http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113673299-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e7a740c78008dda19229e51adb914aec |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2431 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate | 2021-06-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3a402c8d16f00cccf4ddcc698698651e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8579fef509663279c16ec2ed1577331a |
publicationDate | 2021-11-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113673299-A |
titleOfInvention | A detection method of small animals in power distribution room based on deep semantic feature extraction |
abstract | The invention relates to the technical field of power distribution room safety, and discloses a method for detecting small animals in power distribution rooms based on deep semantic feature extraction. The set is marked as animal or not according to whether the image content is an animal; S2: the design of the deep neural network structure, the deep neural network adopts the ResNet50 network; S3: the training of the deep neural network. The present invention uses the existing data set without the need for additional data in the power distribution room environment, extracts the semantic information of the general concept of animals from the information of different animals through the deep learning with the ResNet50 network as the frame, and uses it for distribution. The intelligent detection of the electric room can effectively reduce the error of manual inspection, and make the whole detection process intelligent, reduce the consumption of personnel and significantly improve the detection efficiency. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115755954-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115755954-A |
priorityDate | 2021-06-23-04:00^^<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/CID19402 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419513998 |
Total number of triples: 22.