WO2021132426A1 - スマートトレッドミル - Google Patents
スマートトレッドミル Download PDFInfo
- Publication number
- WO2021132426A1 WO2021132426A1 PCT/JP2020/048346 JP2020048346W WO2021132426A1 WO 2021132426 A1 WO2021132426 A1 WO 2021132426A1 JP 2020048346 W JP2020048346 W JP 2020048346W WO 2021132426 A1 WO2021132426 A1 WO 2021132426A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- treadmill
- target
- belt
- endless belt
- speed
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B22/00—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements
- A63B22/02—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B22/00—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements
- A63B22/02—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills
- A63B22/0235—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills driven by a motor
- A63B22/0242—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills driven by a motor with speed variation
- A63B22/025—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills driven by a motor with speed variation electrically, e.g. D.C. motors with variable speed control
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
- A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6895—Sport equipment
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B22/00—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements
- A63B22/02—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills
- A63B22/0292—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills separate for each leg, e.g. dual deck
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0003—Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0087—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0087—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load
- A63B2024/0093—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load the load of the exercise apparatus being controlled by performance parameters, e.g. distance or speed
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B2071/065—Visualisation of specific exercise parameters
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B2071/0658—Position or arrangement of display
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B22/00—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements
- A63B22/0015—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with an adjustable movement path of the support elements
- A63B22/0023—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with an adjustable movement path of the support elements the inclination of the main axis of the movement path being adjustable, e.g. the inclination of an endless band
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/05—Image processing for measuring physical parameters
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/10—Positions
- A63B2220/13—Relative positions
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/18—Inclination, slope or curvature
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/30—Speed
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/803—Motion sensors
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/806—Video cameras
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/807—Photo cameras
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/83—Special sensors, transducers or devices therefor characterised by the position of the sensor
- A63B2220/833—Sensors arranged on the exercise apparatus or sports implement
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B69/00—Training appliances or apparatus for special sports
- A63B69/0057—Means for physically limiting movements of body parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
- G06T2207/20044—Skeletonization; Medial axis transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Definitions
- the present invention relates to a treadmill, and more particularly to a smart treadmill having a motion capture function and a motion analysis function.
- the treadmill is a device widely used in exercise training and rehabilitation. Some treadmills are equipped with a force plate and a position detection sensor, and some treadmills control the speed of the treadmill according to the detection result (Patent Documents 1 to 9), but basically they have a single function. Most of them are products with (walking / running function). Therefore, when analyzing or evaluating the walking motion of the target on the treadmill, the treadmill is placed in the motion capture space to measure the motion of the target.
- optical motion capture and motion capture using an inertial sensor are known.
- Optical motion capture attaches multiple optical markers coated with retroreflective material to the target's body and captures the movement of the target with multiple cameras such as an infrared camera to capture the movement trajectory of the optical markers. Get the target action.
- optical motion capture using an infrared light source it is necessary to perform measurement in a space surrounded by a camera that is not affected by external light, and the measurement space is limited.
- markerless motion capture technology As used herein, the term “markerless” means that a marker or sensor worn on the subject's body is not used.
- a markerless motion capture technique a method of estimating a joint position from a distance image (depth image) and a method of estimating a joint position from an RGB image are known.
- the video motion capture technology Non-Patent Document 1 is a technology for completely unconstrained motion capture from images of a plurality of RGB cameras.
- the present invention aims to provide a high-performance treadmill by combining a treadmill and a markerless motion capture.
- the technical means adopted by the present invention is with the frame An endless belt that provides a walking surface on which the subject rests, Belt drive and Multiple cameras on the frame with adjustable orientation and / or position
- An operation data acquisition unit that acquires target operation data without markers using the image information acquired by each camera image, It is a motion capture integrated treadmill, equipped with.
- the treadmill includes a motion analysis unit that analyzes the motion of a target using the motion data.
- the motion analysis unit analyzes the motion of the target by using the motion information of the endless belt (velocity information and the inclination of the belt) in addition to the motion data.
- the treadmill includes a control unit that controls the operation of the treadmill based on the operation data.
- the operation of the treadmill includes the rotation of the endless belt and the tilting of the endless belt.
- the control unit A data generation unit that generates input data based on the operation data, A control signal generator that generates a control signal according to the input data, With The control signal is output to the belt drive unit to control the belt speed.
- the endless belt can be tilted by a tilt drive. The control unit outputs the control signal to the precursor tilt drive unit to control the belt tilt.
- the motion data acquisition unit acquires the spatial distribution of the likelihood of the certainty of the joint position of the target by using the image information of the target acquired in each camera image, and obtains the spatial distribution of the likelihood. Based on this, the 3D posture of the target in each frame is acquired. In one embodiment, in the subject, the distance between adjacent joints is obtained as a constant.
- the operation data acquisition unit Using the spatial distribution of likelihood, position candidates for one or more feature points corresponding to each feature point are obtained. By performing an optimization calculation based on inverse kinematics using the position candidates of the feature points and the articulated structure of the target, each joint angle of the target is obtained. By performing forward kinematics calculation using the joint angle, the position of the feature point including the target joint is acquired.
- the search range is a predetermined number of point clouds distributed three-dimensionally at predetermined intervals centered on the positions of the feature points.
- the spatial distribution of likelihood is used in the optimization calculation based on the inverse kinematics.
- the processing unit sets a search range for feature point position candidates using each feature point acquired in one or more frames, and a space of likelihood acquired in frame t + 1. The distribution is used to obtain one or more feature point position candidates for each joint position in frame t + 1.
- the processing unit The positions of the feature points are smoothed in the time direction using the positions of the plurality of feature points acquired in the other plurality of frames.
- Each joint angle of the target is obtained by performing an optimization calculation based on inverse kinematics using the position of the smoothed feature point and the articulated structure of the target. It is configured as follows.
- the treadmill according to the present invention can measure the motion of a walking or running object on the treadmill by simply installing a plurality of video cameras and executing a predetermined algorithm using a computer. With a simpler configuration, motion measurement and motion analysis can be performed in real time, and there is no need to attach markers to the target or prepare to install a large-scale motion capture space. The burden on the subject wearing the marker and the physiotherapist is greatly reduced, and the motion measurement and motion analysis of the subject can be performed with almost the same preparation as when using a normal treadmill.
- the motion capture by combining the treadmill and the markerless motion capture, it is possible to support all kinds of control based on the motion data acquired by the motion capture by using only one means called the motion capture.
- By performing motion analysis or treadmill motion control based on motion data measured by motion capture for example, in walking training, the work that was conventionally performed visually by a physical therapist can be handled by the treadmill function. Can be done.
- FIG. 1 It is a perspective view of the treadmill (double belt type) which concerns on this embodiment. It is a perspective view of the treadmill (single belt type) which concerns on this embodiment. It is a plan view and a side view of the treadmill shown in FIG. 1, and shows the first form of a camera arrangement. It is a top view and a side view of a treadmill, and shows the 2nd form of a camera arrangement. It is a top view and a side view of a treadmill, and shows the 3rd form of a camera arrangement.
- the first mounting structure of the camera posture is shown.
- the second mounting structure of the camera posture is shown.
- the smart treadmill includes a treadmill, a plurality of cameras, one or a plurality of computers, and a display. It is a red mill system.
- the treadmill includes an endless belt that provides a walking surface on which the object rests, a drive unit, and an operation unit.
- the smart treadmill further includes an operation data acquisition unit, an operation analysis unit, and a control unit, which are composed of a computer.
- the motion data acquisition unit is, for example, a markerless motion capture, and the motion data acquisition unit acquires time-series data of a 3D pose during a target exercise (for example, walking).
- the motion analysis unit outputs the analysis data by processing the motion data.
- the control unit controls the operation of the treadmill by outputting a predetermined command to the drive unit of the treadmill using the operation data and / and the analysis data.
- the treadmill has a base frame composed of a front base 1 and left and right side frames 2, a tread base 3 supported between the left and right side frames 2, and above and below the tread base 3. It is equipped with an endless belt (running belt) 4 that runs at a position.
- the endless belt 4 is wound around a front roller (drive roller) rotatably provided in front of the base frame and a rear roller (driven roller) rotatably provided in the base frame, and is wound on the upper side of the endless belt 4.
- the part forms a walking surface or a running surface (hereinafter, collectively referred to as a "walking surface").
- the endless belt 4 includes two endless belts (first belt 4A for the right foot and second belt 4B for the left foot) running in parallel. There is.
- the treadmill includes a first motor (not shown) for driving the first belt 4A and a second motor (not shown) for driving the second belt 4B.
- a double belt type treadmill is known and is disclosed in, for example, Patent Documents 2, 6 and 7.
- Patent Documents 2, 6 and 7. For a specific configuration, refer to the description in Patent Document 2 and Patent Document 7. it can.
- the endless belt 4 may be a single belt.
- the treadmill is located in the front base 1 and includes a belt drive unit including a motor, and the endless belt 4 is driven by driving the drive rollers by the belt drive unit.
- the rotation speed of the motor is variable, and the speed of the endless belt 4 can be adjusted by changing the rotation speed of the motor.
- the speed of the endless belt 4 can be adjusted by operation from an operation unit (not shown).
- the operation unit is provided with, for example, a start button, a stop button, a speed increase button, and a deceleration button.
- the operation unit may be provided with an inclination adjusting button for inclining the walking surface of the endless belt 4.
- the adjustment of the inclination of the endless belt 4 is performed by, for example, the inclination mechanism of the tread base 3 and the endless belt 4.
- the tilting direction of the belt by the tilting mechanism is typically a longitudinal tilt (the heights of the front and rear ends of the belt are different), but in addition to or instead, a lateral tilt (belt). The heights of the left and right ends of the are different).
- the speed of the endless belt 4 can be controlled by the control unit. Further, the inclination of the endless belt 4 may be controlled by the control unit.
- a first support column 5 is provided on the front side of the left and right side frames 2, and a second support column 6 is provided on the rear side.
- a handrail frame 7 is provided between the upper end of the first support and the upper end of the second support.
- a front frame 8 including left and right columns 80 is erected at the front end of the base frame, and a display 9 is supported by the front frame 8.
- a part or a structure front base 1, side frame 2, tread base 3, first strut 5, second strut 6, handrail frame 7, front frame 8) other than the endless belt 4). are collectively called a frame.
- the treadmill according to the present embodiment is provided with four cameras C arranged so as to surround the walking surface, and an object on the traveling belt is photographed by four cameras having different viewpoints. ing.
- cameras C1 and C2 are provided at the upper ends of the left and right columns 80 of the front frame 8, and the width of the rear end of the left and right side frames 2 or the rear end of the tread base 3.
- Cameras C3 and C4 are provided on both sides in the direction.
- cameras C1 and C2 are provided on the left and right first columns 5
- cameras C3 and C4 are provided on the left and right second columns 6.
