http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109558872-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-625 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-56 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-63 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V20-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-56 |
| filingDate | 2018-11-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2022-02-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2022-02-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-109558872-B |
| titleOfInvention | A vehicle color recognition method |
| abstract | The invention discloses a vehicle color recognition method, which includes the following steps: S1: acquiring vehicle color images of white, gray, black, red, pink, yellow, green, blue, purple and brown as training samples; S2: using LIBSVM The linear SVM in the toolbox performs pair-by-pair classification training on the training samples to obtain 45 color classifiers; S3: Perform license plate recognition on the captured frontal image of the vehicle, and obtain a 70×70 pixel color image of the vehicle to be recognized according to the size of the license plate. S4: Obtain the feature vector of the color image of the vehicle to be recognized, and send it to the classifier trained in S2 to determine the vehicle color category. The advantages of the present invention are: the global color information is adopted, which reflects the brightness and chromaticity contrast between the vehicle body and the environment, improves the accuracy of identification, reduces the difficulty of the algorithm and the computational complexity, and overcomes the high difficulty of positioning and easy loss in the prior art. The defects of the information can more accurately represent the color attributes, the structure is simple, the training is easy, and the calculation speed is fast. |
| priorityDate | 2018-11-22-04:00^^<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/CID16013 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID454405548 |
Total number of triples: 18.