http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108492288-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_217f2be73fd6be0be36dd55803d3bec5 |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10032 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24323 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
| filingDate | 2018-03-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4068cb58704cfb8745a44486bec2a0f3 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b922d8192ab80d82ec957efa36a37aa4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0787392fb15d4540535d6759ecdaa4e6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7c7a219b4ce07b7c1474a248fa0ad792 |
| publicationDate | 2018-09-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-108492288-A |
| titleOfInvention | High-resolution satellite image change detection method based on random forest multi-scale layered sampling |
| abstract | The invention discloses a high-resolution satellite image change detection method based on multi-scale layered sampling of random forest. The method adopts the idea of object-oriented, performs multi-scale layered sampling to automatically obtain multi-scale training samples, and subscales samples Combine with the current scale sample; then extract the training sample spectrum, texture and shape features are fused together to form a feature space, and input the sample combination and the corresponding feature space into the random forest to train multiple change classifiers, and choose the smallest out-of-bag error parameter The classifier of , as a change detection classifier, performs change detection. Compared with the traditional method, the present invention proposes a multi-scale layered sampling method, which considers the multi-scale feature information, automatically increases the training samples for the changing area and the non-changing area without increasing the manual workload, and improves the training efficiency. The feature generalization ability of the sample, and the classification for change detection, the method is simple, the operability is strong, and it has good scalability. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109740645-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110717531-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109816707-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111723712-A |
| priorityDate | 2018-03-15-04:00^^<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/CID3001055 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419580923 |
Total number of triples: 26.