US 11,810,306 B2
Motion classification model learning apparatus, motion classification apparatus, motion classification model learning method and program
Mariko Isogawa, Kanagawa (JP); Dan Mikami, Kanagawa (JP); Kosuke Takahashi, Kanagawa (JP); Hideaki Kimata, Kanagawa (JP); and Ayumi Matsumoto, Kanagawa (JP)
Assigned to NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
Appl. No. 17/059,121
Filed by NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
PCT Filed Apr. 23, 2019, PCT No. PCT/JP2019/017217
§ 371(c)(1), (2) Date Nov. 25, 2020,
PCT Pub. No. WO2019/230264, PCT Pub. Date Dec. 5, 2019.
Claims priority of application No. 2018-104669 (JP), filed on May 31, 2018.
Prior Publication US 2021/0225007 A1, Jul. 22, 2021
Int. Cl. G06T 7/20 (2017.01); G06N 3/08 (2023.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 40/20 (2022.01)
CPC G06T 7/20 (2013.01) [G06N 3/08 (2013.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/46 (2022.01); G06V 40/23 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A motion classification model learning apparatus comprising:
a training data acquisition part acquiring training data configured with pairs of video information about a motion that can be classified into any of a plurality of categories according to characteristics of the motion and category information that is a correct label corresponding to the video information,
wherein the motion is associated with:
a player playing a sport,
a worker engaged in a work, or
a machine manipulated by a person,
wherein, when the motion is associated with the player playing the sport, at least one category of the plurality of categories comprises:
the sport including the motion, or
the motion associated with the sport,
wherein, when the motion is associated with the worker engaged in the work, at least one category of the plurality of categories comprises:
the work associated with the motion, or
a work item associated with the work, and
wherein, when the motion is associated with the machine manipulated by the person, at least one category of the plurality of categories comprises:
the machine associated with the motion, or
the motion associated with the machine performing the work;
a motion history image generation part generating a motion history image of the video information; and
a model learning part learning a model that outputs a label that is the category information, with the motion history image as an input.