http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109461173-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-246 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-269 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-269 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-246 |
| filingDate | 2018-10-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2022-03-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2022-03-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-109461173-B |
| titleOfInvention | Rapid corner detection method for time domain vision sensor signal processing |
| abstract | The invention discloses a rapid corner detection method for time domain vision sensor signal processing, which is different from a frame sampling imaging mode, wherein a vision sensor is only sensitive to light intensity change in a shooting scene, the output vision information has the characteristics of real time, extremely low redundancy and small data volume, the processing operation amount and the storage requirement are greatly reduced compared with the traditional frame sampling imaging, and the method is more suitable for high-speed vision application. The invention adopts an event-driven mode and judges whether each input event is generated by an angular point or not according to the time-space correlation among the events. In the calculation process, a local nearest event distribution map with an input event as a center is constructed, and then partition statistics and binarization processing are carried out on the local nearest event distribution map. And judging whether the input event is generated by the corner point by adopting a table lookup method according to the obtained partitioned binary representation. Besides angular point detection, the method can simultaneously judge the direction and the type of the angular point, and provide richer characteristic information for further target identification. |
| priorityDate | 2018-10-25-04:00^^<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/SID419547010 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID24563 |
Total number of triples: 14.