http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113887588-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_edba331323cc8ac15a87318e17019827
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_245a9f62d3415780f368e9a942b76dcc
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62
filingDate 2021-09-17-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_206004b0d97532a06a1ef873b6df2588
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f9c08b1a14fecd92fc01adbb66989bf8
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0f863671afe475513e8e0fb14159b77e
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_98505d0ba7cb7eb01bc53a02979b4ffd
publicationDate 2022-01-04-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-113887588-A
titleOfInvention Vehicle detection method and device based on attention mechanism and feature weighted fusion
abstract The invention discloses a vehicle detection method and device based on an attention mechanism and feature weighted fusion. The method includes: preprocessing an image to be detected; inputting the preprocessed image to be detected into a pretrained vehicle detection model; Using the vehicle detection model, based on the preprocessed image to be detected, the channel and spatial two-dimensional attention mechanism is used to generate the channel attention feature map and the spatial attention feature map; through the weighted bidirectional feature fusion network, based on the channel attention feature map With the spatial attention feature map, differentiated feature fusion is performed to obtain fusion features; based on the fusion features, detection results containing vehicle location and size information are obtained. Compared with the existing vehicle detection technology, the present invention reduces the amount of parameters and improves the detection accuracy while maintaining a relatively fast detection speed, especially for the detection of small-scale vehicles.
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114241792-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114677597-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114677597-B
priorityDate 2021-09-17-04:00^^<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/CID28718
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419513094

Total number of triples: 25.