http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109063577-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d6a6f422b091ba12ea61d4adbf1b0e8e |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-267 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-188 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-34 |
| filingDate | 2018-07-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_00d543400e54725b9653396a75435064 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5a43a496e4f85a89bb8b1b102c14cf27 |
| publicationDate | 2018-12-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-109063577-A |
| titleOfInvention | Optimum Segmentation Scale Determination Method for Satellite Imagery Segmentation Based on Information Gain Rate |
| abstract | The invention discloses a method for determining the optimal segmentation scale of satellite image segmentation based on information gain rate, which includes: obtaining high-resolution satellite remote sensing images, performing preprocessing, and selecting representative regions as samples for determining the optimal segmentation scale. area, and classify the types of ground objects in the sample area, obtain the image classification results of the sample area, and use it as a reference image for determining the optimal segmentation scale; set a series of segmentation scale parameters from small to large, and use multi-scale segmentation technology to separate samples Multi-scale segmentation of regional images to obtain a series of segmented object vectors; based on the Shannon information entropy formula, calculate the information entropy of the reference image and the segmented vector, and calculate the conditional entropy after the reference image is added to the segmented vector, and then calculate the information gain of the segmented vector and Information gain rate; select the best segmentation scale according to the principle of maximum information gain rate. Finally, based on the optimal segmentation scale, multi-scale segmentation is performed on the original image. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110428013-A |
| priorityDate | 2018-07-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 25.