Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_3128c49d9d6cc01c2654df8950f4399b |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20016 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20132 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-12 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-12 |
filingDate |
2021-12-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_99e537760ab96beb7873ebc2891e703e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_06a401c9887c73475601f5e33b848879 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4dd1c8fbda9a58c896d5ba0c1814a34a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f6aa1f44568d2c0064deeaecea902a01 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a295207311009c2241216f34a7e5f575 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_89b542befd204689af71c91e4ae5655f http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b052d25d2a2f2844f7c33a41df0d7a92 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9d43d60bd6668a6f1bbf676d6d281ba8 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_efa3e06825fc957c48cb3b1026e68314 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_067f709efa6881b2159769201ff1e5ef http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0ccdd2ceef626b5ed59d6cded519c6c3 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6a1ecdc86552732a6f46e2e0b905c63a |
publicationDate |
2022-05-20-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-114519723-A |
titleOfInvention |
An automatic extraction method of craters based on pyramid image segmentation |
abstract |
The invention relates to the technical field of artificial intelligence, and discloses an automatic crater extraction method based on pyramid image segmentation. All layer images of the crater are adjusted to a uniform size, and then the images of each layer are input into the U-Net neural network model one by one from the bottom to the top layer to segment the edges of the craters, and then the template matching algorithm is used to extract the pixel matrix of each crater based on the current pyramid image. Pixel center coordinates and size, and finally use the conversion relationship to calculate the actual latitude and longitude center coordinates and radius of each crater. The existing crater segmentation and extraction methods are improved to make them suitable for the accurate extraction of multi-scale craters in lunar DEM, and provide support for a more complete crater catalogue and spacecraft site selection and landing. |
priorityDate |
2021-12-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |