CN115131878B - Method, device, terminal and storage medium for determining motion of intelligent artificial limb - Google Patents
Method, device, terminal and storage medium for determining motion of intelligent artificial limb Download PDFInfo
- Publication number
- CN115131878B CN115131878B CN202211044100.5A CN202211044100A CN115131878B CN 115131878 B CN115131878 B CN 115131878B CN 202211044100 A CN202211044100 A CN 202211044100A CN 115131878 B CN115131878 B CN 115131878B
- Authority
- CN
- China
- Prior art keywords
- standard
- primary screening
- signal
- electromyographic
- standard electromyographic
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
- A61B5/397—Analysis of electromyograms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
- A61F2/50—Prostheses not implantable in the body
- A61F2/68—Operating or control means
- A61F2/70—Operating or control means electrical
- A61F2/72—Bioelectric control, e.g. myoelectric
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/752—Contour matching
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Transplantation (AREA)
- Vascular Medicine (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Cardiology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Prostheses (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method, a device, a terminal and a storage medium for determining the action of an intelligent artificial limb. The problem of among the prior art intelligent artificial limb need match the flesh electrical signal that acquires at present with each standard flesh electrical signal, just can analyze user's motion intention, lead to the flesh electrical signal matching process of intelligent artificial limb consuming time overlength is solved.
Description
Technical Field
The invention relates to the field of intelligent artificial limb application, in particular to a method, a device, a terminal and a storage medium for determining the action of an intelligent artificial limb.
Background
The existing intelligent artificial limb stores myoelectric signals generated when each user executes different actions in advance as standard myoelectric signals, and the currently collected myoelectric signals are matched with the standard myoelectric signals to analyze the current movement intention of the user and control the intelligent artificial limb to execute corresponding actions. Because the actions involved in the daily activities of the users are various, the number of the standard electromyographic signals corresponding to each user is large, and the electromyographic signal matching of the intelligent artificial limb is long in time consumption.
Thus, there is still a need for improvement and development of the prior art.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method, an apparatus, a terminal and a storage medium for determining an action of an intelligent prosthesis, aiming at solving the problem that the myoelectric signal matching process of the intelligent prosthesis consumes too much time because the intelligent prosthesis in the prior art needs to match the currently obtained myoelectric signal with each standard myoelectric signal to analyze the movement intention of the user.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect, an embodiment of the present invention provides a method for determining an action of an intelligent prosthesis, where the method includes:
acquiring an electromyographic signal, positioning data and an environment image corresponding to a target user, wherein the electromyographic signal, the positioning data and the environment image are respectively and correspondingly acquired at the same time;
acquiring a preset standard electromyographic signal database, and determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions;
matching according to the electromyographic signals and the candidate standard electromyographic signals to obtain target standard electromyographic signals;
and determining the target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal.
In one embodiment, the acquisition of the positioning data and the environment image comprises:
acquiring the positioning data through the intelligent terminal equipment of the target user;
and acquiring the environment image through a preset camera device on the intelligent artificial limb.
In one embodiment, the standard electromyographic signal database includes a plurality of standard electromyographic signal sets, each standard electromyographic signal set corresponds to a different action execution region, and the determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image includes:
determining a target standard electromyographic signal set from each standard electromyographic signal set according to the positioning data, and determining a plurality of primary screening standard electromyographic signals according to the target standard electromyographic signal set;
acquiring environment image labels corresponding to the primary screening standard electromyographic signals respectively, and comparing the environment image labels corresponding to the primary screening standard electromyographic signals respectively according to the environment image and the environment image labels corresponding to the primary screening standard electromyographic signals respectively to obtain the similarity corresponding to the primary screening standard electromyographic signals respectively;
determining a plurality of candidate standard electromyographic signals from each primary screening standard electromyographic signal according to the similarity corresponding to each primary screening standard electromyographic signal, wherein the similarity corresponding to each candidate standard electromyographic signal is higher than a first threshold.
In one embodiment, the environmental image tag includes a plurality of environmental markers, and the comparing, according to the environmental image and the environmental image tags corresponding to the primary screening standard electromyographic signals, obtains the similarity corresponding to each of the primary screening standard electromyographic signals, includes:
determining a plurality of local images according to the environment image, wherein the gray value deviation between pixel points in each local image is smaller than a preset deviation threshold;
acquiring the area occupation ratio corresponding to each local image, and determining a plurality of target local images according to the area occupation ratio corresponding to each local image, wherein the area occupation ratio corresponding to each target local image is smaller than a preset value;
determining a plurality of environment indicators according to the target local images, wherein the target local images correspond to the environment indicators one by one;
and comparing each environmental marker corresponding to each primary screening standard electromyographic signal with each environmental indicator to obtain the similarity corresponding to each primary screening standard electromyographic signal.
In an embodiment, the comparing the environmental markers corresponding to each primary screening standard electromyographic signal with the environmental indicators to obtain the similarity corresponding to each primary screening standard electromyographic signal includes:
performing contour matching according to each environmental marker and each environmental indicator corresponding to the primary screening standard electromyographic signal to obtain a plurality of initial pairs, wherein the contour similarity corresponding to each initial pair is greater than a second threshold;
performing texture matching according to the environment marker and the environment indicator in each initial matching pair to obtain a plurality of target matching pairs, wherein the texture similarity corresponding to each target matching pair is greater than a third threshold;
and acquiring the quantity ratio of the environment markers corresponding to the target pairs and the primary screening standard electromyographic signals, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the quantity ratio.
In an embodiment, the determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio includes:
judging whether the number of the environmental markers corresponding to the primary screening standard electromyographic signals is greater than a number threshold value;
when the number of the environment markers corresponding to the primary screening standard electromyographic signals is larger than the number threshold, acquiring a preset compensation value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio and the compensation value;
when the number of the environment markers corresponding to the primary screening standard electromyographic signals is smaller than or equal to the number threshold value, a preset punishment value is obtained, and the similarity corresponding to the primary screening standard electromyographic signals is determined according to the number ratio and the punishment value.
