Presentation | 2015-02-23 Human Tracking Method by Particle Filter Using ORB Feature Value Kota ITO, Akira KUBOTA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Human tracking techniques have been attracted in security and marketing applications. In this report, we present a learning-based human tracking method that is more robust against occluding scenes. The conventional method using particle filtering often fails in tracking for humans who are occluded each other. In the presented method, by using ORB feature and Real Adaboost learning, we tackle this miss-tracking problem. The experiments using 5 occluding scenes show that the tracking accuracy was much improved by the presented method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Particle Filter / ORB / Real Adaboost |
Paper # | ITS2014-56,IE2014-83 |
Date of Issue |
Conference Information | |
Committee | IE |
---|---|
Conference Date | 2015/2/16(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Image Engineering (IE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Human Tracking Method by Particle Filter Using ORB Feature Value |
Sub Title (in English) | |
Keyword(1) | Particle Filter |
Keyword(2) | ORB |
Keyword(3) | Real Adaboost |
1st Author's Name | Kota ITO |
1st Author's Affiliation | Faculty of Engineering, Chuo University() |
2nd Author's Name | Akira KUBOTA |
2nd Author's Affiliation | Faculty of Engineering, Chuo University |
Date | 2015-02-23 |
Paper # | ITS2014-56,IE2014-83 |
Volume (vol) | vol.114 |
Number (no) | 460 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |