http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110009000-B

Outgoing Links

Predicate Object
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02P90-30
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-467
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-40
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-40
filingDate 2019-03-11-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2022-09-02-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2022-09-02-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-110009000-B
titleOfInvention Grain heap target detection method based on ADABOOST+SVM improved classification algorithm
abstract The invention provides a grain pile target detection method based on an ADABOOST+SVM improved classification algorithm, and relates to the technical field of granary robot vision. The steps of the present invention are as follows: Step 1: establish an identification model of the grain pile; Step 2: collect a group of pictures of the actual scene of the granary through image acquisition equipment; Compare, and store the successfully detected candidate regions; Step 4: Arrange the candidate regions according to the similarity, select the f grain piles with the largest similarity, perform secondary discrimination on the color image, and output the color of the marked frame selection area. Image; Step 5: Obtain the parameter set through the color image, calculate the bottom width of the grain pile according to the parameter set, and store the width of the grain pile, the distance between the grain pile mass center and the camera, and the included angle azimuth between the grain pile mass center and the camera. The method realizes the accurate and rapid identification of grain piles, and also reduces the cost of manual closing operations.
priorityDate 2019-03-11-04:00^^<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/CID783
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID425193155

Total number of triples: 16.