Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d9de52bba13e16028dffa8775e3f3f28 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-194 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-13 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2135 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-251 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-32 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate |
2020-07-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_448cb3860958cbfb0b898013b31abb8b http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_005518ef5d359ad89ec2698963ca33ef http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9f907f48d521e4b6ccc5c9a1f8e1a2a2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8c60d916c8a1cc769ae9cdf64e690671 |
publicationDate |
2020-11-06-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-111898534-A |
titleOfInvention |
A spaceborne target fusion detection method based on rotating region convolutional neural network |
abstract |
The invention discloses a spaceborne target fusion detection method based on a rotating area convolutional neural network, and relates to the field of spaceborne target detection. It is oriented to intelligent computing platforms such as general-purpose parallel computing architecture processors, field programmable gate arrays, and system-on-chip (SOC). First, the panchromatic (PAN) image and the multi-spectral (MS) image are fused by the panchromatic sharpening method, and then the object detection based on the rotating region convolutional neural network is used for the fused spaceborne image. framework to detect objects in it. The object detection framework is based on the Faster R‑CNN structure. The invention improves the detection accuracy of small targets in multi-source spaceborne images, the target detection framework has better generalization ability, and can be widely used in target detection, security monitoring and other fields. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112381062-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112434745-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112434745-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115346133-A |
priorityDate |
2020-07-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |