http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108648233-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30164 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/G06T2207-10024 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-74 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23213 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-194 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-762 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-73 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-194 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 |
| filingDate | 2018-03-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2022-04-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2022-04-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-108648233-B |
| titleOfInvention | A deep learning-based target recognition and grasping localization method |
| abstract | The invention discloses a target recognition and grasping positioning method based on deep learning, which belongs to the field of machine vision. First, use the Kinect camera to collect the depth and color images of the scene, and then use the Faster R‑CNN deep learning algorithm to identify the scene target, select the target area to be captured according to the identified category, and use it as the input of the GrabCut image segmentation algorithm to obtain through image segmentation. The contour of the target is obtained, and then the specific position of the target is obtained, which is used as the input of the cascaded neural network to detect the optimal grasping position, and finally the grasping position and grasping posture of the robotic arm are obtained. Through this method, the real-time performance, accuracy and intelligence of target recognition and positioning are improved. |
| priorityDate | 2018-03-24-04:00^^<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/SID419535645 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID43672 |
Total number of triples: 25.