http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109359536-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V40-172 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V40-168 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-53 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V40-161 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 |
filingDate | 2018-09-14-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2020-07-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2020-07-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-109359536-B |
titleOfInvention | Passenger behavior monitoring method based on machine vision |
abstract | The invention discloses a method for monitoring passenger behavior based on machine vision, comprising the steps of: 1) capturing video images of passengers taking an escalator; 2) extracting a deformable component model DPM feature to describe the passenger's face; 3) using SVM to escalate the escalator Detecting passenger faces; 4) Using KCF to track the faces of escalator passengers; 5) Using an improved nearest neighbor matching method to match the results of face detection and tracking; 6) Establishing a face target detection intensity model, correcting Face detection results; 7) Monitor the behavior of passengers in the escalator by analyzing the strength of passenger detection, speed magnitude and speed direction. The method of the invention can detect and track the face target of passengers taking the escalator in real time, stably and accurately, and conduct behavior monitoring based on the face target information. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2022250970-A1 |
priorityDate | 2018-09-14-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 19.