Title:
TARGET TRACKING METHOD, TARGET TRACKING SYSTEM, AND TARGET TRACKING PROGRAM
Document Type and Number:
WIPO Patent Application WO/2020/080535
Kind Code:
A1
Abstract:
In step S1, at least one target in a moving image is recognized at a first frame rate by means of a learning recognition technique. In step S2, an ROI position is initialized on the basis of the target recognized by means of the learning recognition technique. In step S3, the target is tracked in the moving image on the basis of the ROI position at a second frame rate higher than the first frame rate, by template matching employing a template. In step S4, a difference between the ROI in a frame at the point in time at which the target was recognized by means of the learning recognition technique, and the ROI in frames up to the present time, resulting from the continuation of template matching at the second frame rate, is adjusted.
Inventors:
ISHII IDAKU (JP)
KISHI NORIMASA (JP)
JIANG MINGJUN (JP)
KISHI NORIMASA (JP)
JIANG MINGJUN (JP)
Application Number:
PCT/JP2019/041143
Publication Date:
April 23, 2020
Filing Date:
October 18, 2019
Export Citation:
Assignee:
JAPAN SCIENCE & TECH AGENCY (JP)
International Classes:
G06T7/00
Other References:
JIANG, M. ET AL.: "High-frame-rate Target Tracking with CNN-based Object Recognition", PROCEEDINGS OF THE 2018 IEEE /RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS, 5 October 2018 (2018-10-05), pages 599 - 606, XP033491570, ISBN: 978-1-5386-8094-0, DOI: 10.1109/IROS.2018.8594300
"High-speed Target Tracking Using Deep Learning", PROCEEDINGS OF THE 2018 JSME CONFERENCE ON ROBOTICS AND MECHATRONICS, 1 June 2018 (2018-06-01), Tokyo, pages 1 - 4
LAO, M. ET AL.: "Visual Target Detection and Tracking Framework Using Deep Convolutional Neural Networks for Micro Aerial Vehicles", PROCEEDINGS OF THE 2018 IEEE 14TH INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA, 15 June 2018 (2018-06-15), pages 276 - 281, XP033388970, ISBN: 978-1-5386-6089-8, DOI: 10.1109/ICCA.2018.8444232
"High-speed Target Tracking Using Deep Learning", PROCEEDINGS OF THE 2018 JSME CONFERENCE ON ROBOTICS AND MECHATRONICS, 1 June 2018 (2018-06-01), Tokyo, pages 1 - 4
LAO, M. ET AL.: "Visual Target Detection and Tracking Framework Using Deep Convolutional Neural Networks for Micro Aerial Vehicles", PROCEEDINGS OF THE 2018 IEEE 14TH INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA, 15 June 2018 (2018-06-15), pages 276 - 281, XP033388970, ISBN: 978-1-5386-6089-8, DOI: 10.1109/ICCA.2018.8444232
Attorney, Agent or Firm:
MORISHITA Sakaki (JP)
Download PDF:
Previous Patent: PHENYLPYRAZOLE COMPOUND AND METHOD FOR CONTROLLING PLANT DISEASE
Next Patent: ENGINE MOUNT STOPPER AND ENGINE SUPPORT STRUCTURE
Next Patent: ENGINE MOUNT STOPPER AND ENGINE SUPPORT STRUCTURE