http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-107240073-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20221 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10021 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20152 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23213 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-005 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-50 |
| filingDate | 2017-05-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2020-04-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2020-04-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-107240073-B |
| titleOfInvention | A 3D Video Image Inpainting Method Based on Gradient Fusion and Clustering |
| abstract | The invention discloses a three-dimensional video image restoration method based on gradient fusion and clustering, which is carried out according to the following steps: step 1, constructing a gradient image; step 2, using K-means clustering to obtain foreground markers; step 3, extracting foreground and Fix filling voids. In the traditional watershed algorithm, due to the influence of pseudo-local minima on segmentation, it is easy to produce severe over-segmentation. The invention provides a three-dimensional video image hole filling method based on gradient fusion and clustering based on the watershed algorithm, marker extraction, gradient map construction, front/background extraction and other angles. Combining the gradient information of the color map and the depth map can better consider the color characteristics of the color image and the geometric characteristics of the fusion depth image, and can effectively express the gradient of the image; K-means clustering is used to mark the foreground of the depth map to suppress the watershed. over-segmentation. |
| priorityDate | 2017-05-12-04:00^^<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/CID479499 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID415975647 |
Total number of triples: 19.