http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110110586-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_a3ae0b029a35c098ec960159a01de142 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-13 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23213 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
filingDate | 2019-03-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8e4ce6a8bc60739df936ae181a7e993d http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bd85708637a4f29381ac1828f3409ed2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_494f0a533687d47339e6ccfab5cbfce7 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d9ea115a4fca8677180255b60395ab2c |
publicationDate | 2019-08-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110110586-A |
titleOfInvention | Method and device for remote sensing airport aircraft detection based on deep learning |
abstract | The embodiment of the present invention provides a method and device for remote sensing airport aircraft detection based on deep learning, including: acquiring an input remote sensing airport image with a large field of view; Contour, determine the slice of the airport candidate area; extract the features of the airport candidate area according to the determined slice of the airport candidate area, use the K-means clustering algorithm to cluster the extracted features, obtain the feature combination of the airport, and use the support vector machine to classify The machine screens out the suspected airport candidate area; uses the portable network algorithm to extract the aircraft target from the screened suspected airport candidate area, calculates the position of the aircraft target in the acquired remote sensing airport image, and obtains the position information of the aircraft target. The method of value suppression eliminates overlapping coordinate boxes. The embodiment of the present invention combines machine learning and deep learning to realize accurate and rapid detection of large field of view remote sensing airport aircraft. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111340815-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111862006-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111881831-A |
priorityDate | 2019-03-18-04:00^^<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/substance/SID419580923 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID3001055 |
Total number of triples: 22.