CN115220570A - Display device, gesture detection method and storage medium - Google Patents
Display device, gesture detection method and storage medium Download PDFInfo
- Publication number
- CN115220570A CN115220570A CN202210625572.3A CN202210625572A CN115220570A CN 115220570 A CN115220570 A CN 115220570A CN 202210625572 A CN202210625572 A CN 202210625572A CN 115220570 A CN115220570 A CN 115220570A
- Authority
- CN
- China
- Prior art keywords
- image
- hand
- preset
- hand image
- resolution
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- 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
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/117—Biometrics derived from hands
Abstract
The disclosure relates to a display device and a gesture detection method, and relates to the technical field of electronic devices. Wherein, this display device includes: an image acquisition device configured to: collecting an original image; a controller configured to: identifying hand features from the original image, and intercepting a hand image corresponding to the hand features from the original image; under the condition that the size of the hand image is smaller than the preset size, acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image; performing gesture detection on the target hand image to obtain a gesture detection result; and under the condition that the gesture detection result is matched with the preset gesture, triggering and executing the operation corresponding to the preset gesture. The embodiment of the disclosure improves the precision of gesture detection.
Description
Technical Field
The present disclosure relates to the field of electronic devices, and in particular, to a display device, a gesture detection method, and a storage medium.
Background
With the development of science and technology, human-computer interaction is more and more widely applied, and many electronic devices can recognize the user intention through the language or the body movement of the user so as to meet the diversified requirements of the user. At present, the smart television performs gesture detection on a user image directly shot, so that the intention of the user is recognized through gestures, however, the gesture detection algorithm has a high requirement on the processed input image, and factors such as distance and angle can cause that the hand image obtained through shooting is small, so that the requirement on the input image serving as the gesture detection algorithm is difficult to meet, and the gesture detection precision is low.
Disclosure of Invention
In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a display device, a gesture detection method, and a storage medium, which can improve the accuracy of gesture detection.
In order to achieve the above object, the embodiments of the present disclosure provide the following technical solutions:
in a first aspect, there is provided a display device comprising:
an image acquisition device configured to: collecting an original image;
a controller configured to: identifying hand features from the original image, and intercepting a hand image corresponding to the hand features from the original image;
under the condition that the size of the hand image is smaller than the preset size, acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image;
performing gesture detection on the target hand image to obtain a gesture detection result;
under the condition that the gesture detection result is matched with the preset gesture, triggering to execute the operation corresponding to the preset gesture;
wherein the image processing parameters include at least one of: and presetting resolution, length value and width value.
In some embodiments of the disclosure, the image processing parameters include: a preset resolution, the controller further configured to: after a hand image corresponding to the hand features is intercepted from the original image, the resolution ratio of the hand image is calculated;
a controller specifically configured to: acquiring a preset resolution; and under the condition that the size of the hand image is smaller than the preset size and the resolution of the hand image is smaller than the preset resolution, performing resolution adjustment on the hand image according to the preset resolution to obtain a target hand image with the resolution larger than or equal to the preset resolution.
In some embodiments of the disclosure, the image processing parameters include: a preset resolution, the controller further configured to: after a hand image corresponding to the hand features is intercepted from the original image, calculating the size ratio of the hand image relative to the original image;
a controller specifically configured to: acquiring a preset resolution; and under the condition that the size of the hand image is smaller than the preset size and the size ratio is smaller than the preset ratio, carrying out resolution adjustment on the hand image according to the preset resolution to obtain a target hand image with the resolution being larger than or equal to the preset resolution.
In some embodiments of the disclosure, the image processing parameters include: a length value and/or a width value, the controller configured to: determining a length value and/or a width value of the hand image; under the condition that the size of the hand image is smaller than the preset size and the length value of the hand image is not equal to the preset length value, adjusting the length value of the hand image according to the preset length value to obtain a target hand image; and/or under the condition that the size of the hand image is smaller than the preset size and the width value of the hand image is not equal to the preset width value, adjusting the width value of the hand image according to the preset width value to obtain a target hand image; the length value of the target hand image is equal to a preset length value, and/or the width value of the target hand image is equal to a width value.
In some embodiments of the present disclosure, the number of hand images is multiple, and the controller is specifically configured to: intercepting a plurality of hand images corresponding to the hand features from the original image; determining a target hand image from the plurality of hand images; the target hand image includes at least one of: the hand image with the image area larger than or equal to the preset area; the hand image with the image size accounting for the size of the original image being greater than or equal to the preset accounting; and hand images with the image positions in the preset area.
In some embodiments of the present disclosure, the controller is specifically configured to: after a hand image corresponding to the hand features is intercepted from an original image, image enhancement processing is carried out on the hand image to obtain a target hand image; the image enhancement processing includes at least one of: gray level histogram processing, filtering processing and edge sharpening processing.
In some embodiments of the disclosure, the controller is specifically configured to: carrying out feature recognition on the original image to obtain a mask image, wherein the mask image comprises a hand feature region; and intercepting a hand image from the original image according to the hand characteristic region in the mask image.
In a second aspect, a dance and training matching method is provided, which includes:
collecting an original image;
identifying hand features from the original image, and intercepting a hand image corresponding to the hand features from the original image;
under the condition that the size of the hand image is smaller than the preset size, acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image;
performing gesture detection on the target hand image to obtain a gesture detection result;
under the condition that the gesture detection result is matched with the preset gesture, triggering to execute the operation corresponding to the preset gesture;
wherein the image processing parameters include at least one of: and presetting resolution, length value and width value.
In some embodiments of the present disclosure, the image processing parameters include: the method comprises the following steps of presetting resolution, identifying hand features from an original image, and before acquiring image processing parameters after capturing a hand image corresponding to the hand features from the original image, further comprising the following steps: after a hand image corresponding to the hand features is intercepted from an original image, calculating a first resolution of the hand image;
acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image, comprising: acquiring a preset resolution; and under the condition that the size of the hand image is smaller than the preset size and the first resolution is smaller than the preset resolution, carrying out resolution adjustment on the hand image according to the preset resolution so as to obtain a target hand image which is larger than or equal to the preset resolution.
In some embodiments of the disclosure, the image processing parameters include: the method further comprises the following steps of presetting resolution, identifying hand features from the original image, and before acquiring image processing parameters after capturing the hand image corresponding to the hand features from the original image, wherein the resolution is preset, the method further comprises the following steps: after a hand image corresponding to the hand features is intercepted from the original image, calculating the size ratio of the hand image relative to the original image;
acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image, comprising: acquiring a preset resolution; and under the condition that the size of the hand image is smaller than the preset size and the size ratio is smaller than the preset ratio, carrying out resolution adjustment on the hand image according to the preset resolution to obtain a target hand image with the resolution being larger than or equal to the preset resolution.
In some embodiments of the disclosure, the image processing parameters include: the length value and/or the width value, acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image comprises the following steps: determining a length value and/or a width value of the hand image; under the condition that the size of the hand image is smaller than the preset size and the length value of the hand image is not equal to the preset length value, adjusting the length value of the hand image according to the preset length value to obtain a target hand image; and/or under the condition that the size of the hand image is smaller than the preset size and the width value of the hand image is not equal to the preset width value, adjusting the width value of the hand image according to the preset width value to obtain a target hand image; the length value of the target hand image is equal to a preset length value, and/or the width value of the target hand image is equal to a width value.
In some embodiments of the present disclosure, the number of the hand images is multiple, identifying the hand features from the original image, and capturing the hand image corresponding to the hand features from the original image includes: intercepting a plurality of hand images corresponding to the hand features from the original image; acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image, wherein the method comprises the following steps: determining a target hand image from the plurality of hand images; the target hand image includes at least one of: the hand image with the image area larger than or equal to the preset area; the hand image with the image size accounting for the size of the original image being greater than or equal to the preset accounting; and hand images with the image positions in the preset area.
In some embodiments of the present disclosure, acquiring an image processing parameter, and adjusting a hand image according to the image processing parameter to obtain a target hand image includes: carrying out image enhancement processing on the hand image to obtain a target hand image; the image enhancement processing includes at least one of: gray level histogram processing, filtering processing and edge sharpening processing.
In some embodiments of the present disclosure, recognizing a hand feature from an original image, and capturing a hand image corresponding to the hand feature from the original image, includes: carrying out feature recognition on the original image to obtain a mask image, wherein the mask image comprises a hand feature region; and intercepting a hand image from the original image according to the hand characteristic region in the mask image.
In a third aspect, a computer-readable storage medium is provided, comprising: the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements a gesture detection method as described in the second aspect or any one of its alternative embodiments.
In a fourth aspect, a computer program product is provided, comprising: the computer program product, when run on a computer, causes the computer to implement a gesture detection method as in the second aspect or any one of its alternative embodiments.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
the embodiment of the disclosure provides a display device, a gesture detection method and a storage medium. Wherein the display device comprises an image acquisition device and a controller, the image acquisition device is configured to acquire an original image; the controller is configured to firstly identify hand features from an original image, then intercept a hand image corresponding to the hand features from the original image, then acquire image processing parameters under the condition that the size of the hand image is smaller than a preset size, adjust the hand image according to the image processing parameters to obtain a target hand image, further perform gesture detection by using the target hand image to acquire a gesture detection result, and finally trigger execution of an operation corresponding to a preset gesture under the condition that the gesture detection result is matched with the preset gesture. After the original image is obtained, the hand image in the original image is intercepted, and the hand image is adjusted to obtain the target hand image, so that the image details are reserved on the basis of meeting the gesture detection, and the gesture detection precision is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the embodiments or technical solutions in the prior art description will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
Fig. 1A is a schematic view of an operation scenario between a display device and a control apparatus in an embodiment of the present disclosure;
fig. 1B is a schematic view of an operation scene of a display device in an embodiment of the present disclosure;
FIG. 1C is a schematic illustration of an original image and a hand image in an embodiment of the present disclosure;
fig. 2 is a block diagram of a hardware configuration of a display device according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a software configuration in a display device according to an embodiment of the disclosure;
fig. 4 is a schematic flowchart of a gesture detection method according to an embodiment of the disclosure;
FIG. 5 is a schematic diagram of a convolutional neural network in an embodiment of the present disclosure;
FIG. 6A is a first schematic diagram illustrating obtaining a hand image according to an embodiment of the present disclosure;
FIG. 6B is a second schematic diagram illustrating obtaining a hand image according to an embodiment of the present disclosure;
fig. 6C is a third schematic diagram of obtaining a hand image in an embodiment of the present disclosure;
FIG. 6D is a fourth schematic diagram illustrating obtaining a hand image according to an embodiment of the disclosure;
FIG. 7 is a fifth schematic view of obtaining a hand image in an embodiment of the disclosure;
FIG. 8 is a fifth schematic view of obtaining a hand image in an embodiment of the present disclosure;
FIG. 9 is a schematic diagram of position coordinates of a hand image;
FIG. 10 is a schematic diagram of gesture detection provided in embodiments of the present disclosure;
fig. 11 is a schematic diagram of a preset gesture provided in the embodiments of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.
The terms "first," "second," "third," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art. Further, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated object, indicating that there may be three relationships, for example, a and/or B, which may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
At present, the smart television performs gesture detection on a user image directly shot, so that the intention of a user is recognized through gestures, however, the gesture detection algorithm has a high requirement on the processed input image, and factors such as distance and angle can cause the shot hand image to be small, so that the requirement of the input image serving as the gesture detection algorithm is difficult to meet, and the user is required to repeatedly stroke gestures for many times until the requirement is met, so that the experience of the user is influenced. In addition, in the prior art, usually, the user image is directly scaled to be used as an input image of a gesture detection algorithm, but the gesture in the scaled image is smaller and more blurred, which brings a certain difficulty to gesture detection, thereby causing low gesture detection precision.
In order to solve the above problem, embodiments of the present disclosure provide a display device, a gesture detection method, and a storage medium. Wherein the display device comprises an image acquisition apparatus and a controller, the image acquisition apparatus being configured to acquire an original image; the controller is configured to firstly identify hand features from an original image, then intercept a hand image corresponding to the hand features from the original image, then acquire image processing parameters, adjust the hand image according to the image processing parameters to obtain a target hand image, and further perform gesture detection by using the target hand image to acquire a gesture detection result. After the original image is obtained, the hand image in the original image is intercepted, and the hand image is adjusted to obtain the target hand image, so that the image details are reserved on the basis of meeting the gesture detection, and the gesture detection precision is improved.
As shown in fig. 1A, fig. 1A is a schematic view of an operation scene between a display device and a control apparatus in an embodiment of the present disclosure.
In some embodiments, the user may operate the display apparatus 200 through the smart device 300 or the control device 100, and the display apparatus 200 performs data communication with the server 400. As shown in fig. 1A, an application scenario of the display device provided by the present disclosure is described by taking an example of operating the display device 200 by the control apparatus 100. In one application scenario, the control apparatus 100 controls the display device 200 to be powered on, and thereafter, the user desires to control the display device 200 to play the media data through a gesture.
As shown in fig. 1B, fig. 1B is a schematic view of an operation scene of a display device in the embodiment of the present disclosure. Fig. 1B includes a display device 200, and the display device 200 includes an image capture apparatus 201. In a scene that a user desires to play media data through a gesture control display device 200, a gesture indication playing with open five fingers is preset, after the user selects the media data to be played, the user desires to play the media data through the display device 200 with open five fingers, but since the user is far away from the display device 200, an original image of the user acquired by an image acquisition device 201 is shown in fig. 1C, fig. 1C is a schematic diagram of the original image and a hand image in the embodiment of the disclosure, if the gesture in the original image 202 in fig. 1C is small, a hand feature is identified from the original image, a hand image 203 is captured from the original image according to the hand feature, then, in a case that the size of the hand image 203 is smaller than a preset size, an image processing parameter is acquired, the hand image is adjusted according to the image processing parameter to obtain a target hand image, the target hand image meets a gesture detection requirement of gesture detection, the gesture detection performed by using the target hand image can obtain an accurate gesture detection result meeting the user desire, in a case that the gesture detection result matches the preset gesture, the gesture detection result matches the gesture corresponding to the gesture corresponding operation data, the media data displayed by the gesture corresponding to the gesture, and the media data displayed by the gesture detection device 200. The display device 200 captures and adjusts the hand image of the acquired original image to obtain the target hand image meeting the gesture detection requirement, so that an accurate gesture detection result is obtained, the user intention is better understood, and the experience of the user is improved.
In some embodiments, the control apparatus 100 may be a remote controller, and the communication between the remote controller and the terminal device includes infrared protocol communication or bluetooth protocol communication, and other short-distance communication methods, and controls the display device 200 in a wireless or wired manner. The user may input a user instruction through a key on a remote controller, voice input, control panel input, etc., to control the display apparatus 200.
In some embodiments, the smart device 300 (e.g., mobile terminal, tablet, computer, laptop, etc.) may also be used to control the display device 200. For example, the display device 200 is controlled using an application program running on the smart device.
In some embodiments, the display device 200 may also receive the user's control through touch or gesture, etc., instead of using the smart device or control device described above to receive instructions.
In some embodiments, the display device 200 may also be controlled in a manner other than the control apparatus 100 and the smart device 300, for example, the voice command control of the user may be directly received by a module configured inside the display device 200 to obtain a voice command, or may be received by a voice control device provided outside the display device 200.
In some embodiments, the display device 200 may be allowed to be communicatively connected through a Local Area Network (LAN), a Wireless Local Area Network (WLAN), and other networks. The server 400 may provide various contents and interactions to the display apparatus 200. The server 400 may be a cluster or a plurality of clusters, and may include one or more types of servers. Or a cloud server. The above is merely an example, and this is not limited in this embodiment.
Fig. 2 is a block diagram of a hardware configuration of a display device according to an embodiment of the present disclosure. As shown in fig. 2, the display apparatus includes at least one of a tuner demodulator 210, a communicator 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface 280. The controller includes a central processing unit, a video processor, an audio processor, a graphic processor, a Random Access Memory (RAM), a Read-Only Memory (ROM), and first to nth interfaces for input/output. The display 260 may be at least one of a liquid crystal display, an OLED display, a touch display, and a projection display, and may also be a projection device and a projection screen. The tuner demodulator 210 receives a broadcast television signal through a wired or wireless reception manner, and demodulates an audio/video signal, such as an Electronic Program Guide (EPG) data signal, from a plurality of wireless or wired broadcast television signals. The detector 230 is used to collect signals of an external environment or interaction with the outside. The controller 250 and the tuner-demodulator 210 may be located in different separate devices, that is, the tuner-demodulator 210 may also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.
In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in memory. The controller 250 controls the overall operation of the display apparatus 200. The User may enter User commands in a Graphical User Interface (GUI) displayed on display 260, and the User input Interface receives the User input commands through the GUI. Alternatively, the user may input the user command by inputting a specific sound or gesture, and the user input interface receives the user input command by recognizing the sound or gesture through the sensor.
In some embodiments, a "user interface" is a media interface for interaction and information exchange between an application or operating system and a user that enables conversion between an internal form of information and a form that is acceptable to the user. A common presentation form of a user interface is a graphical user interface, which refers to a user interface displayed in a graphical manner and related to computer operations. The interface element may be an icon, a window, a control, or the like, displayed in a display screen of the electronic device, where the control may include at least one of a visual interface element such as an icon, a button, a menu, a tab, a text box, a dialog box, a status bar, a navigation bar, and a Widget (Web Widget).
In some embodiments, the controller includes at least one of a Central Processing Unit (CPU), a video processor, an audio processor, a Graphic Processing Unit (GPU), a RAM Random Access Memory (RAM), a ROM (Read-Only Memory), a first interface to an nth interface for input/output of a Digital Signal Processor (DSP), a communication Bus (Bus), and the like.
A CPU processor. For executing operating system and application program instructions stored in the memory, and executing various application programs, data and contents according to various interactive instructions receiving external input, so as to finally display and play various audio-video contents. The CPU processor may include a plurality of processors. E.g. comprising a main processor and one or more sub-processors.