In one embodiment, the method further comprises:
acquiring action execution time corresponding to the target standard electromyographic signal;
when the action execution time length is longer than the preset time length, the electromyographic sampling frequency of the intelligent artificial limb is adjusted downwards;
and when the action execution duration is less than or equal to the preset duration, the electromyographic sampling frequency of the intelligent artificial limb is adjusted up.
In a second aspect, an embodiment of the present invention further provides a motion determination apparatus for an intelligent prosthesis, where the apparatus includes:
the system comprises a data acquisition module, a data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring an electromyographic signal, positioning data and an environment image corresponding to a target user, and the electromyographic signal, the positioning data and the environment image are respectively corresponding to the same acquisition time;
the signal screening module is used for acquiring a preset standard electromyographic signal database and determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions;
the signal matching module is used for matching according to the electromyographic signals and the candidate standard electromyographic signals to obtain target standard electromyographic signals;
and the action determining module is used for determining the target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal.
In one embodiment, the data acquisition module comprises:
the positioning unit is used for acquiring the positioning data through the intelligent terminal equipment of the target user;
and the camera shooting unit is used for acquiring the environment image through a preset camera shooting device on the intelligent artificial limb.
In one embodiment, the standard electromyographic signal database includes a plurality of standard electromyographic signal sets, each standard electromyographic signal set has a different action execution region, and the signal screening module includes:
the primary screening unit is used for determining a target standard electromyographic signal set from each standard electromyographic signal set according to the positioning data and determining a plurality of primary screening standard electromyographic signals according to the target standard electromyographic signal set;
the comparison unit is used for acquiring environment image labels corresponding to the primary screening standard electromyographic signals respectively, and comparing the environment image labels corresponding to the primary screening standard electromyographic signals respectively according to the environment image labels to obtain the similarity corresponding to the primary screening standard electromyographic signals respectively;
the secondary screening unit is used for determining a plurality of candidate standard electromyographic signals from each primary screening standard electromyographic signal according to the similarity corresponding to each primary screening standard electromyographic signal, wherein the similarity corresponding to each candidate standard electromyographic signal is higher than a first threshold.
In one embodiment, the environment image tag includes a plurality of environment markers, and the alignment unit includes:
the image dividing unit is used for determining a plurality of local images according to the environment image, wherein the gray value deviation between pixel points in each local image is smaller than a preset deviation threshold;
the local screening unit is used for acquiring the area proportion corresponding to each local image and determining a plurality of target local images according to the area proportion corresponding to each local image, wherein the area proportion corresponding to each target local image is smaller than a preset value;
the image conversion unit is used for determining a plurality of environment indicators according to the target local images, wherein each target local image corresponds to each environment indicator one by one;
and the object comparison unit is used for comparing each environmental marker corresponding to each primary screening standard electromyographic signal with each environmental indicator to obtain the similarity corresponding to each primary screening standard electromyographic signal.
In one embodiment, the object matching unit includes:
the contour comparison unit is used for carrying out contour matching on each environmental marker and each environmental indicator corresponding to the primary screening standard electromyographic signals to obtain a plurality of initial pairs, wherein the contour similarity corresponding to each initial pair is greater than a second threshold value;
the texture comparison unit is used for performing texture matching according to the environment markers and the environment indicators in the initial matching pairs to obtain a plurality of target matching pairs, wherein the texture similarity corresponding to each target matching pair is greater than a third threshold;
and the numerical value comparison unit is used for acquiring the quantity ratio of the environmental markers corresponding to the target pairs and the primary screening standard electromyographic signals, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the quantity ratio.
In one embodiment, the numerical value alignment unit includes:
the judging unit is used for judging whether the number of the environment markers corresponding to the primary screening standard electromyographic signals is larger than a number threshold value or not;
the compensation unit is used for acquiring a preset compensation value when the number of the environment markers corresponding to the primary screening standard electromyographic signals is larger than the number threshold value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio and the compensation value;
and the punishment unit is used for acquiring a preset punishment value when the quantity of the environmental markers corresponding to the primary screening standard electromyographic signals is smaller than or equal to the quantity threshold value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the quantity ratio and the punishment value.
In one embodiment, the apparatus further comprises:
the time length acquisition module is used for acquiring action execution time length corresponding to the target standard electromyographic signal;
the frequency down-regulation module is used for down-regulating the electromyography sampling frequency of the intelligent artificial limb when the action execution duration is longer than a preset duration;
and the frequency up-regulation module is used for up-regulating the myoelectricity sampling frequency of the intelligent artificial limb when the action execution time length is less than or equal to the preset time length.
In a third aspect, an embodiment of the present invention further provides a terminal, where the terminal includes a memory and more than one processor; the memory stores more than one program; the program comprises instructions for executing the motion determination method of the intelligent artificial limb; the processor is configured to execute the program.
In a fourth aspect, the embodiment of the present invention further provides a computer readable storage medium, on which a plurality of instructions are stored, wherein the instructions are adapted to be loaded and executed by a processor to implement the steps of the motion determination method for an intelligent prosthesis described in any one of the above.
The invention has the beneficial effects that: according to the embodiment of the invention, the standard electromyographic signals are screened by acquiring the positioning data and the environmental image of the target user, and then electromyographic signal matching is carried out, so that the matching times of the intelligent artificial limb can be effectively reduced. The problem of long time consumption in the electromyographic signal matching process of an intelligent artificial limb caused by the fact that the intelligent artificial limb in the prior art can analyze the movement intention of a user only by matching the currently acquired electromyographic signal with each standard electromyographic signal is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for determining an action of an intelligent prosthesis according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of internal modules of the motion determination apparatus for an intelligent prosthesis according to an embodiment of the present invention.
