Target perception method and related apparatus
By processing a two-dimensional array of multiple frames of CSI data, calculating the subcarrier fluctuation difference and combining it with denoising processing, the problem of existing CSI amplitude signals being susceptible to interference is solved, and more accurate target perception is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- MIDEA GRP (SHANGHAI) CO LTD
- Filing Date
- 2026-02-25
- Publication Date
- 2026-05-29
AI Technical Summary
Existing target perception algorithms based on CSI amplitude signals are easily affected by environmental interference, resulting in a high misjudgment rate and weak universality.
By acquiring and processing multiple frames of CSI data to form a two-dimensional array, the difference between the maximum and minimum values of the subcarrier is calculated to construct a fluctuation data group. The difference between the fluctuation data groups of two time periods is used to determine whether there are moving objects in the target area. Combined with denoising processing, the influence of the environment and interference signals is reduced.
It improves the accuracy of target perception, reduces the impact of environmental and interference signals on perception results, and enhances the ability to identify moving objects.
Smart Images
Figure CN122109987A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of motion sensing, and in particular to a target sensing method and related apparatus. Background Technology
[0002] Algorithms for environmental perception based on CSI (Channel State Information) amplitude signals primarily rely on statistical or similarity measures such as variance, range, or cosine similarity to detect object movement. The core idea of these methods is to capture and compare the fluctuation characteristics of CSI signals under different environments: in a stationary state with no one around, the CSI amplitude typically remains relatively stable; however, when objects are moving, their reflection, scattering, and obstruction of the wireless signal cause significant fluctuations in the signal amplitude. However, in reality, amplitude is easily affected by interference, and the set judgment threshold can change due to environmental factors. Therefore, the algorithms based on fluctuation amplitude and judgment thresholds have certain limitations and suffer from a high false positive rate. Summary of the Invention
[0003] The main objective of this application is to provide a target perception method and related apparatus that can reduce the false judgment rate and improve perception performance.
[0004] In a first aspect, this application provides a target perception method, the method comprising: acquiring a first preset number of frame data, and forming a first two-dimensional array based on the first preset number of frame data; wherein each frame data includes a plurality of subcarriers; wherein the first preset number is greater than one; determining a first fluctuation data group based on the plurality of subcarriers in the column direction of the first two-dimensional array; acquiring a second preset number of frame data, and forming a second two-dimensional array based on the second preset number of frame data; wherein the second preset number is equal to the first preset number, and the acquisition time of at least one frame data in the second preset number of frame data is later than the acquisition time of all frame data in the first preset number of frame data; determining a second fluctuation data group based on the plurality of subcarriers in the column direction of the second two-dimensional array; determining a target data group based on the second fluctuation data group and the first fluctuation data group; acquiring the number of elements in the target data group that meet preset conditions; and determining whether there is a moving object in the region corresponding to the frame data based on the number of elements.
[0005] The first fluctuation data group is determined based on several subcarriers in the column direction of the first two-dimensional array, including: obtaining the maximum and minimum values of several subcarriers in each column of the first two-dimensional array; determining the fluctuation value corresponding to each column based on the maximum and minimum values in each column; and determining the first fluctuation data group based on the fluctuation value corresponding to each column.
[0006] The process of determining the fluctuation value corresponding to each column based on the maximum and minimum values in each column includes: taking the difference between the maximum and minimum values corresponding to each column to obtain the difference value; and using the difference value as the fluctuation value.
[0007] The process of determining the target data group based on the second fluctuation data group and the first fluctuation data group includes: subtracting the corresponding element from the first fluctuation data group from the element in the second fluctuation data group to obtain the element difference; and constructing the target data group using several element differences.
[0008] Among them, obtaining the number of elements in the target data group that meet the preset conditions includes: obtaining the number of elements in the target data group whose element values are greater than a first preset threshold.
[0009] The preset threshold is updated in the following way: in response to the absence of moving objects and the difference between the first average value of all elements in the target data group and the second average value of all elements in the new target data group is less than the preset fluctuation value, the preset threshold is updated based on the preset percentage, the average value of the first average value and the average value of the second average value; the new target data group is obtained based on the processing of new frame data, and at least some of the new frame data is acquired later than the acquisition time of the latest frame data in the second fluctuation data group.
[0010] The preset fluctuation value is obtained based on a preset percentage and a first average value.
[0011] Before determining the first wave data group based on several subcarriers in the column direction of the first two-dimensional array, the method further includes: denoising the first two-dimensional array.
[0012] The denoising process includes a first denoising process, which includes: determining the corresponding target filtering element from the first two-dimensional array; determining the target row based on the target filtering element; and deleting the frame data corresponding to the target row in the first two-dimensional array.
[0013] The denoising process also includes a second denoising process, which includes performing two-dimensional filtering on the two-dimensional array after deleting the frame data corresponding to the target row in the first two-dimensional array.
[0014] Secondly, this application provides an electronic device. The electronic device includes a memory and a processor, the memory storing a computer program that can be executed by the processor to implement the method provided in the first aspect.
[0015] Thirdly, this application provides a computer-readable storage medium. This computer-readable storage medium stores a computer program that can be executed by a processor to implement the method provided in the first aspect.
[0016] Fourthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, is used to implement the method as provided in the first aspect.
[0017] Fifthly, this application provides an air conditioner. The air conditioner includes a memory and a processor, the memory storing a computer program that can be executed by the processor to implement the method provided in the first aspect.
[0018] The beneficial effects of this application are as follows: A first preset number of frame data is acquired, and a first two-dimensional array is formed based on the first preset number of frame data; wherein each frame data includes several subcarriers; wherein the first preset number is greater than one; and a first fluctuation data group capable of characterizing the subcarrier fluctuations in the first preset number of frame data is determined based on several subcarriers in the column direction of the first two-dimensional array; and a second preset number of frame data is acquired, and a second two-dimensional array is formed based on the second preset number of frame data; wherein the second preset number is equal to the first preset number, and the acquisition time of at least one frame data in the second preset number of frame data is later than the acquisition time of all frame data in the first preset number of frame data; a second fluctuation data group capable of characterizing the subcarrier fluctuations in the second preset number of frame data is determined based on several subcarriers in the column direction of the second two-dimensional array; and a target data group is determined based on the second fluctuation data group and the first fluctuation data group; the number of elements in the target data group that meet preset conditions is acquired; and the presence of moving objects in the region corresponding to the frame data is determined based on the number of elements. Since the presence of moving objects in the region corresponding to the frame data is determined by judging the fluctuation or degree of fluctuation between subcarriers of two correlated two-dimensional arrays, the influence of environmental or interference signals on the subcarriers can be reduced, thereby improving the accuracy of sensing moving objects. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 This is a flowchart illustrating an embodiment of the target perception method provided in this application; Figure 2 yes Figure 1 A flowchart illustrating an embodiment of step 12; Figure 3 yes Figure 1 A flowchart of an embodiment of step 15; Figure 4This is a flowchart illustrating another embodiment of the target perception method provided in this application; Figure 5 This is a flowchart illustrating an embodiment of the electronic device of this application; Figure 6 This is a flowchart illustrating an embodiment of the computer-readable medium of this application; Figure 7 This is a schematic diagram of the structure of an embodiment of the computer program product of this application; Figure 8 This is a schematic diagram of the structure of an embodiment of the air conditioner of this application. Detailed Implementation
[0020] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.
[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.
[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0023] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.
[0024] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.
[0025] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).
[0026] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.
[0027] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.
[0028] In typical CSI sensing algorithms, taking the method of calculating the amplitude range as an example, a set of subcarrier signals is selected, including multiple signals, each signal comprising multiple frames of subcarriers. These multiple signals are treated as multiple sensing data groups, each containing multiple sensing data acquired sequentially over time, corresponding to multiple frames of subcarriers. The differences between the maxima and minima of these sensing data are calculated according to the time series, resulting in a one-dimensional array containing multiple differences, the number of differences corresponding to the number of signals. As time progresses, new subcarriers are acquired, updating the original subcarrier signal group to obtain a new set of subcarrier signals. The same processing is then applied to this new set of subcarrier signals to obtain another one-dimensional array.
[0029] The absolute values of the differences between two one-dimensional arrays at corresponding positions are taken to obtain multiple difference values. These multiple differences are then summed and averaged to obtain the perceived change. This perceived change is compared with a preset judgment threshold to determine whether there is motion in the current environment.
[0030] The limitations of the above methods are that the judgment threshold is based on certain experience and environment, resulting in low universality, and the amplitude of the carrier signal is easily affected by external factors, which can easily influence the judgment result. Based on the above considerations, this application provides a target perception method. It can be implemented using the methods described in the following embodiments.
[0031] In some embodiments, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating the first embodiment of the target perception method provided in this application.
[0032] Step 11: Obtain a first preset number of frame data, and form a first two-dimensional array based on the first preset number of frame data.
[0033] Each frame of data includes several subcarriers. The first preset number is greater than one.
[0034] In some embodiments, the two-dimensional array is arranged in rows and columns. Each row in the two-dimensional array represents a frame of data. The columns are arranged according to the order in which the frames of data were acquired. The earlier the frame of data appears in the column, the earlier it was acquired. It can be understood that the sensing device can continuously acquire frame data according to the corresponding sampling period, thereby forming a two-dimensional array.
[0035] Each frame of data is acquired by a sensing device, and each frame of data includes several subcarriers acquired in chronological order.
[0036] Each time a sensing device acquires frame data, it can acquire several subcarriers. These subcarriers are obtained based on signals that are directly or reflected onto the sensing device.
[0037] The first preset quantity corresponds to the acquired frame data, that is, the number of frame data included in each two-dimensional array. The first preset quantity will also serve as the window length for updating subsequent frame data.
[0038] In some embodiments, to ensure the accuracy of perception, the first preset number is typically an integer greater than three. For example, the first preset number can be 5, 10, 15, etc.
[0039] In some embodiments, it is assumed that there are multiple frames of data A1, A2, A3, A4, and A5.
[0040] A1: 45, 67, 89, 23, 12, 56, 78, 90, 34, 21.
[0041] A2: 11, 22, 33, 44, 55, 66, 77, 88, 99, 10.
[0042] A3: 12, 34, 56, 78, 90, 11, 22, 33, 44, 55.
[0043] A4: 67, 89, 12, 34, 56, 78, 90, 11, 22, 33.
[0044] A5: 44, 55, 66, 77, 88, 99, 10, 12, 34, 56.
[0045] Two-dimensional arrays can be formed by arranging rows and columns as shown above.
[0046] Step 12: Determine the first wave data group based on several subcarriers in the column direction of the first two-dimensional array.
[0047] In some embodiments, see Figure 2 Step 12 can be the following process: Step 121: Obtain the maximum and minimum values of several subcarriers in each column of the first two-dimensional array.
[0048] In some embodiments, since the first preset quantity is greater than one, each column of the first two-dimensional array has at least two subcarriers. Each subcarrier can be converted into amplitude form and used as an element in the two-dimensional array, thus obtaining the maximum and minimum values among several subcarriers in each column of the first two-dimensional array.
[0049] Step 122: Determine the fluctuation value corresponding to each column based on the maximum and minimum values in each column.
[0050] In some embodiments, the difference between the maximum and minimum values corresponding to each column is obtained; the difference is used as the fluctuation value corresponding to each column.
[0051] Step 123: Determine the first fluctuation data group based on the fluctuation value corresponding to each column.
[0052] In some embodiments, since the two-dimensional array has multiple columns, multiple fluctuation values can be obtained through the above method. Based on this, the fluctuation values can be filled into the one-dimensional array in column order to obtain the first fluctuation data group.
[0053] For example, the first two-dimensional array is as follows: 45, 67, 89, 23, 12, 56, 78, 90, 34, 21.
[0054] 11, 22, 33, 44, 55, 66, 77, 88, 99, 10.
[0055] 12, 34, 56, 78, 90, 11, 22, 33, 44, 55.
[0056] 67, 89, 12, 34, 56, 78, 90, 11, 22, 33.
[0057] 44, 55, 66, 77, 88, 99, 10, 12, 34, 56.
[0058] The data in the first column (subcarrier) is processed to obtain a fluctuation value of 56 (67-11). The data in the second column is processed to obtain a fluctuation value of 67 (89-22). The remaining columns of data are processed in the same way. Finally, the first fluctuation data group is obtained: 56, 67, 77, 55, 78, 88, 80, 79, 77, 46.
[0059] Step 13: Obtain a second preset number of frame data, and form a second two-dimensional array based on the second preset number of frame data.
[0060] Wherein, the second preset quantity is equal to the first preset quantity, and the acquisition time of at least one frame of data in the second preset quantity of frame data is later than the acquisition time of all frame data in the first preset quantity of frame data.
[0061] For example, if the first two-dimensional array consists of 1-10 frames of data, then the second two-dimensional array consists of 2-11 frames of data.
[0062] For example, if the first two-dimensional array consists of 1-10 frames of data, then the second two-dimensional array consists of 3-12 frames of data.
[0063] For example, if the first two-dimensional array consists of 1-10 frames of data, then the second two-dimensional array consists of 5-14 frames of data.
[0064] The second two-dimensional array is constructed in the same way as the first two-dimensional array, and will not be described in detail here.
[0065] Step 14: Determine the second wave data group based on several subcarriers in the column direction of the second two-dimensional array.
[0066] In some embodiments, the maxima and minima of several subcarriers in each column of the second two-dimensional array are obtained. The fluctuation value corresponding to each column is determined based on the maxima and minima in each column. For example, the difference between the maxima and minima corresponding to each column is calculated to obtain the difference; this difference is used as the fluctuation value corresponding to each column. A second fluctuation data set is determined based on the fluctuation values corresponding to each column.
[0067] In some embodiments, since the two-dimensional array has multiple columns, multiple fluctuation values can be obtained through the above method. Based on this, the fluctuation values can be filled into the one-dimensional array according to the column order to obtain the second fluctuation data group.
[0068] Step 15: Determine the target data set based on the second fluctuation data set and the first fluctuation data set.
[0069] In some embodiments, see Figure 3 Step 15 can be the following process: Step 151: Subtract the corresponding element from the first fluctuation data group from the element in the second fluctuation data group to obtain the element difference.
[0070] Since the second and first wave data groups have the same number of elements as the number of subcarriers, and both are determined by the subcarriers in the column direction of the relevant two-dimensional array, the element difference can be obtained by subtracting the corresponding element in the first wave data group from the element in the second wave data group. For example, if the second wave data group is a1, a2, a3, a4, a5, and the first wave data group is b1, b2, b3, b4, b5, then we can use a1-b1=c1, a2-b2=c2, a3-b3=c3, a4-b4=c4, and a5-b5=c5. In some embodiments, we can use |a1-b1|=c1, |a2-b2|=c2, |a3-b3|=c3, |a4-b4|=c4, and |a5-b5|=c5.
[0071] Step 152: Construct the target data set using the differences between several elements.
[0072] In some embodiments, a target data group is constructed based on c1, c2, c3, c4, and c5 as described above. For example, the target data group is c1, c2, c3, c4, and c5.
[0073] Step 16: Obtain the number of elements in the target data group that meet the preset conditions.
[0074] In some embodiments, the preset condition is greater than a preset threshold. In some embodiments, the preset condition is less than or equal to a preset threshold.
[0075] In some embodiments, the number of elements in the target data group whose element values are greater than a first preset threshold is obtained.
[0076] In some embodiments, the number of elements in the target data group whose element values are less than or equal to a first preset threshold is obtained.
[0077] Step 17: Determine whether there are moving objects in the region corresponding to the frame data based on the number of elements.
[0078] In some embodiments, when the number of elements is the number of elements in the target data group whose element values are greater than a first preset threshold, if the number of elements is greater than a second preset threshold, or the proportion of the number of elements in the target data group is greater than a preset proportion, then it is considered that there are many data points with large fluctuations in the frame data, and it is determined that there are moving objects in the region corresponding to the frame data. If the number of elements is less than or equal to the second preset threshold, or the proportion of the number of elements in the target data group is less than or equal to a preset proportion, then it is considered that there are few data points with large fluctuations in the frame data, and it is determined that there are no moving objects in the region corresponding to the frame data.
[0079] In some embodiments, when the number of elements is the number of elements in the target data group whose values are less than or equal to a first preset threshold, if the number of elements is greater than a second preset threshold, or the proportion of the number of elements in the target data group is greater than a preset proportion, then it is considered that there are few data points with large fluctuations in the frame data, and it is determined that there are no moving objects in the region corresponding to the frame data. If the number of elements is less than or equal to the second preset threshold, or the proportion of the number of elements in the target data group is less than or equal to a preset proportion, then it is considered that there are many data points with large fluctuations in the frame data, and it is determined that there are moving objects in the region corresponding to the frame data.
[0080] In this embodiment, it is considered that when there are no moving objects in the sensing environment, the fluctuation or change amplitude of the acquired subcarriers is similar. However, when there are moving objects in the sensing environment, the fluctuation of the acquired subcarriers is not necessarily consistent. Moving objects move over time and may only affect a portion of the frame data (subcarriers). Therefore, if there is a large fluctuation in the fluctuation, it is determined that there is a moving object; if the fluctuation is not significant, it is determined that there is no moving object. The judgment based on fluctuation is not affected by environmental or interference signals and remains at a constant level.
[0081] In this embodiment, a first preset number of frame data is acquired, and a first two-dimensional array is formed based on the first preset number of frame data; wherein each frame data includes several subcarriers; the first preset number is greater than one; and a first fluctuation data group capable of characterizing the subcarrier fluctuation in the first preset number of frame data is determined based on several subcarriers in the column direction of the first two-dimensional array; and a second preset number of frame data is acquired, and a second two-dimensional array is formed based on the second preset number of frame data; wherein the second preset number is equal to the first preset number, and the acquisition time of at least one frame data in the second preset number of frame data is later than the acquisition time of all frame data in the first preset number of frame data; a second fluctuation data group capable of characterizing the subcarrier fluctuation in the second preset number of frame data is determined based on several subcarriers in the column direction of the second two-dimensional array; and a target data group is determined based on the second fluctuation data group and the first fluctuation data group; the number of elements in the target data group that meet preset conditions is acquired; and the presence of moving objects in the region corresponding to the frame data is determined based on the number of elements. Since the presence of moving objects in the region corresponding to the frame data is determined by judging the fluctuation or degree of fluctuation between subcarriers of two correlated two-dimensional arrays, the influence of environmental or interference signals on the subcarriers can be reduced, thereby improving the accuracy of sensing moving objects.
[0082] In some embodiments, since frame data is continuously acquired, the motion object can be determined by continuously analyzing the frame data within adjacent sliding windows in the manner described above using a sliding window approach.
[0083] In some embodiments, such as Figure 4 As shown, Figure 4 This is a flowchart illustrating the second embodiment of the target perception method provided in this application.
[0084] Step 41: Obtain a first preset number of frame data, and form a first two-dimensional array based on the first preset number of frame data.
[0085] Each frame of data includes several subcarriers. The first preset number is greater than one.
[0086] In some embodiments, the two-dimensional array is arranged in rows and columns. Each row in the two-dimensional array represents a frame of data. The columns are arranged according to the order in which the frames of data were acquired. The earlier the frame of data appears in the column, the earlier it was acquired. It can be understood that the sensing device can continuously acquire frame data according to the corresponding sampling period, thereby forming a two-dimensional array.
[0087] Each frame of data is acquired by a sensing device, and each frame of data includes several subcarriers acquired in chronological order.
[0088] Each time a sensing device acquires frame data, it can acquire several subcarriers. These subcarriers are obtained based on signals that are directly or reflected onto the sensing device.
[0089] The first preset quantity corresponds to the acquired frame data, that is, the number of frame data included in each two-dimensional array. The first preset quantity will also serve as the window length for updating subsequent frame data.
[0090] In some embodiments, to ensure the accuracy of perception, the first preset number is typically an integer greater than three. For example, the first preset number can be 5, 10, 15, etc.
[0091] In some embodiments, it is assumed that there are multiple frames of data A1, A2, A3, A4, and A5.
[0092] A1: 45, 67, 89, 23, 12, 56, 78, 90, 34, 21.
[0093] A2: 11, 22, 33, 44, 55, 66, 77, 88, 99, 10.
[0094] A3: 12, 34, 56, 78, 90, 11, 22, 33, 44, 55.
[0095] A4: 67, 89, 12, 34, 56, 78, 90, 11, 22, 33.
[0096] A5: 44, 55, 66, 77, 88, 99, 10, 12, 34, 56.
[0097] Two-dimensional arrays can be formed by arranging rows and columns as shown above.
[0098] Step 42: Denoise the first two-dimensional array.
[0099] To ensure the accuracy of the sensing results, the two-dimensional array is denoised before processing and sensing, removing abnormal and noisy data.
[0100] In some embodiments, the denoising process includes a first denoising process. Step 42 may be the following process: Step 421: Determine the corresponding target filtering element from the first two-dimensional array.
[0101] In some embodiments, the standard deviation of several subcarriers in each column of the first two-dimensional array is calculated. Subcarriers in each column that are greater than the standard deviation of that column are selected as target filtering elements.
[0102] Step 422: Determine the target row based on the target filter elements.
[0103] Step 423: Delete the frame data corresponding to the target row in the first two-dimensional array.
[0104] Since each row in the two-dimensional array represents a frame of data, after determining the target row based on the target filtering element, the frame data corresponding to the target row in the first two-dimensional array is directly deleted. That is, the frame data of the row containing the target filtering element is deleted.
[0105] For example, the following two-dimensional array is used as an example for illustration: A1: 45, 67, 89, 23, 12, 56, 78, 90, 34, 21.
[0106] A2: 11, 22, 33, 44, 55, 66, 77, 88, 99, 10.
[0107] A3: 12, 34, 56, 78, 90, 11, 22, 33, 44, 55.
[0108] A4: 67, 89, 12, 34, 56, 78, 90, 11, 22, 33.
[0109] A5: 44, 55, 66, 77, 88, 99, 10, 12, 34, 56.
[0110] Here, A1, A2, A3, A4, and A5 represent the sequence numbers of the frame data. The standard deviation for each column of subcarriers is calculated. Subcarriers in the corresponding column that are greater than the standard deviation are selected (target selection elements). This yields 89 in the second column and 99 in the sixth column as target selection elements. Therefore, before processing and sensing the two-dimensional array, the frame data corresponding to A4 (89) and A5 (99) are deleted.
[0111] In some embodiments, the denoising process further includes a second denoising process. The above method also includes performing two-dimensional filtering on the two-dimensional array after deleting the frame data corresponding to the target row in the first two-dimensional array.
[0112] Two-dimensional filtering can include median filtering, mean filtering, Hampelle filtering, Wiener filtering, and so on. For example, filtering a two-dimensional array by row and column separately can reduce noise in the final data used for judgment.
[0113] Step 43: Determine the first wave data group based on several subcarriers in the column direction of the first two-dimensional array.
[0114] Step 44: Obtain a second preset number of frame data, and form a second two-dimensional array based on the second preset number of frame data.
[0115] Wherein, the second preset quantity is equal to the first preset quantity, and the acquisition time of at least one frame of data in the second preset quantity of frame data is later than the acquisition time of all frame data in the first preset quantity of frame data.
[0116] In some embodiments, steps 43 to 44 have the same or similar technical solutions as other embodiments of this application.
[0117] Step 45: Denoise the second two-dimensional array.
[0118] In some embodiments, the denoising process includes a first denoising process. Step 45 may be the following process: Step 451: Determine the corresponding target filtering element from the second two-dimensional array.
[0119] Step 452: Determine the target row based on the target filter elements.
[0120] Step 453: Delete the frame data corresponding to the target row in the second two-dimensional array.
[0121] In some embodiments, the denoising process further includes a second denoising process. The above method also includes performing two-dimensional filtering on the two-dimensional array after deleting the frame data corresponding to the target row in the second two-dimensional array.
[0122] For the first and second denoising processes on the second two-dimensional array, please refer to the above description of the first and second denoising processes on the first two-dimensional array, which will not be repeated here.
[0123] Step 46: Determine the second wave data group based on several subcarriers in the column direction of the second two-dimensional array.
[0124] Step 47: Determine the target data set based on the second fluctuation data set and the first fluctuation data set.
[0125] Step 48: Obtain the number of elements in the target data group that meet the preset conditions.
[0126] In some embodiments, the preset condition is greater than a preset threshold. In some embodiments, the preset condition is less than or equal to a preset threshold.
[0127] Step 49: Determine whether there are moving objects in the region corresponding to the frame data based on the number of elements.
[0128] In some embodiments, steps 46 to 49 have the same or similar technical solutions as other embodiments of this application.
[0129] In some embodiments, the preset threshold in the above embodiments is updated by the following method: In response to the absence of a moving object and the difference between the first average value of all elements in the target data group and the second average value of all elements in the new target data group being less than a preset fluctuation value, update the preset threshold based on the average value of the preset percentage, the first average value, and the second average value; The new target data group is obtained by processing new frame data, and the acquisition time of at least part of the new frame data is later than the acquisition time of the latest acquired frame data in the second fluctuation data group.
[0130] The preset fluctuation value is obtained based on the preset percentage and the first average value.
[0131] Exemplarily, taking the preset percentage M% as an example. When the condition |mean(B1)-mean(B2)|<X is satisfied, the preset threshold can be updated. B1 is the target data group, B2 is the new target data group. X is the preset threshold. mean(B1) is the first average value of all elements in the target data group, and mean(B2) is the second average value of all elements in the new target data group. Exemplarily, X = M% B1. The updated preset threshold F = (mean(B1)+mean(B2)) / 2 M%.
[0132] In the above embodiment, the first fluctuation data group is the extreme value difference of the subcarriers in each column of the first two-dimensional array, which characterizes the fluctuation of multiple frames of data. The second fluctuation data group is the extreme value difference of the subcarriers in each column of the second two-dimensional array, which characterizes the fluctuation of another multiple frames of data. The target data group is obtained by subtracting the first fluctuation data group from the second fluctuation data group, which reduces the global difference benchmark of the fluctuation amplitude but does not change its essential meaning, and it still characterizes the fluctuation of multiple frames of data.
[0133] Refer to Figure 5 , Figure 5 which is a schematic structural diagram of an embodiment of the electronic device of the present application.
[0134] The electronic device includes a processor 110 and a memory 120.
[0135] The processor 110 controls the operation of the electronic device. The processor 110 can also be referred to as a CPU (Central Processing Unit, central processing unit). The processor 110 may be an integrated circuit chip with the ability to process signal sequences. The processor 110 can also be a general-purpose processor, a digital signal sequence processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
[0136] The memory 120 stores the instructions and computer programs required for the processor 110 to operate.
[0137] The processor 110 is used to execute instructions to implement the methods provided by any embodiment and possible combination of the target perception methods described above in this application.
[0138] See Figure 6 , Figure 6 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium of this application.
[0139] One embodiment of the readable storage medium of this application includes a memory 210 storing a computer program that, when executed, implements the method provided in any embodiment and possible combination of the target perception method of this application.
[0140] The memory 210 may include a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or other media that can store program instructions. Alternatively, it may be a server that stores the program instructions, which can send the stored program instructions to other devices for execution or execute the stored program instructions itself.
[0141] See Figure 7 , Figure 7 This is a schematic diagram of the structure of an embodiment of the computer program product of this application.
[0142] The computer program product 310 of this application includes a computer program that, when executed, implements the method provided by any of the embodiments and possible combinations thereof in the above embodiments of the target perception method of this application.
[0143] Computer program product 310 may include media capable of storing program instructions, such as USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, or a server storing the program instructions. The server may send the stored program instructions to other devices for execution, or it may execute the stored program instructions itself.
[0144] See Figure 8 , Figure 8 This is a schematic diagram of the structure of an embodiment of the air conditioner of this application.
[0145] The air conditioner includes a processor 410 and a memory 420.
[0146] Processor 410 controls the operation of electronic devices. Processor 410 can also be referred to as a CPU (Central Processing Unit). Processor 410 may be an integrated circuit chip with signal sequence processing capabilities. Processor 410 can also be a general-purpose processor, a digital signal sequence processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.
[0147] The memory 420 stores the instructions and computer programs required for the processor 410 to operate.
[0148] The processor 410 is used to execute instructions to implement the method provided by any of the embodiments and possible combinations thereof in the above embodiments of the target perception method of this application.
[0149] When the air conditioner detects a moving object based on the aforementioned target perception method, it can perform corresponding control operations based on the detection result, such as power on / off, power control, etc.
[0150] In summary, the process involves: acquiring a first preset number of frame data and forming a first two-dimensional array based on the first preset number of frame data; wherein each frame data includes several subcarriers; wherein the first preset number is greater than one; and determining a first fluctuation data group that can characterize the subcarrier fluctuations in the first preset number of frame data based on several subcarriers in the column direction of the first two-dimensional array; acquiring a second preset number of frame data and forming a second two-dimensional array based on the second preset number of frame data; wherein the second preset number is equal to the first preset number, and the acquisition time of at least one frame data in the second preset number of frame data is later than the acquisition time of all frame data in the first preset number of frame data; determining a second fluctuation data group that can characterize the subcarrier fluctuations in the second preset number of frame data based on several subcarriers in the column direction of the second two-dimensional array; determining a target data group based on the second fluctuation data group and the first fluctuation data group; acquiring the number of elements in the target data group that meet preset conditions; and determining whether there is a moving object in the region corresponding to the frame data based on the number of elements. Since the presence of moving objects in the region corresponding to the frame data is determined by judging the fluctuation or degree of fluctuation between subcarriers of two correlated two-dimensional arrays, the influence of environmental or interference signals on the subcarriers can be reduced, thereby improving the accuracy of sensing moving objects.
[0151] Furthermore, denoising the first two-dimensional array and / or the second two-dimensional array can effectively eliminate abnormal subcarriers and reduce subcarrier noise.
[0152] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
[0153] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0154] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0155] If the integrated units in the other embodiments described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0156] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.
Claims
1. A target perception method, characterized in that, The method includes: A first preset number of frame data is acquired, and a first two-dimensional array is formed based on the first preset number of frame data; wherein each frame data includes several subcarriers; wherein the first preset number is greater than one; The first wave data group is determined based on several subcarriers in the column direction of the first two-dimensional array; Acquire a second preset number of frame data, and form a second two-dimensional array based on the second preset number of frame data; wherein, the second preset number is equal to the first preset number, and the acquisition time of at least one frame data in the second preset number of frame data is later than the acquisition time of all frame data in the first preset number of frame data; The second wave data group is determined based on several subcarriers in the column direction of the second two-dimensional array; The target data group is determined based on the second fluctuation data group and the first fluctuation data group; Obtain the number of elements in the target data group that meet the preset conditions; Based on the number of elements, determine whether there is a moving object in the region corresponding to the frame data.
2. The target perception method according to claim 1, characterized in that, The determination of the first fluctuation data group based on several subcarriers in the column direction of the first two-dimensional array includes: Obtain the maximum and minimum values of several subcarriers in each column of the first two-dimensional array; The fluctuation value corresponding to each column is determined based on the maximum and minimum values in each column; The first fluctuation data group is determined based on the fluctuation value corresponding to each column.
3. The target perception method according to claim 2, characterized in that, The determination of the fluctuation value corresponding to each column based on the maximum and minimum values in each column includes: The difference is obtained by subtracting the maximum and minimum values corresponding to each column; The difference is taken as the fluctuation value.
4. The target perception method according to claim 1, characterized in that, The step of determining the target data group based on the second fluctuation data group and the first fluctuation data group includes: The element difference is obtained by subtracting the element corresponding to the position in the first fluctuation data group from the element in the second fluctuation data group. The target data set is constructed using the differences between several of the elements.
5. The target perception method according to claim 1, characterized in that, The step of obtaining the number of elements in the target data group that meet the preset conditions includes: Obtain the number of elements in the target data group whose element values are greater than a first preset threshold.
6. The target perception method according to claim 5, characterized in that, The preset threshold is updated using the following method: In response to the absence of moving objects and the difference between the first average value of all elements in the target data group and the second average value of all elements in the new target data group being less than a preset fluctuation value, the preset threshold will be updated based on the preset percentage, the average value of the first average value and the average value of the second average value. The new target data set is obtained based on the new frame data, and at least a portion of the new frame data is acquired later than the acquisition time of the latest frame data in the second fluctuation data set.
7. The target perception method according to claim 6, characterized in that, The preset fluctuation value is obtained based on the preset percentage and the first average value.
8. The target perception method according to claim 1, characterized in that, Before determining the first wave data group based on several subcarriers in the column direction of the first two-dimensional array, the method further includes: The first two-dimensional array is then denoised.
9. The target perception method according to claim 8, characterized in that, The noise reduction process includes a first noise reduction process, which includes: Determine the corresponding target filtering element from the first two-dimensional array; The target row is determined based on the target filtering elements; Delete the frame data corresponding to the target row in the first two-dimensional array.
10. The target perception method according to claim 9, characterized in that, The noise reduction process further includes a second noise reduction process, which includes: Two-dimensional filtering is performed on the two-dimensional array after deleting the frame data corresponding to the target row in the first two-dimensional array.
11. An electronic device, characterized in that, It includes a memory and a processor, the memory being used to store a computer program that can be executed by the processor to implement the method as described in any one of claims 1-10.
12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-10.
13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, is used to implement the method as described in any one of claims 1-10.
14. An air conditioner, characterized in that, The air conditioner includes a memory and a processor, the memory being used to store a computer program that can be executed by the processor to implement the method as described in any one of claims 1-10.