# US 12,762,895 B2 · Non-transitory computer readable medium, information processing device, and computer-implemented method for estimating revolutions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,762,895 B2 - Document ID: US12762895B2 - Status: Granted - Kind: B2 - Application number: 18/686,431 - Filed: 2022-08-22 - Published: 2024-10-24 - Granted: 2026-10-13 - Earliest claimed: 2021-08-26 - Assignees: CaTe Inc. - Applicants: CaTe Inc. - Inventors: Kazuhiro Terashima - Web page: https://patentgrep.com/patent/US12762895B2 ## CPC - G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) - G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A program according to an aspect of the present disclosure causes a computer to function as means for acquiring a user video of a user exercising, and means for making an estimation regarding the number of leg revolutions of the user based on the user video. ## Claims ### Claim 1 A non-transitory computer readable medium storing a program that causes a computer to perform operations comprising: acquiring a user video of a user exercising, and depth data indicating a distance to the user detected by a depth sensor; acquiring skeleton data of at least a lower body of the user based on the user video and the depth data; and making an estimation regarding a number of leg revolutions of the user based on analyzing the skeleton data. ### Claim 2 (depends on 1) A non-transitory computer readable medium according to claim 1, wherein making an estimation regarding the number of leg revolutions includes applying an estimation model to input data including the skeleton data. ### Claim 3 (depends on 2) A non-transitory computer readable medium according to claim 2, wherein the estimation model corresponds to a trained model created by supervised training using a labeled dataset containing training input data including data regarding a subject video of a subject exercising and correct data associated with each item of the training input data, or a derived model or a distillation model of the trained model. ### Claim 4 (depends on 3) A non-transitory computer readable medium according to claim 3, wherein making an estimation regarding the number of leg revolutions includes at least one of: cumulative number of leg revolutions, rotational speed, rotational acceleration, or travel distance converted from the cumulative number of leg revolutions. ### Claim 5 (depends on 2) A non-transitory computer readable medium according to claim 2, wherein making an estimation regarding the number of leg revolutions includes at least one of: cumulative number of leg revolutions, rotational speed, rotational acceleration, or travel distance converted from the cumulative number of leg revolutions. ### Claim 6 (depends on 1) A non-transitory computer readable medium according to claim 1, wherein making an estimation regarding the number of leg revolutions includes at least one of: cumulative number of leg revolutions, rotational speed, rotational acceleration, or travel distance converted from the cumulative number of leg revolutions. ### Claim 7 (depends on 1) A non-transitory computer readable medium according to claim 1, wherein the user video is a video of the user pedaling. ### Claim 8 (depends on 1) A non-transitory computer readable medium according to claim 1, wherein the operations further comprise presenting information based on a result of the estimation regarding the number of leg revolutions of the user. ### Claim 9 (depends on 8) A non-transitory computer readable medium according to claim 8, wherein making an estimation regarding the number of leg revolutions includes estimating an evaluation metric regarding the number of leg revolutions, and the operations further comprise presenting the evaluation metric. ### Claim 10 (depends on 9) A non-transitory computer readable medium according to claim 9, wherein presenting the evaluation metric includes presenting change over time of the evaluation metric. ### Claim 11 An information processing device comprising: a memory storing instructions; and a processor configured to execute the instructions to perform operations comprising: acquiring a user video of a user exercising and depth data indicating a distance to the user detected by a depth sensor; acquiring skeleton data of at least a lower body of the user based on the user video and the depth data; and making an estimation regarding a number of leg revolutions of the user based on analyzing the skeleton data. ### Claim 12 A computer-implemented method comprising acquiring, by a computer, a user video of a user exercising and depth data indicating a distance to the user detected by a depth sensor; acquiring, by the computer, skeleton data of at least a lower body of the user based on the user video and the depth data; and making, by the computer, an estimation regarding a number of leg revolutions of the user based on analyzing the skeleton data.