An embodiment of the present disclosure provides a display device, including:
an image acquisition device configured to: collecting an original image;
a controller 250 configured to: identifying hand features from the original image, and intercepting a hand image corresponding to the hand features from the original image; under the condition that the size of the hand image is smaller than the preset size, acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image; performing gesture detection on the target hand image to obtain a gesture detection result; under the condition that the gesture detection result is matched with the preset gesture, triggering to execute the operation corresponding to the preset gesture; wherein the image processing parameters include at least one of: and presetting resolution, length value and width value.
It should be noted that the image capturing device may be an image capturing device included in the detector 230 in fig. 2, and the disclosure does not limit this.
According to the display equipment, the hand images are intercepted and adjusted through the collected original images, the target hand images meeting the gesture detection requirements are obtained, so that accurate gesture detection results are obtained, user expectations are better understood, and the experience of users is improved.
Fig. 3 is a schematic diagram of software configuration in a display device according to an embodiment of the disclosure, and as shown in fig. 3, a system is divided into four layers, which are, from top to bottom, an Application (Application) layer (abbreviated as "Application layer"), an Application Framework (Application Framework) layer (abbreviated as "Framework layer"), an Android runtime (Android runtime) layer, a system library layer (abbreviated as "system runtime library layer"), and a kernel layer. The inner core layer comprises at least one of the following drivers: the mobile terminal includes an audio driver, a display driver, a bluetooth driver, a camera driver, a mobile hotspot (WIFI) driver, a Universal Serial Bus (USB) driver, a High Definition Multimedia Interface (HDMI) driver, a sensor driver (such as a fingerprint sensor, a temperature sensor, a pressure sensor, and the like), and a power supply driver.
It should be noted that the protection scope of the gesture detection method described in the embodiment of the present disclosure is not limited to the execution sequence of the steps listed in the embodiment, and all solutions implemented by adding, subtracting, and replacing steps in the prior art according to the principle of the present disclosure are included in the protection scope of the present disclosure.
As shown in fig. 4, fig. 4 is a flowchart illustrating a gesture detection method according to an embodiment of the present disclosure, which may be executed by a gesture detection apparatus, where the apparatus may be implemented by software and/or hardware, and may be generally integrated in the foregoing display device. As shown in fig. 4, the method mainly includes the following steps:
s401, collecting an original image.
In some embodiments, the aforementioned image acquisition device may be an android camera, and then the android camera is started according to a standard android camera control flow to acquire an original image.
In some embodiments, to facilitate data processing, the aspect ratio, e.g., 16.
S402, identifying hand features from the original image, and intercepting the hand image corresponding to the hand features from the original image.
In some embodiments, the hand features are identified from the original image by a Convolutional Neural Network (CNN). As shown in fig. 5, fig. 5 is a schematic structural diagram of a convolutional neural network in an embodiment of the present disclosure, and the schematic structural diagram includes an initiation module, a convolution module, a downsampled (subsampled) module, and a target detection head. The starting module is used for converting image data into a two-dimensional matrix which can be processed by a computer, the convolution module is used for feature extraction, and the down-sampling module is used for reducing feature dimensionality and retaining effective information to avoid overfitting. The target detection head is used for detecting position information corresponding to the hand features. As shown in fig. 5, the original image is input into the convolutional neural network, processed by the start module, the convolutional module, the down-sampling module, and the target detection head, and output to obtain the hand features.
In some embodiments, after the hand features are identified from the original image, the position coordinates corresponding to the hand features are determined, and the interception position is determined according to the minimum abscissa, the maximum abscissa, the minimum ordinate and the maximum ordinate in the position coordinates.
In general, the positions of the hand features in the original image may be different due to different positions of the users during shooting, and the hand features may be located at the left boundary, the right boundary, the upper boundary or the lower boundary of the original image. Corresponding embodiments are provided in the disclosed embodiments for these four cases to determine the intercepting position, and the minimum recumbent mark is marked with X for the convenience of description min Marking the maximum recumbent position as X max Minimum longitudinal position marked as Y min And maximum longitudinal coordinate marked as Y max 。
1) The hand features are at the left border of the original image
As shown in fig. 6A, fig. 6A is a first schematic diagram of obtaining a hand image according to an embodiment of the present disclosure. First, the width of the hand feature is determined. According to the minimum abscissa X min And maximum abscissa X max Width W of the obtained hand features is X max -X min And then judging whether the gesture features are positioned at the left boundary of the original image according to the formula (1).
In the formula (1), T is a preset threshold value, and is generally 40%; w is the width of the input image of the gesture detection algorithm.
If the minimum abscissa X of the gesture image is min And maximum abscissa X max Satisfying equation (1) indicates that the hand feature is at the left boundary of the original image.
Further, the intercepted initial position abscissa X 0 Set to 0, the ordinate of the starting position being the minimum ordinate Y min Thus intercepting the slave (0,Y) min ) Starting with (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
If the minimum abscissa X of the gesture image is min And maximum abscissa X max If the formula (1) is not satisfied, determining the X-axis of the intercepted initial position 0 The setting is as follows:
ordinate Y of the starting position 0 Is set to Y min Thereby intercepting the slave (X) 0 ，Y min ) Starting with (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
2) The hand feature is at the right border of the original image
As shown in fig. 6B, fig. 6B is a schematic diagram two of obtaining a hand image in the embodiment of the present disclosure. First, the width of the hand feature is determined. According to the minimum abscissa X min And maximum abscissa X max Width W of hand feature is X max -X min And then judging whether the gesture features are positioned at the right boundary of the original image according to formula (3).
In the formula (3), W 0 Is the original image width.
If the minimum abscissa X of the gesture image min And maximum abscissa X max If equation (3) is satisfied, it indicates that the hand feature is at the right boundary of the original image.
Further, the intercepted initial position abscissa X 0 Is arranged as
X 0 ＝W 0 -T*w·············(4)
The ordinate of the starting position being the minimum ordinate Y min . Thereby intercepting the slave (X) 0 ，Y min ) Starting with (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
If the minimum abscissa X of the gesture image min And maximum abscissa X max If the formula (3) is not satisfied, determining the abscissa X of the intercepted initial position 0 The method comprises the following steps:
ordinate Y of the starting position 0 Is set as Y min Thereby intercepting the slave (X) 0 ，Y min ) Starting with (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
3) The hand features are at the upper boundary of the original image
As shown in fig. 6C, fig. 6C is a third schematic diagram of obtaining a hand image in the embodiment of the present disclosure. First, the height of the hand feature is determined. According to the smallest ordinate Y min And the maximum abscissa Y max Height H to obtain hand feature is Y max -Y min And then judging whether the gesture feature is positioned at the upper boundary of the original image according to the formula (5).
In the formula (5), T is a preset threshold value, and is generally 40%; h is the height of the input image of the gesture detection algorithm.
If the minimum ordinate Y of the gesture image min And the maximum ordinate Y max If equation (5) is satisfied, it indicates that the hand feature is at the upper boundary of the original image.
Further, the abscissa of the truncated start position is X min Ordinate Y of the starting position 0 Is set to 0. Thereby intercepting the slave (X) min 0) start to (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
If the minimum ordinate Y of the gesture image min And the maximum ordinate Y max If the formula (5) is not satisfied, the abscissa of the truncated start position is X min Ordinate Y of the starting position 0 The method comprises the following steps:
thereby intercepting the slave (X) min ，Y 0 ) Starting with (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
4) The hand feature is at the lower boundary of the original image
As shown in fig. 6D, fig. 6D is a fourth schematic diagram of obtaining a hand image in the embodiment of the present disclosure. First, the height of the hand feature is determined. According to the minimum ordinate Y min And maximum abscissa Y max Height H to obtain hand feature is Y max -Y min And then judging whether the gesture feature is in the lower boundary of the original image according to the formula (7).
In the formula (7), H 0 Is the original image width.
If the minimum ordinate Y of the gesture image min And the maximum ordinate Y max If equation (7) is satisfied, it indicates that the hand feature is at the lower boundary of the original image.
Further, the abscissa of the intercepted start position is X min Ordinate Y of the starting position 0 Is arranged as
Y 0 ＝H 0 -T*h·······(8)
Thereby intercepting the slave (X) min ，Y 0 ) Starting with (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
If the minimum ordinate Y of the gesture image min And the maximum ordinate Y max If the formula (7) is not satisfied, the abscissa of the truncated start position is X min Ordinate Y of the starting position 0 The setting is as follows:
thereby intercepting the slave (X) min ，Y 0 ) Starting with (X) max ，Y max ) The hand image is obtained by completely retaining the image details in the rectangular area.
According to the embodiment, aiming at different positions of the gesture features in the original image, the initial position coordinates of the captured hand image can be accurately obtained, the situation that the hand features are located at the boundary position of the original image and the captured hand image lacks part of hand features is avoided, and therefore the integrity of the hand image is kept.
In some embodiments, the original image includes a plurality of hand features, a plurality of hand images corresponding to the plurality of hand features are obtained by capturing the original image, and then the target hand image is determined from the plurality of hand images. The target hand image can be a hand image with an area larger than a preset area, the target hand image can also be a hand image with an image size larger than a preset ratio relative to the size of the original image, and the target hand image can also be a hand image in a preset area. The number of hand images is not particularly limited, and the number of target hand images is not particularly limited, and may be one or more.
Exemplarily, as shown in fig. 7, fig. 7 is a schematic diagram five of obtaining a hand image in the embodiment of the present disclosure. When the number of the hand images is two, determining the hand image 701 with the largest area as a target hand image from the hand images 701 and 702; alternatively, the hand image 701 in the center area of the original image is determined to be the target hand image.
In some embodiments, a plurality of hand images corresponding to a plurality of hand features are captured from an original image, center point position coordinates of the hand images, length values and width values of the hand images are determined, and a confidence value of each hand image is determined according to the center point position coordinates of the hand images, the length values and the width values of the hand images. For the certainty factor, which should be described as whether a plurality of features in the original image are enough to match with the conventionally recognized "hand", the deep learning object detection algorithm will learn the information of the hand in the training data, and will predict which places in the original image exist in places similar to the conventionally recognized "hand", thereby correspondingly outputting the certainty factor of the hand, i.e. the higher this value the closer the algorithm considers the original image to be the "hand" of the conventional recognition. Wherein the length and width values of the hand images, and the position coordinates of the historical hand images affect the confidence value.
Calculating a confidence value according to the length value and the width value of the hand image and the formula (9):
in the formula (9), conf' is the original confidence value output by the target detection algorithm, w and h are the length and width of the hand box, and the normalized value interval between w and h is [0,1].
Calculating a confidence value from the position coordinates of the historical hand image and equation (10):
in the formula (10), (x, y) represents the position coordinates of the historical hand image, t represents the current time, t-1 represents the historical time, β is a constant, and the numeric area is [0,1].
In some embodiments, because the background of the original image is complex, the original image can be subjected to feature recognition to obtain a mask image, the mask image comprises a hand feature region, the feature recognition can be a semantic segmentation algorithm, and then the hand image corresponding to the mask image is captured from the original image according to the hand feature region in the mask image, so that background information is removed, the hand image corresponding to the hand feature is obtained, the interference of the background information on gesture detection is avoided, and the gesture detection accuracy is improved.
Exemplarily, as shown in fig. 8, fig. 8 is a sixth schematic diagram of obtaining a hand image in the embodiment of the present disclosure. In fig. 8, the background of the original image 801 is complex, and the hand image 802 obtained by directly capturing the original image 801 has a complex background, which affects the accuracy of gesture detection. In order to obtain a hand image with obvious hand features, firstly, a mask image can be determined according to the hand features, then, a hand image 803 is obtained from the original image 801 according to the mask image, and it can be understood that the hand image 803 is extracted from the original image 801, background information is removed, the hand features in the hand image 803 are obvious in highlighting, and subsequent gesture detection is facilitated.
And S403, under the condition that the size of the hand image is smaller than the preset size, acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image.
Wherein the image processing parameters include at least one of: and presetting resolution, length value and width value. The image processing parameter may also be a pixel value.
In some embodiments, after a hand image corresponding to a hand feature is captured from an original image, it is determined whether the size of the hand image is smaller than a preset size, where the preset size is a size set according to a gesture detection algorithm for a size requirement of an input image. Under the condition that the size of the hand image is smaller than the preset size, the hand image cannot meet the requirements of a gesture detection algorithm, and problems of image blurring and gesture information missing exist possibly.
According to different image processing parameters, the process of adjusting the hand image according to the image processing parameters to obtain the target hand image is described as follows:
(1) Preset resolution
In some embodiments, the gesture detection algorithm has a requirement on the resolution of the input image, and in order to improve the accuracy of gesture detection, an embodiment of the present disclosure provides that, after a hand image corresponding to a hand feature is captured from an original image, the resolution of the hand image is calculated. Then, judging whether the resolution of the hand image is smaller than a preset resolution or not, and under the condition that the resolution of the hand image is smaller than the preset resolution, carrying out resolution adjustment on the hand image according to the preset resolution to obtain a target hand image of which the resolution is greater than or equal to the preset resolution; and when the resolution of the hand image is greater than or equal to the preset resolution, taking the hand image as a target hand image.
In some embodiments, when the gesture occupies a small area in the original image, the resolution of the input image for gesture detection cannot meet the requirement, which affects the accuracy of gesture detection. The embodiment of the disclosure provides an implementation method, after a hand image corresponding to a hand feature is captured from an original image, calculating a size ratio of the hand image to the original image, and then, under the condition that the size ratio is judged to be smaller than a preset ratio, performing resolution adjustment on the hand image according to a preset resolution to obtain a target hand image larger than or equal to the preset resolution; and when the size ratio is larger than or equal to a preset ratio, taking the hand image as a target hand image.
For example, the preset percentage is 15%, after a hand image corresponding to the hand feature is captured from the original image, the calculated percentage of the hand image in size relative to the original image is 10%, which indicates that a gesture in the original image is small and affects a gesture detection result. Further, the hand image is adjusted according to a preset resolution ratio to obtain a target hand image meeting the requirement of gesture detection.
(2) Length value
In some embodiments, after a hand image corresponding to the hand feature is captured from the original image, the length value of the hand image is determined by the vertex position coordinates of the hand image. The embodiment of the present disclosure provides an implementation manner, after a hand image corresponding to a hand feature is captured from an original image, in an image coordinate system, a horizontal coordinate and a vertical coordinate of an upper left corner position and a horizontal coordinate and a vertical coordinate of a lower right corner position of the hand image are obtained, and a length value of the hand image is obtained according to the horizontal coordinate of the upper left corner position and the horizontal coordinate of the lower right corner position.
Illustratively, as shown in fig. 9, fig. 9 is a schematic diagram of position coordinates of a hand image, and in the image coordinate system in fig. 9, the position coordinates of the upper left corner of the hand image are (X1, Y1), the position coordinates of the lower right corner are (X2, Y2), and the length value of the hand image is X2-X1.
The method for calculating the length value of the hand image is only an exemplary illustration, and for example, the length value of the hand image may be calculated according to the abscissa of the lower left corner position and the abscissa of the upper right corner position of the hand image, which is not limited in this disclosure.
After the length value of the hand image is obtained, judging whether the length value of the hand image is equal to a preset length value or not, if the length value of the hand image is equal to the preset length value, taking the hand image as a target hand image, and if the length value of the hand image is not equal to the preset length value, adjusting the length value of the hand image according to the preset length value to obtain the target hand image with the length value equal to the preset length value; and if the length value of the hand image is greater than the preset length value, performing equal-scale reduction processing on the hand image, so as to obtain a target hand image with the length value equal to the preset length value, and reserving the details of the image.
(3) Width value
In some embodiments, after the hand image corresponding to the hand feature is cut from the original image, the width value of the hand image is determined through the vertex position coordinates of the hand image. The embodiment of the disclosure provides an implementation mode, after a hand image corresponding to a hand feature is captured from an original image, in an image coordinate system, a horizontal coordinate and a vertical coordinate of an upper left corner position and a horizontal coordinate and a vertical coordinate of a lower right corner position of the hand image are acquired, and a width value of the hand image is obtained according to the vertical coordinate of the upper left corner position and the vertical coordinate of the lower right corner position.
For example, as shown in fig. 9, fig. 9 is a schematic diagram of position coordinates of a hand image, and in the image coordinate system in fig. 8, the coordinates of the upper left corner and the lower right corner of the hand image are (X1, Y1), X2, Y2, and the width value of the hand image is Y2-Y1.
The above method for calculating the width value of the hand image is only an exemplary illustration, and for example, the width value of the hand image may also be calculated according to the ordinate of the lower left corner position and the ordinate of the upper right corner position of the hand image, which is not limited in this disclosure.
After the width value of the hand image is obtained, judging whether the width value of the hand image is equal to a preset width value or not, and taking the hand image as a target hand image under the condition that the width value of the hand image is equal to the preset width value; under the condition that the width value of the hand image is not equal to the preset width value, if the width value of the hand image is smaller than the preset width value, adjusting the width value of the hand image according to the preset width value to obtain a target hand image with the width value equal to the preset width value; and if the width value of the hand image is greater than the preset width value, performing equal-scale reduction processing on the hand image to obtain a target hand image with the width value equal to the preset width value, and keeping the details of the image.
It should be noted that, in the above embodiments, the hand images are adjusted according to different image processing parameters, and any two or three hand images may be combined, for example, after the hand image corresponding to the hand feature is captured from the original image, a length value and a width value of the hand image are determined, whether the length value of the hand image is equal to a preset length value or not is determined, whether the width value of the hand image is equal to a preset width value or not is determined when the length value of the hand image is equal to the preset length value, and when the width value of the hand image is equal to the preset width value, the hand image is taken as the target hand image, and then the length value of the target hand image is equal to the preset length value and the width value is equal to the preset width value. The combination of the embodiments is not limited, and other combinations are not described herein.
In some embodiments, generally, the size of an input image of a gesture detection algorithm is known, and the embodiments of the present disclosure provide an implementation manner, after a hand image corresponding to a hand feature is captured from an original image, the size of the hand image is compared with the size of the input image, a size ratio of the hand image to the input image may be calculated, and when the size ratio of the hand image to the input image is smaller than a preset input ratio, a resolution of the hand image is adjusted according to a preset resolution to obtain a target hand image with a resolution greater than or equal to the preset resolution; under the condition that the size ratio of the hand image relative to the input image is larger than the preset input ratio, cutting the hand image according to the preset input ratio and the hand image to obtain a target hand image; and under the condition that the size ratio of the hand image relative to the input image is equal to the preset input ratio, the hand image meets the requirement of the input image of a gesture detection algorithm, and then the hand image is taken as a target hand image.
In some embodiments, after the hand image is obtained, image enhancement processing may be performed on the hand image to improve the definition of the hand image, thereby improving the gesture detection effect. In the embodiments of the present disclosure, an implementation is provided for performing a gray histogram processing on a hand image. Specifically, the hand image is subjected to the gradation histogram processing by the function shown in formula (11).
In the formula (11), h is the length of the hand image, w is the width of the hand image, hist is the histogram function of the hand image, and i is the value of the gray histogram from 0 to 255 (each channel is processed separately). A new histogram function H of the hand image is obtained through the function. The new histogram function is adopted in the hand image, so that the image brightness is balanced, namely, brighter display can be adjusted when the light of the hand image is darker, and darker display can be adjusted to when the hand image is closer to the light, and brighter image can be adjusted.
In another implementation manner provided in the embodiments of the present disclosure, a hand image is subjected to filtering processing, and a convolution operation is performed on the hand image by using 3 × 3 filters [0, -1,0, -1,5, -1,0, -1,0], where the filters can achieve soft contrast enhancement and slight denoising of the image to obtain a target hand image, so that the target hand image can show more details to some extent, and further gesture detection is facilitated.
In another embodiment of the present disclosure, an edge sharpening process is performed on a hand image, and a contour line of the hand image is enhanced through high-pass filtering, difference operation, or some transformation to obtain a target hand image, so that details of the target hand image are more prominent, and accuracy of gesture detection is improved.
The three processing methods of the image enhancement processing are as follows: the gray histogram processing, the filtering processing, and the edge sharpening processing may be combined in pairs or three, for example, after the gray histogram processing is performed on the hand image, the filtering processing is performed on the hand image, so that the target hand image after the image enhancement processing is obtained, the details are more complete, and the accuracy of the gesture detection is higher. The combination of the embodiments is not limited, and other combinations are not described herein.
S404, performing gesture detection on the target hand image to obtain a gesture detection result.
In some embodiments, a pre-trained gesture detection model is adopted, the target hand image is used as input, and a gesture detection result is obtained through output. As shown in fig. 10, fig. 10 is a schematic diagram of gesture detection provided in the embodiments of the present disclosure. The hand gesture detection model comprises a pre-trained hand gesture detection model, wherein the hand gesture detection model comprises an area alignment module, a convolution module, a down-sampling module, a full-connection module and a hand type detection module. And taking the target hand image as input, and outputting to obtain a gesture detection result.
S405, under the condition that the gesture detection result is matched with the preset gesture, triggering and executing operation corresponding to the preset gesture.
As shown in fig. 11, fig. 11 is a schematic diagram of a preset gesture provided in the embodiment of the present disclosure. And under the condition that the gesture detection result is matched with the preset gesture, triggering the display equipment to execute the operation corresponding to the preset gesture.
For example, the gesture detection result is a gesture in which five fingers are opened, and the gesture is matched with the preset gesture in the third row and the fifth column in the plurality of preset gestures shown in fig. 11, and if an operation instruction corresponding to the preset gesture plays the media data, the display device executes an operation of playing the media data.
It should be noted that the preset gesture and the operation corresponding to the preset gesture are only exemplary illustrations, and the disclosure does not limit this.
In summary, according to the gesture detection method provided by the embodiment of the present disclosure, an original image is first acquired, then hand features are identified from the original image, then hand images corresponding to the hand features are captured from the original image, image processing parameters are obtained when the size of the hand images is smaller than a preset size, the hand images are adjusted according to the image processing parameters to obtain target hand images, gesture detection is further performed by using the target hand images to obtain gesture detection results, and finally, when the gesture detection results are matched with preset gestures, operation corresponding to the preset gestures is triggered and executed. After the original image is obtained, the hand image in the original image is intercepted, and the hand image is adjusted to obtain the target hand image, so that the image details are reserved on the basis of meeting the gesture detection, and the gesture detection precision is improved.
The embodiment of the disclosure provides a computer-readable storage medium, which is characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the dance and training matching method in the above method embodiments, and can achieve the same technical effect, and is not described herein again to avoid repetition.
The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
Embodiments of the present disclosure provide a computer program product, where the computer program is stored, and when the computer program is executed by a processor, the computer program implements each process of the dance and training matching method in the foregoing method embodiments, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied in the medium.
In the present disclosure, the Processor may be a Central Processing Unit (CPU), and may also be other general purpose processors, digital Signal Processors (DSP), application Specific Integrated Circuits (ASIC), field-Programmable Gate arrays (FPGA) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In the present disclosure, the memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
In the present disclosure, computer-readable media include both non-transitory and non-transitory, removable and non-removable storage media. Storage media may implement information storage by any method or technology, and the information may be computer-readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It is noted that, in this document, relational terms such as "first" and "second," and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A display device, comprising:
an image acquisition device configured to: collecting an original image;
a controller configured to: identifying hand features from the original image, and intercepting a hand image corresponding to the hand features from the original image;
under the condition that the size of the hand image is smaller than a preset size, acquiring an image processing parameter, and adjusting the hand image according to the image processing parameter to obtain a target hand image;
performing gesture detection on the target hand image to obtain a gesture detection result;
under the condition that the gesture detection result is matched with a preset gesture, triggering and executing operation corresponding to the preset gesture;
wherein the image processing parameters include at least one of: and presetting resolution, length value and width value.
2. The display device according to claim 1, wherein the image processing parameters include: a preset resolution, the controller further configured to:
after a hand image corresponding to the hand feature is intercepted from the original image, calculating the resolution of the hand image;
the controller is specifically configured to:
acquiring the preset resolution;
and under the condition that the size of the hand image is smaller than the preset size and the resolution of the hand image is smaller than the preset resolution, carrying out resolution adjustment on the hand image according to the preset resolution so as to obtain the target hand image with the resolution being larger than or equal to the preset resolution.
3. The display device according to claim 1, wherein the image processing parameters include: a preset resolution, the controller further configured to:
after a hand image corresponding to the hand feature is intercepted from the original image, calculating the size ratio of the hand image relative to the original image;
the controller is specifically configured to:
acquiring the preset resolution;
and under the condition that the size of the hand image is smaller than the preset size and the size ratio is smaller than the preset ratio, carrying out resolution adjustment on the hand image according to the preset resolution to obtain the target hand image with the resolution being larger than or equal to the preset resolution.
4. The display device according to claim 1, wherein the image processing parameters include: a length value and/or a width value, the controller being specifically configured to:
determining a length value and/or a width value of the hand image;
when the size of the hand image is smaller than the preset size and the length value of the hand image is not equal to the preset length value, adjusting the length value of the hand image according to the preset length value to obtain the target hand image;
and/or the presence of a gas in the gas,
under the condition that the size of the hand image is smaller than the preset size and the width value of the hand image is not equal to the preset width value, adjusting the width value of the hand image according to the preset width value to obtain the target hand image;
wherein the length value of the target hand image is equal to the preset length value, and/or the width value of the target image is equal to the width value.
5. The display device according to claim 1, wherein the number of hand images is plural, and the controller is configured to:
intercepting a plurality of hand images corresponding to the hand features from the original image;
determining the target hand image from the plurality of hand images;
the target hand image includes at least one of:
the hand image with the image area larger than or equal to the preset area;
the hand image with the image size accounting for the size of the original image being greater than or equal to the preset accounting;
and hand images with the image positions in the preset area.
6. The display device of claim 1, wherein the controller is specifically configured to:
after a hand image corresponding to the hand feature is intercepted from the original image, carrying out image enhancement processing on the hand image to obtain a target hand image;
the image enhancement processing includes at least one of: gray level histogram processing, filtering processing and edge sharpening processing.
7. The display device of claim 1, wherein the controller is specifically configured to:
performing feature recognition on the original image to obtain a mask image, wherein the mask image comprises a hand feature region;
and intercepting the hand image from the original image according to the hand characteristic region in the mask image.
8. A gesture detection method, comprising:
collecting an original image;
identifying hand features from the original image, and intercepting a hand image corresponding to the hand features from the original image;
acquiring image processing parameters, and adjusting the hand image according to the image processing parameters to obtain a target hand image;
performing gesture detection on the target hand image to obtain a gesture detection result;
wherein the image processing parameters include at least one of: and presetting resolution, length value and width value.
9. The method of claim 8, wherein the image processing parameters comprise: the method further includes, after the hand features are identified from the original image and the hand image corresponding to the hand features is cut out from the original image and before the image processing parameters are acquired, presetting a resolution, and before the method includes:
after a hand image corresponding to the hand feature is intercepted from the original image, calculating a first resolution of the hand image;
under the condition that the size of the hand image is smaller than a preset size, acquiring an image processing parameter, and adjusting the hand image according to the image processing parameter to obtain a target hand image, wherein the method comprises the following steps:
acquiring the preset resolution;
and under the condition that the size of the hand image is smaller than the preset size and the first resolution is smaller than the preset resolution, carrying out resolution adjustment on the hand image according to the preset resolution so as to obtain the target hand image with the resolution being larger than or equal to the preset resolution.
10. A computer-readable storage medium, comprising: the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements a gesture detection method as claimed in any one of claims 8 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210625572.3A CN115220570A (en) | 2022-06-02 | 2022-06-02 | Display device, gesture detection method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210625572.3A CN115220570A (en) | 2022-06-02 | 2022-06-02 | Display device, gesture detection method and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115220570A true CN115220570A (en) | 2022-10-21 |
Family
ID=83607439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210625572.3A Pending CN115220570A (en) | 2022-06-02 | 2022-06-02 | Display device, gesture detection method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115220570A (en) |
-
2022
- 2022-06-02 CN CN202210625572.3A patent/CN115220570A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230152962A1 (en) | Techniques for image-based search using touch controls | |
| WO2021185016A1 (en) | Methods and systems for controlling device using hand gestures in multi-user environment | |
| US9554030B2 (en) | Mobile device image acquisition using objects of interest recognition | |
| CN105814522B (en) | Device and method for displaying user interface of virtual input device based on motion recognition | |
| US8861797B2 (en) | Calibrating vision systems | |
| US10311295B2 (en) | Heuristic finger detection method based on depth image | |
| US9721387B2 (en) | Systems and methods for implementing augmented reality | |
| US20130283202A1 (en) | User interface, apparatus and method for gesture recognition | |
| US20190109981A1 (en) | Guided image composition on mobile devices | |
| KR20180018561A (en) | Apparatus and method for scaling video by selecting and tracking image regions | |
| WO2022222510A1 (en) | Interaction control method, terminal device, and storage medium | |
| CN113645494A (en) | Screen fusion method, display device, terminal device and server | |
| CN112906563A (en) | Dynamic gesture recognition method, device and system and readable storage medium | |
| CN110297545B (en) | Gesture control method, gesture control device and system, and storage medium | |
| WO2018076720A1 (en) | One-hand operation method and control system | |
| US20190306435A1 (en) | Electronic apparatus and operating method thereof | |
| CN115220570A (en) | Display device, gesture detection method and storage medium | |
| CN115018899A (en) | Display device and depth image acquisition method | |
| US20210072884A1 (en) | Information processing apparatus and non-transitory computer readable medium | |
| CN113419808A (en) | Map marking method, map marking device, display control equipment and computer readable storage medium | |
| CN114333056A (en) | Gesture control method, system, equipment and storage medium | |
| EP2894866B1 (en) | Display apparatus and display method thereof | |
| CN114217756B (en) | Display device, image detection method and device | |
| CN117612222A (en) | Display device and face recognition method | |
| CN115348438B (en) | Control method and related device for three-dimensional display equipment |
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 |