Gesture recognition method and device, chip, electronic equipment and storage medium

Abstract

The invention discloses a gesture recognition method and device, a chip, electronic equipment and a storage medium. The gesture recognition method comprises the following steps: acquiring original sensing data of a touch panel according to set working parameters; filtering the original sensing data to obtain a first data array; obtaining a touch gesture according to the continuous multi-frame first data array; and comparing the touch gesture with a preset gesture, and judging that gesture recognition succeeds when the touch gesture is consistent with the preset gesture, and the gesture recognition method further comprises the step of adjusting working parameters according to the existing frame number of noise in the first data array under a preset condition. Through adaptive adjustment of the working parameters, processing of the original sensing data can be optimized, and improvement of the accuracy and reliability of gesture recognition is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of touch technology, and in particular to a gesture recognition method, device, chip, electronic device and storage medium. Background Art

[0002] In the field of modern electronic devices, gesture recognition is becoming an increasingly important interactive method to enhance user convenience. Simply performing a specific gesture while the device is in the off state allows the device to quickly sense and automatically wake up, eliminating the need for traditional button presses. This significantly simplifies the user experience and provides a more efficient and streamlined user experience. This technology is widely used in a wide range of products, including smart mobile devices and smart home appliances.

[0003] However, during gesture recognition, various factors, including contamination of the detection area, changes in ambient temperature and humidity, magnetic fields, and external electric fields, can cause noise in the raw sensing data. This noise interference can cause the device to misinterpret a non-wake-up gesture as a wake-up gesture, resulting in unnecessary false wake-ups. It can also prevent the actual wake-up gesture from being correctly recognized due to the noise, reducing the stability and reliability of the screen-off wake-up function and severely impacting the user experience. Summary of the Invention

[0004] In view of the above problems, an object of the present invention is to provide a gesture recognition method, device, chip, electronic device and storage medium.

[0005] According to one aspect of the present application, a gesture recognition method for a touch panel is provided, comprising: obtaining raw sensing data from the touch panel according to set operating parameters; filtering the raw sensing data to obtain a first data array; obtaining a touch gesture based on multiple consecutive frames of the first data array; and comparing the touch gesture with a preset gesture, and determining that gesture recognition is successful when the touch gesture and the preset gesture are consistent. The gesture recognition method further comprises: adjusting the operating parameters according to the number of frames in which noise exists in the first data array under preset conditions.

[0006] Optionally, the operating parameters include a touch threshold, reference scanning data, and reference configuration data, and adjusting the operating parameters according to the number of frames in which noise exists in the first data array includes: adjusting the touch threshold when noise exists in the first data array of a single frame; and adjusting the reference scanning data and resetting the reference configuration data when the number of residual frames of the noise reaches a preset number.

[0007] Optionally, the preset condition includes: the first data array represents an invalid touch state; or the first data array represents a valid touch state, but the touch gesture obtained within a preset time period does not match the preset gesture.

[0008] Optionally, the step of determining whether the first data array represents a valid touch state includes: comparing the first data arrays of the previous and next frames; if the corresponding area shows an increasing data trend, and the peak point or the difference between the peak point and the reference scan data is greater than the corresponding touch threshold, it is determined to be the valid touch state.

[0009] Optionally, the step of obtaining the touch gesture includes: filtering the first data array to obtain a second data array; and obtaining the touch gesture according to a change trend of a peak point of the second data array within the preset time period.

[0010] Optionally, the step of filtering the first data array includes: performing mean filtering on the first data array with an m×m matrix to obtain a data array after matrix filtering, where m>1 and is an integer; and clearing the four edge data of the data array after matrix filtering to obtain the second data array.

[0011] Optionally, the step of filtering the raw sensing data includes: performing mean filtering on the raw sensing data by row to obtain row-filtered sensing data; and performing mean filtering on the row-filtered sensing data by column to obtain the first data array.

[0012] Optionally, the step of performing row-wise mean filtering on the raw sensing data includes: dividing the raw sensing data into a plurality of sub-regions in a row direction; and performing row-wise mean filtering on each of the sub-regions.

[0013] Optionally, the method for judging the noise includes: obtaining a negative pit area or an induction quantity rising area in the first data array, and judging that the noise exists in the first data array when the area of ​​a single negative pit area or the area of ​​a single induction quantity rising area is greater than a preset area.

[0014] Optionally, the gesture recognition method further includes: directly entering a finger scanning mode after acquiring the set working parameters and acquiring the raw sensing data; and entering a low power scanning mode when there is no noise in the first data array.

[0015] Optionally, the raw sensing data is filtered starting from the N+1th frame. For the current gesture recognition process, when the raw sensing data is filtered for the first time, N>0 and is an integer. When the raw sensing data is filtered thereafter, N=0.

[0016] According to another aspect of the present application, a gesture recognition device for a touch panel is provided, comprising: an operating parameter acquisition unit for acquiring set operating parameters; a data acquisition unit for acquiring raw sensing data of the touch panel based on the operating parameters; a data processing unit for filtering the raw sensing data and obtaining a first data array, and acquiring a touch gesture based on multiple consecutive frames of the first data array; a comparison unit for comparing the touch gesture with a preset gesture and determining that gesture recognition is successful when the touch gesture and the preset gesture are consistent; and a parameter adjustment unit for adjusting the operating parameters according to the number of frames in which noise exists in the first data array under preset conditions.

[0017] According to a third aspect of the present application, a chip is provided, which includes the gesture recognition device as described above.

[0018] According to a fourth aspect of the present application, an electronic device is provided, comprising: a memory for storing executable instructions; and a processor for executing the executable instructions to complete any one of the above-mentioned gesture recognition methods.

[0019] According to a fifth aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program can be executed by a processor to perform any one of the gesture recognition methods described above.

[0020] According to the gesture recognition method, device, chip, electronic device, and storage medium provided by the present invention, during the gesture recognition process, system operating parameters are adaptively adjusted based on the noise level of the raw sensing data, thereby optimizing the processing of the raw sensing data and further improving the accuracy and reliability of gesture recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0022] Figure 1 A schematic diagram of an application scenario of a gesture recognition method according to an embodiment of the present invention is shown.

[0023] Figure 2 A schematic flow chart illustrating a gesture recognition method according to an embodiment of the present invention is shown;

[0024] Figure 3 A schematic flow chart showing filtering of raw sensing data is shown;

[0025] Figure 4A Schematic raw sensing data is shown;

[0026] Figure 4B Show Figure 4A The corresponding row filtered sensing data;

[0027] Figure 4C Show Figure 4B a corresponding first data array;

[0028] Figure 5 A schematic flow chart showing filtering of a first data array is shown;

[0029] Figure 6A Show Figure 4C The corresponding matrix filtered data array;

[0030] Figure 6B Show Figure 6A a corresponding second data array;

[0031] Figure 7 A schematic working waveform diagram of a gesture recognition method according to an embodiment of the present invention is shown;

[0032] Figure 8 A schematic structural diagram of a gesture recognition device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0033] Various embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. In each of the accompanying drawings, identical elements are represented by identical or similar reference numerals. For the sake of clarity, the various parts in the accompanying drawings are not drawn to scale.

[0034] Certain terms are used in this specification and claims to refer to specific components. Those skilled in the art will understand that manufacturers may use different terms to refer to the same component. This specification and claims do not distinguish components based on differences in name, but rather on differences in their functions.

[0035] It should be understood that when an element or circuit is said to be "connected to" another element or that an element or circuit is "connected" between two nodes, it can be directly coupled or connected to the other element or there can be intervening elements. The connection between the elements can be physical, logical, or a combination thereof. Conversely, when an element is said to be "directly coupled to" or "directly connected to" another element, it means that there are no intervening elements between the two.

[0036] In addition, it should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0037] It should also be noted that, in the various methods and processes of the present invention, the size of the sequence number of the steps does not mean the order of execution, nor does it constitute any limitation on the implementation process of the embodiments of the present invention.

[0038] To facilitate understanding of the present invention, firstly, applicable application scenarios and related terms of the gesture recognition method according to an embodiment of the present invention are described.

[0039] Figure 1 FIG. 1 shows a schematic diagram of an application scenario of the gesture recognition method according to an embodiment of the present invention. Figure 1 As shown, the application scenario includes a touch device 10. The touch device 10 can be a mobile phone, a tablet computer, or other device equipped with a touch panel. The touch device 10 can adopt the gesture recognition method provided by the embodiment of the present invention, and in particular, the gesture recognition method provided by the present invention can be applied to screen-off gesture recognition, thereby reducing noise interference with the gesture recognition process and data, and improving recognition accuracy, stability, and anti-interference capabilities.

[0040] The touch control device 10 includes a touch panel 100 and a gesture recognition device 200. The touch panel 100 includes a plurality of touch sensors 110. These touch sensors 110 are arranged in a matrix, for example. Figure 1 , one touch sensor 110 is shown as an example.

[0041] The gesture recognition device 200 is connected to the touch panel 100 and performs gesture recognition using the gesture recognition method provided in the embodiment of the present invention.

[0042] The gesture recognition device 200 of the present application can operate in a low power scan mode (Low Power Base, LPBase) and a finger scan mode (Finger Scan Base, FS Base). In LP Base, the gesture recognition device 200 can, for example, short-circuit all touch sensors 110 to obtain changes in the overall sensing quantity on the touch panel 100, and switch to the finger scan mode when the overall sensing quantity indicates that a touch operation may be currently present. In FS Base, each touch sensor 110 operates independently and provides its own collected sensing data to facilitate the gesture recognition device 200 to determine changes in the touch position. Through the collaborative operation of LPBase and FS Base, the low power consumption of the device can be met while improving the accuracy of gesture recognition. In the gesture recognition method disclosed in this embodiment, the relevant terms involved include:

[0043] Raw sensing data: sensing data directly obtained from the touch panel without processing, conversion, or analysis. In this manual, raw sensing data specifically refers to the entire frame of sensing data obtained under FS Base.

[0044] Baseline configuration data: operating parameters of the gesture recognition device, such as the scanning configuration when acquiring raw sensing data.

[0045] Baseline scan data: A reference for changes in sensor data. By comparing the baseline scan data with the original sensor data, the change in sensor data caused by pressure when the touch panel is touched can be determined, thereby determining the location and trajectory of the touch.

[0046] Touch threshold: The benchmark for determining touch operations. When the original sensing data, or the change in the sensing data corresponding to the original sensing data, is greater than or equal to the corresponding touch threshold, it is determined to be a valid touch state.

[0047] Negative pit area and sensor lift area: Areas where sensor data changes. For example, when a finger touches the touch panel, the sensor data in the corresponding area increases, making the sensor data in that area greater than that in other areas. The area touched by the finger is now the sensor lift area. When the baseline scan data correction mechanism is triggered, the sensor data in that area becomes negative after the finger is removed, which is the negative pit area. Generally speaking, areas where sensor data changes may manifest as negative pit areas or sensor lift areas at different stages.

[0048] CG out: The signal output terminal of the gesture recognition device to the touch panel, used to configure the touch panel's scanning level, such as high and low level thresholds. By configuring the scanning level, the touch panel's functions can be controlled and coordinated.

[0049] Figure 2A schematic flow chart of a gesture recognition method according to an embodiment of the present invention is shown. Figure 2 The present invention provides a gesture recognition method. Taking the touch panel screen-off gesture recognition as an example, the gesture recognition method of the present invention includes the following steps:

[0050] In step S11, the system is initialized according to the screen-off gesture instruction.

[0051] The initialization of the touch device after receiving the screen-off gesture instruction includes initialization of the communication port, initialization of the gesture recognition device, and initialization of the gesture buffer.

[0052] The communication port, for example, includes the CG out signal terminal. During initialization, the voltage at the CG out signal terminal typically needs to be raised. Initialization of the gesture recognition device includes initializing the configuration of the device's hardware and software. Initialization of the gesture buffer includes clearing the buffer to ensure that no old data remains in the buffer, preventing it from interfering with gesture recognition.

[0053] In a preferred embodiment, a first delay is inserted after receiving the screen-off gesture command, and system initialization is performed after the delay. This first delay ensures that the gesture recognition device 200 has fully entered normal operating mode during system initialization and can respond to relevant commands promptly and accurately. The first delay can be set, for example, to 100ms based on the actual needs of the touch-sensitive device 10.

[0054] In step S12, the set working parameters are obtained.

[0055] The operating parameters include a touch threshold, reference scanning data, and reference configuration data. The reference configuration data may include, for example, compensation capacitance data of the gesture recognition device 200 under FS Base and LP Base.

[0056] Specifically, in some embodiments, after initialization, the gesture recognition device 200 operates in LP Base and FS Base, respectively, and automatically calibrates the compensation capacitor to obtain compensation capacitance data in these two modes. In a preferred embodiment, a second delay of a duration may be inserted after system initialization, and the compensation capacitor is automatically calibrated after the delay. The second delay ensures that the system has been initialized when the compensation capacitor is calibrated, which helps improve the accuracy of the compensation capacitance data. The second duration can also be set according to the actual needs of the touch device 10, for example, to 100ms.

[0057] In step S13, starting from the N+1th frame, the raw sensing data is filtered to obtain a first data array. For the current gesture recognition process, when the raw data is first filtered, N>0 and is an integer. Each subsequent filtering of the raw sensing data is performed with N=0.

[0058] In the gesture recognition method provided in the present application, after obtaining the set working parameters, the gesture recognition device 200 operates at FS Base and obtains raw sensing data.

[0059] In some embodiments, filtering is performed on the acquired raw sensing data starting from the first frame. However, since the gesture recognition process has just begun, the system is not stable, which may result in high noise in the raw sensing data.

[0060] In a preferred embodiment, Figure 2 In step S13, for the current gesture recognition process, the raw sensing data begins to be filtered for the first time starting from frame N+1, where N is an integer greater than 0. That is, after skipping the raw sensing data of the first N frames, the raw sensing data of frame N+1 is used as the first frame of raw sensing data to be filtered in the current gesture recognition process. Skipping the raw sensing data of the first N frames helps reduce noise in the raw sensing data.

[0061] Specifically, the calculation and filtering of the first N frames of raw sensing data can be skipped by setting a first flag after the system initialization in step S11 is completed, and clearing the first flag after entering FSBase and scanning and acquiring the first N frames of raw sensing data. The first flag is set after step S11, for example, to a Boolean variable, thereby skipping the calculation and filtering of the first N frames of raw sensing data. After acquiring the Nth frame of raw sensing data, the first flag is reset, and filtering processing begins on the acquired raw sensing data. That is, the N+1th frame of raw sensing data is used as the first frame of raw sensing data to be processed in the current gesture recognition process.

[0062] Furthermore, in some embodiments, a second flag may be set after step S12 and cleared after the gesture recognition device 200 operates in the FS Base to ensure that the gesture recognition device 200 correctly enters the FS Base after obtaining the set operating parameters. Specifically, after step S12, the second flag may be set, for example, to a Boolean variable; after entering the FS Base, the second flag may be reset. After obtaining the set operating parameters, the gesture recognition device 200 normally acquires raw scan data, allowing time margin for parameter adjustment in subsequent steps. During the acquisition of the first data array, a touch operation may have occurred. In this case, gesture recognition should be prioritized. Specifically, a touch gesture should be acquired based on multiple consecutive frames of the first data array. The touch gesture should then be compared with the preset gesture to determine whether the gesture was successfully recognized. If the touch gesture matches the preset gesture, gesture recognition is considered successful; otherwise, gesture recognition is considered unsuccessful.

[0063] However, directly performing gesture recognition based on the first data array cannot avoid gesture misjudgment due to noise in the sensing data array. Therefore, in a preferred embodiment, after step S13, the process further includes adjusting operating parameters based on the number of frames in the first data array where noise is present, under preset conditions; and obtaining new raw sensing data after adjusting the operating parameters.

[0064] The preset conditions include: the first data array indicates that no touch is sensed; or the first data array indicates that a touch is sensed, but a touch gesture obtained within a preset time period does not match a preset gesture.

[0065] Accordingly, after step S13, the following steps are included:

[0066] In step S14, it is determined whether the touch state is valid.

[0067] In some embodiments, by comparing the first data arrays of the previous and next frames, if the corresponding area shows an increasing data trend and the peak point or the difference between the peak point and the scan reference data exceeds the corresponding touch threshold, it is determined to be a valid touch state.

[0068] If it is determined to be a valid touch state, the gesture recognition process is continued first, that is, step S15 and subsequent steps are continued; otherwise, step S18 and subsequent steps are continued.

[0069] By prioritizing gesture recognition when there is a touch operation, quick feedback can be provided to the user, which is more conducive to improving the user experience.

[0070] In step S15 , a touch gesture is acquired.

[0071] In this step, the touch gesture is obtained according to the change trajectory of the peak point in the first data array of multiple consecutive frames.

[0072] In some embodiments, the touch gesture may be acquired with reference to the following steps I1-I5.

[0073] In step I1, a region to be selected is delineated with the peak point as the center;

[0074] In step I2, the coordinates of the peak point in the selected area are obtained;

[0075] In step I3, the displacement of the peak point is obtained according to the coordinate change of the peak point in the first data array of the continuous multiple frames;

[0076] In step I4, the moving speed of the peak point is obtained according to the displacement of the peak point and the time relationship; and

[0077] In step I5, a feature vector representing the touch gesture is obtained according to the moving speed and direction of the peak point.

[0078] In some embodiments, the first data array is further filtered to obtain a second data array, and the touch gesture is obtained through the second data array. Filtering the first data array can further improve the quality of the sensing data and more effectively remove noise.

[0079] In some embodiments, the touch gesture acquisition duration is limited to a preset duration to further avoid misidentification of touch gestures due to noise. That is, in step S15, the touch gesture is acquired using multiple consecutive frames of the first data array within the preset duration. Setting the preset duration avoids excessive waiting time during touch gesture acquisition due to misidentification of noise as a touch, thereby improving gesture recognition efficiency.

[0080] The preset duration can be set according to the reference configuration data. For example, when the scanning frequency is low, it can be set to 1 second.

[0081] In step S16, the touch gesture in step S15 is compared with the preset gesture template. If the touch gesture is consistent with the preset gesture, it is determined that the match is successful, and step S17 is executed to exit the gesture recognition process. If the match is unsuccessful, step S18 is executed.

[0082] In step S18, it is determined whether there is noise in the first data array. If there is noise, the process proceeds to step S19.

[0083] In some embodiments, the presence of noise can be determined by the area of ​​the negative pit region or the area of ​​the sensor rise region in the first data array. If the area of ​​the negative pit region or the area of ​​the sensor rise region is greater than a predetermined area, then the first data array is determined to have noise.

[0084] In some embodiments, when a touch device is touched using a finger or stylus, the preset area can be set based on the area between the fingers or the tip of the stylus. If the area of ​​the negative pit region or the area of ​​the sensed lift region is larger than the preset area, it indicates that the current pressure area is abnormal, and the changes in the sensed data in that area are determined to be noise.

[0085] In some embodiments, if there is no noise, the process returns to step S13 to reacquire the original sensing data. In a preferred embodiment, if there is no noise, the gesture recognition device may be switched to a low power consumption mode to wait for a touch operation.

[0086] In step S19, the operating parameters are adjusted according to the number of frames in which noise exists in the first data array.

[0087] In this step, if the first data array acquired for the first time has noise, the touch threshold is dynamically adjusted according to the area and size of the noise. For example, when the noise is large or the area of ​​the noise is large, the touch threshold can be increased.

[0088] If the noise still remains for a predetermined number of frames, the reference scan data is updated and the configuration data is reset.

[0089] After obtaining the adjusted new operating parameters, the process returns to step S13 to obtain new raw sensing data. However, for the current gesture recognition process, the system is already relatively stable when obtaining the new raw data, so there is no need to skip the first N frames, that is, N=0 at this time.

[0090] According to the gesture recognition method provided by the present invention, during the gesture recognition process, the system operating parameters are adaptively adjusted according to the noise conditions of the original sensing data, thereby optimizing the processing of the original sensing data and further improving the accuracy and reliability of gesture recognition.

[0091] Figure 3 A schematic flow chart showing the filtering of raw sensing data is shown. Figure 4A Showing schematic raw sensing data, Figure 4B Show Figure 4A The corresponding row filtered sensing data, Figure 4C Show Figure 4B The corresponding first data array. Figures 3 to 4C In some embodiments, filtering comprises the following steps:

[0092] In step S21, the original sensing data is subjected to mean filtering by row, and sensing data after row filtering is obtained. By performing mean filtering by row, noise interference in the row direction can be reduced.

[0093] In some embodiments, during the process of performing row-wise mean filtering, negative pits in the original sensing data can also be filled, thereby facilitating subsequent further processing of the original sensing data.

[0094] In a preferred embodiment, the original sensing data array can be divided into multiple sub-areas in the row direction, and mean filtering can be performed on a row basis in each sub-area. Figure 4A The raw sensing data shown is divided into a left half and a right half of equal area. Figure 4B The row-filtered sensing data shown has less noise.

[0095] In step S22 , mean filtering is performed on the row-filtered sensing data by column, and a first data array is obtained.

[0096] refer to Figures 4B to 4C By performing column-wise mean filtering, the interference in the column direction of the original sensing data can be eliminated, thereby enhancing the stability of the data.

[0097] Figure 5 shows a schematic flow chart of filtering the first data array, Figure 6A Show Figure 4C The corresponding matrix filtered data array, Figure 6B Show Figure 6A The corresponding second data array. Figures 5 to 6B In some embodiments, filtering the first data array comprises the following steps:

[0098] In step S31, the first data array is subjected to mean filtering using an m×m matrix to obtain a matrix-filtered data array, where m>1 is an integer. The value of m can be set based on the number of touch sensors on the touch panel.

[0099] refer to Figures 4C to 6A Compared with simple row filtering or column filtering, matrix filtering can more comprehensively remove noise and make the data more stable.

[0100] In step S32, the data at the four edges of the matrix-filtered data array are cleared to obtain a second data array.

[0101] refer to Figures 6A to 6B Since the edge area of ​​the touch panel is usually less sensitive to touch and more susceptible to noise, the data quality of this part can be improved by clearing the data around the edge.

[0102] Figure 7 Schematic working waveform diagram of the gesture recognition method according to an embodiment of the present invention is shown. Figure 7 In a preferred embodiment, stage t1 is the first delay time after receiving the screen-off gesture command, stage t2 is the second delay time after system initialization, stage t3 is the automatic calibration stage of the compensation capacitor, stage t4 is the acquisition stage of setting working parameters, and stage t5 is the skipping of the first N frames of raw sensing data.

[0103] Figure 8 The schematic structural diagram of the gesture recognition device according to the embodiment of the present invention is shown in FIG. The gesture recognition device 200 can be applied to Figure 1 The touch device 10 in FIG. 1 , that is, the gesture recognition method provided in the embodiment of the present invention can be used to implement gesture recognition.

[0104] refer to Figure 8 , the gesture recognition device 200 includes:

[0105] The operating parameter acquisition unit 210 is configured to acquire initial operating parameters, which include a touch threshold, reference scanning data, and reference configuration data.

[0106] The data acquisition unit 220 is used to acquire the original sensing data of the touch panel under corresponding working parameters. Specifically, the working parameters are set working parameters or adjusted working parameters.

[0107] The data processing unit 230 is configured to filter the original sensing data to obtain a first data array, and to acquire a touch gesture according to the first data array of multiple consecutive frames.

[0108] The comparison unit 240 is configured to compare the touch gesture with the preset gesture and determine that the gesture recognition is successful when the touch gesture and the preset gesture are consistent.

[0109] The parameter adjustment unit 250 is used to adjust the operating parameters according to the number of frames with noise in the first data array under preset conditions, and to enable the data acquisition unit to acquire new raw sensing data under the new operating parameters.

[0110] When noise exists in the first data array of the first frame, the touch threshold is increased; and when the number of residual frames of noise reaches a preset number, the reference scan data is adjusted and the reference configuration data is reset.

[0111] The preset conditions are, for example, those described above, and since the gesture recognition device 200 can implement the gesture recognition method provided by the present invention, it also has any of the above-mentioned beneficial effects, which will not be described in detail here.

[0112] The present invention further provides a chip, which includes, for example, the gesture recognition device 200 described above and can implement the gesture recognition method provided by the present invention.

[0113] An embodiment of the present invention further provides an electronic device, which may include a memory for storing executable instructions; and a processor for executing the executable instructions and completing the gesture recognition method of the embodiment of the present invention.

[0114] The present invention also provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by a processor to implement the gesture recognition method provided by the present invention.

[0115] According to the gesture recognition method, device, chip, electronic device, and storage medium provided by the present invention, during the gesture recognition process, system operating parameters are adaptively adjusted based on the noise level of the raw sensing data, thereby optimizing the processing of the raw sensing data and further improving the accuracy and reliability of gesture recognition.

[0116] The embodiments of the present invention are as described above, and these embodiments do not describe all details in detail, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations can be made based on the above description. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can make good use of the present invention and its modifications and uses. The scope of protection of the present invention shall be based on the scope defined by the claims of the present invention.

Claims

1. A gesture recognition method for a touch panel, wherein: include: Acquiring raw sensing data of the touch panel according to set working parameters; filtering the raw sensing data to obtain a first data array; Acquire a touch gesture according to the first data array of multiple consecutive frames; as well as Comparing the touch gesture with a preset gesture, and determining that the gesture recognition is successful when the touch gesture is consistent with the preset gesture, The gesture recognition method further includes: Under preset conditions, the operating parameters are adjusted according to the number of frames in which noise exists in the first data array.

2. The gesture recognition method according to claim 1, wherein: The operating parameters include touch threshold, reference scanning data and reference configuration data, Adjusting the operating parameter according to the number of frames in which noise exists in the first data array includes: When noise exists in the first data array of a single frame, adjusting the touch threshold; and When the number of residual frames of the noise reaches a preset number, the reference scanning data is adjusted and the reference configuration data is reset.

3. The gesture recognition method according to claim 1, wherein: The preset conditions include: The first data array represents an invalid touch state; or The first data array represents a valid touch state, but the touch gesture obtained within a preset time period does not conform to the preset gesture.

4. The gesture recognition method according to claim 3, wherein: The step of determining whether the first data array represents a valid touch state includes: Comparing the first data arrays of the previous and next frames, if the corresponding area shows an increasing data trend, and the peak point or the difference between the peak point and the reference scan data is greater than the corresponding touch threshold, it is determined to be the valid touch state.

5. The gesture recognition method according to claim 3, wherein: The step of obtaining the touch gesture includes: filtering the first data array to obtain a second data array; and The touch gesture is obtained according to a change trend of a peak point of the second data array within the preset time period.

6. The gesture recognition method according to claim 5, wherein: The step of filtering the first data array comprises: Performing mean filtering on the first data array using an m×m matrix to obtain a matrix-filtered data array, where m>1 and is an integer; and The peripheral edge data of the matrix-filtered data array are cleared to obtain the second data array.

7. The gesture recognition method according to claim 1, wherein: The step of filtering the raw sensing data comprises: Performing mean filtering on the original sensing data by row to obtain sensing data after row filtering; and The row-filtered sensing data is subjected to column-by-column mean filtering to obtain the first data array.

8. The gesture recognition method according to claim 7, wherein: The step of performing mean filtering on the raw sensing data by row includes: In a row direction, dividing the original sensing data into a plurality of sub-regions; and For each of the sub-regions, mean filtering is performed row by row.

9. The gesture recognition method according to claim 1, wherein: The noise determination method includes: A negative pit region or an induction quantity rising region in the first data array is obtained, and when the area of ​​a single negative pit region or the area of ​​a single induction quantity rising region is greater than a preset area, it is determined that the first data array has the noise.

10. The gesture recognition method according to claim 1, wherein: The gesture recognition method further includes: directly entering the finger scanning mode after obtaining the set working parameters, and obtaining the raw sensing data; and When there is no noise in the first data array, a low power consumption scanning mode is entered.

11. The gesture recognition method according to claim 10, wherein: Filter the raw sensing data starting from the N+1th frame, For the current gesture recognition process, when filtering the raw sensing data for the first time, N>0 and is an integer, and when filtering the raw sensing data thereafter, N=0.

12. A gesture recognition device for a touch panel, wherein: include: A working parameter acquisition unit, used to acquire set working parameters; a data acquisition unit, configured to acquire raw sensing data of the touch panel according to the operating parameters; a data processing unit, configured to filter the raw sensing data to obtain a first data array, and acquire a touch gesture based on a plurality of consecutive frames of the first data array; a comparing unit, configured to compare the touch gesture with a preset gesture, and determine that gesture recognition is successful when the touch gesture is consistent with the preset gesture; as well as The parameter adjustment unit is used to adjust the working parameter according to the number of frames in which noise exists in the first data array under preset conditions.

13. A chip, wherein: The method comprises the gesture recognition device as claimed in claim 12.

14. An electronic device, wherein: include: a memory for storing executable instructions; as well as A processor, configured to execute the executable instructions to implement the gesture recognition method according to any one of claims 1 to 11.

15. A computer-readable storage medium, wherein: The storage medium stores a computer program, and the computer program can be executed by a processor to implement the gesture recognition method according to any one of claims 1 to 11.

Images