- the left and right second columns 6 are provided with extending portions 60 extending upward beyond the handrail bar 7, and the left and right first columns 5 are provided with cameras C1 and C2.
- Cameras C3 and C4 are provided on the extending portions 60 of the left and right second columns 6.
- the number and arrangement of the cameras shown in FIGS. 1 to 4 are examples, and are not limited to the illustrated mode.
- the cameras C1 to C4 are fixed to the frame so that the posture and / or the position can be adjusted.
- 5 and 6 show an example of a camera mounting structure.
- the mounting structure of the camera shown in FIGS. 5 and 6 is an example, and is not limited to the illustrated embodiment.
- the cameras C1 and C2 (FIGS. 1 and 2) according to the first embodiment are attached to the upper end of the front frame 8 in an adjustable posture. As shown in FIG. 5, the camera C2 is rotatably attached to the upper end of the first axis 10, and the first axis 10 is relative to the cylindrical second axis 11 fixed to the frame 8. It is rotatably attached around the first shaft 10.
- the height positions of the cameras C1 and C2 may be adjustable with respect to the frame 8.
- the cameras C3 and C4 (FIGS. 1 and 2) according to the first embodiment may be configured to be able to be stored in the side frame 2 or the tread base 3 (for example, when stored, they are flat with the upper surface of the frame). ..
- the cameras C1 and C2 (FIGS. 3 and 4) according to the second form and the third form are attached to the first support column 5 so that the posture and / height position can be adjusted.
- the camera C2 is rotatably attached to the peripheral surface of the tubular body 12, and the tubular body 12 is rotatable and high in the circumferential direction around the outer periphery of the first support column 6. It is mounted so that it can be moved in the vertical direction.
- a structure similar to the mounting structure of the cameras C1 and C2 can be adopted for the mounting structures of the cameras C3 and C4 (FIGS. 3 and 4) according to the second and third modes.
- the camera is attached to an immovable portion that is not affected by the tilt of the endless belt 4 during the measurement of the walking motion of the subject.
- the camera is attached to any of the first support column 5, the second support column 6, the handrail frame 7, and the front frame 8, even if the endless belt 4 and the tread base 3 are tilted, the posture and position of the camera are changed. It is immutable.
- the plurality of cameras C1 to C4 are attached to the frame with their postures and positions adjusted so that the whole body of the object on the walking surface of the treadmill can be photographed.
- four cameras C1 to C4 are shown, but the number of cameras is not limited. Further, a mirror may be provided to reduce the number of cameras.
- the camera may include a wide-angle lens or a fisheye lens. When a wide-angle lens or a fisheye lens is used, image distortion correction is appropriately applied, and the image after distortion correction is used. Since the plurality of cameras C1 to C4 are incorporated in the frame of the treadmill, motion capture can be executed in substantially the same space as the space occupied by the treadmill.
- a computer is equipped with a processor that processes data and a memory that stores data.
- the computer has an operation data acquisition unit that acquires the target operation data (3D posture time series data) from the target image data, a storage unit for the target time series data obtained by the operation data acquisition unit, and a target time series data. It functions as a motion analysis unit using the motion analysis unit, a storage unit for analysis data by the motion analysis unit, and a control unit for controlling the tread mill based on the analysis data.
- the computer is installed in a frame, eg, a front base 1.
- the computer may be composed of a local computer provided in the frame and a computer or a cloud-based computer capable of wireless data communication between the local computer.
- a motion capture computer, a motion analysis computer, and a treadmill control computer are separately prepared.
- the treadmill according to the present embodiment may be provided with a force plate located below the upper portion of the endless belt 4.
- Treadmills provided with force plates are known and are disclosed, for example, in Patent Documents 1-6.
- Patent Documents 1 to 3 disclose a treadmill including a force plate using a strain gauge.
- Patent Documents 4 and 5 disclose a treadmill including a force plate using a capacitance type sensor.
- Patent Document 6 discloses a treadmill including a crystal oscillator force sensor capable of detecting in three directions.
- the time-series data acquired by the force plate when the object walks or runs on the running belt is stored in the storage unit of the computer.
- the data acquired by the force plate can be used for motion analysis in the motion analysis unit.
- the treadmill may be provided with a unloading device.
- the markerless motion capture according to this embodiment is composed of a plurality of video cameras mounted on a frame of a treadmill and a computer. ..
- the motion capture according to the present embodiment includes a moving image acquisition unit (video camera) for acquiring the target motion and feature points including joint positions based on the image acquired by the moving image acquisition unit (video camera).
- the heat map acquisition unit that acquires heat map information that displays the degree of certainty of the position of Keypoints) in color intensity, and the joint position that acquires the target joint position using the heat map information acquired by the heat map acquisition unit.
- the acquisition unit the smoothing processing unit that smoothes the joint position acquired by the joint position acquisition unit, the skeletal structure of the target body, the time-series data of the image acquired by the video acquisition unit, and the joint position acquisition unit. It is equipped with a storage unit that stores time-series data of the joint positions and the like, and a display that displays an image of the target acquired by the moving image acquisition unit and a skeletal structure corresponding to the posture of the target. Since the physical feature points of the subject are mainly joints, the term “joint” is used as a representative of the feature points in this specification and drawings, and the description of “joint” refers to feature points other than joints. Please note that it also applies to.
- the moving image acquisition unit is composed of a plurality of synchronized cameras, and each camera image acquired at the same time is transmitted to the heat map acquisition unit, and the heat map acquisition unit generates a heat map in each camera image.
- the heat map represents the spatial distribution of the likelihood of the certainty of the position of the feature points on the body.
- the generated heat map information is transmitted to the joint position acquisition unit, and the joint position is acquired by the joint position acquisition unit.
- the acquired joint position data is stored in the storage unit as time-series data of the joint position.
- the acquired joint position data is transmitted to the smoothing processing unit, and the smoothed joint position and joint angle are acquired.
- the posture of the target is determined by the smoothed joint position or joint angle and the skeletal structure of the body of the target, and the movement of the target consisting of time-series data of the posture is displayed on the display.
- the object operating on the walking surface of the treadmill has a link structure or an articulated structure.
- the subject is a human
- the articulated structure is the skeletal structure of the body. It is necessary to prepare the learning data used in the heat map acquisition unit according to the target, but it can also be applied to a non-human target (for example, a non-human animal). Further, the target is not limited to, for example, the whole body of a human being, and may be a part of the body.
- Measurement data and processing data are stored in the storage unit. For example, time-series data of images acquired by the moving image acquisition unit, joint position data acquired by the joint position acquisition unit, and joint angle data are stored.
- the storage unit further stores the smoothed joint position data acquired by the smoothing processing unit, the smoothed joint angle data, the heat map data generated by the heat map acquisition unit, and other data generated in the processing process. You may.
- the storage unit further stores data that determine the skeletal structure of the target body.
- This data includes files that define the skeletal model of the body and distance data between adjacent joints of interest.
- the joint angle and the pose of the target are determined from the position of each joint in the skeletal model, which is an articulated body.
- the skeleton model used in this embodiment is shown in the left figure of FIG.
- the skeleton model shown on the left of FIG. 10 has 40 degrees of freedom, and this skeleton model is an example.
- a constant representing the distance between adjacent joints of the target can be acquired at the time of initial setting of motion capture.
- the inter-articular distance of the target may be acquired in advance by another method, or the already acquired inter-articular distance may be used.
- by using the skeletal structure data of the target body it is possible to give a constraint condition peculiar to the skeletal structure that the distance between adjacent joints does not change with time in the calculation of the joint position.
- a moving image of the target acquired by the moving image acquisition unit On the display, a moving image of the target acquired by the moving image acquisition unit, a time-series skeleton image showing the pose of the target acquired by motion capture, and the like are displayed.
- skeleton image (target pose) data is generated for each frame using the target-specific skeleton structure, calculated joint angle and joint position time series data, and the skeleton image data is determined. Output at the frame rate of and display as a movie on the display.
- the heat map acquisition unit is a two-dimensional or three-dimensional space of the likelihood of the certainty of the position of the feature points (keypoints) on the body including each joint position based on the input image.
- a distribution is generated and the spatial distribution of the likelihood is displayed in heatmap format.
- the likelihood acquired by the heat map acquisition unit is given to each pixel on the two-dimensional image, and the heat map information from a plurality of viewpoints is integrated into the three-dimensional existence of the feature points. Information on the certainty of the position can be obtained.
- a heat map displays values that spread and change in space in terms of color intensity like a temperature distribution, and enables visualization of likelihood.
- the heat map acquisition unit holds the spatial distribution of the likelihood of the certainty of the position of the feature point on the body including each joint, that is, the heat map information (a value in which each pixel of the image represents the likelihood). It is not necessary to display the heat map as long as it has been acquired.
- the heat map acquisition unit typically uses a convolutional neural network (CNN) to heat map the positions of feature points (typically joint positions) on the target body from a single input image.
- CNN convolutional neural network
- the convolutional neural network (CNN) has an input layer, an intermediate layer (hidden layer), and an output layer, and the intermediate layer is constructed by deep learning using the teacher data of the existence position of the two-dimensional map on the image of the feature point. ing.
- OpenPose Non-Patent Document 2
- OpenPose 18 keypoints on the body are set (see the right figure in FIG. 10).
- the 18 feature points consist of 13 joints, a nose, left and right eyes, and left and right ears.
- OpenPose uses a trained convolutional neural network (CNN) to generate Part Confidence Maps (PCM) of 18 keypoints on the body from one RGB image offline or in real time. Display in heat map format.
- CNN convolutional neural network
- PCM Part Confidence Maps
- PCM may be used for the spatial distribution or heat map of the likelihood of the certainty of the position of the feature point on the body, but the position of the feature point on the body including each joint position is certain. It should be noted that the index representing the spatial distribution of likelihood of likelihood is not limited to PCM.
- OpenPose For each RGB image acquired from multiple synchronized cameras, OpenPose generates Part Condence Maps (PCM) of 18 feature points.
- a method other than OpenPose can be used for the heat map acquisition unit.
- Various methods have been proposed as methods for acquiring a heat map showing the certainty of the position of a feature point on the target body. For example, a method that has won a high ranking in the COCO Keypoints challenge (Non-Patent Document 3) can be adopted.
- a learning device for the heat map acquisition unit is created independently, and a convolutional neural network (CNN) is constructed using, for example, an image taken by a camera mounted on a treadmill frame as learning data. You may.
- CNN convolutional neural network
- the present invention does not exclude such a motion data acquisition method, it is difficult to measure motion with high accuracy as in optical motion capture due to erroneous estimation of two-dimensional coordinates of joint positions and the like. Therefore, in the present embodiment, a method of three-dimensionally reconstructing the joint position using heat map information, and a method of measuring motion with high accuracy such as optical motion capture is adopted.
- Camera calibration Acquire camera parameters for three-dimensionally reconstructing a plurality of camera images in order to perform motion capture using a plurality of cameras.
- Camera parameters include internal parameters such as focal length and optical center, external parameters that represent the posture and position of the camera, and distortion parameters.
- a calibration device (checker board, calibration wand, etc.) having a known shape and dimensions is placed in a space on the walking surface of the tread mill to determine the posture and position. It can be adjusted and photographed by multiple cameras fixed to the frame, and executed by optimization calculation using each camera image.
- the distortion parameters can be obtained at the same time as the internal parameters.
- Camera parameters can be used to obtain a projection matrix for projecting any point in three-dimensional space onto the image plane of each camera.
- the function (matrix) for converting the points of any three-dimensional shape to the pixel position of the imaging plane of the camera P i is obtained.
- the function (matrix) Pi is stored in the storage unit.
- calibration is performed using a double-face checkerboard with checker patterns on both sides.
- the checker board is installed vertically on the walking surface (belt) of the treadmill.
- the checker board is provided, for example, in a vertical posture on a support frame erected located in the middle of the walking surface (belt) in the front-rear direction.
- the first checker pattern on the first surface of the checkerboard and the second checker pattern on the second surface match.
- the relative position / orientation between the first checker pattern and the second checker pattern is determined.
- the first checker pattern is photographed by the two front cameras, and the second checker pattern is photographed by the two rear cameras.
- the four cameras are mounted on the treadmill frame, but the four cameras may be independent of the treadmill.
- the four cameras are arranged separately in two coordinate spaces O chk1 and O chk2 formed by the first checker pattern and the second checker pattern, respectively.
- coordinate p chk1 in O chk1 it can be expressed by the following equation.
- the relative positions and orientations of the four cameras can be expressed and acquired in the same space O chk1.
- the world coordinate system O floor set from the coordinate space O chk1 to the floor surface based on the height at which the checker pattern on the checker board is installed and the flat plate being installed perpendicular to the floor.
- the homologous transformation matrix to chk1 R floor can be derived. Therefore, the coordinates p floor in the world coordinate system O floor of points, denoted p chk1 in the coordinate space O chk1, can be expressed by the following equation. From the above, through the coordinate spaces O chk1 and O chk2 , the coordinates of all points in the space and the positions and orientations of all the cameras can be represented by the world coordinate system O floor. In the present embodiment, as shown in FIG.
- the three-dimensional coordinates have the origin at the center of the walking surface of the treadmill, the y-axis in the direction from the rear to the front along the traveling direction of the treadmill belt, and the belt.
- Let the coordinate space have the width direction as the x-axis and the vertical upward direction as the z-axis.
- the position / orientation of the treadmill belt and the position / orientation of the object on the belt can be specified in world coordinates.
- the three-dimensional joint position data of the object defines the position information of the object on the belt of the treadmill in addition to the posture of the object at a certain time point.
- the speed of the belt is the speed along the y-axis.
- the plurality of cameras used for motion capture include one or a plurality of front cameras located on the front side of the endless belt and a rear camera located on the rear side of the endless belt.
- a calibrator can be installed in the tread mill, and the calibrator includes a checkerboard located in the middle of the endless belt in the front-rear direction and provided vertically.
- a first checker pattern photographed by the front camera is provided on the first surface of the checkerboard, and a second checker pattern photographed by the rear camera is provided on the second surface of the checker board.
- FIG. 13 shows a mode in which motion capture is performed using two cameras on the front side and two cameras on the rear side. For example, only the two cameras on the front side or two cameras on the rear side are used.
- the checker pattern on either side may be used.
- the checker boat in a horizontal posture installed parallel to the belt plane may be used alone or in combination with the double face checker board for calibration.
- the double face checker board may be provided on the support frame so as to be rotatable between the vertical posture and the horizontal posture.
- the joints in the skeletal model and the 18 feature points in OpenPose according to the present embodiment are both representative feature points in the body, and cover all possible feature points. Not something that exists. For example, more detailed feature points may be set. Alternatively, all physical features may be joints.
- the joint angle, which cannot be determined only by the 18 feature points of OpenPose, is determined as a result of optimization considering restrictions such as the range of motion. If the joints of the skeletal model and the feature points from which the spatial distribution of the likelihood is acquired correspond from the beginning, this association is unnecessary.
- the optimization calculation based on inverse kinematics requires a constant of the distance between adjacent feature points (distance between joints), that is, the link length, but since the link length differs for each object, the link of the skeletal model for each object Calculate the length.
- the skeletal model is a model of a standard human skeletal structure, which is scaled systemically or site by site to generate a skeletal model suitable for the target body shape.
- each link length of the skeleton model is updated based on the obtained initial posture.
- the scaling parameters used for updating the link length are calculated from the positions of the feature points based on the correspondence in FIGS. 10 and 1.
- the link lengths in the left figure of FIG. 10 the link lengths of 1-2, 2-3, 3-4, 3-6, 3-10, 6-7, and 10-11 are the corresponding features. Since there are no points, the scale parameters cannot be determined in the same way. Therefore, the length is determined using other link length scale parameters.
- each scaling parameter is obtained from the left and right averages so as to be even on the left and right, and the initial link length of the skeleton model is even on the left and right. ..
- the scaling parameter is calculated with the midpoint of the feature point position of both ears as the location of the head joint.
- Each link length of the skeleton model is updated using the acquired scaling parameters.
- the positions of the nose, eyes, and ears are calculated based on the correspondence as shown in Table 2.
- the link length may be obtained by another method or may be obtained in advance. Alternatively, if a skeletal model unique to the subject is obtained, it may be used. The subject's unique skeletal model can also be used in the motion analysis unit.
- the joint position acquisition unit estimates joint position candidates using the heat map information acquired from the heat map acquisition unit, and optimizes based on reverse kinematics using the joint position candidates. It is characterized in that the joint angle and joint position of the skeletal model are updated by executing the calculation.
- the joint position acquisition unit is a joint position candidate acquisition unit that estimates joint position candidates based on heat map data, and an inverse motion that calculates joint angles by executing optimization calculations based on inverse kinematics using joint position candidates. It is equipped with an academic calculation unit and an forward kinematics calculation unit that calculates joint positions by executing forward kinematics calculations using the calculated joint angles.
- the joint position candidate acquisition unit sets the search range of the joint position candidate using the 3D position of each joint acquired in one or a plurality of frames (for example, the joint position of the front frame t). , All or part of the points in the search range are converted to the pixel positions of each camera image plane, and the spatial distribution of the likelihood obtained in the frame t + 1 is used to determine the joint positions in the frame t + 1. Acquire one or indirect position candidate.
- each joint position t + 1 J n of the frame t + 1 is a function of the joint angle t + 1 Q, as shown in the equation (3), by the optimization calculation based on the inverse kinematics.
- the joint angle t + 1 Q is calculated, and the joint position t + 1 J n is calculated by forward kinematics calculation.
- the weights t + 1 W n of each joint in the optimization calculation based on inverse kinematics The sum of the PCM values at the predicted positions of each joint is used as specified.
- Each joint position acquired by the joint position acquisition unit is stored in the storage unit as time-series data of the joint position.
- each joint position acquired by the joint position acquisition unit is smoothed by the smoothing processing unit to generate a smoothed joint position.
- a place where the PCM score is high with a plurality of points (for example, 7 points) among all the grid points as the joint position point group. You may perform an optimization calculation based on inverse kinematics by searching for.
- a point cloud in the three-dimensional space is projected onto a two-dimensional plane, and the PCM value of the pixel coordinates is acquired. Then, the sum (PCM score) is obtained, and the point with the highest PCM score in the point cloud is set as a joint position candidate as a point in the three-dimensional space where the PCM score is maximum.
- the calculation of projecting a three-dimensional point on each camera plane and calculating the PCM score is light.
- the search for joint position candidates according to the present embodiment is calculated by limiting the search range using the information of the previous frame and reprojecting the three-dimensional positions of the grid points in the search range onto a two-dimensional image (PCM). And improve the estimation accuracy of the joint position.
- the smoothing joint position acquisition unit of the smoothing processing unit uses the time-series information of the joints to perform smoothing processing in consideration of temporal continuity. For example, when smoothing the joint position acquired in frame t + 1, typically, the joint position acquired in frame t + 1, the joint position acquired in frame t, and frame t-1. The acquired joint position is used. Further, the smoothed joint position acquisition unit does not necessarily have to use continuous frames. To simplify the calculation, first smoothing is performed without using body structure information.
- the link length which is the distance between adjacent joints, is not preserved. Then, using the joint position after smoothing, the optimization calculation based on the inverse kinematics using the skeletal structure of the target was performed again to obtain each joint angle of the target, thereby preserving the link length. Perform smoothing.
- the smoothed joint position acquisition unit performs temporal smoothing of the joint position by a low-pass filter.
- the smoothing process by the low-pass filter is applied to the joint position acquired by the joint position acquisition unit, the smoothed joint position is set as the target position of each joint, and the optimization calculation based on the inverse kinematics is performed. This makes it possible to utilize the smoothness of the time change of the joint position under the skeletal condition that the distance between each joint is invariant. If each joint position obtained by the low-pass filter is used as the output of video motion capture, the temporal smoothness of each joint can be obtained, but the condition that the distance between adjacent joints is constant may be broken.
- the joint position after the application of this low-pass filter is set as the target joint position of each joint again, and the optimization calculation based on the inverse kinematics is performed again.
- Equation (3) can be used for the optimization calculation based on the inverse kinematics, but the optimization calculation based on the inverse kinematics is executed assuming that the weights of all joints are uniform (but not limited to this).
- the smoothness of the time change of the joint position adapted to the low-pass filter can be utilized under the skeletal condition that the distance between each joint is invariant.
- the output of the smoothing processing unit includes, for example, joint angle information and skeletal structure, and joint position information that can be uniquely calculated from the two. For example, when drawing CG, the movement of the body is drawn by forward kinematics calculation using the joint angle information and the skeletal structure file of the body.
- the information included in the output of the smoothing processing unit may be stored in the storage unit.
- [B-6] Flow of acquisition of target motion data The process from acquiring the joint angle and the position of the feature point from the input image according to the present embodiment will be described.
- a plurality of synchronized cameras capture the movement of the object on the walking surface of the treadmill, and each camera outputs an RGB image at a predetermined frame rate.
- the heat map acquisition unit receives the input image, it generates a heat map (spatial distribution of the likelihood of the certainty of the joint position) at all the feature points on the target body based on the input image.
- the joint position acquisition unit searches for joint position candidates using the heat map information of each image.
- the search range is set based on the joint position of the frame t, and the joint position candidate is searched. Then, the same process is executed for all joints, and joint position candidates for all joints are acquired.
- the joint position candidate and the joint of the skeletal model are associated with each other, and the skeletal model is fitted to the skeletal model unique to the subject.
- the joint angle and joint position are acquired by executing optimization calculation and forward kinematics calculation based on inverse kinematics.
- the joint position in the past frame is used for the acquired feature point position, and the smoothing process is executed to smooth the temporal movement of the joint position.
- the position of the smoothed feature points is used to perform the optimization calculation based on inverse kinematics again to obtain the joint angle of the target, and the obtained joint angle is used to perform the forward kinematics calculation to perform the target. Get the joint position of.
- the motion capture according to the present embodiment is markerless by performing three-dimensional reconstruction in consideration of the structure of the human skeleton and the continuity of motion from the joint positions estimated by using deep learning from the images of a plurality of cameras. Get smooth motion measurements comparable to traditional optical motion capture. Multiple cameras are built into the frame of the treadmill, eliminating the hassle of installing cameras and attaching markers to the target.
- a motion capture integrated treadmill can be provided in substantially the same space as the space occupied by the treadmill.
- the motion data acquisition unit acquires time-series data of the 3D posture of the object walking on the walking surface.
- the 3D posture of the object in each frame is specified by the three-dimensional coordinates of all the feature points (joint positions).
- the motion analysis unit performs various motion analyzes using the time series data of the target 3D posture.
- the motion analysis unit executes walking analysis using, for example, three-dimensional motion measurement. For example, it is possible to determine the wobbling of the target in the anteroposterior direction or the lateral direction from the center of gravity position and the center of gravity sway data. Generate a Lissajous diagram of the position of the center of gravity of the target and the position of a certain part of the body (for example, the position of a joint).
- the motion analysis unit estimates the muscle tension and muscle activity of the target during walking, visualizes them, and displays them on the display.
- the position of the center of gravity in each frame of the target the time-series data of the position of the center of gravity of the target, the sway data of the center of gravity of the target, the sway data of a predetermined part of the target body, the whole of the target body, or Partial speed and acceleration, variation in joint angle of certain joints of the target body, stride length, difference between left and right stride length, lisage diagram of the position of the center of gravity of the target and the position of a certain part of the body, and other existing walking movements
- Motion analysis can be performed by using any one or a combination of a plurality of these pieces of information.
- the motion analysis unit can perform motion analysis using the motion information of the treadmill in addition to the motion data acquired by the motion data acquisition unit.
- the operation information of the treadmill is, for example, the traveling speed and the inclination angle of the endless belt when the object walks on the walking surface.
- the target operation data and the operation data of the treadmill are stored in the storage unit in synchronization. For example, by synchronizing the movement of the whole body including the movement of the upper body such as the movement of the target's arm and shoulder with the treadmill and quantifying or visualizing it in detail, the effect of rehabilitation that appears as smooth movement of the whole body is numerically calculated. Can be converted.
- the swing of the center of gravity of the target, the movement of the foot, and the movement of the treadmill can be observed in conjunction with each other.
- by observing the change in the movement of the whole body of the target when the running speed of the endless belt of the treadmill is changed it is possible to evaluate the effect of rehabilitation that cannot be observed only by the treadmill or the mocap.
- the motion analysis unit can perform motion analysis using the information acquired by the force plate. For example, the landing and leaving of the foot may be detected and used for motion analysis. Further, the biological information (heart rate, oxygen uptake, etc.) of the target during walking may be acquired, and the biological information may be used in the analysis of the motion analysis unit.
- the biological information heart rate, oxygen uptake, etc.
- FIG. 12 illustrates a processing process of motion analysis using motion capture.
- the motion capture acquires time-series data of the joint angle and joint position of the target during walking. Furthermore, based on this, the joint torque is acquired by inverse dynamics calculation, and the joint torque is used to optimize the wire tension in a musculoskeletal model equipped with a wire that imitates a muscle (secondary programming method or linear programming). Method), the muscle activity is calculated using the wire tension, a musculoskeletal image with colors assigned according to the degree of muscle activity is generated, and the musculoskeletal image with the visualized muscle activity is generated. The image is output at a predetermined frame rate and displayed as a moving image on the display.
- a detailed description will be given.
- the displacement of the total degrees of freedom of the skeleton at each frame time, the velocity that is the time derivative, and the time derivative Calculate a certain acceleration.
- the position, angle, velocity, angular velocity, acceleration, and angular acceleration of each link calculated from them are sent to the inverse dynamics engine, and the dynamic information is calculated according to the motion of the skeleton assuming mass, so that it matches the motion. Calculate the joint torque.
- Each segment of the skeleton is a rigid body, and its mass, center of gravity position, and inertia tensor can be estimated from statistical measurement information of each part of a person using physique information. Alternatively, these parameters can be estimated by identification from the motion information of the target.
- the physique information of the target used for estimation is acquired in advance.
- Non-Patent Document 4 can be referred to for the calculation of the wire tension.
- An electromyogram or a force plate may be used to obtain the muscle tension.
- the value obtained by dividing the acquired muscle tension by the maximum muscle tension assumed by the muscle is used as the muscle activity, and an image of the whole body musculoskeletal system in which the muscle color is changed according to the muscle activity is generated, and this is used as the frame rate. It is output at (typically 30 FPS) and displayed as an image on the display. In addition, an image of the skeleton pose is generated, output at the frame rate, and displayed as an image on the display. Furthermore, changes in the values of each variable (for example, joint angle, velocity, muscle tension, floor reaction force, center of gravity position, etc.) are graphed and output. These outputs are presented as analysis results in images and graphs, and are used as a record of muscle and body activities during exercise, or movements of each part of the body. In this way, it is possible to automatically and efficiently perform the shooting of the movement of the target, the acquisition of the three-dimensional pose of the target during the movement, and the estimation and visualization of the muscle activity required for the movement.
- each variable for example, joint angle, velocity, muscle tension
- the motion analysis unit reproduces the time series information of the 3D pose of the skeleton of the object walking or running on the walking surface of the treadmill.
- muscle tension and muscle activity during exercise can be estimated by performing kinetic calculations that take mass into consideration.
- equipping the treadmill itself with a motion capture function and a motion analysis function it is possible to complete what used to require a large-scale measurement environment with just the treadmill.
- engineers such as treadmills, motion capture, and motion analysis have collaborated to perform motion analysis, but since these can be performed consistently, it leads to labor saving and time saving.
- the burden on the subject wearing the marker and the physiotherapist is greatly reduced, and the movement of the subject is evaluated and analyzed with almost the same preparation as a normal treadmill. The results can be visualized as appropriate.
- the treadmill has operation data acquired by an operation data acquisition unit (typically, when the target posture is walking. It is provided with a control unit that controls the operation of the treadmill based on the series data) or / and the analysis data acquired by the motion analysis unit.
- an operation data acquisition unit typically, when the target posture is walking. It is provided with a control unit that controls the operation of the treadmill based on the series data) or / and the analysis data acquired by the motion analysis unit.
- the motion data includes a target posture, time-series data of the target posture, and information obtained based on the target posture and / or the time-series data of the posture.
- the latter information does not prevent duplication with the information obtained by motion analysis.
- the motion data may be, for example, position information (specified by one or more joint positions) of the whole body or a part of the target body in a certain frame.
- the information that can be acquired by motion analysis is, for example, the position of the center of gravity in each frame of the target, the time-series data of the position of the center of gravity of the target, the sway data of the center of gravity of the target, the sway data of a predetermined part of the target body, the entire body of the target, or all of the target bodies. Partial speed and acceleration, variation in joint angle of a given joint of the target body, stride length, difference between left and right stride length.
- the operation of the treadmill includes the rotation of the endless belt and the tilting of the endless belt.
- the control of the rotation of the endless belt is to control the rotation speed (belt speed) via the drive unit (motor), and the belt speed is decelerated, increased, maintained at a predetermined speed, stopped after deceleration, stopped, and so on. Includes reverse rotation of the endless belt. Further, the rotation speeds of the two endless belts traveling in parallel may be controlled independently.
- the inclination of the endless belt is, for example, the inclination of the tread base and the endless belt that support the upper part of the endless belt via the drive unit (motor), and the change of the inclination is the increase of the inclination angle of the endless belt (walking).
- the walking surface may become a downhill
- the inclination angle is reduced (movement from the inclined state to the flat state)
- the inclination angle is maintained.
- the inclination of the endless belt may include a lateral inclination in addition to a vertical inclination.
- the control unit that controls the operation of the treadmill will be described in detail with reference to FIG. 7A.
- the control unit includes an input data generation unit that generates input data based on motion data acquired by motion capture, and a control signal generation unit that generates a control signal according to the input data. It is output to the drive unit to obtain the desired belt speed and inclination.
- the control by the control unit is executed according to one or more control programs stored in the memory.
- the control program defines what kind of information is used and what kind of control is executed.
- the input data generation unit generates input data according to the control program.
- the control signal generation unit generates a control signal according to the input data according to the control program.
- the control unit controls the operation of the treadmill when an abnormal state or anomaly (some accident has occurred in the moving object) of the object is detected based on the operation data.
- the control program defines the information (input data) used for abnormality detection and the conditions for determining the abnormality.
- the control program for example, detects a change from the normal state (specified based on the operation data) of the target to an abnormal state (specified based on the operation data) or the continuation of the abnormal state, and determines an abnormality. ..
- Abnormalities in the target are detected, for example, by comparing changes in the posture of the target, changes in the posture, and changes in the center of gravity (fluctuations can be detected from changes in the posture and changes in the center of gravity) with predetermined reference values or threshold values. can do.
- the operation control of the treadmill when an abnormality is detected is typically a deceleration of the belt speed or a stop after the deceleration.
- the control unit slows down or stops the belt speed when the subject is excessively close to the front or rear end of the walking surface. For example, based on the position information of the whole body or a predetermined part of the target detected based on the motion data, it is detected that the target protrudes backward (y-axis direction) from the steady position (predetermined area on the walking surface), and the belt The speed may be reduced slowly. Alternatively, the belt speed may be slowly reduced by detecting that the position of the center of gravity of the target protrudes rearward (in the y-axis direction) from the steady position (predetermined region on the walking surface).
- the target protrudes forward (y-axis direction) from the steady position (predetermined area on the walking surface), and the belt.
- the speed may be increased slowly.
- the belt speed may be slowly increased by detecting that the position of the center of gravity of the target protrudes forward (in the y-axis direction) from the steady position (predetermined region on the walking surface).
- the belt speed After decelerating the belt speed as described above, it may be detected that the target has returned to the steady position, and the belt speed may be increased to return to the original speed. Similarly, after increasing the belt speed, it may be detected that the target has returned to the steady position, and the belt speed may be reduced to return to the original speed.
- the control unit further determines that the target protrudes laterally (x-axis direction) from the steady position (predetermined area on the walking surface) based on the position information of the whole body or a predetermined part of the target detected based on the motion data. It may be detected to slowly reduce the belt speed, or it may be stopped after deceleration. Alternatively, the belt speed may be slowly reduced or stopped after decelerating by detecting that the position of the center of gravity of the target protrudes from the steady position (predetermined area on the walking surface) in the lateral direction (x-axis direction). Good. Alternatively, the belt speed may be slowly decelerated by detecting the magnitude of the acceleration information and the magnitude of the sway of the center of gravity of a target portion, or the belt speed may be decelerated and then stopped.
