http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-105740891-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-217 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
| filingDate | 2016-01-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2019-10-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2019-10-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-105740891-B |
| titleOfInvention | Object Detection Based on Multi-Level Feature Extraction and Context Model |
| abstract | Based on the multi-level feature extraction and the target detection of the context model, the model constructed by the present invention mainly counts the spatial position relationship between the images in the real picture, so that the correct rate of target detection can be improved. No matter whether the images are of the same category or different categories, there will be some specific spatial position relationships. First, select and search a picture to generate a large number of region proposals, then perform feature extraction on all the region proposals of each picture, using a 7-layer convolutional neural network, and finally classify with a support vector machine. The present invention provides a new method for finding the best object detection position. The main technical problem to be solved is to provide a new context model to replace the original non-maximum value suppression method to obtain better target detection accuracy. |
| priorityDate | 2016-01-27-04:00^^<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/CID6441250 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID426108734 |
Total number of triples: 13.