http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110232314-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_6fbb91e3f8cdf858527814216aa11142 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V40-103 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
filingDate | 2019-04-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_cf63de727c632046f5fd460b8e1d6aa1 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_fb80aebf37e46a67caeaac1d8acae8b7 |
publicationDate | 2019-09-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110232314-A |
titleOfInvention | An image pedestrian detection method based on improved Hog feature combined with neural network |
abstract | The invention discloses an image pedestrian detection method based on an improved Hog feature combined with a neural network. The image pixel gradient is calculated by using a directional controllable filter algorithm to improve the operation rate. In addition, when detecting pedestrians, instead of using a fixed window to slide the entire image for detection, the frame difference method is used to determine the motion area first, and the motion area is scaled to a certain extent, and the detection is performed in the area to reduce the computational cost. time and improve detection efficiency. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113163110-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113163110-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112488039-A |
priorityDate | 2019-04-28-04:00^^<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/SID419474851 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID21855 |
Total number of triples: 19.