- the control unit when the belt is in the uphill posture, the control unit further positions the target rearward from the steady position (predetermined area on the walking surface) based on the position information of the whole body or the predetermined part of the target detected based on the motion data. It may be detected that the belt is tilted to slowly return to a flat state, and / or the belt speed may be slowly reduced or stopped after deceleration.
- the double belt type treadmill includes two belts that can be operated independently by each belt drive unit, an inclination drive unit that changes the inclination of the belt, and an operation unit, and follows instructions from the operation unit. Operate the belt drive unit and the tilt drive unit.
- the tilting direction of the belt by the tilting drive is typically a longitudinal tilting (the heights of the front and rear ends of the belt are different), but in addition to or instead, a lateral tilting (the height of the front and rear ends of the belt is different). The height of the left end and the right end of the belt may be different).
- the double-bed type treadmill is used, for example, as a gait analysis system, a gait training system, or a gait rehabilitation support system for hemiplegic patients.
- FIG. 7B shows a markerless motion capture and a double belt type treadmill, the technical idea of controlling the operation of the treadmill according to the motion data of the target acquired by the motion capture is the markerless motion capture. And not limited to double belt type treadmills.
- the treadmill includes a control unit that controls the operation of the treadmill according to the operation data of the target acquired in real time by motion capture.
- the motion data of the object walking on the double belt is acquired by markerless motion capture.
- the motion data is typically time-series data of the target 3D pose, and from the time-series data of the 3D pose, for example, the 3D position of the whole body, the 3D position of the part, the posture of the whole body, the posture of the part, and the whole body. Movement, movement of a part (limb, foot, etc.), speed of all or part of the target body, position of the center of gravity, sway of the center of gravity, sway of the part can be obtained.
- control unit controls the operation of the treadmill according to the control program in response to the input of the data generated according to the predetermined control program.
- the control unit independently controls the traveling speed of each belt according to the operation data.
- the speed of one belt may be adjusted according to the speed of movement of the left and right legs and the difference in stride length between the left and right legs.
- the speed change (accelerating or decelerating) of the traveling belt according to the movement of the paralyzed foot can be automatically controlled by the control unit.
- the running belt is stopped or the belt is appropriately accelerated to correct the forward leaning state and lead to correct walking. It may be.
- control unit controls the tilt of both belts according to the motion data.
- the inclination of the belt may be adjusted by detecting a posture indicating that the patient has bent forward on the belt and controlling the inclination driving unit according to the posture.
- the speed control by the control unit may include reverse rotation of the endless belt in addition to speeding up, decelerating, and stopping.
- the traveling belt may be rotated in the reverse direction when the paralyzed foot is stepped forward to support walking.
- the operation of the movable portion may be controlled.
- the handrail bar may be moved in the front-rear direction, and the handrail bar may be moved according to the movement of the target hand or arm.
- the first control method drives the belt at a speed that matches the patient's athletic performance. If the walking speed is too slow for the patient's athletic ability, the effect of rehabilitation diminishes, and conversely, if the patient tries to walk at high speed forcibly, there is a risk of falling.
- the belt speed control according to the present embodiment, the belt speed as large as possible is output within the range in which the patient can walk safely and comfortably.
- the second control method controls the patient to maintain an appropriate walking posture close to upright even if the patient has a difference in athletic ability between the left and right legs.
- a belt speed control method that combines the first control method and the second control method is provided.
- the first control method will be described.
- position control will be described. If the belt speed is slow and the patient can walk comfortably, the patient moves forward on the treadmill. On the other hand, if the belt speed is high and the patient's walking speed cannot keep up, the flow of the belt pushes the patient back.
- a method is adopted in which the belt speed is adjusted to the walking speed of the patient by maintaining the walking position of the patient at a predetermined position (typically near the center) on the walking surface of the treadmill. As an index showing the walking position of the patient, the three-dimensional position estimation result of the left and right hip joints is output from the video motion capture.
- the midpoint of the left and right hip joints is regarded as the "lumbar center", and the lumbar center is regarded as the pseudo body center.
- the y-coordinate of the lumbar center at time t can be obtained from the y-coordinate y Lplv (t) of the left hip joint and the y-coordinate y Rplv (t) of the right hip joint at time t.
- the difference between the y-coordinate average value of the lumbar center and the target value y ref plv of the lumbar center during one walking cycle (for example, 1 second) ⁇ y plv (t) Is controlled to approach 0.
- the second control method will be described.
- the range of motion of both legs of the patient is displaced in the anteroposterior direction (y-axis direction). ing. This is directly due to the difference in stride length between the left and right.
- the difference in the exercise capacity of both legs is compensated, and the centers of the exercise ranges of both legs are aligned.
- ⁇ y LRa (t) is defined as follows. Since this ⁇ y LRa (t) represents the deviation of the center of motion of both legs in the y direction, a second control method that brings ⁇ y LRa (t) closer to 0 is added to the position control or speed control in the first control method. .. That is, the second control method can be applied in combination with the position control or speed control of the first control method.
- the first control method position control, speed control
- the first control method position control, speed control
- the first control method can also be used for the exercise of a healthy person or an athlete.
- FIG. 14 shows a block diagram showing a method of calculating the left belt target speed v L, ref (t) and the right belt target speed v R, ref (t) of the treadmill at time t.
- the initial velocities v L, ref (0), v R, ref (0) of both belts are determined as follows.
- the belt speeds v L, ref (nf), v R, ref (nf) at the time nf seconds are set for each f frame according to the following update formula using the operation data of the target on the treadmill.
- Update ⁇ v L, ref (nf) and ⁇ v R, ref (nf) are correction terms for updating the belt speed.
- e (t) is defined as follows.
- ⁇ p (t) is defined as follows.
- k s1 and k s2 are defined as follows.
- ⁇ s (t) is defined as follows.
- ⁇ v L, ref (nf) and ⁇ v R, ref (nf) are defined as follows.
- the values of k p1 , k p2 , k s1 , and k s2 are appropriately set by those skilled in the art.
- the first control is performed based on the motion data acquired by the motion capture.
- a plurality of controls according to the method and the second control method can be performed at the same time.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Vascular Medicine (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Social Psychology (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Radiology & Medical Imaging (AREA)
- Databases & Information Systems (AREA)
- Psychiatry (AREA)
- Evolutionary Computation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Artificial Intelligence (AREA)
- Dentistry (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
Description
フレームと、
対象が載る歩行面を提供するエンドレスベルトと、
ベルト駆動部と、
フレームに設けてあり、姿勢および/あるいは位置が調整可能である複数のカメラと、
各カメラ画像で取得した画像情報を用いてマーカレスで対象の動作データを取得する動作データ取得部と、
を備えたモーションキャプチャ一体型トレッドミル、である。
1つの態様では、前記動作分析部は、前記動作データに加えて、エンドレスベルトの動作情報(速度情報やベルトの傾き)を用いて対象の動作を分析する。
トレッドミルの動作には、エンドレスベルトの回転、エンドレスベルトの傾斜が含まれる。エンドレスベルトの回転駆動部、エンドレスベルトの傾斜駆動部を制御することで、エンドレスベルトの走行速度(ベルト速度)、エンドレスベルトの傾きを制御することができる。
1つの態様では、前記制御部は、
前記動作データに基づいて入力データを生成するデータ生成部と、
前記入力データに応じて制御信号を生成する制御信号生成部と、
を備え、
前記制御信号を前記ベルト駆動部に出力してベルト速度を制御する。
1つの態様では、エンドレスベルトは傾斜駆動部によって傾斜可能であり、
前記制御部は、前記制御信号を前駆傾斜駆動部に出力してベルト傾斜を制御する。
1つの態様では、前記対象において、隣接する関節間の距離が定数として得られており、
前記動作データ取得部は、
前記尤度の空間分布を用いて、各特徴点に対応する1つあるいは複数の特徴点の位置候補を取得し、
前記特徴点の位置候補と前記対象の多関節構造を用いた逆運動学に基づく最適化計算を行うことで、前記対象の各関節角を取得し、
前記関節角を用いて順運動学計算を行うことで、前記対象の関節を含む特徴点の位置を取得する。
1つの態様では、前記探索範囲は、前記特徴点の位置を中心として所定間隔で3次元状に分布する所定数の点群である。
1つの態様では、前記逆運動学に基づく最適化計算において、前記尤度の空間分布が用いられる。
1つの態様では、前記処理部は、1つあるいは複数のフレームで取得されている各特徴点を用いて特徴点位置候補の探索範囲を設定し、フレームt+1で取得された尤度の空間分布を用いて、フレームt+1における各関節位置の1つあるいは複数の特徴点位置候補を取得する。
1つの態様では、前記処理部は、
前記特徴点の位置を、他の複数のフレームで取得された複数の特徴点の位置を用いて時間方向に平滑化し、
平滑化された特徴点の位置と前記対象の多関節構造を用いた逆運動学に基づく最適化計算を行うことで、前記対象の各関節角を取得する、
ように構成されている。
本発明では、トレッドミルとマーカレスモーションキャプチャを組み合わせることで、モーションキャプチャという1つの手段を用いるだけで、モーションキャプチャにより取得した動作データに基づいて、あらゆる制御に対応可能である。
モーションキャプチャにより計測された動作データに基づいて動作分析ないしトレッドミルの動作制御を行うことで、例えば、歩行訓練において、従来理学療法士が目視で行っていた作業をトレッドミルの機能で対応することができる。
図7に示すように、本実施形態に係るスマートトレッドミルは、トレッドミルと、複数台のカメラと、1つあるいは複数のコンピュータと、ディスプレイから構成されるトレッドミルシステムである。トレッドミルは、対象が載る歩行面を提供するエンドレスベルトと、駆動部と、操作部と、を備える。スマートトレッドミルは、さらに、動作データ取得部と、動作分析部と、制御部とを備えており、これらはコンピュータによって構成される。動作データ取得部は、例えば、マーカレスモーションキャプチャであり、動作データ取得部によって対象の運動時(例えば、歩行時)の3Dポーズの時系列データが取得される。動作分析部は、動作データを処理することで分析データを出力する。制御部は、動作データあるいは/および分析データを用いて、トレッドミルの駆動部に所定の指令を出力して、トレッドミルの動作を制御する。
[B-1]マーカレスモーションキャプチャの全体構成
本実施形態に係るマーカレスモーションキャプチャは、トレッドミルのフレームに取り付けられた複数台のビデオカメラと、コンピュータから構成される。図8に示すように、本実施形態に係るモーションキャプチャは、対象の動作を取得する動画取得部(ビデオカメラ)と、動画取得部で取得された画像に基づいて、関節位置を含む特徴点(Keypoints)の位置の確からしさの程度を色強度で表示するヒートマップ情報を取得するヒートマップ取得部と、ヒートマップ取得部で取得されたヒートマップ情報を用いて対象の関節位置を取得する関節位置取得部と、関節位置取得部で取得された関節位置を平滑化する平滑化処理部と、対象の身体の骨格構造、動画取得部で取得された画像の時系列データ、関節位置取得部で取得された関節位置の時系列データ等を記憶する記憶部と、動画取得部で取得された対象の画像や対象の姿勢に対応する骨格構造等を表示するディスプレイと、を備えている。対象の身体上の特徴点は主として関節であるため、本明細書及び図面において、特徴点を代表して「関節」という文言を用いており、「関節」についての説明は、関節以外の特徴点にも適用される点に留意されたい。
ヒートマップ取得部は、入力画像に基づいて、各関節位置を含む身体上の特徴点(keypoints)の位置の確からしさの尤度の2次元あるいは3次元の空間分布を生成し、前記尤度の空間分布をヒートマップ形式で表示する。本実施形態では、ヒートマップ取得部で取得された尤度は、2次元の画像上の各ピクセルに与えられており、複数視点からのヒートマップ情報を総合して特徴点の3次元的な存在位置の確からしさの情報を得ることができる。ヒートマップは、空間に広がって変化する値を温度分布のように色強度で空間上に表示すものであり、尤度の可視化を可能とする。本実施形態において、ヒートマップ取得部は、各関節を含む身体上の特徴点の位置の確からしさの尤度の空間分布、すなわち、ヒートマップ情報(画像の各ピクセルが尤度を表す値を保持している)が取得されていればよく、必ずしも、ヒートマップを表示することを要しない。
図3を参照しつつ、本実施形態に係るモーションキャプチャシステムにおける、カメラのキャリブレーション、骨格モデルの初期姿勢の取得、対象の関節間距離の取得について説明する。
複数のカメラを用いたモーションキャプチャを行うために、複数のカメラ画像を3次元再構成するためのカメラパラメータを取得する。カメラパラメータには、焦点距離や光学的中心等の内部パラメータ、カメラの姿勢・位置を表す外部パラメータ、歪みパラメータがある。カメラパラメータを取得するためのカメラキャリブレーションは、例えば、既知の形状や寸法のキャリブレーション器具(チェッカーボードやキャリブレーションワンド等)をトレッドミルの歩行面上の空間に位置させて、姿勢・位置を調整してフレームに固定した複数台のカメラで撮影し、各カメラ画像を用いた最適化計算によって実行し得る。歪みパラメータは、内部パラメータと同時に取得され得る。カメラパラメータを用いて、3次元空間上の任意の点を各カメラの画像面に投影するための投影行列を得ることができる。各カメラについての投影行列を用いて、3次元状の任意の点をカメラの撮影面のピクセル位置に変換する関数(行列)Pi が得られる。関数(行列)Pi は記憶部に格納される。
この変換により、同一の空間Ochk1で4台のカメラの相対位置・姿勢が表現・取得できる。さらに、チェッカーボード上のチェッカーパターンが設置されている高さ、並びに平板が床に対して垂直に設置されていることに基づいて、座標空間Ochk1から床面上に設定した世界座標系Ofloorへの同次変換行列chk1Rfloorが導出可能である。したがって、座標空間Ochk1においてpchk1と表される点の世界座標系Ofloorにおける座標pfloorを、次式で表すことができる。
以上から、座標空間Ochk1、Ochk2を通じて、空間内の全ての点の座標、並びに全てのカメラの位置・姿勢を、世界座標系Ofloorで表すことができる。本実施形態では、図7Aに示すように、3次元座標は、原点をトレッドミルの歩行面の中央にとり、トレッドミルのベルトの走行方向に沿って後方から前方へ向かう向きをy軸、ベルトの幅方向をx軸、鉛直上向きをz 軸とする座標空間とする。トレッドミルのベルトの位置・姿勢及びベルト上の対象の位置・姿勢は、世界座標で規定することができる。対象の3次元関節位置データは、ある時点における対象の姿勢に加えて、トレッドミルのベルト上の対象の位置情報を規定する。ベルトの速度は、y軸に沿った速度である。本実施形態に係るキャリブレーション装置についてまとめると、モーションキャプチャに用いる複数のカメラは、前記エンドレスベルトの前側に位置する1つあるいは複数の前側カメラと、前記エンドレスベルトの後側に位置する後側カメラと、を含み、前記トレッドミルには、キャリブレーション装置が設置可能であり、前記キャリブレーション装置は、前記エンドレスベルトの前後方向の中間に位置して垂直に設けられるチェッカーボードを備え、前記チェッカーボードの第1面には、前記前側カメラによって撮影される第1チェッカーパターンが設けてあり、前記チェッカーボードの第2面には、前記後側カメラによって撮影される第2チェッカーパターンが設けてある。図13では、前側の2台のカメラ及び後側の2台のカメラを用いてモーションキャプチャを行う態様を示しているが、例えば、前側の2台のカメラのみ、あるいは、後側の2台のカメラのみでモーションキャプチャを行う場合には、いずれか一方の面のチェッカーパターンを用いてもよい。また、ベルト平面に平行に設置した水平姿勢のチェッカーボートを、単独で用いて、あるいは、ダブルフェースチェッカーボードと組み合わせて用いて、キャリブレーションを行ってもよい。また、ダブルフェースチェッカーボードを、垂直姿勢と水平姿勢との間で回動可能に支持フレームに設けてもよい。
骨格モデルの各関節(図10左図)と、ヒートマップ取得部における身体の特徴点(図10右図、a,o,p,q,rを除く)とを対応させる。対応関係を表1に示す。
対象の動作計測の始点となる初期姿勢を取得する。本実施形態では、関節間距離・初期姿勢の推定を、初期画像に対し、OpenPoseを適用することで算出された特徴点のピクセル位置から求める。例えば、OpenPoseから算出した各特徴点の初期ヒートマップの重心のピクセル位置を特徴点の2次元位置と推定する。各カメラ画像上の対応する点の位置と、カメラパラメータを用いて、3次元空間上の特徴点の初期位置を推定する。初期位置が誤推定と判断された場合には、初期設定を再度行う。例えば、推定された特徴点の3D位置を各カメラ画像に投影した時の各座標のPCMスコアに閾値を設定することで誤推定を判定する。
関節位置取得部は、ヒートマップ取得部から取得されたヒートマップ情報を用いて関節位置候補を推定し、当該関節位置候補を用いて逆運動学に基づく最適化計算を実行することで骨格モデルの関節角、関節位置を更新する点に特徴を備えている。関節位置取得部は、ヒートマップデータに基づいて関節位置候補を推定する関節位置候補取得部と、関節位置候補を用いて逆運動学に基づく最適化計算を実行して関節角を算出する逆運動学計算部と、算出された関節角を用いて順運動学計算を実行して関節位置を算出する順運動学計算部と、を備えている。
関節位置取得部で取得された各関節位置は、関節位置の時系列データとして記憶部に格納される。本実施形態では、関節位置取得部で取得された各関節位置は平滑化処理部によって平滑化処理されて、平滑化関節位置が生成される。
関節位置取得部で用いたPCMの取得、逆運動学に基づく最適化計算は時系列的な関係を考慮していないため、出力される関節位置が時間的に滑らかである保証は無い。平滑化処理部の平滑化関節位置取得部では、関節の時系列情報を用いて、時間的な連続性を考慮した平滑化処理を行う。例えば、フレームt+1で取得された関節位置を平滑化する場合には、典型的には、フレームt+1で取得された関節位置、フレームtで取得された関節位置、フレームt-1で取得された関節位置が用いられる。また、平滑化関節位置取得部では、必ずしも連続するフレームを用いなくてもよい。計算を単純にするために、先ず、身体構造情報を用いずに平滑化を行う。このため隣接する関節の距離であるリンク長は保存されない。次いで、平滑化後の関節位置を用いて、再度、対象の骨格構造を使った逆運動学に基づく最適化計算を行って、前記対象の各関節角を取得することで、リンク長を保存した平滑化を行う。
本実施形態に係る入力画像から関節角度、特徴点の位置を取得するまでの工程を説明する。複数の同期したカメラによってトレッドミルの歩行面上の対象の動作が撮影され、各カメラから所定のフレームレートでRGB画像が出力される。ヒートマップ取得部は、入力画像を受信すると、対象の身体上の全特徴点において、該入力画像に基づいてヒートマップ(関節位置の確からしさの尤度の空間分布)を生成する。
動作データ取得部によって、歩行面上で歩行する対象の3D姿勢の時系列データが取得される。各フレームにおける対象の3D姿勢は、全ての特徴点(関節位置)の3次元座標によって特定される。動作分析部では、対象の3D姿勢の時系列データを用いて各種の動作分析を行う。動作分析部は、例えば、3次元動作計測を用いた歩行分析を実行する。例えば、重心位置や重心動揺データによって、対象の前後方向あるいは側方へのふらつきを判断することができる。対象の重心位置や身体のある部位の位置(例えば関節位置)のリサージュ図を生成する。また、動作分析部は、歩行中の対象の筋張力や筋活動を推定し、可視化してディスプレイに表示する。
例えば、対象の腕や肩の動きなどの上半身の動作も含め全身の運動をトレッドミルと同期させて詳細に定量化ないし可視化することで、全身の滑らかな運動として現れるようなリハビリテーションの効果を数値化できる。また、対象の重心の揺動と足の動き、トレッドミルの動きを連動させて観察することができる。また、トレッドミルのエンドレスベルトの走行速度を変化させる際の対象の全身の動作の変化をみることで、トレッドミルのみ、あるいはモーキャップのみでは観察できない、リハビリテーションの効果の評価ができる。
