http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112819794-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_215fd62f148bc5aab2bfc8e46ecd6126 |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20172 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/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
| filingDate | 2021-02-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_967b61d03e09808afbbf05881bd4d5a5 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1c1569cc03e0adcc7b64dca36128bfe6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5963fc9aa01b610bbce906f1ade347db http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2be9cc40ea7048f47937a3b984ac626a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3ca994dc5dd36a4f273382541570cbd6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9d3233e7eddd53d88585e73858af9c9c |
| publicationDate | 2021-05-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-112819794-A |
| titleOfInvention | A deep learning-based detection method for small celestial craters |
| abstract | The invention discloses a small celestial crater detection method based on deep learning, which belongs to the field of deep space detection. The implementation method of the invention is as follows: first, in order to effectively enhance and retain the characteristics of the crater, the local variance equalization algorithm is used to optimize the data set, and the affine transformation, mean filtering and other methods are used to enhance the data set, and small celestial bodies are obtained through deep learning network training. The crater detection model in the environment; secondly, for the problem of missed detection of small craters in high-resolution images, the predicted image is adaptively divided into several sub-images with overlapping areas and sent to the detection network respectively; The value suppression method removes redundant boxes and merges the prediction results. The method overcomes the problems of slow speed and low recognition rate of the traditional target detection method, is superior to the current mainstream target detection network, and can better complete the small celestial crater detection task. |
| priorityDate | 2021-02-04-04:00^^<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/CID1983 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419557597 |
Total number of triples: 25.