Fig. 3 is a schematic block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
The invention discloses a method, a device, a terminal and a storage medium for determining the action of an intelligent artificial limb, and in order to make the purpose, the technical scheme and the effect of the invention clearer and clearer, the invention is further described in detail by referring to the attached drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
When a human body performs corresponding actions, the brain gives corresponding muscle instructions through a nervous system, and even if the disabled person goes to limbs, the nervous path of the disabled person can also transmit electric signals, so that the movement intention of the person can be analyzed by detecting the electromyographic signals. The intelligent artificial limb assists the user to carry out daily activities by detecting the electromyographic signals of the user. The existing intelligent artificial limb stores myoelectric signals generated when each user executes different actions in advance as standard myoelectric signals, and the currently collected myoelectric signals are matched with the standard myoelectric signals to analyze the current movement intention of the user and control the intelligent artificial limb to execute corresponding actions. Because the actions involved in the daily activities of the users are various, the number of the standard electromyographic signals corresponding to each user is large, and the time consumption of the electromyographic signal matching process of the intelligent artificial limb is too long.
Aiming at the defects of the prior art, the invention provides a motion determination method of an intelligent artificial limb, which comprises the steps of obtaining an electromyographic signal, positioning data and an environment image corresponding to a target user, wherein the electromyographic signal, the positioning data and the environment image are respectively corresponding to the same acquisition time; acquiring a preset standard electromyographic signal database, and determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions; matching according to the electromyographic signals and the candidate standard electromyographic signals to obtain target standard electromyographic signals; and determining the target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal. According to the invention, standard electromyogram signals are screened by acquiring the positioning data and the environmental image of the target user, and then electromyogram signal matching is carried out, so that the matching times of the intelligent artificial limb can be effectively reduced. The problem of among the prior art intelligent artificial limb need match the flesh electrical signal that acquires at present with each standard flesh electrical signal, just can analyze user's motion intention, lead to the flesh electrical signal matching process of intelligent artificial limb consuming time overlength is solved.
Exemplary method
As shown in fig. 1, the method comprises the steps of:
step S100, acquiring an electromyographic signal, positioning data and an environment image corresponding to a target user, wherein the electromyographic signal, the positioning data and the environment image respectively correspond to the same acquisition time.
Specifically, the target user in this embodiment may be any user who uses an intelligent prosthesis. In order to determine the movement intention reflected by the electromyographic signal as soon as possible, the embodiment also needs to acquire positioning data and an environmental image of the target user while acquiring the electromyographic signal. The positioning data of the target user can reflect the current area of the target user, and the possible movement intention of the target user can be analyzed through the positioning data because the area activities of the target user in different areas are different and the action types required by different area activities are different. In addition, in order to analyze the current movement intention of the target user more accurately, the present embodiment further needs to acquire a current environment image of the target user, and since the environment image may reflect various facilities that may exist in the environment where the target user is currently located, and the use actions of different facilities are different, the possible movement intention of the target user may also be analyzed through the environment image. The embodiment combines the positioning data and the environment image, so that the possible movement intention of the target user can be analyzed more accurately, and the calculation overhead of the follow-up electromyographic signal matching is reduced.
In one implementation, the step S100 specifically includes the following steps:
s101, acquiring the positioning data through the intelligent terminal equipment of the target user;
and S102, acquiring the environment image through a preset camera device on the intelligent artificial limb.
Specifically, since the intelligent terminal device is an article that the target user most often carries with him, and the intelligent terminal device has a positioning function, the intelligent artificial limb can acquire the positioning data of the target user by establishing data connection with the intelligent terminal device. In addition, in order to obtain an image of the environment where the target user is located, in this embodiment, a camera device is mounted on the intelligent artificial limb in advance, and the intelligent artificial limb obtains the positioning data and the camera device takes a picture at the same time, so as to obtain an image of the environment of the target user.
As shown in fig. 1, the method further comprises the steps of:
step S200, a preset standard electromyographic signal database is obtained, and a plurality of candidate standard electromyographic signals are determined from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions.
Specifically, in order to analyze the movement intention of the target user according to the electromyographic signals, a standard electromyographic signal database is constructed in advance in the embodiment, and the standard electromyographic signal database contains standard electromyographic signals generated by the movement intentions of the target user based on different actions. Because the positioning data and the environment image can both reflect the current possible movement intention of the target user, a plurality of candidate standard electromyographic signals which accord with the current possible movement intention of the target user can be screened out from a plurality of standard electromyographic signals according to the positioning data and the environment image, so that the number of the standard electromyographic signals for subsequent electromyographic matching is reduced, and the purpose of reducing the time consumption of the electromyographic matching process is achieved.
In one implementation manner, the standard electromyographic signal database includes a plurality of standard electromyographic signal sets, and the action execution regions corresponding to the standard electromyographic signal sets are different, where the step S200 includes:
step S201, determining a target standard electromyographic signal set from each standard electromyographic signal set according to the positioning data, and determining a plurality of primary screening standard electromyographic signals according to the target standard electromyographic signal set;
step S202, acquiring environment image labels corresponding to the primary screening standard electromyographic signals respectively, and comparing the environment image labels corresponding to the environment image labels and the primary screening standard electromyographic signals respectively to obtain the similarity corresponding to the primary screening standard electromyographic signals respectively;
step S203, determining a plurality of candidate standard electromyographic signals from each primary screening standard electromyographic signal according to the similarity corresponding to each primary screening standard electromyographic signal, wherein the similarity corresponding to each candidate standard electromyographic signal is higher than a first threshold.
Specifically, in order to increase the screening speed, the present embodiment classifies the standard electromyographic signals of the standard electromyographic signal database in advance, and divides the standard electromyographic signals generated in the same region into the same standard electromyographic signal set. In addition, each standard electromyographic signal is also stored with an environment image label in association, and the environment image label is actually an image shot by the camera device when the intelligent artificial limb collects the standard electromyographic signal. In practical application, firstly, the area where the target user is located is judged according to the positioning data, then the standard electromyographic signal set corresponding to the area is used as the target standard electromyographic signal set, and the standard electromyographic signals contained in the target standard electromyographic signal set are the signals primarily screened out, namely the primarily screened standard electromyographic signals. Because the number of the primary screening standard electromyographic signals is still large, in this embodiment, an environmental image label of each primary screening standard electromyographic signal is also required to be acquired, and the similarity of each primary screening standard electromyographic signal is obtained by comparing the currently acquired environmental image with the environmental image label of each primary screening standard electromyographic signal, wherein the higher the similarity is, the lower the similarity is, and vice versa. The present embodiment sets a first threshold in advance for determining the level of similarity. Because the target user has higher possibility of repeating the same action in the same environment, the primary screening standard electromyographic signals can be screened for the second time according to the similarity of the primary screening standard electromyographic signals, so that the primary screening standard electromyographic signals with the similarity higher than the first threshold value are selected, and the signals screened for the second time are used as candidate standard electromyographic signals.
It should be noted that the standard electromyographic signals in different standard electromyographic signal sets may overlap, but the environmental image labels of the same standard electromyographic signal in different standard electromyographic signal sets may be different.
In one implementation, the environment image tag includes a plurality of environment markers, and the step S202 specifically includes the following steps:
step S2021, determining a plurality of local images according to the environment image, wherein the gray value deviation between pixel points in each local image is smaller than a preset deviation threshold;
step S2022, obtaining area ratios corresponding to the local images respectively, and determining a plurality of target local images according to the area ratios corresponding to the local images respectively, wherein the area ratios corresponding to the target local images are smaller than a preset value;
step S2023, determining a plurality of environment indicators according to the target local images, wherein each target local image corresponds to each environment indicator one by one;
step S2024, comparing each environmental marker corresponding to each primary screening standard electromyographic signal with each environmental indicator to obtain the similarity corresponding to each primary screening standard electromyographic signal.
Specifically, the environment image includes not only various facilities in the environment where the target user is currently located, but also a large amount of redundant background information, so that the embodiment first needs to divide the environment image according to the gray values of the pixels in the environment image, so that the pixels with similar gray values are divided into the same part, and a plurality of partial images are obtained after the division is completed. Then, the area ratio of each local image in the whole environment image is calculated, and the larger the area ratio is, the higher the possibility that the local image is the background image is, so that the local images with the large area ratio need to be removed, and only the local images with the area ratios smaller than a preset value are reserved and taken as the target local images. Then, because the gray values of the pixel points in the same target local image are similar and the gray values of the pixel points in different target local images are different, each target local image may respectively refer to different environmental facilities/objects, and therefore, an environmental indicator is determined according to each target local image and is used for reflecting one environmental facility/object in the current environment where the target user is located. Because each standard electromyographic signal in the standard electromyographic signal database is stored with an environmental image label in a correlated manner, each environmental image label comprises a plurality of corresponding environmental markers for reflecting a plurality of environmental facilities/objects. Therefore, aiming at each primary screening standard electromyographic signal, comparing each environmental marker corresponding to the primary screening standard electromyographic signal with each current environmental indicator so as to obtain the similarity between the current environment of the target user and the environment corresponding to the primary screening standard electromyographic signal.
In another implementation manner, the environment image tag includes a plurality of environment markers, and the step S202 specifically includes the following steps:
determining a foreground image according to the environment image;
determining a plurality of local images according to the foreground image, wherein the gray value deviation between pixel points in each local image is smaller than a preset deviation threshold;
determining a plurality of environment indicators according to the local images, wherein the local images correspond to the environment indicators one by one;
and comparing each environmental marker corresponding to each primary screening standard electromyographic signal with each environmental indicator to obtain the similarity corresponding to each primary screening standard electromyographic signal.
Specifically, in order to remove the redundant background in the environmental image data, the foreground in the environmental image data may be extracted first to obtain the foreground image in this embodiment. And dividing the foreground image into a plurality of local images according to the gray value of each pixel point in the foreground image, so that the pixel points with similar gray values are divided into the same local image. Because the gray values of the pixel points in the same local image are similar and the gray values of the pixel points in different local images are different, the local images may respectively refer to different environmental facilities/objects, and therefore an environmental indicator is determined according to each local image and is used for reflecting one environmental facility/object in the current environment where the target user is located. The subsequent steps are the same as those described above, and will not be repeated here.
In one implementation, the step S2024 specifically includes the following steps:
step S20241, performing contour matching according to each environment marker and each environment indicator corresponding to the primary screening standard electromyographic signal to obtain a plurality of initial pairs, wherein the contour similarity corresponding to each initial pair is greater than a second threshold;
step S20242, performing texture matching according to the environment marker and the environment indicator in each initial matching pair to obtain a plurality of target matching pairs, wherein the texture similarity corresponding to each target matching pair is greater than a third threshold;
step S20243, obtaining the quantity ratio of the environmental markers corresponding to the target pairs and the primary screening standard electromyographic signals, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the quantity ratio.
Specifically, for each primary screening standard electromyographic signal, performing contour matching on each environmental marker corresponding to the primary screening standard electromyographic signal and each environmental indicator corresponding to the current environment where the target user is located. Wherein the contour matching process comprises: and sequentially calculating the contour similarity between the environment indicator and each environment indicator aiming at each environment indicator, and taking the environment indicator which has the highest contour similarity with the environment indicator and is larger than a second threshold value and the environment indicator as an initial pair. It is understood that the environmental indicator is rejected if the contour similarity between the environmental indicator and each environmental marker is less than or equal to a second threshold value, which indicates that there is no pairing with the environmental indicator. Each initial pair is then texture matched to screen out the target pair. The texture matching process comprises the following steps: calculating the texture similarity between the environmental indicators and the environmental markers in each initial pairing, and if the texture similarity is greater than a third threshold value, taking the initial pairing as a target pairing; and if the texture similarity is smaller than or equal to a third threshold value, rejecting the initial pairing. And finally, calculating the total number of the target pairs, and obtaining a number ratio of the total number of the environmental markers corresponding to the primary screening standard electromyographic signals to the total number of the environmental markers corresponding to the primary screening standard electromyographic signals, wherein the larger the number ratio is, the higher the similarity degree between the environmental markers corresponding to the primary screening standard electromyographic signals and the environmental indicators in the current environment where the target user is located is, the higher the similarity degree corresponding to the primary screening standard electromyographic signals is, and the lower the similarity degree is otherwise.
In one implementation, the step S20243 specifically includes the following steps:
step S202431, judging whether the number of the environmental markers corresponding to the prescreening standard electromyographic signals is larger than a number threshold value;
step S202432, when the number of the environment markers corresponding to the primary screening standard electromyographic signals is larger than the number threshold, acquiring a preset compensation value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio and the compensation value;
step S202433, when the number of the environment markers corresponding to the primary screening standard electromyographic signals is smaller than or equal to the number threshold value, acquiring a preset penalty value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio and the penalty value.
Specifically, when the number of the environment markers corresponding to the primary screening standard electromyographic signal is small, the situation that the similarity of the primary screening standard electromyographic signal is high in a virtual manner may occur, so that when the number of the environment markers corresponding to the primary screening standard electromyographic signal is smaller than or equal to a number threshold value, a penalty value needs to be subtracted on the basis of a numerical ratio in the embodiment, and the similarity corresponding to the primary screening standard electromyographic signal can be obtained to avoid the situation that the similarity is high in a virtual manner. On the contrary, when the number of the environment markers corresponding to the primary screening standard electromyographic signals is large, the condition that the similarity of the primary screening standard electromyographic signals is low is possible, so that in this embodiment, when the number of the environment markers corresponding to the primary screening standard electromyographic signals is larger than the number threshold, the compensation value needs to be added on the basis of the numerical ratio to obtain the similarity corresponding to the primary screening standard electromyographic signals, so as to avoid the condition that the similarity is low.
As shown in fig. 1, the method further comprises the steps of:
and step S300, matching according to the electromyographic signals and the candidate standard electromyographic signals to obtain target standard electromyographic signals.
Specifically, since each candidate standard electromyogram signal and the currently detected electromyogram signal are generated in a similar environment in the same region, each candidate standard electromyogram signal is more likely to be successfully matched with the electromyogram signal, so that the matching priority of each candidate standard electromyogram signal is increased, that is, the electromyogram signal is preferentially matched with each candidate standard electromyogram signal. Thereby quickly determining the target standard electromyographic signal corresponding to the electromyographic signal.
In one implementation, the method further comprises the steps of:
step S301, acquiring action execution duration corresponding to the target standard electromyogram signal;
step S302, when the action execution duration is longer than a preset duration, the electromyography sampling frequency of the intelligent artificial limb is adjusted downwards;
and step S303, when the action execution time length is less than or equal to the preset time length, the myoelectricity sampling frequency of the intelligent artificial limb is adjusted upwards.
Specifically, the action execution time length of the target standard electromyogram signal is obtained according to historical data, if the action execution time length is longer than the preset time length, the action corresponding to the target standard electromyogram signal lasts for a certain time length, and the action is not changed in the time length, so that the electromyogram sampling frequency of the intelligent artificial limb can be reduced in order to save energy consumption; if the action execution time is less than or equal to the preset time, the action corresponding to the target standard electromyographic signal is executed in a short time, and the electromyographic sampling frequency of the intelligent artificial limb can be increased in order to detect the electromyographic signal of the next action in time.
As shown in fig. 1, the method further comprises the steps of:
and S400, determining the target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal.
Because the target standard electromyogram signal is consistent with the movement intention corresponding to the currently acquired electromyogram signal, the target action which the intelligent artificial limb needs to execute currently can be determined according to the action corresponding to the target standard electromyogram signal.
Based on the above embodiment, the present invention further provides a motion determination device for an intelligent prosthesis, as shown in fig. 2, the device comprising:
the data acquisition module 01 is used for acquiring an electromyographic signal, positioning data and an environment image corresponding to a target user, wherein the electromyographic signal, the positioning data and the environment image are respectively corresponding to the same acquisition time;
the signal screening module 02 is used for acquiring a preset standard electromyographic signal database, and determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions;
the signal matching module 03 is configured to match the electromyographic signals with the candidate standard electromyographic signals to obtain target standard electromyographic signals;
and the action determining module 04 is used for determining the target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal.
In one implementation, the data obtaining module 01 includes:
the positioning unit is used for acquiring the positioning data through the intelligent terminal equipment of the target user;
and the camera shooting unit is used for acquiring the environment image through a preset camera shooting device on the intelligent artificial limb.
In one implementation manner, the standard electromyographic signal database includes a plurality of standard electromyographic signal sets, where action execution regions corresponding to the standard electromyographic signal sets are different, and the signal screening module 02 includes:
the primary screening unit is used for determining a target standard electromyographic signal set from each standard electromyographic signal set according to the positioning data and determining a plurality of primary screening standard electromyographic signals according to the target standard electromyographic signal set;
the comparison unit is used for acquiring environment image labels corresponding to the primary screening standard electromyographic signals respectively, and comparing the environment image labels corresponding to the primary screening standard electromyographic signals respectively according to the environment image labels to obtain the similarity corresponding to the primary screening standard electromyographic signals respectively;
the secondary screening unit is used for determining a plurality of candidate standard electromyographic signals from each primary screening standard electromyographic signal according to the similarity corresponding to each primary screening standard electromyographic signal, wherein the similarity corresponding to each candidate standard electromyographic signal is higher than a first threshold.
In one implementation, the environment image tag includes a plurality of environment markers, and the comparing unit includes:
the image dividing unit is used for determining a plurality of local images according to the environment image, wherein the gray value deviation between pixel points in each local image is smaller than a preset deviation threshold;
the local screening unit is used for acquiring the area occupation ratio corresponding to each local image and determining a plurality of target local images according to the area occupation ratio corresponding to each local image, wherein the area occupation ratio corresponding to each target local image is smaller than a preset value;
the image conversion unit is used for determining a plurality of environment indicators according to the target local images, wherein each target local image corresponds to each environment indicator one by one;
and the object comparison unit is used for comparing each environmental marker corresponding to each primary screening standard electromyographic signal with each environmental indicator to obtain the similarity corresponding to each primary screening standard electromyographic signal.
In one implementation, the object comparison unit includes:
the contour comparison unit is used for carrying out contour matching on each environmental marker and each environmental indicator corresponding to the primary screening standard electromyographic signal to obtain a plurality of initial pairs, wherein the contour similarity corresponding to each initial pair is greater than a second threshold;
the texture comparison unit is used for performing texture matching according to the environment marker and the environment indicator in each initial pairing to obtain a plurality of target pairings, wherein the texture similarity corresponding to each target pairing is greater than a third threshold value;
and the numerical value comparison unit is used for acquiring the quantity ratio of the environmental markers corresponding to the target pairs and the primary screening standard electromyographic signals, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the quantity ratio.
In one implementation manner, the numerical value comparison unit includes:
the judging unit is used for judging whether the number of the environmental markers corresponding to the primary screening standard electromyographic signals is larger than a number threshold value or not;
the compensation unit is used for acquiring a preset compensation value when the number of the environmental markers corresponding to the primary screening standard electromyographic signals is larger than the number threshold value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio and the compensation value;
and the punishment unit is used for acquiring a preset punishment value when the quantity of the environment markers corresponding to the primary screening standard electromyographic signals is smaller than or equal to the quantity threshold value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the quantity ratio and the punishment value.
In one implementation, the apparatus further comprises:
the time length acquisition module is used for acquiring action execution time length corresponding to the target standard electromyographic signal;
the frequency down-regulation module is used for down-regulating the myoelectricity sampling frequency of the intelligent artificial limb when the action execution time length is longer than a preset time length;
and the frequency up-regulation module is used for up-regulating the electromyogram sampling frequency of the intelligent artificial limb when the action execution duration is less than or equal to the preset duration.
Based on the above embodiment, the present invention further provides a terminal, and a functional block diagram of the terminal may be as shown in fig. 3. The terminal comprises a processor, a memory, a network interface and a display screen which are connected through a system bus. Wherein the processor of the terminal is configured to provide computing and control capabilities. The memory of the terminal comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the terminal is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a method of motion determination for an intelligent prosthesis. The display screen of the terminal can be a liquid crystal display screen or an electronic ink display screen.
It will be understood by those skilled in the art that the block diagram shown in fig. 3 is a block diagram of only a portion of the structure associated with the inventive arrangements and is not intended to limit the terminals to which the inventive arrangements may be applied, and that a particular terminal may include more or less components than those shown, or may have some components combined, or may have a different arrangement of components.
In one implementation, one or more programs are stored in a memory of the terminal and configured to be executed by one or more processors include instructions for performing a method of motion determination for an intelligent prosthesis.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases or other media used in the embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
In summary, the invention discloses a method, a device, a terminal and a storage medium for determining an action of an intelligent prosthesis, wherein the method comprises the steps of acquiring an electromyographic signal, positioning data and an environment image corresponding to a target user, wherein the electromyographic signal, the positioning data and the environment image are respectively corresponding to the same acquisition time; acquiring a preset standard electromyographic signal database, and determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions; matching according to the electromyographic signals and the candidate standard electromyographic signals to obtain target standard electromyographic signals; and determining the target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal. According to the invention, standard electromyographic signals are screened by acquiring the positioning data and the environmental image of the target user, and then electromyographic signal matching is carried out, so that the matching times of the intelligent artificial limb can be effectively reduced. The problem of among the prior art intelligent artificial limb need match the flesh electrical signal that acquires at present with each standard flesh electrical signal, just can analyze user's motion intention, lead to the flesh electrical signal matching process of intelligent artificial limb consuming time overlength is solved.
It will be understood that the invention is not limited to the examples described above, but that modifications and variations will occur to those skilled in the art in light of the above teachings, and that all such modifications and variations are considered to be within the scope of the invention as defined by the appended claims.
Claims (9)
1. A method for motion determination in an intelligent prosthesis, the method comprising:
acquiring an electromyographic signal, positioning data and an environment image corresponding to a target user, wherein the electromyographic signal, the positioning data and the environment image respectively correspond to the same acquisition time;
acquiring a preset standard electromyographic signal database, and determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions;
matching according to the electromyographic signals and the candidate standard electromyographic signals to obtain target standard electromyographic signals;
determining a target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal;
the standard electromyogram signal database comprises a plurality of standard electromyogram signal sets, action execution areas corresponding to the standard electromyogram signal sets are different, a plurality of candidate standard electromyogram signals are determined from the standard electromyogram signal database according to the positioning data and the environment image, and the standard electromyogram signal database comprises:
determining a target standard electromyographic signal set from each standard electromyographic signal set according to the positioning data, and determining a plurality of primary screening standard electromyographic signals according to the target standard electromyographic signal set;
acquiring environment image labels corresponding to the primary screening standard electromyographic signals respectively, and comparing the environment image labels corresponding to the primary screening standard electromyographic signals respectively according to the environment image and the environment image labels corresponding to the primary screening standard electromyographic signals respectively to obtain the similarity corresponding to the primary screening standard electromyographic signals respectively;
determining a plurality of candidate standard electromyographic signals from each primary screening standard electromyographic signal according to the similarity corresponding to each primary screening standard electromyographic signal, wherein the similarity corresponding to each candidate standard electromyographic signal is higher than a first threshold.
2. An intelligent prosthetic motion determination method according to claim 1, wherein the acquisition of the positioning data and the environmental image comprises:
acquiring the positioning data through the intelligent terminal equipment of the target user;
and acquiring the environment image through a preset camera device on the intelligent artificial limb.
3. An intelligent prosthetic motion determination method according to claim 1, wherein the environmental image tags include a plurality of environmental markers, and the obtaining of the similarity corresponding to each prescreening standard electromyographic signal by comparing the environmental image tags corresponding to the environmental image and each prescreening standard electromyographic signal respectively comprises:
determining a plurality of local images according to the environment image, wherein the gray value deviation between pixel points in each local image is smaller than a preset deviation threshold;
acquiring the area occupation ratio corresponding to each local image, and determining a plurality of target local images according to the area occupation ratio corresponding to each local image, wherein the area occupation ratio corresponding to each target local image is smaller than a preset value;
determining a plurality of environment indicators according to the target local images, wherein the target local images correspond to the environment indicators one by one;
and comparing each environmental marker corresponding to each primary screening standard electromyographic signal with each environmental indicator to obtain the similarity corresponding to each primary screening standard electromyographic signal.
4. An intelligent prosthetic motion determination method according to claim 3, wherein the comparing of the environmental markers corresponding to each prescreening standard electromyographic signal with the environmental indicators to obtain the similarity corresponding to each prescreening standard electromyographic signal comprises:
carrying out contour matching on each environment marker and each environment indicator corresponding to the primary screening standard electromyographic signals to obtain a plurality of initial pairs, wherein the contour similarity corresponding to each initial pair is greater than a second threshold;
performing texture matching according to the environment marker and the environment indicator in each initial matching pair to obtain a plurality of target matching pairs, wherein the texture similarity corresponding to each target matching pair is greater than a third threshold;
and acquiring the quantity ratio of the environmental markers corresponding to the target pairs and the primary screening standard electromyographic signals, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the quantity ratio.
5. An intelligent artificial limb movement determination method according to claim 4, wherein the determining the similarity corresponding to the prescreening standard electromyographic signals according to the number ratio comprises:
judging whether the number of the environmental markers corresponding to the primary screening standard electromyographic signals is larger than a number threshold value or not;
when the number of the environment markers corresponding to the primary screening standard electromyographic signals is larger than the number threshold, acquiring a preset compensation value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio and the compensation value;
when the number of the environment markers corresponding to the primary screening standard electromyographic signals is smaller than or equal to the number threshold value, acquiring a preset punishment value, and determining the similarity corresponding to the primary screening standard electromyographic signals according to the number ratio and the punishment value.
6. A method of motion determination for an intelligent prosthesis according to claim 1, the method further comprising:
acquiring action execution time corresponding to the target standard electromyographic signal;
when the action execution duration is longer than a preset duration, the electromyographic sampling frequency of the intelligent artificial limb is adjusted downwards;
and when the action execution duration is less than or equal to the preset duration, the electromyographic sampling frequency of the intelligent artificial limb is adjusted up.
7. An intelligent prosthesis motion determination apparatus, the apparatus comprising:
the system comprises a data acquisition module, a data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring an electromyographic signal, positioning data and an environment image corresponding to a target user, and the electromyographic signal, the positioning data and the environment image are respectively corresponding to the same acquisition time;
the signal screening module is used for acquiring a preset standard electromyographic signal database and determining a plurality of candidate standard electromyographic signals from the standard electromyographic signal database according to the positioning data and the environment image, wherein the standard electromyographic signal database comprises a plurality of standard electromyographic signals, and each standard electromyographic signal corresponds to different types of actions;
the signal matching module is used for matching according to the electromyographic signals and the candidate standard electromyographic signals to obtain target standard electromyographic signals;
the action determining module is used for determining the target action of the intelligent artificial limb corresponding to the target user according to the target standard electromyographic signal;
the standard electromyogram signal database comprises a plurality of standard electromyogram signal sets, action execution areas corresponding to the standard electromyogram signal sets are different, a plurality of candidate standard electromyogram signals are determined from the standard electromyogram signal database according to the positioning data and the environment image, and the standard electromyogram signal database comprises:
determining a target standard electromyographic signal set from each standard electromyographic signal set according to the positioning data, and determining a plurality of primary screening standard electromyographic signals according to the target standard electromyographic signal set;
acquiring environment image labels corresponding to the primary screening standard electromyographic signals respectively, and comparing the environment image labels corresponding to the primary screening standard electromyographic signals respectively according to the environment image and the environment image labels corresponding to the primary screening standard electromyographic signals respectively to obtain the similarity corresponding to the primary screening standard electromyographic signals respectively;
determining a plurality of candidate standard electromyographic signals from each primary screening standard electromyographic signal according to the similarity corresponding to each primary screening standard electromyographic signal, wherein the similarity corresponding to each candidate standard electromyographic signal is higher than a first threshold.
8. A terminal, characterized in that the terminal comprises a memory and more than one processor; the memory stores more than one program; the program comprises instructions for performing a method of motion determination for an intelligent prosthesis according to any of claims 1-6; the processor is configured to execute the program.
9. A computer readable storage medium having stored thereon a plurality of instructions adapted to be loaded and executed by a processor to perform the steps of the method for motion determination of an intelligent prosthesis according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211044100.5A CN115131878B (en) | 2022-08-30 | 2022-08-30 | Method, device, terminal and storage medium for determining motion of intelligent artificial limb |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211044100.5A CN115131878B (en) | 2022-08-30 | 2022-08-30 | Method, device, terminal and storage medium for determining motion of intelligent artificial limb |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115131878A CN115131878A (en) | 2022-09-30 |
| CN115131878B true CN115131878B (en) | 2022-11-11 |
Family
ID=83387220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211044100.5A Active CN115131878B (en) | 2022-08-30 | 2022-08-30 | Method, device, terminal and storage medium for determining motion of intelligent artificial limb |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115131878B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110310668A (en) * | 2019-05-21 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Mute detection method, system, equipment and computer readable storage medium |
| WO2021219039A1 (en) * | 2020-04-30 | 2021-11-04 | 京东数科海益信息科技有限公司 | Gesture recognition method and apparatus, man-machine interaction method and apparatus, and device and storage medium |
| CN113673276A (en) * | 2020-05-13 | 2021-11-19 | 广东博智林机器人有限公司 | Target object identification docking method and device, electronic equipment and storage medium |
| CN113850807A (en) * | 2021-11-30 | 2021-12-28 | 大族激光科技产业集团股份有限公司 | Image sub-pixel matching positioning method, system, device and medium |
| CN113970968A (en) * | 2021-12-22 | 2022-01-25 | 深圳市心流科技有限公司 | Intelligent bionic hand action pre-judging method |
| CN114625257A (en) * | 2022-05-16 | 2022-06-14 | 浙江强脑科技有限公司 | Action recognition method and device based on electromyographic signals |
| CN114935972A (en) * | 2021-12-02 | 2022-08-23 | 浙江科顿科技有限公司 | MR/AR/VR labeling and searching control method, mobile terminal and readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2405237A1 (en) * | 2010-07-07 | 2012-01-11 | Leica Geosystems AG | Target Point Recognition Method and Surveying Instrument |
| CN109766759A (en) * | 2018-12-12 | 2019-05-17 | 成都云天励飞技术有限公司 | Emotion identification method and Related product |
| CN114167995B (en) * | 2022-02-14 | 2022-05-17 | 浙江强脑科技有限公司 | Gesture locking method and device for bionic hand, terminal and storage medium |
-
2022
- 2022-08-30 CN CN202211044100.5A patent/CN115131878B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110310668A (en) * | 2019-05-21 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Mute detection method, system, equipment and computer readable storage medium |
| WO2021219039A1 (en) * | 2020-04-30 | 2021-11-04 | 京东数科海益信息科技有限公司 | Gesture recognition method and apparatus, man-machine interaction method and apparatus, and device and storage medium |
| CN113673276A (en) * | 2020-05-13 | 2021-11-19 | 广东博智林机器人有限公司 | Target object identification docking method and device, electronic equipment and storage medium |
| CN113850807A (en) * | 2021-11-30 | 2021-12-28 | 大族激光科技产业集团股份有限公司 | Image sub-pixel matching positioning method, system, device and medium |
| CN114935972A (en) * | 2021-12-02 | 2022-08-23 | 浙江科顿科技有限公司 | MR/AR/VR labeling and searching control method, mobile terminal and readable storage medium |
| CN113970968A (en) * | 2021-12-22 | 2022-01-25 | 深圳市心流科技有限公司 | Intelligent bionic hand action pre-judging method |
| CN114625257A (en) * | 2022-05-16 | 2022-06-14 | 浙江强脑科技有限公司 | Action recognition method and device based on electromyographic signals |
Non-Patent Citations (3)
| Title |
|---|
| Recurrent Neural Network for electromyographic gesture recognition in transhumeral amputees;OlivierBarron等;《Applied Soft Computing》;20201130;第96卷;1-9 * |
| 基于人工鱼群算法优化SVM的手部动作sEMG识别;洪洁等;《传感器与微系统》;20161231(第2期);23-25 * |
| 基于局部背景特征点的目标定位和跟踪;张铁等;《中南大学学报(自然科学版)》;20160926(第09期);140-149 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115131878A (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898168B (en) | Compression method and system of convolutional neural network model for target detection | |
| CN111008640B (en) | Image recognition model training and image recognition method, device, terminal and medium | |
| CN110136103A (en) | Medical image means of interpretation, device, computer equipment and storage medium | |
| CN110991249A (en) | Face detection method, face detection device, electronic equipment and medium | |
| CN108875746A (en) | A kind of licence plate recognition method, device, system and storage medium | |
| CN114359970A (en) | Pedestrian re-identification method and device, electronic equipment and storage medium | |
| CN115131878B (en) | Method, device, terminal and storage medium for determining motion of intelligent artificial limb | |
| CN114668563A (en) | Multi-level regulation method for sampling frequency of electromyographic signals | |
| CN113536965B (en) | Method and related device for training face shielding recognition model | |
| CN114943924B (en) | Pain assessment method, system, equipment and medium based on facial expression video | |
| CN111667457A (en) | Medical image-based spine information automatic identification method, system, terminal and storage medium | |
| CN114676737B (en) | Dynamic regulation method for sampling frequency of electromyographic signal | |
| CN111652108B (en) | Anti-interference signal identification method and device, computer equipment and storage medium | |
| CN115984613A (en) | Fundus image classification method, device, equipment and storage medium | |
| CN110934565B (en) | Method and device for measuring pupil diameter and computer readable storage medium | |
| CN112734701A (en) | Fundus focus detection method, fundus focus detection device and terminal equipment | |
| CN112834047A (en) | Wearable temperature monitoring device, temperature monitoring method and storage medium | |
| CN111462087A (en) | Image detection method, device and system based on artificial intelligence and storage medium | |
| CN112115751A (en) | Training method and device for animal mood recognition model | |
| CN112233014B (en) | Face processing method and face processing platform based on big data and artificial intelligence | |
| CN113408669B (en) | Image determining method and device, storage medium and electronic device | |
| CN117253096B (en) | Finger-adaptive health index monitoring method, device, equipment and storage medium | |
| CN113434738B (en) | Data processing method and device of wearable device, computer device and medium | |
| CN111666878B (en) | Object detection method and device | |
| CN115793861B (en) | APP theme scene setting method and device, terminal equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |