WO2021219643A1 - Procédé de détermination du développement ou de l'état de développement d'un petit enfant ou d'un nourrisson - Google Patents

Procédé de détermination du développement ou de l'état de développement d'un petit enfant ou d'un nourrisson Download PDF

Info

Publication number
WO2021219643A1
WO2021219643A1 PCT/EP2021/060995 EP2021060995W WO2021219643A1 WO 2021219643 A1 WO2021219643 A1 WO 2021219643A1 EP 2021060995 W EP2021060995 W EP 2021060995W WO 2021219643 A1 WO2021219643 A1 WO 2021219643A1
Authority
WO
WIPO (PCT)
Prior art keywords
development
infant
toddler
body model
measured values
Prior art date
Application number
PCT/EP2021/060995
Other languages
German (de)
English (en)
Inventor
A. Sebastian SCHRÖDER
Nikolas HESSE
Sergi PUJADES
Original Assignee
Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
MAX-PLANCK-Gesellschaft zur Förderung der Wissenschaften e.V.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V., MAX-PLANCK-Gesellschaft zur Förderung der Wissenschaften e.V. filed Critical Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
Publication of WO2021219643A1 publication Critical patent/WO2021219643A1/fr

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
    • 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
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1071—Measuring physical dimensions, e.g. size of the entire body or parts thereof measuring angles, e.g. using goniometers
    • 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
    • A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
    • A61B5/1122—Determining geometric values, e.g. centre of rotation or angular range of movement of movement trajectories
    • 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
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/04—Babies, e.g. for SIDS detection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4842—Monitoring progression or stage of a disease

Definitions

  • Embodiments of the present invention relate to a method for evaluating a motor or mental development or level of development of a toddler or infant, and in particular to a method for determining a motor or mental development of a toddler or infant based on RGB-D movement detection Toddlers or infants.
  • Marker-based movement detection of infants is known from [1] and [18].
  • this marker-based movement detection has the disadvantages that the infants' freedom of movement is impaired, that fastening the sensors is very complex, that movements can only be measured at individual points, and that the costs required for this are sometimes very high.
  • Motion detection using 2D RGB cameras is known from [2], [4], [20] and [21], but this does not allow a comprehensive detection ("skeleton") and no detection of rotations.
  • a categorization of movement data is known from [5].
  • sensors such as electromagnetic sensors or video cameras
  • movements are recorded, which are then processed with any method, so that an automated classification into any categories can take place.
  • electromagnetic sensors again has the disadvantage that freedom of movement is impaired, that fastening the sensors is very complex, and that movements can only be measured at individual points.
  • video cameras has the disadvantage that only relatively imprecise 2D movement data can be derived from the video data obtained.
  • SMPL model Skinned Multi-Person Linear Model
  • the conventional methods described above for detecting movements have the disadvantage that they supply relatively imprecise movement data and / or require a doctor to manually evaluate the models derived from the movement data.
  • the present invention is therefore based on the object of creating a concept which enables the movements of an infant or toddler to be recorded with greater accuracy and an automated evaluation of the recorded movements.
  • Embodiments create a method for determining [eg assessment or assessment or evaluation] of [eg motor and / or mental [eg cognitive]] development [eg or stage of development] of a toddler or infant.
  • the method comprises a step of determining a sequence of 3D point clouds [e.g. three-dimensional point clouds] from 3D data [e.g. three-dimensional data, such as three-dimensional video data] obtained by recording the toddler or infant with a depth camera [e.g. RGB depth camera] became.
  • the method also includes a step of embedding [eg registering] a 3D body model [eg three-dimensional body model] of the toddler or infant in the sequence of 3D point clouds.
  • the method further comprises a step of performing measurements on the embedded 3D body model in order to obtain measured values which describe at least one movement of the 3D body model. Furthermore, the method comprises a step of determining the [eg motor and / or mental] development [eg or the level of development] of the toddler or infant based on the measured values. The method further comprises a step of outputting a signal that describes the motor and / or mental development of the toddler or infant.
  • the determination of the motor and / or mental development of the toddler or infant can be automated [e.g. by a computer or microprocessor]
  • the measured values can describe a time profile of the at least one movement of the 3D body model.
  • the measured values can describe at least one of the angle of at least one joint of the 3D body model
  • At least one parameter e.g. Standard deviation
  • the measured values e.g. Angles and / or positions of a joint of the 3D body mode
  • the measured values or parameters derived therefrom can be evaluated using an artificial neural network or an algorithm based on machine learning.
  • the measured values or parameters derived therefrom can be used can be compared with reference measured values or reference parameters stored in a database.
  • the output signal can indicate a development class.
  • the output signal can also indicate a confidence value.
  • distances between points of the 3D point clouds and corresponding points [e.g. a surface] of the 3D body model is reduced [e.g. minimized].
  • the 3-D body model can include a surface model and joints, the joints having at least one degree of freedom [e.g. with two or three degrees of freedom] are modeled.
  • the method can have a step of recording the toddler or infant with the RGB depth camera in order to obtain the 3D data.
  • the 3D data can have a sequence of depth images, wherein when determining the sequence of 3D point clouds, the sequence of 3D point clouds is determined from the sequence of depth images as a function of parameters of the RGB depth camera [e.g. is calculated.
  • Further exemplary embodiments relate to a detection of the movement of infants / children and an automated, objective assessment (motor and / or mental development / early detection of movement disorders / objective description of the developmental neurological state).
  • Further exemplary embodiments relate to a quantitative assessment of the motor and / or mental development of infants and small children based on RGB-D movement detection using a statistical body model.
  • Device for determining [e.g. assessment or assessment] of a motor and / or mental development of a toddler or infant the device being a digital data processing device [e.g. a processor, SoC [system on a chip, German one-chip system] or microcontroller] , an input interface that works with the digital Data processing device is connected, and an output interface which is connected to the digital data processing device, wherein the digital data processing device is configured to
  • FIG. 1 shows a flow chart of a method for determining a motor and / or mental development of a toddler or infant, according to an exemplary embodiment of the present invention.
  • FIG. 2 shows a schematic view of an automated determination of a motor and / or mental development of a toddler or infant, according to an exemplary embodiment of the present invention
  • FIG. 3 shows a schematic block diagram of a device for determining a motor and / or mental development of a toddler or infant, according to an exemplary embodiment of the present invention.
  • FIG. 1 shows a flow chart of a method 100 for determining a motor and / or mental development of a toddler or infant, according to an exemplary embodiment of the present invention.
  • the method 100 includes a step 102 determining a sequence of 3D point clouds from 3D data obtained by capturing the toddler or infant with a depth camera.
  • the method 100 further comprises a step 104 of embedding or registering a 3D body model of the toddler or infant in the sequence of 3D point clouds.
  • the method 100 further comprises a step 106 of performing measurements on the embedded 3D body model in order to obtain measured values which describe at least one movement of the 3D body model.
  • the method 100 further includes a step 108 of determining the motor and / or mental development of the toddler or infant based on the measured values.
  • the method 100 further comprises a step 110 of outputting a signal that describes the motor and / or mental development of the toddler or infant.
  • the toddler or infant can be filmed, for example, with a depth camera, such as an RGB depth camera or RGB-D camera, in order to obtain the 3D data, which include, for example, 3D point maps (depth information) and color images.
  • a depth camera such as an RGB depth camera or RGB-D camera
  • RGB red, green, blue
  • D Depth
  • the sequence of 3D point clouds can be determined from these 3D data.
  • the recording of the toddler or infant with such a depth camera does not necessarily have to be part of the method 100.
  • the 3D data can also be provided by means of a data carrier or a network connection, the 3D data having been obtained in advance, for example, by recording the toddler or infant with a depth camera.
  • the 3D body model e.g. toddler or infant model
  • this data e.g. 3D point clouds
  • any measurements can be made in 3D on the registered 3D body model, such as joint angles, positions, speeds, Accelerations. Since the shape and pose of the registered 3D body fashion (eg essentially) correspond to the real toddler or infant, the measured values can be directly transferred to the real toddler or the real infant.
  • these measurements can be used for a medical assessment of the motor and / or mental development status, for example to train a machine learning classifier that assigns a class, e.g. normal / abnormal motor and / or mental development, to the measured movements.
  • a class e.g. normal / abnormal motor and / or mental development
  • the RGB-D sensor used in exemplary embodiments is inexpensive, 3D-capable, does not impair the movements, and requires only minimal effort to use.
  • the 3D body model used in exemplary embodiments can capture movements of the entire body, including a body surface and body joints, including rotations. It has been shown that enough movement information is recorded for medical movement analysis.
  • relevant features can be extracted (e.g. from the 3D body model or from the measurements carried out on the body model), on the basis of which an abnormal motor and / or mental development can be recognized.
  • two complementary features can be extracted which provide a "confidence value" for the recognition. This is used to subdivide into predictions with high confidence and predictions with low confidence for which a human expert is consulted.
  • FIG. 2 shows a schematic view of an automated determination of a motor and / or mental development of a toddler or infant 120, according to an exemplary embodiment of the present invention.
  • the toddler or infant 120 can be recorded by means of a depth camera 122.
  • the depth camera 122 supplies 3D data 124, such as depth images (e.g. color images and depth Information).
  • 3D data can also be provided by means of a data carrier or via a network connection, as has already been indicated above.
  • a sequence 126 of 3D point clouds 128 can be determined from the 3D data 124, in which a 3D body model 130 of the toddler or infant 120 can be registered or embedded.
  • 3D point clouds can be calculated from the depth images with the aid of the camera parameters.
  • the 3D body mode can be fitted into this (or registered or embedded).
  • the distance between the points of the point cloud and the surface of the body model is minimized.
  • the registration or embedding of the body model in the sequence of 3D point clouds is described in detail in [9] and [10].
  • measurements can be carried out on the basis of the embedded 3D body model in order to obtain measured values 131 which describe one or more movements of the 3D body model 130 or a temporal course of the movements.
  • the measured values 131 can be, for example:
  • Speeds of one or more joints of the 3D body model speeds of one or more points of the 3D body model, accelerations of one or more joints of the 3D body model, and / or accelerations of one or more points of the 3D body model.
  • one of the motor and / or mental development 132 of the toddler or infant 120 can be determined based on the measured values 131, for example by deriving one or more parameters 134 from the measured values 131 and determining the motor and / or mental development 132 as a function the parameter 134.
  • a signal 140 can also be output which describes the motor and / or mental development of the toddler or infant.
  • the 3-D body model allows all joint angles to be read out directly, since the surface model contains a “skeleton” with defined joints. Each joint is modeled with three degrees of freedom. In addition, all joint positions or any points on the body surface can be derived in 3D (in the camera's reference coordinate system).
  • joint angles or positions viewed over time represent the recorded movements as time series. These values can be used to derive quantitative parameters that can be interpreted by humans and that can be helpful to doctors when assessing a patient, such as the standard deviation of the joint angles / positions over the entire recording, volume covered with extremities in space, distance covered by the extremities, or the distance covered opposite to gravity.
  • the above-mentioned parameters defined by experts can be used to train a machine learning classifier, e.g. neural networks, support vector machines.
  • a machine learning classifier e.g. neural networks, support vector machines.
  • CNNs convolutional neural networks
  • RNNs recurrent neural networks
  • LSTM long-short term memory neural networks
  • movement data can also be used directly as input for machine learning methods.
  • relevant parameters or features that contribute to the decision-making process are not determined by experts, but learned.
  • the expert knowledge can be incorporated in that they have medically assessed the sequences from which the training data originate and thus each training sequence receives a label, ie a medical point value, such as in clinical examinations for the Early detection of CP (cerebral palsy, dt. Infantile cerebral palsy) or for assessing the condition of children with spinal muscular atrophy.
  • a confidence value can be output in exemplary embodiments so that, for example, a traffic light system can be implemented in which, for example, green means: the child definitely shows normal movement patterns, red: the child definitely shows abnormal movement patterns and requires further examinations by experts, yellow: the measured values do not allow a clear statement and the child should be checked regularly until a clear decision can be made.
  • a traffic light system can be implemented in which, for example, green means: the child definitely shows normal movement patterns, red: the child definitely shows abnormal movement patterns and requires further examinations by experts, yellow: the measured values do not allow a clear statement and the child should be checked regularly until a clear decision can be made.
  • the device 180 comprises a digital data processing device 182, such as a processor, SoC (System on a Chip, dt. One-Chip-Syetm) or microcontroller, an input interface 184, which is connected to the digital data processing device 182, and an output interface 184, which is connected to the digital data processing device 182, wherein the digital data processing device 182 is configured to
  • 3D data 124 which were obtained by recording the toddler or baby with a depth camera, via the input interface 184, to determine a sequence of 3D point clouds from the 3D data, to add a 3D body model of the toddler or baby to the sequence embed from 3D point clouds,
  • the input interface 184 can be connectable, for example, to a depth camera in order to obtain the 3D data.
  • the input interface 184 can also be connectable to a network or a data carrier in order to receive the 3D data that were obtained in advance, for example, by recording the toddler or infant with a depth camera.
  • the output interface 186 can, for example, be connectable to a display or else to a network or a data carrier.
  • Embodiments of the present invention enable a highly precise, detailed recording of movements of the whole body including rotations of the individual joints in 3D with little cost and time expenditure, without impairing the patient.
  • Embodiments of the present invention also provide confidence for prediction, which is an important factor for practical application in, for example, a clinic.
  • Embodiments of the present invention are used for an objective, automated medical analysis of movements.
  • exemplary embodiments are used for a comprehensive screening of the general population in order to identify children with motor development deviating from the norm and to examine them in more detail or to refer them to experts.
  • Quantitative movement data support doctors in making / verifying a diagnosis.
  • exemplary embodiments are used to track the development of a child over time, i.e. the evaluation in the course no longer only depends on the subjective perception of a doctor, but can be understood on the basis of quantitative measurements.
  • aspects have been described in connection with a device, it goes without saying that these aspects also represent a description of the corresponding method, so that a block or a component of a device is also to be understood as a corresponding method step or as a feature of a method step. Analogously, aspects that have been described in connection with or as a method step also represent a description of a corresponding block or details or features of a corresponding device.
  • Some or all of the method steps can be carried out by a hardware apparatus (or using a hardware Apparatus), such as a microprocessor, a programmable computer or an electronic circuit. In some embodiments, some or more of the most important process steps can be performed by such an apparatus.
  • embodiments of the invention can be implemented in hardware or in software.
  • the implementation can be carried out using a digital storage medium such as a floppy disk, a DVD, a Blu-ray disk, a CD, a ROM, a PROM, an EPROM, an EEPROM or a FLASH memory, a hard disk or other magnetic memory or optical memory, on which electronically readable control signals are stored, which can interact or cooperate with a programmable computer system in such a way that the respective method is carried out. Therefore, the digital storage medium can be computer readable.
  • Some exemplary embodiments according to the invention thus include a data carrier which has electronically readable control signals which are capable of interacting with a programmable computer system in such a way that one of the methods described herein is carried out.
  • exemplary embodiments of the present invention can be implemented as a computer program product with a program code, the program code being effective to carry out one of the methods when the computer program product runs on a computer.
  • the program code can, for example, also be stored on a machine-readable carrier.
  • exemplary embodiments include the computer program for performing one of the methods described herein, the computer program being stored on a machine-readable carrier.
  • an exemplary embodiment of the method according to the invention is thus a computer program which has a program code for performing one of the methods described herein when the computer program runs on a computer.
  • a further exemplary embodiment of the method according to the invention is thus a data carrier (or a digital storage medium or a computer-readable medium) on which the computer program for performing one of the methods described herein is recorded.
  • the data carrier, the digital storage medium or the computer-readable one Medium are typically tangible and / or non-perishable or non-transitory.
  • a further exemplary embodiment of the method according to the invention is thus a data stream or a sequence of signals which represents or represents the computer program for performing one of the methods described herein.
  • the data stream or the sequence of signals can, for example, be configured to be transferred via a data communication connection, for example via the Internet.
  • Another exemplary embodiment comprises a processing device, for example a computer or a programmable logic component, which is configured or adapted to carry out one of the methods described herein.
  • a processing device for example a computer or a programmable logic component, which is configured or adapted to carry out one of the methods described herein.
  • Another exemplary embodiment comprises a computer on which the computer program for performing one of the methods described herein is installed.
  • a further exemplary embodiment according to the invention comprises a device or a system which is designed to transmit a computer program for performing at least one of the methods described herein to a receiver.
  • the transmission can take place electronically or optically, for example.
  • the receiver can be, for example, a computer, a mobile device, a storage device or a similar device.
  • the device or the system can comprise, for example, a file server for transmitting the computer program to the recipient.
  • a programmable logic component for example a field-programmable gate array, an FPGA
  • a field-programmable gate array can interact with a microprocessor in order to carry out one of the methods described herein.
  • the methods are performed by any hardware device. This can be hardware that can be used universally, such as a computer processor (CPU), or hardware specific to the method, such as an ASIC, for example.
  • the devices described herein can be implemented, for example, using a hardware device, or using a computer, or using a combination of a hardware device and a computer.
  • the devices described herein, or any components of the devices described herein can be implemented at least partially in hardware and / or in software (computer program).
  • the methods described herein can be implemented using hardware apparatus, or using a computer, or using a combination of hardware apparatus and a computer.

Abstract

Les modes de réalisation selon l'invention se rapportent à un procédé de détermination du développement moteur d'un petit enfant ou d'un nourrisson. Le procédé présente les étapes consistant à déterminer une séquence des nuages de points en 3D à partir de données 3D qui ont été obtenues par enregistrement du petit enfant ou du nourrisson au moyen d'une caméra de profondeur RGB ; à intégrer un modèle corporel en 3D du petit enfant ou du nourrisson dans la séquence des nuages de points en 3D ; à réaliser des mesures sur le modèle corporel en 3D intégré afin d'obtenir des valeurs de mesure qui décrivent au moins un mouvement du modèle corporel en 3D ; à déterminer le développement moteur du petit enfant ou du nourrisson sur la base des valeurs de mesure ; et à émettre un signal qui décrit le développement moteur du petit enfant ou du nourrisson.
PCT/EP2021/060995 2020-04-29 2021-04-27 Procédé de détermination du développement ou de l'état de développement d'un petit enfant ou d'un nourrisson WO2021219643A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102020205434.7A DE102020205434A1 (de) 2020-04-29 2020-04-29 Verfahren zur Ermittlung einer Entwicklung oder eines Entwicklungsstands eines Kleinkinds oder Säuglings
DE102020205434.7 2020-04-29

Publications (1)

Publication Number Publication Date
WO2021219643A1 true WO2021219643A1 (fr) 2021-11-04

Family

ID=75769567

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2021/060995 WO2021219643A1 (fr) 2020-04-29 2021-04-27 Procédé de détermination du développement ou de l'état de développement d'un petit enfant ou d'un nourrisson

Country Status (2)

Country Link
DE (1) DE102020205434A1 (fr)
WO (1) WO2021219643A1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114081447B (zh) * 2021-11-22 2024-04-02 西安交通大学 一种基于普通视频输入的婴儿脑发育状态评估系统
CN114469072B (zh) * 2021-12-08 2023-08-08 四川大学华西第二医院 用摄像机自动预测婴儿心理发育的方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050265583A1 (en) 1999-03-08 2005-12-01 Vulcan Patents Llc Three dimensional object pose estimation which employs dense depth information
WO2007029012A1 (fr) 2005-09-09 2007-03-15 Ntnu Technology Transfer As Classement de donnees de mouvement dans des categories
US20140066780A1 (en) * 2010-08-26 2014-03-06 University Of California System for evaluating infant movement using gesture recognition
US20140153794A1 (en) 2011-01-25 2014-06-05 John Varaklis Systems and methods for medical use of motion imaging and capture
CN104524742A (zh) 2015-01-05 2015-04-22 河海大学常州校区 一种基于Kinect传感器的脑瘫儿童康复训练方法
WO2016207311A1 (fr) 2015-06-24 2016-12-29 MAX-PLANCK-Gesellschaft zur Förderung der Wissenschaften e.V. Modèle linéaire multi-personne revêtu

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050265583A1 (en) 1999-03-08 2005-12-01 Vulcan Patents Llc Three dimensional object pose estimation which employs dense depth information
WO2007029012A1 (fr) 2005-09-09 2007-03-15 Ntnu Technology Transfer As Classement de donnees de mouvement dans des categories
US20140066780A1 (en) * 2010-08-26 2014-03-06 University Of California System for evaluating infant movement using gesture recognition
US20140153794A1 (en) 2011-01-25 2014-06-05 John Varaklis Systems and methods for medical use of motion imaging and capture
CN104524742A (zh) 2015-01-05 2015-04-22 河海大学常州校区 一种基于Kinect传感器的脑瘫儿童康复训练方法
WO2016207311A1 (fr) 2015-06-24 2016-12-29 MAX-PLANCK-Gesellschaft zur Förderung der Wissenschaften e.V. Modèle linéaire multi-personne revêtu

Non-Patent Citations (27)

* Cited by examiner, † Cited by third party
Title
A. CENCI ET AL.: "Movements Analysis of Preterm Infants by Using Depth Senso", PROCEEDINGS OF THE 1ST INTERNATIONAL CONFERENCE ON INTERNET OF THINGS AND MACHINE LEARNING, vol. 12, no. 1-12, pages 9
GRAVEM, D.SINGH, M.CHEN, C.RICH, J.VAUGHAN, J.GOLDBERG, K.WAFFARN, F.CHOU, P.COOPER, D.REINKENSMEYER, D. ET AL.: "Assessment of infant movement with a compact wireless accelerometer system", JOURNAL OF MEDICAL DEVICES, vol. 6, no. 2, 2012, pages 021013
H. RAHMATI ET AL.: "Frequency Analysis and Feature Reduction Method for Prediction of Cerebral Palsy in Young Infants", IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, vol. 24, no. 11, 2016, pages 1225 - 1234, XP011635257, ISSN: issn: 1534-4320., DOI: 10.1109/TNSRE.2016.2539390
HEIKE PHILIPPIDOMINIK KARCHKEUN-SUN KANGKATARZYNA WOCHNERJOACHIM PIETZHARTMUT DICKHAUSMIJA HADDERS-ALGRA: "Coputer-based analysis of general movement reveals sterotypies predicting cerebral palsy", DEVELOPMENTAL MEDICINE & CHILD NEUROLOGY, vol. 56, no. 10, 2014, pages 960 - 967
HEINZE, F.HESELS, K.BREITBACH-FALLER, N.SCHMITZ-RODE, T.DISSELHORST-KLUG,C.: "Movement analysis by accelerometry of newborns and infants for the early detection of movement disorders due to infantile cerebral palsy", MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, vol. 48, no. 8, 2010, pages 765 - 772, XP019835526
HESSE NIKOLAS ET AL: "Learning an Infant Body Model from RGB-D Data for Accurate Full Body Motion Analysis", 26 September 2018, ADVANCES IN INTELLIGENT DATA ANALYSIS XIX; [LECTURE NOTES IN COMPUTER SCIENCE; LECT.NOTES COMPUTER], SPRINGER INTERNATIONAL PUBLISHING, CHAM, PAGE(S) 792 - 800, ISBN: 978-3-540-28540-3, ISSN: 0302-9743, XP047557672 *
HESSE NIKOLAS ET AL: "Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, IEEE COMPUTER SOCIETY, USA, vol. 42, no. 10, 5 June 2019 (2019-06-05), pages 2540 - 2551, XP011807104, ISSN: 0162-8828, [retrieved on 20200902], DOI: 10.1109/TPAMI.2019.2917908 *
KANEMARU, N.WATANABE, H.KIHARA, H.NAKANO, H.NAKAMURA, T.NAKANO, J.KONISHI, Y.: "Jerky spontaneous movements at term age in preterm infants who later developed cerebral palsy", EARLY HUMAN DEVELOPMENT, vol. 90, no. 8, 2014, pages 387 - 392
KANEMARU, N.WATANABE, H.KIHARA, H.NAKANO, H.TAKAYA, R.NAKAMURA, T.NAKANO, J.TAGA, G.KONISHI, Y: "Specific characteristics of spontaneous move ments in preterm infants at term age are associated with developmental delays at age 3 years", DEVELOPMENTAL MEDICINE & CHILD NEUROLOGY, vol. 55, no. 8, 2013, pages 713 - 721
KARCH, D.KANG, K.S.WOCHNER, K.PHILIPPI, H.HADDERS-ALGRA, M.PIETZ, J.DICKHAUS, H.: "Kinematic assessment of stereotypy in spontaneous movements in infants", GAIT & POSTURE, vol. 36, no. 2, 2012, pages 307 - 311, XP028499142, DOI: 10.1016/j.gaitpost.2012.03.017
KARCH, D.KIM, K.S.WOCHNER, K.PIETZ, J.DICKHAUS, H.PHILIPPI, H: "Quantification of the segmental kinematics of spontaneous infant movements", JOURNAL OF BIOMECHANICS, vol. 41, no. 13, 2008, pages 2860 - 2867, XP025405284, DOI: 10.1016/j.jbiomech.2008.06.033
KARCH, D.WOCHNER, K.KIM, K.PHILIPPI, H.HADDERS-ALGRA, M.PIETZ, J.DICKHAUS, H.: "Quantitative score for the evaluation of kinematic recordings in neuropediatric diagnostics", METHODS OF INFORMATION IN MEDICINE, vol. 49, no. 05, 2010, pages 526 - 530
L. ADDE ET AL.: "Early prediction of cerebral palsy by computer-based video analysis of general movements: a feasibility study", DEVELOPMENTAL MEDICINE & CHILD NEUROLOGY, vol. 52, no. 8, 2010, pages 773 - 778
L. ADDE ET AL.: "Identification of fidgety movements and prediction of CP by the use of computer-based video analysis is more accurate when based on two video recordings", PHYSIOTHERAPY THEORY AND PRACTICE, vol. 29, no. 6, 2013, pages 469 - 475
L. MEINECKEN. BREITBACH-FALLERC. BARTZR. DAMENG. RAUC. DISSELHORST-KLUG: "Movement analysis in the early detection of newborns at risk for developing spasticity due to infantile cerebral palsy", HUMAN MOVEMENT SCIENCE, vol. 25, no. 2, 2006, pages 125 - 144
LARS ADDEJORUNN L. HELBOSTADALEXANDER REFSUM JENSENIUSGUNNAR TARALDSENRAGNHILD STOEN: "Using computer-based video analysis in the study of fidgety movements", EARLY HUMAN DEVELOPMENT, vol. 85, no. 9, 2009, pages 541 - 547, XP026520684, DOI: 10.1016/j.earlhumdev.2009.05.003
M. D. OLSEN ET AL.: "Computer Vision - ECCV 2014 Workshops", 2015, SPRINGER INTERNATIONAL PUBLISHING, article "Model-Based Motion Tracking of Infants", pages: 673 - 685
MACHIREDDY, A.VAN SANTEN, J.WILSON, J.L.MYERS, J.HADDERS-ALGRA, M.SONG,X.: "39th An-nual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC", 2017, IEEE, article "A video/IMU hybrid system for movement estimation in infants", pages: 730 - 733
MCCAY KEVIN D ET AL: "Abnormal Infant Movements Classification With Deep Learning on Pose-Based Features", IEEE ACCESS, IEEE, USA, vol. 8, 11 March 2020 (2020-03-11), pages 51582 - 51592, XP011779899, DOI: 10.1109/ACCESS.2020.2980269 *
NIKOLAS HESSESERGI PUJADESJAVIER ROMEROMICHAEL J. BLACKCHRISTOPH BODENSTEINERMICHAEL ARENSULRICH GHOFMANN, UTA TACKEMIJNA HADDERS-: "Learning an Infant Body Model from RGB-D Data for Accurate Full Body Motion Analysis", MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, 2018, pages 792 - 800, XP047488736, DOI: 10.1007/978-3-030-00928-1_89
NIKOLAS HESSESERGI PUJADESMICHAEL BLACKMICHAEL ARENSULRICH HOFMANNSEBASTIAN SCHROEDER: "Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019
RAHMATI, H.AAMO, O. M.STAVDAHL, 0.DRAGON, R.ADDE, L.: "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society", August 2014, IEEE., article "Videobased early cerebral palsy prediction using motion segmentation", pages: 3779 - 3783
RAHMATI, H.DRAGON, R.AAMO, O.M.ADDE, LSTAVDAHL, 0.VAN GOOL, L: "Weakly supervised motion segmentation with particle matching", COMPUTER VISIONAND IMAGE UNDERSTANDING, vol. 140, 2015, pages 30 - 42, XP029269239, DOI: 10.1016/j.cviu.2015.07.004
RANGNHILD STOENNILS THOMAS SONGSTADINGER EISABETH SILBERGTORIL FJOETORFT, ALEXANDERREFSUM JENSENIUSLARS ADDE ON BEHALF OFT HE CIMA: "Computer-based video analysis identifies infants with absence of fidgety movements", PEDIATRIC RESEARCH, vol. 82, no. 4, 2017, pages 665 - 670
S. ORLANDI ET AL.: "Detection of Atypical and Typical Infant Movements using Computer-based Video Analysis", 2018 40TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC, 2018, pages 3598 - 3601, XP033429126, DOI: 10.1109/EMBC.2018.8513078
S. S. SHIVAKUMAR ET AL.: "Stereo 3D tracking of infants in natural play conditions", 2017 INTERNATIONAL CONFERENCE ON REHABILITATION ROBOTICS (ICORR, 2017, pages 841 - 846, XP033141682, DOI: 10.1109/ICORR.2017.8009353
STAHL, A.SCHELLEWALD, C.STAVDAHL, 0.AAMO, O.M.ADDE, L.KIRKEROD, H.: "Anoptical flow-based method to predict infantile cerebral palsy", IEEE TRANSACTIONSON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, vol. 20, no. 4, 2012, pages 605 - 614, XP011491743, DOI: 10.1109/TNSRE.2012.2195030

Also Published As

Publication number Publication date
DE102020205434A1 (de) 2021-11-04

Similar Documents

Publication Publication Date Title
Marchi et al. Automated pose estimation captures key aspects of General Movements at eight to 17 weeks from conventional videos
WO2021219643A1 (fr) Procédé de détermination du développement ou de l'état de développement d'un petit enfant ou d'un nourrisson
Hesse et al. Body pose estimation in depth images for infant motion analysis
US20220138967A1 (en) Markerless Motion Capture of Animate Subject with Prediction of Future Motion
DE102014100352A1 (de) Fahrerblickdetektionssystem
Choi et al. Robot-assisted ADHD screening in diagnostic process
EP3188080A1 (fr) Procédé d'évaluation de gestes
Jaroensri et al. A video-based method for automatically rating ataxia
CN113688710A (zh) 儿童孤独症训练系统及其方法
Belmokhtar et al. Classification of alzheimer's disease from 3d structural mri data
JPWO2019172181A1 (ja) 診断支援装置、プログラム、学習済みモデル、および学習装置
CN112438723A (zh) 认知功能评估方法、认知功能评估装置以及存储介质
DE102017213714A1 (de) Verfahren zum Ermitteln einer Erkrankungsprognose eines Kraftfahrzeuginsassen sowie Prognoseeinrichtung
CN116671902A (zh) 一种辅助诊断脑瘫的婴儿运动姿态分析系统
Kour et al. A vision-based gait dataset for knee osteoarthritis and parkinson’s disease analysis with severity levels
CN115131503A (zh) 一种虹膜三维识别的健康监测方法及其系统
CN115116039A (zh) 一种车辆座舱外视线追踪方法、装置、车辆和存储介质
Tian et al. Automated analysis of seizure behavior in video: methods and challenges
WO2016038215A1 (fr) Système et procédé pour étudier quantitativement le contrôle postural de personnes
DE102019217145A1 (de) Audiopille
Sadek et al. Computer vision-based approach for detecting arm-flapping as autism suspect behaviour
Dey et al. Autonomous vision-guided approach for the analysis and grading of vertical suspension tests during Hammersmith Infant Neurological Examination (HINE)
Hassan et al. Direct Cup-to-Disc Ratio Estimation for Glaucoma Screening via Semi-supervised Learning
Morais et al. Robust and Interpretable General Movement Assessment Using Fidgety Movement Detection
US20240070854A1 (en) Tracking, analysing and assessment of huamn body movements using a subject-specific digital twin model of the human body

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: 21722805

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21722805

Country of ref document: EP

Kind code of ref document: A1