http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109299652-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_9d202e64d0b4f9009b6087a489c7a8d0 |
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-462 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23213 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q50-06 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-73 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q50-06 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-73 |
filingDate | 2018-07-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a0ff7918e91eddf392d1fb1b33420754 |
publicationDate | 2019-02-01-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-109299652-A |
titleOfInvention | A model training method for image positioning, image positioning method and device |
abstract | The invention discloses a model training method for image positioning, an image positioning method and a device, wherein the model training method for image positioning comprises the following steps: extracting the to-be-located area and the non-to-be-determined area in several pre-collected images The SURF feature points of the bit region form the first visual dictionary and the second visual dictionary respectively; extract the SURF feature points of the to-be-located region in a standard image to form the original feature set; combine the feature points in the original feature set with the first visual dictionary Match the feature points of the original feature points, and remove the wrongly matched feature points from the original feature set to obtain a standard feature set; complete the training of the model. When the feature set of the to-be-located area in an image to be recognized is mapped to the standard feature set, that is, when the to-be-recognized image is mapped to the model, the to-be-located area in the to-be-recognized image can be obtained through the to-be-located area in the model, Enables the model to be used to locate different devices of the same class without having to model it over and over again. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113984072-A |
priorityDate | 2018-07-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 25.