http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111739079-B

Outgoing Links

Predicate Object
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10028
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/G06T7-55
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-55
filingDate 2020-06-18-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2022-10-11-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2022-10-11-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-111739079-B
titleOfInvention A fast matching method for multi-source low-altitude stereo pairs based on semantic features
abstract The invention discloses a fast matching method for multi-source stereo image pairs based on semantic features. First, a multi-scale difference of Convolutional Layers (DoC) is constructed to extract the multi-scale high-frequency information of the image to detect stable extreme points, and the scale-space DoC function is used to perform the curve fitting equation to accurately locate the feature points. It is detected by low-level-high-level semantic features; then, the range of local feature support areas is determined based on the scale of semantic feature points; finally, the semantic feature points are quickly measured by a deep convolutional neural network wedged into a multi-level similarity measure module, and The RANSAC algorithm combined with the geometric constraints of the kernel removes the mismatched points and gross errors. The invention solves the fast matching problem of semantic feature scale invariance under the condition of wide baseline, large inclination angle and background nonlinear change of multi-source stereo images.
priorityDate 2020-06-18-04:00^^<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/compound/CID60825
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419582621

Total number of triples: 19.