http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20160093341-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_87d40fb4785f5b3f1a4dba8c69339d1a |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02A90-30 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01C11-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-00 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01C11-00 |
| filingDate | 2015-01-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a0033fd66dbcacde8d187bfbb4c307b6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_47d4aa05ed690b523a7efb3f32b358f4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3b0810bcfdac08c6ee061f621ccfeb43 |
| publicationDate | 2016-08-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | KR-20160093341-A |
| titleOfInvention | Automatic river segmentation system and method using combination of satellite images and random forest classifiers |
| abstract | According to an aspect of the present invention, there is provided an automatic river detection system using a combination of a satellite image and a random forest classifier, the system comprising: an input module receiving a predetermined number of bands of a satellite image; A conversion module for converting the input image into TOA (Top Of Atmosphere) reflectivity and WI (Water Index) images; A feature extraction module for extracting a feature vector for a stream region from the transformed image; A learning module for learning a plurality of random forest classifiers using the extracted feature vectors; A test module for converting the input test image into a TOA reflectivity and a WI image, extracting a feature vector, applying the feature vector to the learned random forest classifiers, and obtaining a result value; And a detection module that combines the obtained result values and detects the detected result as an area of the river when the threshold value is exceeded. According to another aspect of the present invention, there is provided an automatic stream detection method using a satellite image and a random forest classifier. The automatic stream detection method includes: (1) receiving an image of a predetermined band among satellite images; (2) converting the input image into TOA (Top Of Atmosphere) reflectivity and WI (Water Index) images; (3) extracting a feature vector for a stream region from the transformed image; (4) learning a plurality of random forest classifiers using the extracted feature vectors; (5) transforming the input test image into a TOA reflectivity and a WI image, extracting a feature vector, and applying the feature vector to the learned random forest classifiers to obtain a result value; And (6) combining the obtained result values and detecting the result as an area of the river when the threshold value is exceeded. According to the automatic river detection system and method using the combination of the satellite image and the random forest classifier proposed in the present invention, TOA (Top Of Atmosphere) reflectivity and WI (water index) are extracted from the multispectral image of the satellite image as feature vectors , And learns multiple types of random forest classifiers using TOA reflectivity and WI instead of heuristic threshold or autonomous learning method and detects stream areas from test images using learned classifiers to automatically classify rivers automatically have. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20210064672-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20190115758-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200017583-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20220093914-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114022789-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200012373-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200063682-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-101976959-B1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-107527397-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200128966-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20190095847-A |
| priorityDate | 2015-01-29-04:00^^<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/substance/SID419512635 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID962 |
Total number of triples: 30.