図7に示すように、本実施形態に係るトレッドミルは、動作データ取得部によって取得された動作データ(典型的には、歩行時の対象の姿勢の時系列データ)、あるいは/および、動作分析部で取得された分析データに基づいて、トレッドミルの動作を制御する制御部を備えている。
歩行リハビリテーション支援のため、トレッドミル上における患者(対象)の歩行運動データを利用してトレッドミルのベルト速度を制御する手法について説明する。第1の制御方式は、ベルトを患者の運動能力に合わせた速度で駆動する。患者の運動能力に対して歩行速度が遅すぎるとリハビリテーションの効果が薄まり、逆に無理に高速歩行を行おうとすると転倒などの危険が伴う。本実施形態に係るベルト速度制御では、患者が安全に無理なく歩けることが保証される範囲内で、可能な限り大きなベルト速度を出力する。第2の制御方式は、左右の脚に運動能力の差がある患者でも、直立に近い適切な歩行姿勢を保つように制御する。片麻痺などが原因で両脚の運動能力に差が生じると、運動能力が低い方の脚を引き摺るような姿勢で歩くことになる。トレッドミルのベルト速度に左右差をつけることによって両脚の運動能力差を補償する。本実施形態では、第1の制御方式と第2の制御方式を組み合わせたベルト速度制御手法を提供する。
を0に近づけるような制御を行う。目標値yref plvはキャリブレーション時に設定した座標系にしたがって設定され、本実施形態ではyref plv=0mmとする。
この値を0に近づけるような制御を行う。
ここで、ΔyLRa(t)を以下の通り定める。
このΔyLRa(t)は両脚の運動範囲のy方向中心のずれを表すので、第1制御方式における位置制御ないし速度制御に、ΔyLRa(t)を0に近づけるような第2制御方式を加える。すなわち、第2制御方式は、第1制御方式の位置制御あるいは速度制御と組み合わせて適用され得る。なお、第1制御方式(位置制御、速度制御)は健常者やアスリートの運動に用いることもできる。
本実施形態では、トレッドミル上の対象の動作データを用いて、時刻nf秒における各ベルト速度vL,ref(nf)、vR,ref(nf)を、以下の更新式に従ってfフレームごとに更新する。
ここで、ΔvL,ref(nf)、ΔvR,ref(nf)はベルト速度更新用の修正項である。
2つの定数kp1、kp2を用いてΔp(t)を以下のように定める。
2つの定数ks1、ks2を用いてΔs(t)を以下のように定める。
Δp(t)、Δs(t)を用いて、ΔvL,ref(nf)、ΔvR,ref(nf)を以下のように定める。
kp1、kp2、ks1、ks2の値は、当業者において適宜設定される。例えば、kp1=1.0、kp2=0.5、ks1=0.3、ks2=0.1、とする。図14に示すように、本実施形態では、トレッドミルとマーカレスモーションキャプチャを組み合わせることで、モーションキャプチャという1つの手段を用いるだけで、モーションキャプチャにより取得した動作データに基づいて、第1の制御方式と第2の制御方式にしたがった複数の制御を同時に行うことができる。
Claims (28)
- フレームと、
対象が載る歩行面を提供するエンドレスベルトと、
ベルト駆動部と、
フレームに設けてあり、姿勢および/あるいは位置が調整可能である複数のカメラと、
各カメラ画像で取得した画像情報を用いてマーカレスで対象の動作データを取得する動作データ取得部と、
を備えたモーションキャプチャ一体型トレッドミル。 - 前記動作データは、対象の姿勢及び対象の姿勢の時系列データを含む、
請求項1に記載のトレッドミル。 - 前記動作データは、前記対象の姿勢および/あるいは前記姿勢の時系列データに基づいて得られた情報を含む、
請求項2に記載のトレッドミル。 - 前記対象の姿勢は、エンドレスベルトの走行方向の第1軸、エンドレスベルトの幅方向の第2軸、鉛直方向の第3軸によって規定された3次元座標値として得られる、
請求項1、2いずれか1項に記載のトレッドミル。 - 前記動作データ取得部は、各カメラ画像で取得した対象の画像情報を用いて、対象の関節位置の確からしさの尤度の空間分布を取得し、前記尤度の空間分布に基づいて、各フレームおける対象の3次元姿勢を取得する、請求項1~4いずれか1項に記載のトレッドミル。
- 前記動作データを用いて対象の動作を分析する動作分析部を備えた請求項1~5いずれか1項に記載のトレッドミル。
- 前記動作分析部は、前記動作データに加えて、エンドレスベルトの動作情報を用いて対象の動作を分析する、
請求項6に記載のトレッドミル。 - 前記動作データに基づいて、当該トレッドミルの動作を制御する制御部を備えた、請求項1~7いずれか1項に記載のトレッドミル。
- 前記制御部は、
前記動作データに基づいて入力データを生成するデータ生成部と、
前記入力データに応じて制御信号を生成する制御信号生成部と、
を備え、
前記制御信号を前記ベルト駆動部に出力してベルト速度を制御する、
請求項8に記載のトレッドミル。 - エンドレスベルトは傾斜駆動部によって傾斜可能であり、
前記制御部は、前記制御信号を前駆傾斜駆動部に出力してベルト傾斜を制御する、
請求項9に記載のトレッドミル。 - 前記制御部は、対象の姿勢に基づいて得られた対象の位置情報に応じてベルト速度を制御する、
請求項9、10いずれか1項に記載のトレッドミル。 - 前記制御部は、対象の所定部位の位置を目標値に一致させるようにベルト速度を制御する、
請求項11に記載のトレッドミル。 - 前記制御部は、対象の姿勢の時系列データに基づいて得られた対象の所定部位の速度に応じてベルト速度を制御する、
請求項9、10いずれか1項に記載のトレッドミル。 - 前記制御部は、対象の所定部位の世界座標系における移動速度を0に近づけるようにベルト速度を制御する、
請求項13に記載のトレッドミル。 - 前記エンドレスベルトは、対象の左足が載る第1エンドレスベルトと、対象の右足が載る第2エンドレスベルトと、を含み、
前記駆動部は、第1エンドレスベルト用の第1駆動部と、第2エンドレスベルト用の第2駆動部と、を備え、
前記制御部は、前記動作データに応じて第1エンドレスベルトの速度及び第2エンドレスベルトの速度を独立して制御する、
請求項8~14いずれか1項に記載のトレッドミル。 - 前記制御部は、前記動作データに基づいて得られた左右の歩幅に差がある場合に、当該歩幅差を補償するように、前記第1エンドレスベルトの速度と前記第2エンドレスベルトの速度を制御する、
請求項15に記載のトレッドミル。 - 前記制御部は、前記動作データに基づいて前記対象の異変を検知した場合に、前記トレッドミルの動作を制御する、請求項8~10いずれか1項に記載のトレッドミル。
- 前記トレッドミルには、キャリブレーション装置が設置可能であり、
前記キャリブレーション装置は、前記エンドレスベルトの前後方向の中間に位置して垂直に設けられるチェッカーボードを備え、
前記チェッカーボードの第1面には、前記複数のカメラのうちの1つあるいは複数のカメラによって撮影可能な第1チェッカーパターンが設けてあり、
前記チェッカーボードの第2面には、前記複数のカメラのうちの残りの1つあるいは複数のカメラによって撮影可能な第2チェッカーパターンが設けてある、
請求項1に記載のトレッドミル。 - エンドレスベルトと、
ベルト駆動部と、
エンドレスベルト上で運動する対象の動きを取得するマーカレスモーションキャプチャと、
トレッドミルの動作を制御する制御部と、
を備え、
前記制御部は、前記モーションキャプチャで取得した対象の動作データに応じて前記トレッドミルの動作を制御する、
トレッドミル制御システム。 - 前記制御部は、
前記動作データに基づいて入力データを生成するデータ生成部と、
前記入力データに応じて制御信号を生成する制御信号生成部と、
を備え、
前記制御信号を前記ベルト駆動部に出力してベルト速度を制御する、
請求項19に記載のトレッドミル制御システム。 - エンドレスベルトは傾斜駆動部によって傾斜可能であり、
前記制御部は、前記制御信号を前駆傾斜駆動部に出力してベルト傾斜を制御する、
請求項20に記載のトレッドミル制御システム。 - 前記制御部は、対象の姿勢に基づいて得られた対象の位置情報に応じてベルト速度を制御する、
請求項20、21いずれか1項に記載のトレッドミル制御システム。 - 前記制御部は、対象の所定部位の位置を目標値に一致させるようにベルト速度を制御する、
請求項22に記載のトレッドミル制御システム。 - 前記制御部は、対象の姿勢の時系列データに基づいて得られた対象の所定部位の速度に応じてベルト速度を制御する、
請求項20、21いずれか1項に記載のトレッドミル制御システム。 - 前記制御部は、対象の所定部位の世界座標系における移動速度を0に近づけるようにベルト速度を制御する、
請求項24に記載のトレッドミル。 - 前記エンドレスベルトは、対象の左足が載る第1エンドレスベルトと、対象の右足が載る第2エンドレスベルトと、を含み、
前記駆動部は、第1エンドレスベルト用の第1駆動部と、第2エンドレスベルト用の第2駆動部と、を備え、
前記制御部は、前記動作データに応じて第1エンドレスベルトの速度及び第2エンドレスベルトの速度を独立して制御する、
請求項19~25いずれか1項に記載のトレッドミル制御システム。 - 前記制御部は、前記動作データに基づいて得られた左右の歩幅に差がある場合に、当該歩幅差を補償するように、前記第1エンドレスベルトの速度と前記第2エンドレスベルトの速度を制御する、
請求項26に記載のトレッドミル制御システム。 - 前記制御部は、前記動作データに基づいて前記対象の異変を検知した場合に、前記トレッドミルの動作を制御する、請求項19~21いずれか1項に記載のトレッドミル制御システム。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP20906820.4A EP4082635A4 (en) | 2019-12-26 | 2020-12-24 | SMART TREADMILL |
US17/786,773 US20230031291A1 (en) | 2019-12-26 | 2020-12-24 | Smart treadmill |
JP2021567590A JPWO2021132426A1 (ja) | 2019-12-26 | 2020-12-24 | |
KR1020227024162A KR20220116237A (ko) | 2019-12-26 | 2020-12-24 | 스마트 트레드밀 |
CN202080089354.1A CN114845785A (zh) | 2019-12-26 | 2020-12-24 | 智能跑步机 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2019236645 | 2019-12-26 | ||
JP2019-236645 | 2019-12-26 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021132426A1 true WO2021132426A1 (ja) | 2021-07-01 |
Family
ID=76574314
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/048346 WO2021132426A1 (ja) | 2019-12-26 | 2020-12-24 | スマートトレッドミル |
Country Status (7)
Country | Link |
---|---|
US (1) | US20230031291A1 (ja) |
EP (1) | EP4082635A4 (ja) |
JP (1) | JPWO2021132426A1 (ja) |
KR (1) | KR20220116237A (ja) |
CN (1) | CN114845785A (ja) |
TW (1) | TW202135902A (ja) |
WO (1) | WO2021132426A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7047176B1 (ja) | 2021-09-10 | 2022-04-04 | 株式会社エクサウィザーズ | 端末装置、情報処理方法、情報処理システム、及びプログラム |
JPWO2023027046A1 (ja) * | 2021-08-26 | 2023-03-02 | ||
EP4316610A1 (en) * | 2022-08-04 | 2024-02-07 | Pegatron Corporation | Treadmill and speed control method thereof |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI823561B (zh) * | 2021-10-29 | 2023-11-21 | 財團法人工業技術研究院 | 多模感知協同訓練系統及多模感知協同訓練方法 |
CN114694431A (zh) * | 2022-04-02 | 2022-07-01 | 浙江广厦建设职业技术大学 | 一种空中乘务教学用的仪态辅助训练装置 |
WO2024010825A1 (en) * | 2022-07-06 | 2024-01-11 | Terry Walter L | Smart individual motion capture and spatial translation (simcast) system |
DE102022120173A1 (de) | 2022-08-10 | 2024-02-15 | Centigrade GmbH | Laufbandsystem und Bausatz |
CN115501545B (zh) * | 2022-10-10 | 2024-03-08 | 江苏因特利斯智慧医疗科技研究院有限公司 | 医疗康复辅助训练装置 |
CN117162116B (zh) * | 2023-11-03 | 2024-01-12 | 合肥探奥自动化有限公司 | 一种融合人工智能的模仿人体动作机器人 |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5368532A (en) | 1993-02-03 | 1994-11-29 | Diversified Products Corporation | Treadmill having an automatic speed control system |
JPH10243979A (ja) | 1997-03-05 | 1998-09-14 | Hitachi Ltd | 歩行訓練装置 |
KR20100026691A (ko) * | 2008-09-01 | 2010-03-10 | 강성식 | 온라인 마라톤 연습장치 |
KR20120097119A (ko) * | 2011-02-24 | 2012-09-03 | 한국과학기술원 | 트레드밀 장치 |
JP2013226340A (ja) | 2012-04-27 | 2013-11-07 | Tekku Gihan:Kk | 歩行訓練装置 |
JP2015107247A (ja) | 2013-12-05 | 2015-06-11 | トヨタ自動車株式会社 | 歩行リハビリシステム |
US9526451B1 (en) * | 2012-01-11 | 2016-12-27 | Bertec Corporation | Force measurement system |
CN106540407A (zh) * | 2016-12-26 | 2017-03-29 | 唐小石 | 跑步机速度控制方法及装置 |
JP2017064120A (ja) * | 2015-09-30 | 2017-04-06 | 株式会社リコー | 情報処理装置およびシステム |
US9916011B1 (en) * | 2015-08-22 | 2018-03-13 | Bertec Corporation | Force measurement system that includes a force measurement assembly, a visual display device, and one or more data processing devices |
CN109646876A (zh) * | 2018-12-29 | 2019-04-19 | 中国科学院合肥物质科学研究院 | 一种基于虚拟场景共享的跑步机及其健身方法 |
JP6573739B1 (ja) * | 2019-03-18 | 2019-09-11 | 航 梅山 | 室内用有酸素運動装置、運動システム |
US10413230B1 (en) * | 2013-01-19 | 2019-09-17 | Bertec Corporation | Force measurement system |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4416293A (en) * | 1981-03-19 | 1983-11-22 | Anderson Blair V | Method and apparatus for recording gait analysis in podiatric diagnosis and treatment |
US4830021A (en) | 1988-08-29 | 1989-05-16 | Thornton William E | Monitoring system for locomotor activity |
WO1993006779A1 (en) | 1991-10-10 | 1993-04-15 | Neurocom International, Inc. | Apparatus and method for characterizing gait |
FR2730154B1 (fr) | 1995-02-08 | 1997-07-11 | Stephanois Rech | Dispositif de mesure des efforts exerces lors de la marche |
JP3153744B2 (ja) | 1995-09-26 | 2001-04-09 | 日立テクノエンジニアリング株式会社 | 走者応答運動装置 |
US6811517B1 (en) * | 2003-08-05 | 2004-11-02 | Paul William Eschenbach | Polestrider exercise apparatus with dual treads |
DE102007049323A1 (de) | 2007-10-15 | 2009-04-23 | Zebris Medical Gmbh | Vorrichtung und Verfahren zur Ganganalyse unter Einsatz eines Laufbandes |
US9770203B1 (en) * | 2013-01-19 | 2017-09-26 | Bertec Corporation | Force measurement system and a method of testing a subject |
-
2020
- 2020-12-24 KR KR1020227024162A patent/KR20220116237A/ko unknown
- 2020-12-24 JP JP2021567590A patent/JPWO2021132426A1/ja active Pending
- 2020-12-24 US US17/786,773 patent/US20230031291A1/en active Pending
- 2020-12-24 TW TW109146021A patent/TW202135902A/zh unknown
- 2020-12-24 WO PCT/JP2020/048346 patent/WO2021132426A1/ja unknown
- 2020-12-24 EP EP20906820.4A patent/EP4082635A4/en active Pending
- 2020-12-24 CN CN202080089354.1A patent/CN114845785A/zh active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5368532A (en) | 1993-02-03 | 1994-11-29 | Diversified Products Corporation | Treadmill having an automatic speed control system |
JPH10243979A (ja) | 1997-03-05 | 1998-09-14 | Hitachi Ltd | 歩行訓練装置 |
KR20100026691A (ko) * | 2008-09-01 | 2010-03-10 | 강성식 | 온라인 마라톤 연습장치 |
KR20120097119A (ko) * | 2011-02-24 | 2012-09-03 | 한국과학기술원 | 트레드밀 장치 |
US9526451B1 (en) * | 2012-01-11 | 2016-12-27 | Bertec Corporation | Force measurement system |
JP2013226340A (ja) | 2012-04-27 | 2013-11-07 | Tekku Gihan:Kk | 歩行訓練装置 |
US10413230B1 (en) * | 2013-01-19 | 2019-09-17 | Bertec Corporation | Force measurement system |
JP2015107247A (ja) | 2013-12-05 | 2015-06-11 | トヨタ自動車株式会社 | 歩行リハビリシステム |
US9916011B1 (en) * | 2015-08-22 | 2018-03-13 | Bertec Corporation | Force measurement system that includes a force measurement assembly, a visual display device, and one or more data processing devices |
JP2017064120A (ja) * | 2015-09-30 | 2017-04-06 | 株式会社リコー | 情報処理装置およびシステム |
CN106540407A (zh) * | 2016-12-26 | 2017-03-29 | 唐小石 | 跑步机速度控制方法及装置 |
CN109646876A (zh) * | 2018-12-29 | 2019-04-19 | 中国科学院合肥物质科学研究院 | 一种基于虚拟场景共享的跑步机及其健身方法 |
JP6573739B1 (ja) * | 2019-03-18 | 2019-09-11 | 航 梅山 | 室内用有酸素運動装置、運動システム |
Non-Patent Citations (5)
Title |
---|
MOTIONMETRIX: "Markerless Motion Capture", 0, 25 December 2019 (2019-12-25), XP055837831, Retrieved from the Internet <URL:https://web.archive.org/web/20191225050822/http://www.motionmetrix.se/4-technology> [retrieved on 20210312] * |
MUNDERMANN LARS, CORAZZA STEFANO, CHAUDHARI AJIT M., ALEXANDER EUGENE J., ANDRIACCHI THOMAS P.: "Most favorable camera configuration for a shape-from-silhouette markerless motion capture system for biomechanical analysis", VIDEOMETRICS VIII, PROCEEDINGS OF SPIE, vol. 5665, 17 January 2005 (2005-01-17), pages 1 - 11, XP055837835 * |
See also references of EP4082635A4 |
T. OHASHIY. IKEGAMIK. YAMAMOTOW. TAKANOY. NAKAMURA: "Video Motion Capture from the Part Confidence Maps of Multi-Camera Images by Spatiotemporal Filtering Using the Human Skeletal Model", 2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), MADRID, 2018, pages 4226 - 4231 |
Y. NAKAMURAK. YAMANEY. FUJITAI. SUZUKI: "Somatosensory computation for man-machine interface from motion-capture data and musculoskeletal human model", TRANS. ROB., vol. 21, no. 1, February 2005 (2005-02-01), pages 58 - 66, XP011126459, DOI: 10.1109/TRO.2004.833798 |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPWO2023027046A1 (ja) * | 2021-08-26 | 2023-03-02 | ||
WO2023027046A1 (ja) * | 2021-08-26 | 2023-03-02 | 株式会社CaTe | プログラム、情報処理装置、および情報処理方法 |
JP7411945B2 (ja) | 2021-08-26 | 2024-01-12 | 株式会社CaTe | プログラム、情報処理装置、および情報処理方法 |
JP7047176B1 (ja) | 2021-09-10 | 2022-04-04 | 株式会社エクサウィザーズ | 端末装置、情報処理方法、情報処理システム、及びプログラム |
JP2023040882A (ja) * | 2021-09-10 | 2023-03-23 | 株式会社エクサウィザーズ | 端末装置、情報処理方法、情報処理システム、及びプログラム |
EP4316610A1 (en) * | 2022-08-04 | 2024-02-07 | Pegatron Corporation | Treadmill and speed control method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN114845785A (zh) | 2022-08-02 |
JPWO2021132426A1 (ja) | 2021-07-01 |
TW202135902A (zh) | 2021-10-01 |
EP4082635A4 (en) | 2023-06-14 |
KR20220116237A (ko) | 2022-08-22 |
EP4082635A1 (en) | 2022-11-02 |
US20230031291A1 (en) | 2023-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021132426A1 (ja) | スマートトレッドミル | |
US10860843B1 (en) | Measurement system that includes at least one measurement assembly, a head-mounted visual display device, and a data processing device | |
US10555688B1 (en) | Measurement system that includes at least one measurement assembly, a head-mounted visual display device, and a data processing device | |
US9916011B1 (en) | Force measurement system that includes a force measurement assembly, a visual display device, and one or more data processing devices | |
WO2020054442A1 (ja) | 関節位置の取得方法及び装置、動作の取得方法及び装置 | |
CN107174255B (zh) | 基于Kinect体感技术的三维步态信息采集与分析方法 | |
Noma et al. | Design for locomotion interface in a large scale virtual environment ATLAS: ATR locomotion interface for active self motion | |
US20180070864A1 (en) | Methods and devices for assessing a captured motion | |
US9727779B2 (en) | Motion information processing apparatus | |
CN107632698B (zh) | 基于影像的动作分析系统与方法 | |
Gruben et al. | Force direction pattern stabilizes sagittal plane mechanics of human walking | |
CN108564643B (zh) | 基于ue引擎的表演捕捉系统 | |
US9360932B1 (en) | Systems and methods for virtually displaying real movements of objects in a 3D-space by means of 2D-video capture | |
Wang et al. | Quantitative assessment of dual gait analysis based on inertial sensors with body sensor network | |
CN102679964B (zh) | 步态参数测量系统及其数据处理装置和方法 | |
CN110327187A (zh) | 一种外骨骼的带先验力矩无模型控制方法 | |
CN117529278A (zh) | 步态监测方法及机器人 | |
Laribi et al. | Human lower limb operation tracking via motion capture systems | |
CN113940667B (zh) | 基于助行器的防摔倒助行方法、系统和终端设备 | |
JP5949477B2 (ja) | 移動体の遠隔操作方法および遠隔操作装置 | |
US20110166821A1 (en) | System and method for analysis of ice skating motion | |
JP6123520B2 (ja) | 下肢形状変化測定装置、方法及びプログラム | |
US11857331B1 (en) | Force measurement system | |
US20200320283A1 (en) | Determining golf swing characteristics | |
WO2016203285A1 (en) | Systems and methods for virtually displaying real movements of objects in a 3d-space |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20906820 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2021567590 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20227024162 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2020906820 Country of ref document: EP Effective date: 20220726 |