http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109345495-B

Outgoing Links

Predicate Object
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20221
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-50
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-50
filingDate 2018-09-11-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2021-06-15-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2021-06-15-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-109345495-B
titleOfInvention Image fusion method and device based on energy minimization and gradient regularization
abstract The invention provides a 2 Energy minimization sum 1 The gradient regularization image fusion method and device are used for acquiring infrared images and visible light images which come from the same scene and are subjected to image registration, performing multi-scale and multi-directional decomposition on the infrared images and the visible light images through NSST (non-subsampled contourlet transform), obtaining corresponding low-frequency subband coefficients and high-frequency subband coefficients, and aiming at the low-frequency subband coefficients reflecting energy information, adopting a method based on l 2 -an energy-minimized optimization model as a fusion rule; exploiting l-based basis for high-frequency subband coefficients reflecting texture information 1 The optimized model of the gradient regularization is used as a fusion rule, the hidden infrared significant target information is combined with the gradient texture information of the visible light through the two fusion rules, so that the final fusion image conforms to the human visual system, and a better fusion effect is obtained by perfectly combining the texture information of the visible light with the significance characteristics of the infrared image.
priorityDate 2018-09-11-04:00^^<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/SID419559532
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID24404

Total number of triples: 13.