Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_2df384e38c54aa0bbff49095e7dedcfd |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30268 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20032 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2415 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-136 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-002 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-136 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
filingDate |
2021-06-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f6a7ce1b82b461f63226dc3e9d698083 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_803a0e0611b8a014e6d64671cdb47e7a |
publicationDate |
2021-09-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-113436157-A |
titleOfInvention |
A vehicle-mounted image recognition method for pantograph faults |
abstract |
The invention discloses a vehicle-mounted image recognition method for pantograph faults. Bow head positioning is realized by designing a bow head positioning model based on the principle of Faster R-CNN target detector, and in-transit detection is realized by applying ResNet and FPN. The complex background interference and the multi-scale detection of the pantograph solve the problem that the traditional image method has poor target detection effect in a complex and changing environment. The detection results under some extreme conditions show that the bow head detection designed by the present invention is effective The model has good robustness and generalization, and realizes fast detection and localization. The invention solves the problem of insufficient detection of the pantograph state by the current fixed-point detection system, and combines the image processing technology of deep learning with the traditional image template matching and other technologies to solve the problem of complex background interference in the detection of the vehicle-mounted image, and realizes a good robustness. The excellent on-board fault detection algorithm can improve the efficiency of image monitoring and recognition, and has the value of popularization and application. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114067106-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113989666-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115527170-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116109987-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114898229-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113989666-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114898229-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114067106-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114782441-A |
priorityDate |
2021-06-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |