Touch gesture recognition method and device

Abstract

The invention provides a touch gesture recognition method and device, and the method comprises the steps: obtaining a data frame of each elastic wave sensor, carrying out the high-pass filtering processing of the data frames of a first number of elastic wave sensors, obtaining a high-pass data frame, carrying out the low-pass filtering processing of the data frames of a second number of elastic wave sensors, and obtaining a low-pass data frame; obtaining a low-pass data frame; and determining a current phase relationship between the high-pass data frame and the low-pass data frame, and when the current phase relationship does not meet a preset phase relationship, determining that the gesture is a non-sliding gesture. According to the touch gesture recognition method and device provided by the invention, the problem of random opening of the vehicle door caused by mistaken touch of the door handle is effectively avoided, and the reliability of controlling the opening of the vehicle door is ensured.

Description

Technical Field

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

[0002] With the continuous improvement of living standards, cars have entered thousands of households and become the first choice for people to travel. People have become more and more dependent on cars. In recent years, with the accelerated pace of automobile intelligence development, the safety and convenience of vehicles have been improved. Among them, the intelligent upgrade of door opening control has greatly improved the user experience.

[0003] At present, the intelligent way to open the car door is touch unlocking, that is, the passenger touches the door sensing area, and the sensing area opens the door after receiving the pressure signal. Compared with the traditional mechanical door handle, touch unlocking improves the intelligence level of the vehicle and effectively improves the riding experience. However, the current touch unlocking is based on only a single pressure signal perception, so the problem of random door opening due to accidental touch often occurs during use, especially during the car washing process due to water pressure or rainwater flowing through the touch area on rainy days, causing the door to open accidentally, which can easily cause pollution to the cab. Summary of the invention

[0004] In order to solve the problems in the prior art, the present invention provides a touch gesture recognition method and device.

[0005] The present invention provides a touch gesture recognition method, comprising:

[0006] Acquire a data frame of each elastic wave sensor, perform high-pass filtering on the data frames of the first number of elastic wave sensors to obtain high-pass data frames, and perform low-pass filtering on the data frames of the second number of elastic wave sensors to obtain low-pass data frames;

[0007] A current phase relationship between the high-pass data frame and the low-pass data frame is determined, and when the current phase relationship does not satisfy a preset phase relationship, it is determined to be a non-sliding gesture.

[0008] According to a touch gesture recognition method provided by the present invention, the method further includes: when the current phase relationship satisfies a preset phase relationship,

[0009] Performing amplitude-frequency conversion on the high-pass data frame to obtain an amplitude-frequency characteristic of the high-pass data frame, and determining an energy difference value between a first frequency band energy parameter and a second frequency band energy parameter based on the amplitude-frequency characteristic;

[0010] Determine a point number difference value between the number of data points in the high-pass data frame that meet a preset threshold condition and the number of all data points in the high-pass data frame;

[0011] When the calculated value of the energy difference value and the point difference value is greater than the target value, the touch gesture is still determined to be a non-sliding gesture, otherwise it is a sliding gesture.

[0012] According to a touch gesture recognition method provided by the present invention, the preset threshold condition is:

[0013] x i ·x i+k ≤thr_b, where x i represents the i-th data point in the high-pass data frame, x i+k It represents the (i+k)th data point in the high-pass data frame, where i and k are both positive integers, and thr_b is the preset threshold.

[0014] According to a touch gesture recognition method provided by the present invention, the step of acquiring a data frame of each elastic wave sensor includes:

[0015] An initial sensing data value whose absolute value is greater than a preset reference value is selected as an initial data frame selection point, and a preset number of initial sensing data are selected for each elastic wave sensor using the initial data frame selection point as a reference point to obtain multiple initial data frames, and an average value or a preset value of the initial data frame of the corresponding elastic wave sensor is subtracted from each of the initial sensing data in each of the initial data frames to obtain multiple updated data frames as the data frames of each elastic wave sensor.

[0016] According to a touch gesture recognition method provided by the present invention, the filter passband when high-pass filtering is performed on the data frame is 0-1 kHz, and the filter passband when low-pass filtering is performed on the data frame is 0-20 Hz.

[0017] The present invention also provides a touch gesture recognition device, comprising: a sensor group, a filter circuit, and a micro-control unit; wherein:

[0018] The sensor group is electrically connected to the filter circuit, and the sensor group includes a plurality of elastic wave sensors;

[0019] The filter circuit is also electrically connected to the micro-control unit, and includes a high-pass filter circuit and a low-pass filter circuit;

[0020] At least one of the elastic wave sensors is electrically connected to the high-pass filter circuit, and at least one of the elastic wave sensors is electrically connected to the low-pass filter circuit;

[0021] The high-pass filter circuit performs high-pass filtering on the data frame of the electrically connected elastic wave sensor to obtain a high-pass data frame;

[0022] The low-pass filter circuit performs low-pass filtering on the data frame of the electrically connected elastic wave sensor to obtain a low-pass data frame;

[0023] The micro-control unit determines a current phase relationship between the high-pass data frame and the low-pass data frame, and when the current phase relationship does not satisfy a preset phase relationship, determines it as a non-sliding gesture.

[0024] According to a touch gesture recognition device provided by the present invention, before determining the current phase relationship between the high-pass data frame and the low-pass data frame, the micro-control unit further performs a secondary filtering on the high-pass data frame with the same or lower passband as the high-pass filter circuit, and performs a secondary filtering on the low-pass data frame with the same or lower passband as the low-pass filter circuit.

[0025] The present invention also provides a touch gesture recognition device, comprising: a sensor group and a micro-control unit, wherein the sensor group is electrically connected to the micro-control unit; wherein:

[0026] The sensor group includes a plurality of elastic wave sensors, and the elastic wave sensors perform data collection;

[0027] The micro-control unit acquires a data frame of each elastic wave sensor, performs high-pass filtering on the data frames of the first number of elastic wave sensors to obtain high-pass data frames, and performs low-pass filtering on the data frames of the second number of elastic wave sensors to obtain low-pass data frames; and

[0028] A current phase relationship between the high-pass data frame and the low-pass data frame is determined, and when the current phase relationship does not satisfy a preset phase relationship, it is determined to be a non-sliding gesture.

[0029] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above touch gesture recognition methods are implemented.

[0030] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above touch gesture recognition methods are implemented.

[0031] The present invention further provides a computer program product, comprising a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the steps of any of the above touch gesture recognition methods are implemented.

[0032] The touch gesture recognition method and device provided by the present invention install multiple sensors at the vehicle door handle and perform differential filtering processing on each sensor respectively, that is, ensuring that high-pass filtering and low-pass filtering exist at the same time, so that the data obtained from each sensor have a certain phase order, and the different phase orders effectively distinguish between sliding gestures (valid touch gestures) and non-sliding gestures (invalid touch gestures), and the door is opened only when it is determined to be a valid sliding gesture. Based on this, other external interference is effectively avoided, accidental opening of the door is avoided, and the reliability of the door opening control is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 This is one of the flow charts of the touch gesture recognition method provided by the present invention;

[0035] Figure 2 is a schematic diagram of the sliding surface of the door handle provided by the present invention;

[0036] Figure 3 This is the second flow chart of the touch gesture recognition method provided by the present invention;

[0037] Figure 4-1 This is one of the structural schematic diagrams of the touch gesture recognition device provided by the present invention;

[0038] Figure 4-2 This is the second structural schematic diagram of the touch gesture recognition device provided by the present invention;

[0039] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Figure 1 is one of the flow charts of the touch gesture recognition method provided by the present invention, such as Figure 1As shown, the method includes:

[0042] Step S110, acquiring a data frame of each elastic wave sensor, performing high-pass filtering on the data frames of the first number of elastic wave sensors to obtain high-pass data frames, and performing low-pass filtering on the data frames of the second number of elastic wave sensors to obtain low-pass data frames;

[0043] Step S120, determining a current phase relationship between the high-pass data frame and the low-pass data frame, and when the current phase relationship does not satisfy a preset phase relationship, determining it as a non-sliding gesture.

[0044] It should be noted that high-pass filtering refers to a filtering method whose rule is that high-frequency signals can pass normally, while low-frequency signals below the set critical value are blocked and weakened; correspondingly, the rule of low-pass filtering is that low-frequency signals can pass normally, while high-frequency signals exceeding the set critical value are blocked and weakened.

[0045] The preset phase relationship is a phase sequence relationship, which means that the phase change trend between the acquired data frames conforms to the arrangement order of the sensors, and when the current phase relationship is consistent with the preset phase relationship, that is, when the current phase relationship is a phase sequence relationship, it indicates that the touch gesture may be a sliding gesture, and when the current phase relationship is a non-sequential relationship, it indicates that the touch gesture must be a non-sliding gesture; it should be clear that the sliding gesture is an effective touch gesture that successfully opens the door, and the non-sliding gesture is an invalid touch gesture that cannot open the door. For example, the sensors are arranged from left to right as #1, #2 and #3, and the preset phase relationship means that the phase change trend of the high-pass data frame and the low-pass data frame meets the order of #1, #2 and #3 or #3, #2 and #1, such as the peak of the #1 sensor appears first, followed by #2, and finally #3.

[0046] The touch gesture recognition method provided by the present invention installs multiple sensors at the vehicle door handle and performs differential filtering processing on each sensor respectively, that is, ensuring that high-pass filtering and low-pass filtering exist at the same time, so that the data obtained from each sensor have a certain phase order, and the different phase orders effectively distinguish between sliding gestures (valid touch gestures) and non-sliding gestures (invalid touch gestures), and the door is opened only when it is determined to be a sliding gesture. Based on this, other external interference is effectively avoided, accidental opening of the door is avoided, and the reliability of the door opening control is guaranteed.

[0047] According to the touch gesture recognition method provided by the present invention, in the present invention, the method further comprises: when the current phase relationship satisfies the preset phase relationship,

[0048] Performing amplitude-frequency conversion on the high-pass data frame to obtain an amplitude-frequency characteristic of the high-pass data frame, and determining an energy difference value between a first frequency band energy parameter and a second frequency band energy parameter based on the amplitude-frequency characteristic;

[0049] Determine a point number difference value between the number of data points in the high-pass data frame that meet a preset threshold condition and the number of all data points in the high-pass data frame;

[0050] When the calculated value of the energy difference value and the point difference value is greater than the target value, the touch gesture is still determined to be a non-sliding gesture, otherwise it is a sliding gesture.

[0051] It should be noted that the energy parameter includes one of the energy sum, energy mean, energy maximum or extreme value, and energy quantile; a sliding gesture, i.e., a valid touch gesture, will show excellent low-frequency information in the high-pass data frame, i.e., low-frequency information accounts for the main component of the spectrum information, while an invalid touch gesture, i.e., interference data, does not have this feature. Accordingly, when sliding effectively, the energy difference value and the point difference value mentioned above are both within a set threshold range, so by setting the calculated value and target value of the energy difference value and the point difference value for comparison, it is determined whether the touch gesture is a sliding gesture based on the comparison result, and the specific calculation logic includes but is not limited to subtraction or division. For example, a first ratio between an energy parameter of a first frequency band and an energy parameter of a second frequency band is determined based on the amplitude-frequency characteristic, and a second ratio between the number of data points in a high-pass data frame that meet a preset threshold condition and the number of all data points in the high-pass data frame is determined. Accordingly, when effective sliding occurs, the values ​​of the first ratio and the second ratio mentioned above are both smaller than the values ​​of the first ratio and the second ratio when interference occurs; when the calculated value of the first ratio and the second ratio is greater than the target value, the touch gesture is still determined to be a non-sliding gesture, otherwise it is a sliding gesture.

[0052] For example, the first frequency band may be set to 20-1kHz and the second frequency band may be set to 0-20Hz.

[0053] The touch gesture recognition method provided by the present invention, when the current phase relationship is consistent with the preset phase relationship, finally completes the further determination of the sliding gesture through the calculation of the amplitude-frequency characteristic curve and the subsequent first ratio and the second ratio, refines the determination process of the sliding gesture, and further ensures the accuracy and reliability of the determination of the sliding gesture, thereby more accurately eliminating the interference of irrelevant sliding gestures on the opening of the vehicle door.

[0054] According to the touch gesture recognition method provided by the present invention, in the present invention, the preset threshold condition is:

[0055] x i ·x i+k ≤thr_b, where x irepresents the i-th data point in the high-pass data frame, x i+k It represents the (i+k)th data point in the high-pass data frame, where i and k are both positive integers, and thr_b is the preset threshold.

[0056] It should be noted that the interference signal has more high-frequency components, and the lines between adjacent or spaced data points will cross the threshold line thr_b multiple times, and the number of data points of the interference signal that meet this condition is greater than the sliding gesture.

[0057] The touch gesture recognition method provided by the present invention selects data points in a high-pass data frame by setting a preset threshold condition, and then obtains a second ratio, and finally compares the product of the first ratio and the second ratio with a target value, and quickly obtains a determination result of the touch gesture based on the comparison result, so as to clarify whether the touch gesture is a sliding gesture or an interference action.

[0058] According to the touch gesture recognition method provided by the present invention, in the present invention, the acquiring of the data frame of each elastic wave sensor comprises:

[0059] An initial sensing data value whose absolute value is greater than a preset reference value is selected as an initial data frame selection point, and a preset number of initial sensing data are selected for each elastic wave sensor using the initial data frame selection point as a reference point to obtain multiple initial data frames, and an average value or a preset value of the initial data frame of the corresponding elastic wave sensor is subtracted from each of the initial sensing data in each of the initial data frames to obtain multiple updated data frames as the data frames of each elastic wave sensor.

[0060] It should be noted that, assuming that three sensors respectively acquire sensor data, three sensor data sequences can be obtained over time; first, the initial sensor data points whose absolute values ​​are greater than the preset reference values ​​are searched point by point in the three sensor data sequences, and after selection, the corresponding reference data points in the other two sensors at the same sampling time are determined based on the initial data points, and then a preset number of data points are selected forward and / or backward in the sampling time sequence based on their respective reference data points as initial data frames, and finally three initial data frames corresponding to each sensor are obtained; the average value of each initial data frame is calculated respectively, and the corresponding initial data frame average value is subtracted from each initial data frame in the data frame in units of a single data frame to obtain updated data frames corresponding to each sensor.

[0061] It is worth mentioning that when processing the initial data frame here, it is preferred to use each initial sensing data in the initial data frame minus the average value of the initial data frame of the corresponding elastic wave sensor to update the data frame; any value other than the average value of the initial data frame can also be selected as the subtrahend when updating the data frame.

[0062] In the touch gesture recognition method provided by the present invention, during the sensor data collection process, the collection result may have a certain data bias due to the system's own program. By removing the DC component, the data bias can be effectively removed, thereby making the acquired data more accurate.

[0063] According to the touch gesture recognition method provided by the present invention, in the present invention, the filter passband when high-pass filtering is performed on the data frame is 0-1kHz, and the filter passband when low-pass filtering is performed on the data frame is 0-20Hz.

[0064] It should be noted that in order to avoid interference of sound signals on sliding recognition, the cutoff frequency of the low-pass filter passband should not be higher than 20Hz. In order to retain the information of interference signals such as water spray and leave enough difference, the cutoff frequency of the high-pass filter passband should be higher than 20Hz, which is 1kHz in this embodiment.

[0065] The touch gesture recognition method provided by the present invention solves the problems of sliding recognition based on capacitive sensors and misoperation and non-operation of mechanical buttons in scenes such as car washing and rain by introducing multi-channel differential filtering and feature recognition, making sliding recognition more reliable.

[0066] Figure 3 FIG. 2 is a flow chart of the touch gesture recognition method provided by the present invention. Figure 2 As shown, the method includes:

[0067] Step 1, start;

[0068] Step 2, multi-sensor data sequence acquisition: The sensor here is an elastic wave sensor, which is a piezoelectric sensor, but it is also applicable to signals collected by other sensors, such as capacitive sensors, etc.;

[0069] Step 3, remove the DC component: Step 3-1, judge the trigger condition of the collected signal point by point, and judge whether the maximum value of the absolute value of the multi-channel sampling value meets the condition that it is greater than or equal to the threshold a. If it meets the condition, go to Step 3-2, if not, continue to judge point by point; Step 3-2: intercept the data between the m points before the current point and the n points after the current point as the data frame X[x1,x2,...,x l ]; Step 3-3: Calculate the mean of data frame X Subtract each point from the data frame And update to data frame X;

[0070] Step 4, filtering: at least one sensor uses high-pass filtering, and multiple sensors use low-pass filtering;

[0071] Step 5, determine the phase difference between each sensor: determine the order relationship between the maximum or minimum points of the sampling data of each sensor to obtain the phase relationship;

[0072] Step 6, determine whether the phase difference meets the preset conditions, if not, determine the sliding gesture as interference; if yes, jump to execute Step 7;

[0073] Step 7, determine whether it is an interference action, if so, the sliding gesture is determined as interference; if not, the sliding gesture is determined as a valid sliding;

[0074] Step 8, end.

[0075] The touch gesture recognition method provided by the present invention installs multiple sensors at the vehicle door handle and performs differential filtering processing on each sensor respectively, that is, ensuring that high-pass filtering and low-pass filtering exist at the same time, so that the data obtained from each sensor have a certain phase order, and the different phase orders effectively distinguish between sliding gestures (valid touch gestures) and non-sliding gestures (invalid touch gestures), and the door is opened only when it is determined to be a sliding gesture. Based on this, other external interference is effectively avoided, accidental opening of the door is avoided, and the reliability of the door opening control is guaranteed.

[0076] Figure 4-1 FIG. 1 is a schematic diagram of a touch gesture recognition device provided by the present invention. Figure 4-1 As shown, a sensor group, a filter circuit, and a micro-control unit; wherein:

[0077] The sensor group is electrically connected to the filter circuit, and the sensor group includes a plurality of elastic wave sensors;

[0078] The filter circuit is also electrically connected to the micro-control unit, and includes a high-pass filter circuit and a low-pass filter circuit;

[0079] At least one of the elastic wave sensors is electrically connected to the high-pass filter circuit, and at least one of the elastic wave sensors is electrically connected to the low-pass filter circuit;

[0080] The high-pass filter circuit performs high-pass filtering on the data frame of the electrically connected elastic wave sensor to obtain a high-pass data frame;

[0081] The low-pass filter circuit performs low-pass filtering on the data frame of the electrically connected elastic wave sensor to obtain a low-pass data frame;

[0082] The micro-control unit determines a current phase relationship between the high-pass data frame and the low-pass data frame, and when the current phase relationship does not satisfy a preset phase relationship, determines it as a non-sliding gesture.

[0083] It should be noted that the sensor group is electrically connected to the filter circuit, including:

[0084] The sensor board is used to arrange a specific number of sensors. The number of special sensor modules should be greater than or equal to 2;

[0085] A connector for connecting the sensor board to the controller board;

[0086] A filter circuit is used to obtain a data frame corresponding to each sensor, and arbitrarily select a first number of data frames to perform high-pass filtering to obtain high-pass data frames, and select a second number of data frames to perform low-pass filtering to obtain low-pass data frames; specifically, one of the filter circuit 1 and the filter circuit 2 can be selected as a low-pass filter circuit, and the other one is a high-pass filter circuit, and the filter circuit 3 can use both a high-pass filter and a low-pass filter circuit;

[0087] A differential amplifier circuit is used to amplify the filtered analog signal and improve the anti-interference ability of the circuit;

[0088] AD conversion, used to convert the analog signal from the differential amplifier circuit into a digital signal;

[0089] MCU, micro control unit, is used to calculate and determine the current phase relationship between the high-pass data frame and the low-pass data frame, and when the current phase relationship does not meet the preset phase relationship, it is determined to be a non-sliding gesture. In particular, the MCU can also filter the data frame of each channel again before determining the phase relationship.

[0090] According to the touch gesture recognition device provided by the present invention, in the present invention, before determining the current phase relationship between the high-pass data frame and the low-pass data frame, the micro-control unit also performs secondary filtering on the high-pass data frame with the same or lower passband as the high-pass filter circuit, and performs secondary filtering on the low-pass data frame with the same or lower passband as the low-pass filter circuit.

[0091] It should be noted that the essence of filtering is to separate useful signals from noise, improve the signal's anti-interference ability and signal-to-noise ratio, and improve analysis accuracy by filtering out frequency components of no interest; in the micro-control unit, signal noise is removed by performing secondary filtering on the high-pass data frame and the low-pass data frame, and the signal difference between the high-pass data frame and the low-pass data frame is further clarified. Based on this, it is possible to better judge whether the touch gesture is a sliding gesture based on the sensor signal.

[0092] Figure 4-2 FIG. 2 is a second structural diagram of the touch gesture recognition device provided by the present invention. Figure 4-2As shown, the touch gesture recognition device includes: a sensor group and a micro-control unit, and the sensor group is electrically connected to the micro-control unit; wherein:

[0093] The sensor group includes a plurality of elastic wave sensors, and the elastic wave sensors perform data collection;

[0094] The micro-control unit obtains the data frame of each elastic wave sensor, performs high-pass filtering on the data frames of a first number of elastic wave sensors to obtain high-pass data frames, and performs low-pass filtering on the data frames of a second number of elastic wave sensors to obtain low-pass data frames; and determines the current phase relationship between the high-pass data frame and the low-pass data frame. When the current phase relationship does not satisfy the preset phase relationship, it is determined to be a non-sliding gesture.

[0095] It should be noted that the processing effect of the filtering circuit at this time can be placed in a micro-control unit (MCU), and after software filtering, the current phase relationship between the high-pass data frame and the low-pass data frame can be calculated and determined. When the current phase relationship does not meet the preset phase relationship, it is determined to be a non-sliding gesture.

[0096] Figure 4-1 or Figure 4-2 The touch gesture recognition method corresponding to the device is as follows:

[0097] Step 1, selecting an initial sensing data value whose absolute value is greater than a preset reference value as an initial data frame selection point, and using the initial data frame selection point as a reference point to select a preset number of initial sensing data for each elastic wave sensor, to obtain a plurality of initial data frames, and subtracting an average value or a preset value of the initial data frame of the corresponding elastic wave sensor from each initial sensing data in each initial data frame, to obtain a plurality of updated data frames as data frames of each elastic wave sensor;

[0098] Step 2, performing high-pass filtering on the data frames of the first number of elastic wave sensors to obtain high-pass data frames, and performing low-pass filtering on the data frames of the second number of elastic wave sensors to obtain low-pass data frames;

[0099] Determine a current phase relationship between the high-pass data frame and the low-pass data frame, and when the current phase relationship does not satisfy a preset phase relationship, determine it as a non-sliding gesture;

[0100] Step 3, when the current phase relationship meets the preset phase relationship,

[0101] Performing amplitude-frequency conversion on the high-pass data frame to obtain the amplitude-frequency characteristic of the high-pass data frame, and determining the energy difference value between the first frequency band energy parameter and the second frequency band energy parameter based on the amplitude-frequency characteristic;

[0102] Determine the difference between the number of data points that meet the preset threshold condition in the high-pass data frame and the number of all data points in the high-pass data frame;

[0103] When the calculated value of the energy difference value and the point difference value is greater than the target value, the touch gesture is still determined to be a non-sliding gesture, otherwise it is a sliding gesture.

[0104] Figure 2 Schematic diagram of the sliding surface of the door handle provided by the present invention, such as Figure 2 As shown, the door handle is equipped with three sensors S1, S2, and S3; optionally, hardware filtering can be used, that is, using Figure 4-1 The device in the embodiment of FIG. 1 is used to set the hardware passband of the post-processing sampling circuit of any two sensors in S1-S3 to 0-20Hz and the other to 0-1kHz; optionally, software filtering can also be used, that is, using Figure 4-2 The device in the embodiment filters the post-processing sampling data of any two sensors in S1-S3, and the filter passband is 0-20 Hz, and the other one is 0-1 kHz; in particular, the hardware and software combined filtering method can also be used to filter the data of any two sensors in S1-S3, and the filter passband is 0-20 Hz, and the other one is 0-1 kHz.

[0105] The touch gesture recognition device provided by the present invention installs multiple sensors at the vehicle door handle and performs differential filtering processing on each sensor respectively, that is, ensuring that high-pass filtering and low-pass filtering exist at the same time, so that the data obtained from each sensor have a certain phase order, and the different phase orders effectively distinguish between sliding gestures (valid touch gestures) and non-sliding gestures (invalid touch gestures), and the door is opened only when it is determined to be a valid sliding gesture. Based on this, other external interference is effectively avoided, accidental opening of the door is avoided, and the reliability of the door opening control is guaranteed.

[0106] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the touch gesture recognition method, which includes: acquiring a data frame of each elastic wave sensor, performing high-pass filtering on the data frames of the first number of elastic wave sensors to obtain high-pass data frames, and performing low-pass filtering on the data frames of the second number of elastic wave sensors to obtain low-pass data frames;

[0107] A current phase relationship between the high-pass data frame and the low-pass data frame is determined, and when the current phase relationship does not satisfy a preset phase relationship, it is determined to be a non-sliding gesture.

[0108] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0109] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can execute the touch gesture recognition method provided by the above methods, the method comprising: acquiring a data frame of each elastic wave sensor, performing high-pass filtering on the data frames of a first number of elastic wave sensors to obtain high-pass data frames, performing low-pass filtering on the data frames of a second number of elastic wave sensors to obtain low-pass data frames;

[0110] A current phase relationship between the high-pass data frame and the low-pass data frame is determined, and when the current phase relationship does not satisfy a preset phase relationship, it is determined to be a non-sliding gesture.

[0111] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for identifying the touch gesture provided above is implemented, the method comprising: acquiring a data frame of each elastic wave sensor, performing high-pass filtering on the data frames of a first number of elastic wave sensors to obtain high-pass data frames, and performing low-pass filtering on the data frames of a second number of elastic wave sensors to obtain low-pass data frames;

[0112] A current phase relationship between the high-pass data frame and the low-pass data frame is determined, and when the current phase relationship does not satisfy a preset phase relationship, it is determined to be a non-sliding gesture.

[0113] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A touch gesture recognition method, characterized in that: include: Acquire a data frame of each elastic wave sensor, perform high-pass filtering on the data frames of the first number of elastic wave sensors to obtain high-pass data frames, and perform low-pass filtering on the data frames of the second number of elastic wave sensors to obtain low-pass data frames; A current phase relationship between the high-pass data frame and the low-pass data frame is determined, and when the current phase relationship does not satisfy a preset phase relationship, it is determined to be a non-sliding gesture.

2. The touch gesture recognition method according to claim 1, characterized in that: The method further includes: when the current phase relationship satisfies a preset phase relationship, Performing amplitude-frequency conversion on the high-pass data frame to obtain an amplitude-frequency characteristic of the high-pass data frame, and determining an energy difference value between a first frequency band energy parameter and a second frequency band energy parameter based on the amplitude-frequency characteristic; Determine a point number difference value between the number of data points in the high-pass data frame that meet a preset threshold condition and the number of all data points in the high-pass data frame; When the calculated value of the energy difference value and the point difference value is greater than the target value, the touch gesture is still determined to be a non-sliding gesture, otherwise it is a sliding gesture.

3. The touch gesture recognition method according to claim 2, characterized in that: The preset threshold condition is: x i ·x i+k ≤thr_b, where x i represents the i-th data point in the high-pass data frame, x i+k It represents the (i+k)th data point in the high-pass data frame, where i and k are both positive integers, and thr_b is the preset threshold.

4. The touch gesture recognition method according to claim 1, characterized in that: The step of acquiring the data frame of each elastic wave sensor comprises: An initial sensing data value whose absolute value is greater than a preset reference value is selected as an initial data frame selection point, and a preset number of initial sensing data are selected for each elastic wave sensor using the initial data frame selection point as a reference point to obtain multiple initial data frames, and an average value or a preset value of the initial data frame of the corresponding elastic wave sensor is subtracted from each of the initial sensing data in each of the initial data frames to obtain multiple updated data frames as the data frames of each elastic wave sensor.

5. The touch gesture recognition method according to claim 1, characterized in that: The filter passband when high-pass filtering is performed on the data frame is 0-1 kHz, and the filter passband when low-pass filtering is performed on the data frame is 0-20 Hz.

6. A touch gesture recognition device, characterized in that: include: A sensor group, a filter circuit, and a micro-control unit; wherein: The sensor group is electrically connected to the filter circuit, and the sensor group includes a plurality of elastic wave sensors; The filter circuit is also electrically connected to the micro-control unit, and includes a high-pass filter circuit and a low-pass filter circuit; At least one of the elastic wave sensors is electrically connected to the high-pass filter circuit, and at least one of the elastic wave sensors is electrically connected to the low-pass filter circuit; The high-pass filter circuit performs high-pass filtering on the data frame of the electrically connected elastic wave sensor to obtain a high-pass data frame; The low-pass filter circuit performs low-pass filtering on the data frame of the electrically connected elastic wave sensor to obtain a low-pass data frame; The micro-control unit determines a current phase relationship between the high-pass data frame and the low-pass data frame, and when the current phase relationship does not satisfy a preset phase relationship, determines it as a non-sliding gesture.

7. The touch gesture recognition device according to claim 6, characterized in that: Before determining the current phase relationship between the high-pass data frame and the low-pass data frame, the micro-control unit also performs secondary filtering on the high-pass data frame with the same or lower passband as the high-pass filter circuit, and performs secondary filtering on the low-pass data frame with the same or lower passband as the low-pass filter circuit.

8. A touch gesture recognition device, characterized in that: include: A sensor group and a micro-control unit, wherein the sensor group is electrically connected to the micro-control unit; wherein: The sensor group includes a plurality of elastic wave sensors, and the elastic wave sensors perform data collection; The micro-control unit obtains the data frame of each elastic wave sensor, performs high-pass filtering on the data frames of a first number of elastic wave sensors to obtain high-pass data frames, and performs low-pass filtering on the data frames of a second number of elastic wave sensors to obtain low-pass data frames; and determines the current phase relationship between the high-pass data frame and the low-pass data frame. When the current phase relationship does not satisfy the preset phase relationship, it is determined to be a non-sliding gesture.

9. A non-transitory computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the touch gesture recognition method as described in any one of claims 1 to 5 are implemented.

10. A computer program product, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the touch gesture recognition method as described in any one of claims 1 to 5 are implemented.

Images