http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109272484-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20056 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10016 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30192 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-254 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01W1-14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-41 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-254 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01W1-14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-41 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
filingDate | 2018-08-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2021-07-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2021-07-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-109272484-B |
titleOfInvention | A Rainfall Detection Method Based on Video Image |
abstract | The invention discloses a rainfall detection method based on video images, comprising the following steps: S1: adopting a single camera to collect water surface grayscale image sequences at fixed time intervals, and the water surface grayscale image sequences are divided into training sample images and images to be tested; The training sample images are divided into four categories: no rain, light rain, moderate rain, and heavy rain according to the amount of rainfall and annotated; S2: The image texture is enhanced by the method based on phase consistency, and the grayscale of the two frames of images at adjacent moments after the enhancement is performed. The residual image is obtained by difference; S3: Fast Fourier transform is performed on the residual image to obtain the residual magnitude spectrum, and then normalized to extract four features; S4: SVM classifier is trained according to the extracted residual magnitude spectrum features ; S5: Apply the generated SVM classifier to identify the rainfall type of the image to be tested. The invention has small calculation amount and low cost, and the result is intuitive and easy to verify. |
priorityDate | 2018-08-03-04:00^^<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/SID419512635 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID962 |
Total number of triples: 24.