http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113378731-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/G06T2207-10032 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20132 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-13 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-13 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/G06N3-04 |
| filingDate | 2021-06-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ae8dcbecd16c1719b68556028d6f1626 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_cbcbede8c5f8216ff503d8f2092ac312 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_93803828b001cbf3c04f864f28b10d7b |
| publicationDate | 2021-09-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-113378731-A |
| titleOfInvention | Vector extraction method of green space water system based on convolutional neural network and edge energy constraint optimization |
| abstract | The invention provides an end-to-end green space water system vector extraction method based on convolution neural network and edge constraint energy optimization, and designs a green space water system extraction network architecture suitable for remote sensing images. The architecture includes the extraction and fusion of remote sensing image context features to realize the extraction of basic image features in the area to be processed; on the basis of extracting rich features, combining the convolution layer and the upsampling layer, and adopting an end-to-end energy-optimized iterative method, we obtain Finer and smoother green water system edges; finally fine-tuned to fine green water system edges using fully connected layers or graph convolution layers. In addition, the present invention adopts two kinds of losses, cross entropy and Dice loss, for semantic identification of green space water system, and constrains the identification results at the full convolution network end and the edge energy constraint optimization end, and proposes a multi-layer coordinate point matching loss function to achieve Constraints on the contour points enable the model to make the predicted nodes better approximate the ground-truth contour points. |
| priorityDate | 2021-06-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 25.