Title:
MULTIPLE-PEDESTRIAN TRACKING METHOD AND SYSTEM USING TEACHER-STUDENT RANDOM FERN
Document Type and Number:
WIPO Patent Application WO/2020/085653
Kind Code:
A1
Abstract:
According to a multiple-pedestrian tracking method and system using a teacher-student random fern provided in the present invention, by extracting the feature values of pedestrians by means of tiny YOLO which is a type of depth network, and learning a random fern by means of the extracted feature values, real-time learning is made possible and erroneous tracking due to changes in the shapes and sizes of the pedestrians can be minimized.
Inventors:
KO BYOUNG CHUL (KR)
NAM JAE YEAL (KR)
KIM SANG JUN (KR)
NAM JAE YEAL (KR)
KIM SANG JUN (KR)
Application Number:
PCT/KR2019/012101
Publication Date:
April 30, 2020
Filing Date:
September 18, 2019
Export Citation:
Assignee:
UNIV KEIMYUNG IACF (KR)
International Classes:
G06K9/00; G06K9/46; G06N3/04; G06N3/08
Foreign References:
JP2018060511A | 2018-04-12 | |||
KR20160132731A | 2016-11-21 | |||
KR101771146B1 | 2017-08-24 | |||
KR20170028591A | 2017-03-14 |
Other References:
SON , SE JI: "YOLO : Real-Time Object Detection DY N DY", LET'S PRACTICE YOLO : REAL-TIME OBJECT DETECTION. DY N DY, 19 October 2016 (2016-10-19), pages 1 - 7
Attorney, Agent or Firm:
KIM, Keon Woo (KR)
Download PDF: