WO2021244650A1 - 控制方法、装置、终端及存储介质 - Google Patents

控制方法、装置、终端及存储介质 Download PDF

Info

Publication number
WO2021244650A1
WO2021244650A1 PCT/CN2021/098464 CN2021098464W WO2021244650A1 WO 2021244650 A1 WO2021244650 A1 WO 2021244650A1 CN 2021098464 W CN2021098464 W CN 2021098464W WO 2021244650 A1 WO2021244650 A1 WO 2021244650A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
control method
position information
posture
navigation mark
Prior art date
Application number
PCT/CN2021/098464
Other languages
English (en)
French (fr)
Inventor
方迟
王笑
Original Assignee
北京字节跳动网络技术有限公司
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 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Priority to JP2022574219A priority Critical patent/JP2023527906A/ja
Priority to EP21817903.4A priority patent/EP4149116A4/en
Publication of WO2021244650A1 publication Critical patent/WO2021244650A1/zh
Priority to US18/073,567 priority patent/US20230093983A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/42201—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] biosensors, e.g. heat sensor for presence detection, EEG sensors or any limb activity sensors worn by the user
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G06F3/014—Hand-worn input/output arrangements, e.g. data gloves
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
    • G06F3/0485—Scrolling or panning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • 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
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30241—Trajectory
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/4223—Cameras

Definitions

  • the present disclosure relates to the field of computer technology, in particular to control methods, devices, terminals, and storage media.
  • Smart TV has been widely used instead of traditional TV, and it can carry a variety of programs and applications for users to choose and watch.
  • the existing smart TV is controlled by a remote control, and usually only four direction keys can be used to control the selection direction, which has low interaction efficiency and is time-consuming and labor-intensive.
  • the content of the invention is provided to introduce concepts in a brief form, and these concepts will be described in detail in the following specific embodiments.
  • the content of the invention is not intended to identify the key features or essential features of the technical solution that is required to be protected, nor is it intended to be used to limit the scope of the technical solution that is required to be protected.
  • control method including:
  • a control instruction is determined according to the posture information of the second part, and the control instruction is used to control the visual element pointed to by the navigation mark.
  • control method including:
  • a control instruction is determined according to the posture information of the second part, and the control instruction is used to control the controlled element pointed to by the navigation mark.
  • a control method device including:
  • An acquiring and identifying unit configured to acquire the position information of the first part of the user and the posture information of the second part of the user according to the image;
  • the movement track unit is used to determine the movement track of the navigation marker according to the position information of the first part
  • the control instruction unit is configured to determine a control instruction according to the posture information of the second part, and the control instruction is used to control the visual element pointed to by the navigation mark.
  • a control method device including:
  • An acquiring and identifying unit configured to acquire the position information of the first part of the user and the posture information of the second part of the user according to the image;
  • the movement track unit is configured to determine the position information of the navigation mark according to the position information of the first part, and/or move the controlled element according to the position information of the first part and/or the preset posture of the second part;
  • the control instruction unit is configured to determine a control instruction according to the posture information of the second part, and the control instruction is used to control the controlled element pointed to by the navigation mark. According to one or more embodiments of the present disclosure, there is provided a terminal, which is characterized in that the terminal includes:
  • At least one memory and at least one processor are At least one memory and at least one processor
  • the memory is used to store program code
  • the processor is used to call the program code stored in the memory, so that the terminal executes the control method provided according to one or more embodiments of the present disclosure.
  • a computer storage medium wherein the computer storage medium stores program code, and when the program code is executed by a computer device, the computer device executes the program code.
  • One or more disclosed embodiments provide a control method.
  • the movement track of the navigation mark is determined according to the position information of the first part, and the control command is determined according to the posture information of the second part, so that the control command is The determination is separated from the determination of the position of the navigation mark.
  • the determination of the control instruction is based on static posture information, and the determination of the position of the navigation mark is based on the dynamic position change, which can provide convenience for the use of different characteristic algorithms to determine the above two processes; on the other hand, the determination of the control instruction
  • the position of the navigation mark is determined based on the user's different body parts, so that the determination process of the two does not affect each other, especially the contour shape of the first part does not change with the posture of the second part, which can prevent the change of the gesture from affecting the movement of the navigation mark , Which can improve the recognition accuracy of user instructions.
  • Fig. 1 shows a flowchart of a control method provided according to an embodiment of the present disclosure
  • FIG. 2 shows a schematic diagram of a scene for controlling a far-field display device according to a control method provided by an embodiment of the present disclosure
  • Fig. 3 shows a flow chart of a control method provided according to another embodiment of the present disclosure
  • FIG. 4 shows a schematic structural diagram of a control method device according to one or more embodiments of the present disclosure
  • Fig. 5 is a schematic structural diagram of a terminal device used to implement an embodiment of the present disclosure.
  • FIG. 1 shows a flow chart of a control method 100 provided according to an embodiment of the present disclosure.
  • the method 100 can be used for terminal devices including, but not limited to, a far-field display device, where the far-field display device refers to a user Display devices that cannot be directly contacted with body parts or other physical control devices such as stylus, including but not limited to electronic devices such as televisions and conference screens.
  • the method 100 includes step S101-step S104:
  • Step S101 Receive an image captured by the camera device.
  • the camera device can be built-in or externally connected to the terminal device, and it can send the captured image data to the terminal device in real time for processing by the terminal device.
  • the camera device can be set in a way that can face the user, so that the user's physical instructions to the terminal device can be captured.
  • images may be received in other ways, or images captured or transmitted by other devices may be received, which is not limited in the present disclosure.
  • Step S102 Acquire the position information of the first part and the posture information of the second part of the user according to the image.
  • the first part and the second part are the user's body parts, such as hands, arms, etc.;
  • the position information of the first part refers to the position of the first part in the image, or the position of the first part relative to the controlled terminal device Information;
  • the posture information of the second part refers to the form of the second part, such as gestures.
  • the position information of the first part and the posture information of the second part of the user in the image can be acquired.
  • Step S103 Determine the movement track of the navigation marker according to the position information of the first part.
  • the navigation mark can be used to select and control the visual elements on the display interface.
  • the navigation mark can be represented by an icon, such as the mouse pointer of the Windows system; the navigation mark can also be hidden, which can highlight the visual element or produce other animation effects, indicating that the visual element is selected.
  • the movement track of the navigation mark includes one or a group of movement vectors, which reflect the displacement and direction of the movement of the navigation mark. The movement track of the navigation mark is determined by the position information of the user's first part.
  • the controlled element pointed to by the navigation identifier may be determined according to the position information of the first part, for example, the navigation on the controlled device may be determined according to the position information of the first part relative to the controlled device
  • the position and/or movement track of the mark determines the controlled element pointed to by the navigation mark based on the position and/or movement track.
  • Step S104 Determine a control instruction according to the posture information of the second part, where the control instruction is used to control the visual element pointed to by the navigation mark.
  • the control instruction of the navigation mark is the control or operation of the visual element pointed to by the navigation mark, including clicking, tapping, long-pressing, zooming in, zooming out, rotating, etc. on the visual element.
  • the mapping relationship between the posture information of each second part and the control instruction can be preset, so that the control instruction corresponding to the acquired posture information of the second part can be determined according to the mapping relationship.
  • the movement track of the navigation mark is determined according to the position information of the first part, and the control command is determined according to the posture information of the second part, so that the determination of the control command and the navigation
  • the identification of the location of the mark is separated.
  • the determination of the control instruction is based on static posture information, and the determination of the position of the navigation mark is based on the dynamic position change, which can provide convenient conditions for the use of different characteristic algorithms to determine the above two processes.
  • the determination of the control instruction It can be based on static posture information, and the navigation mark position is determined based on dynamically changing position information.
  • the calculation module of the corresponding characteristics can be used to calculate the position information of the first part and the second part respectively.
  • Posture information thereby improving the pertinence of information acquisition, increasing calculation accuracy and computing resource utilization;
  • the determination of control instructions and the determination of the position of the navigation mark are based on the user's different body parts, which can make the two determination processes different from each other.
  • the contour shape of the first part does not change with the posture of the second part, which can prevent the change of the gesture from affecting the movement of the navigation mark, thereby improving the recognition accuracy of the user instruction.
  • the first part and the second part belong to different body parts of the same user.
  • the first part and the second part do not have an inclusive relationship.
  • the first part may be a wrist or an elbow instead of a finger.
  • the embodiments of the present disclosure separately determine the movement track and control instruction of the navigation mark according to different body parts of the user, thereby preventing the user from affecting the confirmation of the control instruction when the user changes the position of the first part or affecting the movement of the navigation mark when the user changes the posture of the second part. Confirmation of the trajectory.
  • the position of the second part can follow the change of the position of the first part; the position or posture of the first part itself does not affect the posture of the second part.
  • the position of the second part can follow the position of the first part to change, so that the first part and the second part can move in the interrelated space, avoiding the limitation of the imaging range of the imaging device due to the excessive spatial distance between the two. It is difficult to capture images of the first part and the second part at the same time, so as to improve the success rate and ease of operation of controlling the controlled element by using the first part and the second part.
  • the position and/or posture change of the first part will not affect the posture of the second part, and the accuracy of generating control commands based on the posture of the second part can also be improved, so that the position of the navigation mark can be controlled accurately and conveniently And issue control commands.
  • the first part is a hand and the second part is a wrist.
  • the wrist can accurately and stably reflect the displacement of the gesture, and is less affected by the gesture changes than the fingers, palms and other parts, so that precise control of the movement of the navigation mark can be achieved. And the movement of the wrist will not affect the gestures, so that the control commands can be issued conveniently and accurately.
  • step S102 further includes:
  • A1 Obtain the position information of the first part of the user according to the image based on the first calculation module
  • A2 Obtain the posture information of the second part of the user based on the second calculation module according to the image.
  • the determination of the control instruction is based on static posture information, and the determination of the position of the navigation mark is based on dynamic position changes. Therefore, in this embodiment, the position information of the first part and the posture of the second part are respectively calculated by using calculation modules with different characteristics. Information can improve the pertinence of information acquisition, thereby improving calculation accuracy and computing resource utilization.
  • the first calculation module may run the first machine learning model
  • the second calculation module may run the second machine learning model.
  • the first and second machine learning models are trained to reliably recognize and distinguish the first part and the second part of the user. By using a trained machine learning model to determine the position information of the first part and the posture information of the second part, the recognition accuracy can be improved, and computing resources and hardware costs can be reduced.
  • step S104 further includes:
  • the first posture may include one or more preset hand shapes.
  • step S104 further includes:
  • the navigator identifier is moved only according to the position information of the first part.
  • step S102 further includes:
  • Step C1 Determine the key point of the first part in the image
  • Step C2 Determine the position information of the first part according to the positions of the key points of the first part in the image.
  • the method 100 further includes:
  • Step S105 Based on the position information of the first part acquired according to at least two frames of target images, control the visual element pointed by the navigation mark.
  • the controlled element pointed to by the navigation mark can be controlled according to the position change information of the first part obtained by at least two frames of target images, wherein the method of controlling the navigation mark to point to the controlled element includes but is not limited to Control the movement of the controlled element on the controlled device by scrolling or moving, for example, moving or scrolling the application interface, icons or other controls.
  • the method for determining the at least two frames of target images includes:
  • Step D1 when the posture information of the second part meets the preset second posture, use the image corresponding to the posture information of the second part as the target image;
  • Step D2 Select at least two frames of target images from the target images of consecutive multiple frames.
  • the target image is an image whose posture information conforms to the second posture.
  • the posture information conforms to the second posture the position change of the first part is triggered to be converted into the scrolling effect of the visual element.
  • the user can control the navigation mark to scroll the visual elements, thereby improving the interaction efficiency.
  • the second posture may include one or more preset hand shapes.
  • the controlled element may be moved according to the position information of the first part and/or the preset posture of the second part, so as to determine the controlled element pointed to by the navigation mark.
  • step S105 further includes:
  • Step E1 Determine the movement information of the first part according to the position information of the first part obtained by the at least two frames of target images;
  • Step E2 Scroll the visual element according to the movement information of the first part.
  • the movement information of the first part includes one or more of the following: movement time of the first part, movement speed of the first part, movement displacement of the first part, and movement acceleration of the first part.
  • the initial parameters and conditions required for scrolling the visual element can be realized, thereby determining the relevant scrolling parameter of the visual element.
  • step E2 further includes:
  • the second posture is a preset number of fingers spread out.
  • the second posture is five fingers stretched out.
  • the scrolling operation usually requires a faster movement speed of the gesture, and in the case of fast movement, the preset number of fingers spread out is easier to recognize than other gestures, so that the recognition accuracy can be improved.
  • step S103 further includes: if the posture information of the second part conforms to the preset third posture, determining the movement track of the navigation marker according to the position information of the first part.
  • the third posture may include multiple preset hand shapes.
  • the movement trajectory of the navigation mark is determined according to the position information of the first part, for example, based only on the first hand of the hand conforming to the preset hand shape. Moving the navigation mark at the position of the part can prevent the user from unintentionally moving the first part to cause the navigation mark to move incorrectly.
  • step S103 further includes: determining the movement track of the navigation mark according to the position information of the first part obtained from the interval image.
  • the navigation mark in order to prevent the navigation mark from shaking up and down or left and right when the user is waving the first part, the navigation mark can determine the movement track of the navigation mark according to the position information of the first part obtained from the interval images. Compared with the movement track of the navigation mark determined based on the position change of the first part determined based on two adjacent frames, the jitter of the navigation mark can be reduced.
  • the interval images can be images with a predetermined number of frames, or images with a dynamically adjusted number of frames.
  • the position change of the position information of the first part in multiple frames (such as multiple consecutive frames) arranged one after another in chronological order or the navigation mark coordinates transformed from the position change can be fitted into a smooth Curve, so as to determine the movement trajectory of the navigation mark according to the curve.
  • the camera device is a separate RGB camera
  • the method 100 further includes a color space preprocessing step.
  • the color space preprocessing step performs HSV color space processing on the image data to convert the color space of the image data into HSV colors. space.
  • the RGB camera usually has three independent CCD sensors to obtain three color signals, which can collect very accurate color images. The accuracy of the extraction and recognition of the posture feature of the second part and the key point feature of the first part can be improved.
  • the color space of the image data captured by the camera is further preprocessed to convert the color space of the image data into the HSV color space, which can make subsequent The recognition and extraction of the posture feature of the second part and the key point feature of the first part are more accurate.
  • the first machine learning model is a convolutional neural network (Convolutional Neural Networks, CNN); the method 100 further includes a binarization preprocessing step and a white balance preprocessing step.
  • the binarization preprocessing step may The image data is binarized to obtain binarized image data, and the white balance preprocessing step may perform white balance processing on the image data.
  • Convolutional neural network is a kind of input to output mapping. It does not need accurate mathematical expressions to learn the mapping relationship between input and output, and does not require any precise mathematical expressions between input and output. Knowing the pattern for training can have the ability to map between input and output pairs, which is used to identify the displacement of the two-dimensional graphics with high accuracy.
  • the embodiment of the present disclosure can greatly reduce the amount of image data by binarizing the image to highlight the posture contour of the second part, and the white balance processing can correct the lighting conditions of the image data, so that the subsequent second part
  • the recognition and extraction of the posture feature and the key point feature of the first part are more accurate.
  • step S103 further includes: adopting a filtering algorithm and an anti-shake algorithm based on the position information of the first part to determine the final movement trajectory of the navigation marker.
  • the filtering algorithm may include a Kalman filtering algorithm
  • the anti-shake algorithm may include a moving average method.
  • Fig. 2 shows a schematic diagram of a scene for controlling a far-field display device according to a control method provided in an embodiment of the present disclosure.
  • the far-field display device 100 has a camera device 110 configured to capture an image in a certain area in front of the far-field display device 100.
  • the user (not shown) can move the navigation mark 120 displayed by the far-field display device 100 by waving the wrist 210 in the specific area, and can control the hand 220 To send a specific control instruction to the visual element 130 pointed to by the navigation mark 120.
  • FIG. 3 shows a flowchart of a control method 200 provided according to another embodiment of the present disclosure.
  • the method 200 includes step S201-step S206:
  • Step S201 Receive an image captured by an RGB camera
  • Step S202 Perform HSV color space preprocessing, binarization preprocessing, and white balance preprocessing on the image
  • Step S203 Obtain the user's wrist position information from the preprocessed image based on the convolutional neural network model
  • Step S204 Obtain the user's hand posture information from the preprocessed image based on the random forest model; among them, the random forest is a machine learning algorithm that has a good tolerance for noise and outliers. There will be over-fitting, and the extraction and recognition of various posture features of the second part has a high degree of accuracy.
  • Step S205 Determine the movement track of the navigation mark according to the obtained wrist position information
  • Step S206 Determine the control instruction of the navigation mark according to the acquired hand posture information and the mapping relationship with the control instruction.
  • the control instruction is used to control the visual element pointed to by the navigation mark.
  • FIG. 4 shows a schematic structural diagram of a control method device 300 according to an embodiment of the present disclosure.
  • the device 300 includes a data receiving unit 301, a data receiving unit 301, a first machine learning unit 302, and a second machine learning unit.
  • the unit 303, the control instruction unit 304 and the movement track unit 305 wherein:
  • the data receiving unit 301 is configured to receive images captured by the camera device
  • the acquiring unit 302 is configured to acquire the position information of the first part and the posture information of the second part of the user according to the image;
  • the movement track unit 303 determines the movement track of the navigation marker according to the position information of the first part
  • the control instruction unit 304 is configured to determine a control instruction according to the posture information of the second part, and the control instruction is used to control the visual element pointed to by the navigation mark.
  • the movement track of the navigation marker is determined according to the position information of the first part, and the control command is determined according to the posture information of the second part, so that the determination of the control command is consistent with The determination of the position of the navigation mark is separated.
  • the determination of the control instruction is based on static posture information, and the determination of the position of the navigation mark is based on the dynamic position change, which can provide convenient conditions for the use of different characteristic algorithms to determine the above two processes.
  • the determination of the control instruction It can be based on static posture information, and the navigation mark position is determined based on dynamically changing position information.
  • the calculation module of the corresponding characteristics can be used to calculate the position information of the first part and the second part respectively.
  • Posture information thereby improving the pertinence of information acquisition, increasing calculation accuracy and computing resource utilization;
  • the determination of control instructions and the determination of the position of the navigation mark are based on the user's different body parts, which can make the two determination processes different from each other.
  • the contour shape of the first part does not change with the posture of the second part, which can prevent the change of the gesture from affecting the movement of the navigation mark, thereby improving the recognition accuracy of the user instruction.
  • images may be received in other ways, or images captured or transmitted by other devices may be received, which is not limited in the present disclosure.
  • the relevant part can refer to the part of the description of the method embodiment.
  • the device embodiments described above are merely illustrative, and the modules described as separate modules may or may not be separate. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement without creative work.
  • the obtaining unit 302 is further configured to obtain the position information of the first part of the user according to the image based on the first calculation module, and obtain the posture information of the second part of the user according to the image based on the second calculation module .
  • the determination of the control instruction is based on static posture information, and the determination of the position of the navigation mark is based on dynamic position changes. Therefore, in this embodiment, the position information of the first part and the posture of the second part are respectively calculated by using calculation modules with different characteristics. Information can improve the pertinence of information acquisition, thereby improving calculation accuracy and computing resource utilization.
  • the first calculation module runs a first machine learning model
  • the second calculation module runs a second machine learning model.
  • the first and second machine learning models are trained to reliably recognize and distinguish the first part and the second part of the user.
  • the recognition accuracy can be improved, and computing resources and hardware costs can be reduced.
  • control instruction unit 304 is further configured to control the controlled element according to the posture information of the second part if the posture information of the second part meets the preset first posture.
  • the first posture may include one or more preset hand shapes.
  • control instruction unit 304 is further configured to not control the controlled element if the posture information of the second part does not meet the preset first posture.
  • the navigator identifier is moved only according to the position information of the first part.
  • the acquiring unit 302 further includes:
  • the key point determination subunit is used to determine the key point of the first part in the image.
  • the position determining subunit is configured to determine the position information of the first part according to the positions of the key points of the first part in the image.
  • the device 300 further includes a scrolling unit for scrolling the visual element pointed to by the navigation indicator based on the position information of the first part obtained from at least two frames of target images.
  • the rolling unit further includes:
  • the target image determining subunit is configured to use the image corresponding to the posture information of the second part as the target image when the posture information of the second part meets the preset second posture;
  • the target image selection subunit is used to select at least two frames of target images from the target images of a plurality of consecutive frames.
  • the target image is an image whose posture information conforms to the second posture.
  • the posture information conforms to the second posture the position change of the first part is triggered to be converted into a scrolling effect of visual elements, so that the user can control the navigation Identify scrolling visual elements to improve interaction efficiency.
  • the second posture may include one or more preset hand shapes.
  • the scroll unit further includes:
  • the motion information subunit is configured to determine the motion information of the first part according to the position information of the first part obtained by the at least two frames of target images;
  • the scrolling subunit is used to scroll the visual element according to the movement information of the first part.
  • the movement information of the first part includes one or more of the following: movement time of the first part, movement speed of the first part, movement displacement of the first part, and movement acceleration of the first part.
  • the initial parameters and conditions required for scrolling the visual element can be realized, thereby determining the relevant scrolling parameter of the visual element.
  • the scrolling subunit is further used to determine whether the motion information of the first part meets a preset motion condition, and is used to determine whether the motion information of the first part meets the preset motion condition, according to the motion of the first part The information determines the scroll direction and scroll distance of the visual element.
  • the second posture is five fingers stretched out.
  • the scrolling operation usually requires a faster movement speed of the gesture, and in the case of fast movement, the five-finger extension is easier to recognize than other gestures, which can improve the recognition accuracy.
  • the movement track unit 303 is further configured to determine the movement track of the navigation marker according to the position information of the first part if the posture information of the second part meets the preset third posture.
  • the third posture may include multiple preset hand shapes.
  • the movement trajectory of the navigation mark is determined according to the position information of the first part, for example, based only on the first hand of the hand conforming to the preset hand shape. Moving the navigation mark at the position of the part can prevent the user from unintentionally moving the first part to cause the navigation mark to move incorrectly.
  • the movement track unit 303 is further configured to determine the movement track of the navigation mark according to the position information of the first part obtained from the interval image.
  • the navigation mark can determine the movement track of the navigation mark based on the position information of the first part obtained from the spaced image, compared to the adjacent two.
  • the movement track of the navigation mark determined by the position change of the first part determined by the frame can reduce the jitter of the navigation mark.
  • the position change of the position information of the first part in multiple consecutive frames or the navigation mark coordinates transformed from the position change may be fitted into a smooth curve, so as to determine the movement track of the navigation mark according to the curve .
  • the camera device is a separate RGB camera
  • the device 300 further includes a color space preprocessing unit for performing HSV color space processing on the image data to convert the color space of the image data into the HSV color space.
  • the RGB camera usually has three independent CCD sensors to obtain three color signals, which can collect very accurate color images. The accuracy of the extraction and recognition of the posture feature of the second part and the key point feature of the first part can be improved.
  • the color space of the image data captured by the camera is further preprocessed to convert the color space of the image data into the HSV color space, which can make subsequent The recognition and extraction of the posture feature of the second part and the key point feature of the first part are more accurate.
  • the first machine learning model is a convolutional neural network (Convolutional Neural Networks, CNN); the device 300 further includes a binarization and white balance preprocessing unit, which is used to perform binarization and white balance processing on the image.
  • Convolutional neural network is a kind of input to output mapping. It does not need accurate mathematical expressions to learn the mapping relationship between input and output, and does not require any precise mathematical expressions between input and output. Knowing the pattern for training can have the ability to map between input and output pairs, which is used to identify the displacement of the two-dimensional graphics with high accuracy. Therefore, using the convolutional neural network model to obtain the position of the first part has higher accuracy.
  • the embodiment of the present disclosure can greatly reduce the amount of image data through image binarization to highlight the posture contour of the second part, and the white balance processing can correct the lighting conditions of the image data, so that the subsequent second part
  • the recognition and extraction of the posture feature and the key point feature of the first part are more accurate.
  • the movement trajectory unit 303 is further configured to adopt a filtering algorithm and an anti-shake algorithm based on the position information of the first part to determine the final movement trajectory of the navigation marker.
  • the filtering algorithm may include a Kalman filtering algorithm
  • the anti-shake algorithm may include a moving average method.
  • a terminal device including:
  • At least one memory and at least one processor are At least one memory and at least one processor
  • the memory is used to store program code
  • the processor is used to call the program code stored in the memory, so that the terminal executes the control method provided according to one or more embodiments of the present disclosure.
  • a non-transitory computer storage medium stores program code, and when the program code is executed by a computer device, the computer device executes According to the control method provided by one or more embodiments of the present disclosure.
  • FIG. 5 shows a schematic structural diagram of a terminal device 800 suitable for implementing embodiments of the present disclosure.
  • the terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Car navigation terminals) and other mobile terminals and fixed terminals such as smart TVs, desktop computers, etc.
  • the terminal device shown in FIG. 5 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the terminal device 800 may include a processing device (such as a central processing unit, a graphics processor, etc.) 801, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 802 or from a storage device 808
  • the program in the memory (RAM) 803 executes various appropriate actions and processing.
  • various programs and data required for the operation of the terminal device 800 are also stored.
  • the processing device 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804.
  • An input/output (I/O) interface 805 is also connected to the bus 804.
  • the following devices can be connected to the I/O interface 805: including input devices 806 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, vibration An output device 807 such as a device; a storage device 808 such as a magnetic tape, a hard disk, etc.; and a communication device 809.
  • the communication device 809 may allow the terminal device 800 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 5 shows the terminal device 800 with various devices, it should be understood that it is not required to implement or have all the illustrated devices. It may be implemented alternatively or provided with more or fewer devices.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 809, or installed from the storage device 808, or installed from the ROM 802.
  • the processing device 801 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the client and server can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communication e.g., communication network
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future research and development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned terminal device; or it may exist alone without being assembled into the terminal device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the terminal device When the above-mentioned one or more programs are executed by the terminal device, the terminal device: receives an image; obtains the position information of the user's first part and the second part according to the image Determine the movement track of the navigation mark according to the position information of the first part; and determine the control instruction according to the posture information of the second part, the control instruction is used to control the visual element pointed to by the navigation mark.
  • the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the terminal device, the terminal device: receives an image; obtains location information of the user's first part according to the image And the posture information of the second part; determine the controlled element pointed to by the navigation mark according to the position information of the first part; determine the control instruction according to the posture information of the second part, and the control instruction is used for the navigation Identify the controlled element pointed to for control.
  • the computer program code used to perform the operations of the present disclosure can be written in one or more programming languages or a combination thereof.
  • the above-mentioned programming languages include, but are not limited to, object-oriented programming languages—such as Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user’s computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions can also occur in a different order from the order marked in the drawings. For example, two blocks shown one after the other can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware. Among them, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • the acquiring and identifying unit can also be described as “used to acquire the position information of the user's first part and the second part according to the image. Unit of posture information”.
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Product
  • SOC System on Chip
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium, which may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • the machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing.
  • machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read only memory
  • magnetic storage device or any suitable combination of the foregoing.
  • a control method including: receiving an image captured by a camera; acquiring position information of a first part of a user and posture information of a second part according to the image; The position information of the navigation mark determines the movement track; the control instruction is determined according to the posture information of the second part, and the control instruction is used to control the visual element pointed to by the navigation mark.
  • the first part and the second part belong to different body parts of the same user.
  • the position of the second part can follow the change of the position of the first part; the position and/or posture of the first part itself does not affect the second part The posture of the part.
  • the first part is a hand
  • the second part is a wrist
  • acquiring the position information of the first part of the user and the posture information of the second part of the user according to the image includes: acquiring the position information of the first part of the user according to the image based on the first calculation module; The second calculation module obtains the posture information of the second part of the user according to the image.
  • the first calculation module runs a first machine learning model
  • the second calculation module runs a second machine learning model
  • control instruction is determined according to the posture information of the second part, and the control instruction is used to control the visual element pointed to by the navigation mark, including: if the posture information of the second part meets the preset In the first posture, the visual elements are controlled according to the posture information of the second part.
  • control instruction is determined according to the posture information of the second part, and the control instruction is used to control the visual element pointed to by the navigation mark, including: if the posture information of the second part does not meet the preset The first posture does not control the visual elements.
  • acquiring the position information of the first part of the user according to the image includes: determining the key point of the first part in the image; determining the first part according to the position of the key point of the first part in the image Location information of a part.
  • the control method provided according to one or more embodiments of the present disclosure further includes: scrolling the visual element pointed to by the navigation mark based on the position information of the first part obtained from at least two frames of target images;
  • the determination method includes: when the posture information of the second part meets the preset second posture, taking the image corresponding to the posture information of the second part as the target image; and selecting at least two target images from the target images of consecutive multiple frames.
  • controlling the visual element pointed to by the navigation mark includes: The position information determines the movement information of the first part; the visual elements are scrolled according to the movement information of the first part.
  • the controlling the visual element pointed by the navigation mark includes: scrolling or moving the visual element pointed by the navigation mark.
  • the movement information of the first part includes one or more of the following: movement time of the first part, movement speed of the first part, movement displacement of the first part, and Movement acceleration.
  • controlling the visual element according to the motion information of the first part includes: determining whether the motion information of the first part meets a preset motion condition; if so, determining the visual element according to the motion information of the first part The scroll direction and scroll distance of the element.
  • the second posture is a preset number of fingers spread out.
  • the second posture is five fingers spread out.
  • determining the movement track of the navigation marker according to the position information of the first part includes: if the posture information of the second part meets the preset third posture, then according to the position information of the first part Determine the movement track of the navigation mark.
  • determining the movement track of the navigation mark according to the position information of the first part includes: determining the movement track of the navigation mark according to the position information of the first part obtained from the interval images.
  • the camera device is a separate RGB camera; the control method further includes: performing HSV color space preprocessing on the image to convert the color space of the image into the HSV color space.
  • the first machine learning model is a convolutional neural network model; the control method further includes: performing binarization preprocessing and white balance preprocessing on the image.
  • determining the movement track of the navigation mark based on the position information of the first part includes: adopting a filtering algorithm and an anti-shake algorithm based on the position information of the first part to determine the final movement track of the navigation mark.
  • the acquiring the position information of the first part of the user and the posture information of the second part of the user according to the image includes: acquiring the position information of the first part of the user in the image and The posture information of the second part.
  • a control method and device including: a data receiving unit for receiving an image captured by a camera device; and an acquisition and recognition unit for acquiring the position of a user's first part according to the image Information and the posture information of the second part; the movement track unit is used to determine the movement track or position information of the navigation mark according to the position information of the first part, and/or according to the position information of the first part and/or the second part The preset posture of the part moves the controlled element; and the control instruction unit is used to determine the control instruction according to the posture information of the second part, and the control instruction is used to control the visual element pointed to by the navigation mark.
  • a terminal includes: at least one memory and at least one processor; wherein the memory is used to store program code, and the processor is used to call the program code stored in the memory to The terminal is caused to execute the control method provided according to one or more embodiments of the present disclosure.
  • a computer storage medium stores a program code.
  • the program code is executed by a computer device, the computer device executes one or more implementations according to the present disclosure.
  • the control method provided by the example.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Social Psychology (AREA)
  • Biophysics (AREA)
  • Chemical & Material Sciences (AREA)
  • Neurosurgery (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Analytical Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开涉及计算机技术领域，具体涉及控制方法、装置、终端及存储介质。根据本公开实施例提供的控制方法，包括：接收图像；根据图像获取用户的第一部位的位置信息和第二部位的姿态信息；根据第一部位的位置信息确定导航标识的移动轨迹；根据第二部位的姿态信息确定控制指令，控制指令用于对导航标识所指向的视觉元素进行控制。

Description

控制方法、装置、终端及存储介质
相关申请的交叉引用
本申请基于申请号为202010507222.8、申请日为2020年06月05日、名称为“控制方法、装置、终端及存储介质”的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及计算机技术领域，具体涉及控制方法、装置、终端及存储介质。
背景技术
智能电视已替代传统电视被广泛使用，其可以搭载多种多样的节目和应用程序供用户选择和观看。现有的智能电视由遥控器控制，其通常只有上下左右四个方向键可以用来控制选择方向，交互效率较低，费时费力。
发明内容
提供该发明内容部分以便以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。该发明内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
根据本公开的一个或多个实施例，提供了一种控制方法，包括：
接收图像；
根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；
根据所述第一部位的位置信息确定导航标识的移动轨迹；
根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的视觉元素进行控制。
根据本公开的一个或多个实施例，提供了一种控制方法，包括：
接收图像；
根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；
根据所述第一部位的位置信息确定导航标识所指向的被控元素；
根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的被控元素进行控制。
根据本公开的一个或多个实施例，提供了一种控制方法装置，包括：
数据接收单元，用于接收图像；
获取识别单元，用于根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；
移动轨迹单元，用于根据所述第一部位的位置信息确定导航标识的移动轨迹；
控制指令单元，用于根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的视觉元素进行控制。
根据本公开的一个或多个实施例，提供了一种控制方法装置，包括：
数据接收单元，用于接收图像；
获取识别单元，用于根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；
移动轨迹单元，用于根据所述第一部位的位置信息确定导航标识的位置信息，和/或，根据所述第一部位的位置信息和/或第二部位的预设姿态移动被控元素；
控制指令单元，用于根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的被控元素进行控制。根据本公开的一个或多个实施例，提供了一种终端，其特征在于，所述终端包括：
至少一个存储器和至少一个处理器；
其中，所述存储器用于存储程序代码，所述处理器用于调用所述存储器所存储的程序代码，以使所述终端执行根据本公开的一个或多个实施例提供的控制方法。
根据本公开的一个或多个实施例，提供了一种计算机存储介质，其特征在于，所述计算机存储介质存储有程序代码，所述程序代码被计算 机设备执行时，使得所述计算机设备执行本公开的一个或多个实施例提供的控制方法。
根据本公开的一个或多个实施例提供的控制方法，通过根据所述第一部位的位置信息确定导航标识的移动轨迹，并根据所述第二部位的姿态信息确定控制指令，使控制指令的确定与导航标识位置的确定相分离。一方面，控制指令的确定基于静态的姿态信息，而导航标识位置的确定基于动态的位置变化，进而可以为采用不同特性算法分别确定上述两个过程提供便利条件；另一方面，控制指令的确定与导航标识位置的确定基于用户不同的身体部位，可以使二者确定过程互不影响，尤其是第一部位的轮廓形状不随第二部位的姿态而改变，可以避免手势的变化影响导航标识的移动，从而可以提高用户指令的识别精度。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1示出了根据本公开一实施例提供的控制方法的流程图；
图2示出了根据本公开实施例提供的控制方法控制远场显示设备的场景示意图；
图3示出了根据本公开另一实施例提供的控制方法的流程图；
图4示出了根据本公开的一个或多个实施例提供的控制方法装置的结构示意图；
图5为用来实现本公开实施例的终端设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
参考图1，图1示出了根据本公开一实施例提供的控制方法100的流程图，该方法100可用于包括但不限于远场显示设备的终端设备，其中，远场显示设备是指用户无法用身体部位或其他诸如触控笔等物理控制设备以直接接触的方式实现接触式控制的显示设备，包括但不限于电视、会议屏幕等电子设备。具体地，方法100包括步骤S101-步骤S104：
步骤S101：接收摄像装置捕获的图像。
其中，摄像装置可以内置或外接于终端设备，其可以将捕获到的图像数据实时发送给终端设备供终端设备进行处理。有利地，摄像装置以可以正对用户的方式设置，从而可以捕获用户对终端设备发出的肢体指令。
需要说明的是，在另一些其他实施例中，还可以通过其他方式接收图像，或者接收其他装置捕获或传输的图像，本公开在此不做限制。
步骤S102：根据图像获取用户的第一部位的位置信息和第二部位的姿态信息。
其中，第一部位和第二部位是用户的身体部位，例如手、手臂等；第一部位的位置信息是指第一部位在图像中的位置，或第一部位相对于被 控终端设备的位置信息；第二部位的姿态信息是指第二部位所处的形态，例如手势等。
示例性地，可以获取所述图像中用户的第一部位的位置信息和第二部位的姿态信息。
步骤S103：根据第一部位的位置信息确定导航标识的移动轨迹。
其中，导航标识可以用来选中和控制显示界面上的视觉元素。导航标识可以用图标表示，例如Windows系统的鼠标指针；导航标识还可以被隐藏，可以使视觉元素高亮或产生其他动画效果，表示该视觉元素被选中。导航标识的移动轨迹包括一个或一组移动向量，其反映导航标识移动的位移和方向。导航标识的移动轨迹由用户第一部位的位置信息决定。
示例性地，可以根据所述第一部位的位置信息确定导航标识所指向的被控元素，例如，根据所述第一部位相对于被控设备的位置信息，确定所述被控设备上的导航标识的位置和/或移动轨迹，基于所述位置和/或移动轨迹确定所述导航标识所指向的被控元素。
步骤S104：根据第二部位的姿态信息确定控制指令，其中，控制指令用于对导航标识所指向的视觉元素进行控制。
其中，导航标识的控制指令系对被导航标识所指向的视觉元素的控制或实施的操作，包括对视觉元素的点击、轻触、长按、放大、缩小、旋转等。在一些实施例中，可以预先设置各个第二部位的姿态信息与控制指令的映射关系，从而可以根据该映射关系确定获取的第二部的姿态信息所对应的控制指令。
这样，根据本公开实施例提供的控制方法，通过根据所述第一部位的位置信息确定导航标识的移动轨迹，并根据所述第二部位的姿态信息确定控制指令，使控制指令的确定与导航标识位置的确定相分离。一方面，控制指令的确定基于静态的姿态信息，而导航标识位置的确定基于动态的位置变化，进而可以为采用不同特性算法分别确定上述两个过程提供便利条件，示例性的，控制指令的确定可以基于静态的姿态信息，而导航标识位置的确定基于动态变化的位置信息，因此针对上述两种不同的计算特性，可以采用相应特性的计算模块分别计算第一部位的位置信息和第二部位的姿态信息，从而提高信息获取的针对性，提高计算准确率和计算资源利用率；另一方面，控制指令的确定与导航标识位置的确定基于用 户不同的身体部位，可以使二者确定过程互不影响，尤其是第一部位的轮廓形状不随第二部位的姿态而改变，可以避免手势的变化影响导航标识的移动，从而可以提高用户指令的识别精度。
在一些实施例中，第一部位和所述第二部位属于同一用户不同的身体部位。第一部位和第二部位二者没有包含关系，例如，当第二部位是手时，第一部位可以为手腕、手肘，而非手指。本公开实施例通过根据用户不同的身体部位分别确定导航标识的移动轨迹和控制指令，从而可以防止用户改变第一部位的位置时影响控制指令的确认或用户改变第二部位姿态时影响导航标识移动轨迹的确认。
在一些实施例中，所述第二部位的位置能够跟随所述第一部位的位置的变化而变化；所述第一部位本身的位置或姿态不影响所述第二部位的姿态。这样，第二部位的位置能够跟随第一部位的位置进行变化，使得第一部位和第二部位能够在相互关联的空间内活动，避免由于两者空间距离过大导致摄像装置由于摄像范围所限难以同时捕捉到第一部位和第二部位的图像，从而提高控制利用第一部位和第二部位对被控元素进行控制的成功率和易操作性。另外，第一部位的位置和/或姿态变化不会对第二部位的姿态产生影响，也能够提高根据第二部位的姿态生成控制指令的准确性，从而可精确、方便地控制导航标识的位置和发出控制指令。
在一些实施例中，第一部位为手，所述第二部位为手腕。在本公开实施例中，手腕可以准确且稳定的反映手势的位移，且较手指、手掌等部位受手势变化的影响较小，从而可以实现对导航标识移动的精准控制。并且手腕的移动不会对手势产生影响，从而可以方便、精确地发出控制指令。
在一些实施例中，步骤S102进一步包括：
A1：基于第一计算模块根据所述图像获取用户的第一部位的位置信息；
A2：基于第二计算模块根据所述图像获取用户的第二部位的姿态信息。
控制指令的确定基于静态的姿态信息，而导航标识位置的确定基于动态的位置变化，因此在本实施例中，通过采用特性不同的计算模块分别计算第一部位的位置信息和第二部位的姿态信息可以提高信息获取的针对性，进而提高计算精度和计算资源利用率。
在一些实施例中，第一计算模块可以运行第一机器学习模型，第二计算模块可以运行第二机器学习模型。第一和第二机器学习模型被训练为以可靠地识别和区分用户的第一部位和第二部位。通过使用训练好的机器学习模型确定第一部位的位置信息和第二部位的姿态信息，可以提升识别精度，降低计算资源和硬件成本。
在一些实施例中，步骤S104进一步包括：
B1：若所述第二部位的姿态信息符合预设的第一姿态，则根据所述第二部位的姿态信息对所述被控元素进行控制。
其中，第一姿态可以包括一种或多种预设手型。
在一些实施例中，步骤S104进一步包括：
B2：若所述第二部位的姿态信息不符合预设的第一姿态，则不对所述被控元素进行控制。
在本公开实施例中，当第二部位的姿态信息不符合预设的第一姿态，则仅根据第一部位的位置信息移动导航器标识。
在一些实施例中，步骤S102进一步包括：
步骤C1：确定所述图像中的第一部位的关键点；
步骤C2：根据所述第一部位的关键点在所述图像中的位置确定所述第一部位的位置信息。
在一些实施例中，方法100还包括：
步骤S105：基于根据至少两帧目标图像获取的第一部位位置信息，控制被所述导航标识指向的视觉元素。示例性地，可以根据至少两帧目标图像获取的第一部位的位置变化信息，控制所述导航标识所指向的被控元素，其中，控制所述导航标识指向被控元素的方式包括但不限于通过滚动或移动等方式控制被控元素在被控设备上移动，例如，移动或滚动应用界面、图标或其他控件等。
其中，所述至少两帧目标图像的确定方法包括：
步骤D1：当所述第二部位的姿态信息符合预设的第二姿态时，将所述第二部位的姿态信息对应的图像作为目标图像；
步骤D2：从连续多个帧的所述目标图像中选取至少两帧目标图像。
根据本公开的一个或多个实施例，目标图像为姿态信息符合第二姿态的图像，通过当姿态信息符合第二姿态时，触发将第一部位的位置变化 转化为视觉元素的滚动效果，使用户可以控制导航标识滚动视觉元素，从而提升交互效率。其中，第二姿态可以包括一种或多种预设手型。示例地，可以根据第一部位的位置信息和/或第二部位的预设姿态移动被控元素，从而确定导航标识指向的被控元素。
在一些实施例中，步骤S105进一步包括：
步骤E1：根据所述至少两帧目标图像获取的第一部位的位置信息确定第一部位的运动信息；
步骤E2：根据所述第一部位的运动信息滚动所述视觉元素。
第一部位的运动信息包括以下一种或多种：第一部位的运动时间、第一部位的运动速度、第一部位的运动位移、第一部位的运动加速度。在本实施例中，通过根据位置信息确定运动信息，可以实现滚动视觉元素所需的初始参数和条件，从而确定视觉元素的相关滚动参数。
在一些实施例中，步骤E2进一步包括：
确定所述第一部位的运动信息是否满足预设的运动条件；
若是，根据所述第一部位的运动信息确定所述视觉元素的滚动方向和滚动距离。
在一些实施例中，所述第二姿态为预设数量的手指张开。示例性地，第二姿态为五指伸开。滚动操作通常要求手势的移动速度较快，而在快速移动的情况下，预设数量的手指张开较其他手势更易识别，从而可以提高识别准确率。
在一些实施例中，步骤S103进一步包括：若所述第二部位的姿态信息符合预设的第三姿态，则根据所述第一部位的位置信息确定导航标识的移动轨迹。其中，第三姿态可以包括多种预设手型。在本实施例中，当第二部位的姿态信息符合预设的第三姿态时，才根据第一部位的位置信息确定导航标识的移动轨迹，例如仅基于符合预设手型的手的第一部位位置移动导航标识，可以避免用户无意地运动第一部位产生导航标识误移动。
在一些实施例中，步骤S103进一步包括：根据从间隔的图像获取的第一部位的位置信息确定导航标识的移动轨迹。在本公开实施例中，为防止用户在挥动第一部位时不可避免地上下或左右晃动引起导航标识抖动，导航标识可以根据从间隔的图像获取的第一部位的位置信息确定导航标 识的移动轨迹，相比基于相邻两帧确定的第一部位的位置变化所确定的导航标识移动轨迹，可以减少导航标识抖动。其中，间隔的图像可以是间隔预定帧数的图像，也可以是动态调整间隔帧数的图像。示例性地，可以将第一部位的位置信息在按照时间顺序前后排列的多个帧(例如连续多个帧)中的位置变化或由该位置变化转化的导航标识坐标，拟合成一条平滑的曲线，从而根据该曲线确定导航标识的移动轨迹。
在一些实施例中，摄像装置为单独的RGB摄像头，方法100还包括颜色空间预处理步骤，该颜色空间预处理步骤对图像数据进行HSV颜色空间处理，以将图像数据的颜色空间转化为HSV颜色空间。RGB摄像头通常由三个独立的CCD传感器来获取三种彩色信号，其可以采集非常精确的彩色图像。可以提升第二部位姿态特征和第一部位关键点特征提取和识别的准确性。但是因RGB模式的图像不利于肤色分割，因而在本公开实施例中，通过进一步对摄像装置捕获的图像数据进行颜色空间预处理，将图像数据的颜色空间转化为HSV颜色空间，可以使后续的第二部位姿态特征和第一部位关键点特征的识别和提取更加准确。
在一些实施例中，第一机器学习模型为卷积神经网络模型(Convolutional Neural Networks,CNN)；方法100还包括二值化预处理步骤和白平衡预处理步骤，该二值化预处理步骤可以对图像数据进行二值化处理从而得到二值化图像数据，该白平衡预处理步骤可以对图像数据进行白平衡处理。卷积神经网络是一种输入到输出的映射，其无需准确的数学表达式即可学习输入与输出之间的映射关系，而不需要任何输入和输出之间的精确的数学表达式，通过已知模式进行训练，就能具有输入输出对之间的映射能力，其用来识别二维图形的位移具有较高的准确率。因此，采用卷积神经网络模型获取第一部位的位置具有较高的准确性。进一步地，本公开实施例通过图像的二值化使可以大幅减少图像数据的数据数量，以凸显第二部位姿态轮廓，而白平衡处理可以修正图像数据的光照条件，从而使后续的第二部位姿态特征和第一部位关键点特征的识别和提取更加准确。
在一些实施例中，步骤S103进一步包括：基于第一部位的位置信息采用滤波算法和防抖算法，确定导航标识的最终移动轨迹。其中，滤波算法可以包括卡尔曼滤波算法，防抖算法可以包括移动平均法。在本公开实 施例中，通过采用滤波算法和防抖算法对第一部位关键点特征的位置变化或由该位置变化确定的导航标识坐标变化进行处理，可以使导航标识的移动轨迹更加平滑流畅，防止导航标识抖动。
图2示出了根据本公开实施例提供的控制方法控制远场显示设备的场景示意图。远场显示设备100具有摄像装置110，摄像装置110被配置为可以捕获远场显示设备100前方一定区域内的图像。根据本公开的一个或多个实施例提供的控制方法，用户(未示出)在该特定区域内可以通过挥动手腕210移动该远场显示设备100显示的导航标识120，并可以通过控制手220的姿态来对导航标识120所指向的视觉元素130发出特定的控制指令。
参考图3，图3示出了根据本公开另一实施例提供的控制方法200的流程图，方法200包括步骤S201-步骤S206：
步骤S201：接收RGB摄像头捕获的图像；
步骤S202：对该图像进行HSV颜色空间预处理、二值化预处理和白平衡预处理；
步骤S203：基于卷积神经网络模型从预处理后的图像获取用户的手腕位置信息；
步骤S204：基于随机森林模型从预处理后的图像获取用户的手部姿态信息；其中，随机深林(Random forest)是一种机器学习算法，其对噪声和异常值具有很好的容忍度，不会出现过拟合，对各种各样的第二部位姿态特征的提取和识别具有较高的准确度。
步骤S205：根据获取的手腕位置信息确定导航标识的移动轨迹；
步骤S206：根据获取的手部姿态信息及其与控制指令的映射关系，确定导航标识的控制指令。控制指令用于对所述导航标识所指向的视觉元素进行控制。
针对上述控制方法，图4示出了根据本公开一实施例提供的控制方法装置300的结构示意图，装置300包括数据接收单元301、数据接收单元301、第一机器学习单元302、第二机器学习单元303、控制指令单元304和移动轨迹单元305，其中：
数据接收单元301，用于接收摄像装置捕获的图像；
获取单元302，用于根据所述图像获取用户的第一部位的位置信息 和第二部位的姿态信息；
移动轨迹单元303，根据所述第一部位的位置信息确定导航标识的移动轨迹；
控制指令单元304，用于根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的视觉元素进行控制。
这样，根据本公开实施例提供的控制方法装置，通过根据所述第一部位的位置信息确定导航标识的移动轨迹，并根据所述第二部位的姿态信息确定控制指令，使控制指令的确定与导航标识位置的确定相分离。一方面，控制指令的确定基于静态的姿态信息，而导航标识位置的确定基于动态的位置变化，进而可以为采用不同特性算法分别确定上述两个过程提供便利条件，示例性的，控制指令的确定可以基于静态的姿态信息，而导航标识位置的确定基于动态变化的位置信息，因此针对上述两种不同的计算特性，可以采用相应特性的计算模块分别计算第一部位的位置信息和第二部位的姿态信息，从而提高信息获取的针对性，提高计算准确率和计算资源利用率；另一方面，控制指令的确定与导航标识位置的确定基于用户不同的身体部位，可以使二者确定过程互不影响，尤其是第一部位的轮廓形状不随第二部位的姿态而改变，可以避免手势的变化影响导航标识的移动，从而可以提高用户指令的识别精度。
需要说明的是，在另一些其他实施例中，还可以通过其他方式接收图像，或者接收其他装置捕获或传输的图像，本公开在此不做限制。
对于装置的实施例而言，由于其基本对应于方法实施例，所以相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中作为分离模块说明的模块可以是或者也可以不是分开的。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
在一些实施例中，获取单元302进一步用于基于第一计算模块根据所述图像获取用户的第一部位的位置信息，以及基于第二计算模块根据所述图像获取用户的第二部位的姿态信息。
控制指令的确定基于静态的姿态信息，而导航标识位置的确定基于动态的位置变化，因此在本实施例中，通过采用特性不同的计算模块分别 计算第一部位的位置信息和第二部位的姿态信息可以提高信息获取的针对性，进而提高计算精度和计算资源利用率。
在一些实施例中，第一计算模块运行第一机器学习模型，第二计算模块运行第二机器学习模型。第一和第二机器学习模型被训练为以可靠地识别和区分用户的第一部位和第二部位。通过使用训练好的机器学习模型确定第一部位的位置信息和第二部位的姿态信息，可以提升识别精度，降低计算资源和硬件成本。
在一些实施例中，控制指令单元304进一步用于若所述第二部位的姿态信息符合预设的第一姿态，则根据所述第二部位的姿态信息对所述被控元素进行控制。
其中，第一姿态可以包括一种或多种预设手型。
在一些实施例中，控制指令单元304进一步用于若所述第二部位的姿态信息不符合预设的第一姿态，则不对所述被控元素进行控制。
在本公开实施例中，当第二部位的姿态信息不符合预设的第一姿态，则仅根据第一部位的位置信息移动导航器标识。
在一些实施例中，获取单元302进一步包括：
关键点确定子单元，用于确定所述图像中的第一部位的关键点；以及
位置确定子单元，用于根据所述第一部位的关键点在所述图像中的位置确定所述第一部位的位置信息。
在一些实施例中，装置300还包括滚动单元，用于基于根据至少两帧目标图像获取的第一部位位置信息，滚动被所述导航标识指向的视觉元素。
其中，滚动单元进一步包括：
目标图像确定子单元，用于当所述第二部位的姿态信息符合预设的第二姿态时，将所述第二部位的姿态信息对应的图像作为目标图像；以及
目标图像选取子单元，用于从连续多个帧的所述目标图像中选取至少两帧目标图像。
在本公开实施例中，目标图像为姿态信息符合第二姿态的图像，通过当姿态信息符合第二姿态时，触发将第一部位的位置变化转化为视觉元素的滚动效果，使用户可以控制导航标识滚动视觉元素，从而提升交互效率。其中，第二姿态可以包括一种或多种预设手型。
在一些实施例中，滚动单元进一步包括：
运动信息子单元，用于根据所述至少两帧目标图像获取的第一部位的位置信息确定第一部位的运动信息；
滚动子单元，用于根据所述第一部位的运动信息滚动所述视觉元素。
第一部位的运动信息包括以下一种或多种：第一部位的运动时间、第一部位的运动速度、第一部位的运动位移、第一部位的运动加速度。在本实施例中，通过根据位置信息确定运动信息，可以实现滚动视觉元素所需的初始参数和条件，从而确定视觉元素的相关滚动参数。
在一些实施例中，滚动子单元进一步用于确定所述第一部位的运动信息是否满足预设的运动条件，以及用于若确定满足预设的运动条件，则根据所述第一部位的运动信息确定所述视觉元素的滚动方向和滚动距离。
在一些实施例中，所述第二姿态为五指伸开。滚动操作通常要求手势的移动速度较快，而在快速移动的情况下，五指伸开较其他手势更易识别，从而可以提高识别准确率。
在一些实施例中，移动轨迹单元303进一步用于若所述第二部位的姿态信息符合预设的第三姿态，则根据所述第一部位的位置信息确定导航标识的移动轨迹。其中，第三姿态可以包括多种预设手型。在本实施例中，当第二部位的姿态信息符合预设的第三姿态时，才根据第一部位的位置信息确定导航标识的移动轨迹，例如仅基于符合预设手型的手的第一部位位置移动导航标识，可以避免用户无意地运动第一部位产生导航标识误移动。
在一些实施例中，移动轨迹单元303进一步用于根据从间隔的图像获取的第一部位的位置信息确定导航标识的移动轨迹。为防止用户在挥动第一部位时不可避免地上下或左右晃动引起导航标识抖动，导航标识可以根据从间隔的图像获取的第一部位的位置信息确定导航标识的移动轨迹，相比基于相邻两帧确定的第一部位的位置变化所确定的导航标识移动轨迹，可以减少导航标识抖动。示例性地，可以将第一部位的位置信息在连续多个帧中的位置变化或由该位置变化转化的导航标识坐标，拟合成一条平滑的曲线，从而根据该曲线确定导航标识的移动轨迹。
在一些实施例中，摄像装置为单独的RGB摄像头，装置300还包括颜色空间预处理单元，用于对图像数据进行HSV颜色空间处理，以将图 像数据的颜色空间转化为HSV颜色空间。RGB摄像头通常由三个独立的CCD传感器来获取三种彩色信号，其可以采集非常精确的彩色图像。可以提升第二部位姿态特征和第一部位关键点特征提取和识别的准确性。但是因RGB模式的图像不利于肤色分割，因而在本公开实施例中，通过进一步对摄像装置捕获的图像数据进行颜色空间预处理，将图像数据的颜色空间转化为HSV颜色空间，可以使后续的第二部位姿态特征和第一部位关键点特征的识别和提取更加准确。
在一些实施例中，第一机器学习模型为卷积神经网络模型(Convolutional Neural Networks,CNN)；装置300还包括二值化和白平衡预处理单元，用于对图像进行二值化处理和白平衡处理。卷积神经网络是一种输入到输出的映射，其无需准确的数学表达式即可学习输入与输出之间的映射关系，而不需要任何输入和输出之间的精确的数学表达式，通过已知模式进行训练，就能具有输入输出对之间的映射能力，其用来识别二维图形的位移具有较高的准确率。因此，采用卷积神经网络模型获取第一部位的位置具有较高的准确性。进一步地，本公开实施例通过图像的二值化使可以大幅减少图像数据的数据数量，以凸显第二部位姿态轮廓，而白平衡处理可以修正图像数据的光照条件，从而使后续的第二部位姿态特征和第一部位关键点特征的识别和提取更加准确。
在一些实施例中，移动轨迹单元303进一步用于基于第一部位的位置信息采用滤波算法和防抖算法，确定导航标识的最终移动轨迹。其中，滤波算法可以包括卡尔曼滤波算法，防抖算法可以包括移动平均法。在本公开实施例中，通过采用滤波算法和防抖算法对第一部位关键点特征的位置变化或由该位置变化确定的导航标识坐标变化进行处理，可以使导航标识的移动轨迹更加平滑流畅，防止导航标识抖动。
相应地，根据本公开的一个或多个实施例，提供了一种终端设备，包括：
至少一个存储器和至少一个处理器；
其中，存储器用于存储程序代码，处理器用于调用存储器所存储的程序代码，以使所述终端执行根据本公开一个或多个实施例提供的控制方法。
相应地，根据本公开的一个或多个实施例，提供了一种非暂态计算机存储介质，非暂态计算机存储介质存储有程序代码，程序代码被计算机设备执行时，使得所述计算机设备执行根据本公开一个或多个实施例提供的控制方法。
下面参考图5，其示出了适于用来实现本公开实施例的终端设备800的结构示意图。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如智能电视、台式计算机等等的固定终端。图5示出的终端设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图5所示，终端设备800可以包括处理装置(例如中央处理器、图形处理器等)801，其可以根据存储在只读存储器(ROM)802中的程序或者从存储装置808加载到随机访问存储器(RAM)803中的程序而执行各种适当的动作和处理。在RAM 803中，还存储有终端设备800操作所需的各种程序和数据。处理装置801、ROM 802以及RAM 803通过总线804彼此相连。输入/输出(I/O)接口805也连接至总线804。
通常，以下装置可以连接至I/O接口805：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置806；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置807；包括例如磁带、硬盘等的存储装置808；以及通信装置809。通信装置809可以允许终端设备800与其他设备进行无线或有线通信以交换数据。虽然图5示出了具有各种装置的终端设备800，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置809从网络上被下载和安装，或者从存储装置808被安装，或者从ROM 802被安装。在该计算机程序被处理装置801执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述终端设备中所包含的；也可以是单独存在，而未装配入该终端设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该终端设备执行时，使得该终端设备：接收图像；根据图像获取用户的第一部位的位置信息和第二部位的姿态信息；根据第一部位的位置信息确定导航标识的移动轨迹；以及根据第二部位的姿态信息确定控制指令，控制指令用于对导航标识所指向的视觉元素进行控制。
或者，上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该终端设备执行时，使得该终端设备：接收图像；根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；根据所述第一部位的位置信息确定导航标识所指向的被控元素；根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的被控元素进行控制。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取识别单元还可以被描述为“用于根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，提供了一种控制方法，包括：接收摄像装置捕获的图像；根据图像获取用户的第一部位的位置信息和第二部位的姿态信息；根据第一部位的位置信息确定导航标识的移动轨迹；根据第二部位的姿态信息确定控制指令，控制指令用于对导航标识所指向的视觉元素进行控制。
根据本公开的一个或多个实施例，第一部位和第二部位属于同一用户不同的身体部位。
根据本公开的一个或多个实施例，所述第二部位的位置能够跟随所述第一部位的位置的变化而变化；所述第一部位本身的位置和/或姿态不影响所述第二部位的姿态。
根据本公开的一个或多个实施例，第一部位为手，第二部位为手腕。
根据本公开的一个或多个实施例，根据图像获取用户的第一部位的位置信息和第二部位的姿态信息，包括：基于第一计算模块根据图像获取用户的第一部位的位置信息；基于第二计算模块根据图像获取用户的第二部位的姿态信息。
根据本公开的一个或多个实施例，第一计算模块运行第一机器学习模型，第二计算模块运行第二机器学习模型。
根据本公开的一个或多个实施例，根据第二部位的姿态信息确定控制指令，控制指令用于对导航标识所指向的视觉元素进行控制，包括：若第二部位的姿态信息符合预设的第一姿态，则根据第二部位的姿态信息对视觉元素进行控制。
根据本公开的一个或多个实施例，根据第二部位的姿态信息确定控制指令，控制指令用于对导航标识所指向的视觉元素进行控制，包括：若第二部位的姿态信息不符合预设的第一姿态，则不对视觉元素进行控制。
根据本公开的一个或多个实施例，根据图像获取用户的第一部位的位置信息，包括：确定图像中的第一部位的关键点；根据第一部位的关键点在图像中的位置确定第一部位的位置信息。
根据本公开的一个或多个实施例提供的控制方法还包括：基于根据至少两帧目标图像获取的第一部位的位置信息，滚动被导航标识指向的视觉元素；其中，至少两帧目标图像的确定方法包括：当第二部位的姿态信息符合预设的第二姿态时，将第二部位的姿态信息对应的图像作为目标图像；从连续多个帧的目标图像中选取至少两帧目标图像。
根据本公开的一个或多个实施例，基于根据至少两帧目标图像获取的第一部位的位置信息，控制被导航标识指向的视觉元素，包括：根据至少两帧目标图像获取的第一部位的位置信息确定第一部位的运动信息；根据第一部位的运动信息滚动视觉元素。
根据本公开的一个或多个实施例，所述控制被所述导航标识指向的视觉元素，包括：滚动或移动被所述导航标识指向的视觉元素。
根据本公开的一个或多个实施例，第一部位的运动信息包括以下一种或多种：第一部位的运动时间、第一部位的运动速度、第一部位的运动位移、第一部位的运动加速度。
根据本公开的一个或多个实施例，根据第一部位的运动信息控制视觉元素，包括：确定第一部位的运动信息是否满足预设的运动条件；若是，根据第一部位的运动信息确定视觉元素的滚动方向和滚动距离。
根据本公开的一个或多个实施例，第二姿态为预设数量的手指张开。
根据本公开的一个或多个实施例，第二姿态为五指伸开。
根据本公开的一个或多个实施例，根据第一部位的位置信息确定导航标识的移动轨迹，包括：若第二部位的姿态信息符合预设的第三姿态， 则根据第一部位的位置信息确定导航标识的移动轨迹。
根据本公开的一个或多个实施例，根据第一部位的位置信息确定导航标识的移动轨迹，包括：根据从间隔的图像获取的第一部位的位置信息确定导航标识的移动轨迹。
根据本公开的一个或多个实施例，摄像装置为单独的RGB摄像头；控制方法还包括：对图像进行HSV颜色空间预处理，以将图像的颜色空间转化为HSV颜色空间。
根据本公开的一个或多个实施例，第一机器学习模型为卷积神经网络模型；控制方法还包括：对图像进行二值化预处理和白平衡预处理。
根据本公开的一个或多个实施例，根据第一部位的位置信息确定导航标识的移动轨迹，包括：基于第一部位的位置信息采用滤波算法和防抖算法，确定导航标识的最终移动轨迹。
根据本公开的一个或多个实施例，所述根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息，包括：获取所述图像中用户的第一部位的位置信息和第二部位的姿态信息。
根据本公开的一个或多个实施例，提供了一种控制方法装置，包括：数据接收单元，用于接收摄像装置捕获的图像；获取识别单元，用于根据图像获取用户的第一部位的位置信息和第二部位的姿态信息；移动轨迹单元，用于根据第一部位的位置信息确定导航标识的移动轨迹或位置信息，和/或，根据所述第一部位的位置信息和/或第二部位的预设姿态移动被控元素；以及控制指令单元，用于根据第二部位的姿态信息确定控制指令，控制指令用于对导航标识所指向的视觉元素进行控制。
根据本公开的一个或多个实施例，提供了一种终端，终端包括：至少一个存储器和至少一个处理器；其中，存储器用于存储程序代码，处理器用于调用存储器所存储的程序代码，以使所述终端执行根据本公开的一个或多个实施例提供的控制方法。
根据本公开的一个或多个实施例，提供了一种计算机存储介质，计算机存储介质存储有程序代码，程序代码被计算机设备执行时，使得所述计算机设备执行根据本公开的一个或多个实施例提供的控制方法。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技 术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (30)

  1. 一种控制方法，其特征在于，包括：
    接收图像；
    根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；
    根据所述第一部位的位置信息确定导航标识的移动轨迹；
    根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的视觉元素进行控制。
  2. 如权利要求1所述的控制方法，其特征在于，所述第一部位和所述第二部位属于同一用户不同的身体部位。
  3. 如权利要求2所述的控制方法，其特征在于，
    所述第二部位的位置能够跟随所述第一部位的位置的变化而变化；和/或，所述第一部位本身的位置和/或姿态不影响所述第二部位的姿态。
  4. 如权利要求3所述的控制方法，其特征在于，所述第一部位为手，所述第二部位为手腕。
  5. 如权利要求1所述的控制方法，其特征在于，所述根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息，包括：
    基于第一计算模块根据所述图像获取用户的第一部位的位置信息；
    基于第二计算模块根据所述图像获取用户的第二部位的姿态信息。
  6. 如权利要求5所述的控制方法，其特征在于，
    所述第一计算模块用于运行第一机器学习模型，所述第二计算模块用于运行第二机器学习模型。
  7. 如权利要求1所述的控制方法，其特征在于，所述根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的视觉元素进行控制，包括：
    若所述第二部位的姿态信息符合预设的第一姿态，则根据所述第二部位的姿态信息对所述视觉元素进行控制。
  8. 如权利要求7所述的控制方法，其特征在于，所述根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的视觉元素进行控制，包括：
    若所述第二部位的姿态信息不符合预设的第一姿态，则不对所述视觉元素进行控制。
  9. 如权利要求1所述的控制方法，其特征在于，根据所述图像获取用户的第一部位的位置信息，包括：
    确定所述图像中的第一部位的关键点；
    根据所述第一部位的关键点在所述图像中的位置确定所述第一部位的位置信息。
  10. 如权利要求1所述的控制方法，其特征在于，还包括：
    基于根据至少两帧目标图像获取的第一部位的位置信息，控制被所述导航标识指向的视觉元素；
    其中，所述至少两帧目标图像的确定方法包括：
    当所述第二部位的姿态信息符合预设的第二姿态时，将所述第二部位的姿态信息对应的图像作为目标图像；
    从连续多个帧的所述目标图像中选取至少两帧目标图像。
  11. 如权利要求10所述的控制方法，其特征在于，所述基于根据至少两帧目标图像获取的第一部位的位置信息，控制被所述导航标识指向的视觉元素，包括：
    根据所述至少两帧目标图像获取的第一部位的位置信息确定第一部位的运动信息；
    根据所述第一部位的运动信息控制所述视觉元素。
  12. 如权利要求11所述的控制方法，其特征在于，所述第一部位的运动信息包括以下一种或多种：第一部位的运动时间、第一部位的运动速度、第一部位的运动位移、第一部位的运动加速度。
  13. 如权利要求11所述的控制方法，其特征在于，所述根据所述第一部位的运动信息控制所述视觉元素，包括：
    确定所述第一部位的运动信息是否满足预设的运动条件；
    若是，根据所述第一部位的运动信息确定所述视觉元素的滚动方向和滚动距离。
  14. 如权利要求10所述的控制方法，其特征在于，所述控制被所述导航标识指向的视觉元素，包括：
    滚动或移动所述视觉元素。
  15. 如权利要求10所述的控制方法，其特征在于，所述第二姿态为预设数量的手指张开。
  16. 如权利要求1所述的控制方法，其特征在于，根据所述第一部位的位置信息确定导航标识的移动轨迹，包括：
    若所述第二部位的姿态信息符合预设的第三姿态，则根据所述第一部位的位置信息确定导航标识的移动轨迹。
  17. 如权利要求1所述的控制方法，其特征在于，所述根据所述第一部位的位置信息确定导航标识的移动轨迹，包括：
    根据从间隔的图像获取的第一部位的位置信息确定导航标识的移动轨迹。
  18. 如权利要求1所述的控制方法，其特征在于，所述接收图像包括：
    接收摄像装置捕获的图像。
  19. 如权利要求18所述的控制方法，其特征在于，
    所述摄像装置为单独的RGB摄像头；
    所述控制方法还包括：对所述图像进行HSV颜色空间预处理，以将所述图像的颜色空间转化为HSV颜色空间。
  20. 如权利要求6所述的控制方法，其特征在于，
    所述第一机器学习模型为卷积神经网络模型；
    所述控制方法还包括：对所述图像进行二值化预处理和白平衡预处理。
  21. 如权利要求1所述的控制方法，其特征在于，所述根据所述第一部位的位置信息确定导航标识的移动轨迹，包括：
    基于所述第一部位的位置信息采用滤波算法和防抖算法，确定所述导航标识的最终移动轨迹。
  22. 如权利要求1所述的控制方法，其特征在于，所述根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息，包括：
    获取所述图像中用户的第一部位的位置信息和第二部位的姿态信息。
  23. 如权利要求1所述的控制方法，其特征在于，
    所述根据所述第一部位的位置信息确定导航标识的移动轨迹，包括：根据所述第一部位相对于被控设备的位置信息，确定所述被控设备上的导航标识的移动轨迹；
    所述控制指令用于对所述导航标识所指向的视觉元素进行控制包括：所述控制指令用于对所述导航标识所指向的位于所述被控设备上的视觉元素进行控制。
  24. 一种控制方法，其特征在于，包括：
    接收图像；
    根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；
    根据所述第一部位的位置信息确定导航标识所指向的被控元素；
    根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的被控元素进行控制。
  25. 如权利要求24所述的控制方法，其特征在于，所述根据所述第一部位的位置信息确定导航标识所指向的被控元素，包括：
    根据所述第一部位相对于被控设备的位置信息，确定所述被控设备上的导航标识的位置和/或移动轨迹，基于所述位置和/或移动轨迹确定所述导航标识所指向的被控元素；
    和/或，根据至少两帧目标图像获取的第一部位的位置变化信息，控制所述导航标识所指向的被控元素。
  26. 根据权利要求25所述的控制方法，其特征在于，所述控制所述导航标识所指向的被控元素，包括：
    控制被控元素在被控设备上移动。
  27. 一种控制方法装置，其特征在于，包括：
    数据接收单元，用于接收图像；
    获取识别单元，用于根据所述图像获取用户的第一部位的位置信息和第二部位的姿态信息；
    移动轨迹单元，用于根据所述第一部位的位置信息确定导航标识的移动轨迹；
    控制指令单元，用于根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的视觉元素进行控制。
  28. 一种控制方法装置，其特征在于，包括：
    数据接收单元，用于接收图像；
    获取识别单元，用于根据所述图像获取用户的第一部位的位置信息 和第二部位的姿态信息；
    移动轨迹单元，用于根据所述第一部位的位置信息确定导航标识的位置信息，和/或，根据所述第一部位的位置信息和/或第二部位的预设姿态移动被控元素；
    控制指令单元，用于根据所述第二部位的姿态信息确定控制指令，所述控制指令用于对所述导航标识所指向的被控元素进行控制。
  29. 一种终端，其特征在于，所述终端包括：
    至少一个存储器和至少一个处理器；
    其中，所述存储器用于存储程序代码，所述处理器用于调用所述存储器所存储的程序代码，以使所述终端执行权利要求1至26中任一项所述的控制方法。
  30. 一种计算机存储介质，其特征在于，所述计算机存储介质存储有程序代码，所述程序代码被计算机设备执行时，使得所述计算机设备执行权利要求1至26中任一项所述的控制方法。
PCT/CN2021/098464 2020-06-05 2021-06-04 控制方法、装置、终端及存储介质 WO2021244650A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2022574219A JP2023527906A (ja) 2020-06-05 2021-06-04 制御方法、装置、端末および記憶媒体
EP21817903.4A EP4149116A4 (en) 2020-06-05 2021-06-04 CONTROL METHOD AND DEVICE, TERMINAL AND STORAGE MEDIUM
US18/073,567 US20230093983A1 (en) 2020-06-05 2022-12-02 Control method and device, terminal and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010507222.8 2020-06-05
CN202010507222.8A CN111601129B (zh) 2020-06-05 2020-06-05 控制方法、装置、终端及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/073,567 Continuation US20230093983A1 (en) 2020-06-05 2022-12-02 Control method and device, terminal and storage medium

Publications (1)

Publication Number Publication Date
WO2021244650A1 true WO2021244650A1 (zh) 2021-12-09

Family

ID=72192464

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/098464 WO2021244650A1 (zh) 2020-06-05 2021-06-04 控制方法、装置、终端及存储介质

Country Status (5)

Country Link
US (1) US20230093983A1 (zh)
EP (1) EP4149116A4 (zh)
JP (1) JP2023527906A (zh)
CN (1) CN111601129B (zh)
WO (1) WO2021244650A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111601129B (zh) * 2020-06-05 2022-04-01 北京字节跳动网络技术有限公司 控制方法、装置、终端及存储介质
CN112256367A (zh) * 2020-10-19 2021-01-22 北京字节跳动网络技术有限公司 图形用户界面的显示方法、装置、终端和存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102270037A (zh) * 2010-06-04 2011-12-07 宏碁股份有限公司 徒手人机界面操作系统及其方法
CN102981742A (zh) * 2012-11-28 2013-03-20 无锡市爱福瑞科技发展有限公司 基于计算机视觉的手势交互系统
KR20140139726A (ko) * 2013-05-28 2014-12-08 엘에스산전 주식회사 Ｈｍｉ의 동작 인식장치
CN105892636A (zh) * 2015-11-20 2016-08-24 乐视致新电子科技（天津）有限公司 一种应用于头戴设备的控制方法及头戴设备
CN109696958A (zh) * 2018-11-28 2019-04-30 南京华捷艾米软件科技有限公司 一种基于深度传感器手势识别的手势控制方法及系统
CN109710071A (zh) * 2018-12-26 2019-05-03 青岛小鸟看看科技有限公司 一种屏幕控制方法和装置
CN111601129A (zh) * 2020-06-05 2020-08-28 北京字节跳动网络技术有限公司 控制方法、装置、终端及存储介质

Family Cites Families (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8793620B2 (en) * 2011-04-21 2014-07-29 Sony Computer Entertainment Inc. Gaze-assisted computer interface
US9696808B2 (en) * 2006-07-13 2017-07-04 Northrop Grumman Systems Corporation Hand-gesture recognition method
US20110304541A1 (en) * 2010-06-11 2011-12-15 Navneet Dalal Method and system for detecting gestures
CN102324041B (zh) * 2011-09-09 2014-12-03 深圳泰山在线科技有限公司 像素归类方法、关节体姿态识别方法及鼠标指令生成方法
CN103135745B (zh) * 2011-11-25 2018-01-02 夏普株式会社 基于深度图像的非接触控制方法、信息设备和系统
US20130249793A1 (en) * 2012-03-22 2013-09-26 Ingeonix Corporation Touch free user input recognition
CN103425238A (zh) * 2012-05-21 2013-12-04 刘鸿达 以手势为输入的控制系统云端系统
WO2014015521A1 (en) * 2012-07-27 2014-01-30 Nokia Corporation Multimodal interaction with near-to-eye display
CN102854983B (zh) * 2012-09-10 2015-12-02 中国电子科技集团公司第二十八研究所 一种基于手势识别的人机交互方法
US9696867B2 (en) * 2013-01-15 2017-07-04 Leap Motion, Inc. Dynamic user interactions for display control and identifying dominant gestures
CN103970260B (zh) * 2013-01-31 2017-06-06 华为技术有限公司 一种非接触式手势控制方法及电子终端设备
EP3090331B1 (en) * 2014-01-03 2020-03-04 Intel Corporation Systems with techniques for user interface control
CN107209582A (zh) * 2014-12-16 2017-09-26 肖泉 高直观性人机界面的方法和装置
CN104750397B (zh) * 2015-04-09 2018-06-15 重庆邮电大学 一种基于体感的虚拟矿井自然交互方法
WO2016189390A2 (en) * 2015-05-28 2016-12-01 Eyesight Mobile Technologies Ltd. Gesture control system and method for smart home
CN105867717A (zh) * 2015-11-20 2016-08-17 乐视致新电子科技（天津）有限公司 用户界面的操控方法、装置及终端
EP3267289B1 (en) * 2016-07-05 2019-02-27 Ricoh Company, Ltd. Information processing apparatus, position information generation method, and information processing system
CN106569596A (zh) * 2016-10-20 2017-04-19 努比亚技术有限公司 一种手势控制方法和设备
EP3316075B1 (en) * 2016-10-26 2021-04-07 Harman Becker Automotive Systems GmbH Combined eye and gesture tracking
CN206922960U (zh) * 2017-05-31 2018-01-23 广东长虹电子有限公司 一种使用手势遥控的智能电视机
EP3652701A4 (en) * 2017-07-13 2021-11-03 Shiseido Company, Limited VIRTUAL FACE MAKEUP REMOVAL, FAST FACE RECOGNITION AND LANDMARK TRACKING
CN107958218A (zh) * 2017-11-22 2018-04-24 南京邮电大学 一种实时手势识别的方法
US11221669B2 (en) * 2017-12-20 2022-01-11 Microsoft Technology Licensing, Llc Non-verbal engagement of a virtual assistant
US10296102B1 (en) * 2018-01-31 2019-05-21 Piccolo Labs Inc. Gesture and motion recognition using skeleton tracking
CN110045825B (zh) * 2018-03-27 2022-05-13 杭州凌感科技有限公司 用于车辆交互控制的手势识别系统
CN109614922B (zh) * 2018-12-07 2023-05-02 南京富士通南大软件技术有限公司 一种动静态手势识别方法和系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102270037A (zh) * 2010-06-04 2011-12-07 宏碁股份有限公司 徒手人机界面操作系统及其方法
CN102981742A (zh) * 2012-11-28 2013-03-20 无锡市爱福瑞科技发展有限公司 基于计算机视觉的手势交互系统
KR20140139726A (ko) * 2013-05-28 2014-12-08 엘에스산전 주식회사 Ｈｍｉ의 동작 인식장치
CN105892636A (zh) * 2015-11-20 2016-08-24 乐视致新电子科技（天津）有限公司 一种应用于头戴设备的控制方法及头戴设备
CN109696958A (zh) * 2018-11-28 2019-04-30 南京华捷艾米软件科技有限公司 一种基于深度传感器手势识别的手势控制方法及系统
CN109710071A (zh) * 2018-12-26 2019-05-03 青岛小鸟看看科技有限公司 一种屏幕控制方法和装置
CN111601129A (zh) * 2020-06-05 2020-08-28 北京字节跳动网络技术有限公司 控制方法、装置、终端及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4149116A4 *

Also Published As

Publication number Publication date
EP4149116A4 (en) 2023-11-08
JP2023527906A (ja) 2023-06-30
US20230093983A1 (en) 2023-03-30
EP4149116A1 (en) 2023-03-15
CN111601129A (zh) 2020-08-28
CN111601129B (zh) 2022-04-01

Similar Documents

Publication Publication Date Title
US11175726B2 (en) Gesture actions for interface elements
WO2021139408A1 (zh) 显示特效的方法、装置、存储介质及电子设备
CN110476189B (zh) 用于在电子装置中提供增强现实功能的方法和设备
US10635180B2 (en) Remote control of a desktop application via a mobile device
US20230093983A1 (en) Control method and device, terminal and storage medium
US10528145B1 (en) Systems and methods involving gesture based user interaction, user interface and/or other features
JP7181375B2 (ja) 目標対象の動作認識方法、装置及び電子機器
CN104081307A (zh) 图像处理装置、图像处理方法和程序
WO2021004412A1 (zh) 手持输入设备及其指示图标的显示位置控制方法和装置
WO2020156058A1 (zh) 基于终端的图像拖拽变形实现方法和装置
WO2021244651A1 (zh) 信息显示方法、装置、终端及存储介质
US9665232B2 (en) Information-processing device, storage medium, information-processing method, and information-processing system for enlarging or reducing an image displayed on a display device
CN115033097A (zh) 一种智能眼镜的控制方法、装置和智能眼镜
WO2021004413A1 (zh) 一种手持输入设备及其指示图标的消隐控制方法和装置
CN108874141B (zh) 一种体感浏览方法和装置
KR20130085094A (ko) 유저 인터페이스 장치 및 유저 인터페이스 제공 방법
CN113703704A (zh) 界面显示方法、头戴式显示设备和计算机可读介质
WO2021073204A1 (zh) 对象的显示方法、装置、电子设备及计算机可读存储介质
US20230376122A1 (en) Interface displaying method, apparatus, device and medium
WO2023116495A1 (zh) 一种视频切换方法、装置、电子设备及存储介质
CN111860209B (zh) 手部识别方法、装置、电子设备及存储介质
CN113253906B (zh) 一种输入数据处理方法、装置及设备
WO2023025181A1 (zh) 图像识别方法、装置和电子设备
US20240103625A1 (en) Interaction method and apparatus, electronic device, storage medium, and computer program product
CN118034483A (zh) 手势姿态识别方法、装置、设备、存储介质和程序产品

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: 21817903

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022574219

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2021817903

Country of ref document: EP

Effective date: 20221209

NENP Non-entry into the national phase

Ref country code: DE