyperspectral image X 0 . The invention can effectively realize the reconstruction of RGB images to high-resolution hyperspectral images, and has the advantages of high reconstruction accuracy, high calculation efficiency, low memory consumption and strong generalization ability. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2022217746-A1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114998109-A |
priorityDate |
2021-04-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |