http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114758030-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_be2c55a9de09e08e3404c0a5a1ae4dc7 |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20221 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 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/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T11-005 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-006 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-007 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-50 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T11-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 |
| filingDate | 2022-04-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6a845f3f01fcb3b80309883833f291f2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_29e889a268f396ef957090cc46059aec http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_55ea5d6cb25505d54ae229eca817a8ae http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9b1f7285b13b6cfb0cff08f32f863e12 |
| publicationDate | 2022-07-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-114758030-A |
| titleOfInvention | An underwater polarization imaging method that combines physical models and deep learning |
| abstract | The invention discloses an underwater polarization image de-scattering method integrating physical model and deep learning, which includes constructing a polarization image data set under turbid underwater; preprocessing original polarization image data; The core network is used to obtain the output polarization modulation parameters and the underwater imaging polarization de-scattering correction model; and based on the polarization modulation parameters and the underwater imaging polarization de-scattering correction model, the restored clear images are calculated; the network is optimized using the polarization-aware loss function , using the deep features of the predicted image and the clear polarized image for better image restoration. The invention integrates the physical model of underwater polarization imaging into the deep neural network, better constrains the training of the neural network through the physical model, realizes the unification of the training process and physical laws, and uses the polarization perception loss function to constrain the model to realize water scattering The improvement of imaging contrast and imaging distance in the environment is especially suitable for image restoration in high turbidity underwater environment. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115147394-A |
| priorityDate | 2022-04-29-04:00^^<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/SID419512635 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID962 |
Total number of triples: 29.