阅读说明：本技术 雷达数据的处理方法、处理系统以及计算机存储介质 (Radar data processing method, processing system and computer storage medium ) 是由 何伟 于 2021-01-11 设计创作，主要内容包括：本申请提供了一种雷达数据的处理方法、处理系统以及计算机存储介质。该处理方法包括：获取采集的雷达原始数据,该原始数据是对触摸区域的触摸事件所产生的；使用透视变换矩阵进行映射得到雷达矫正数据；对雷达矫正数据进行标准化处理得到雷达标准化数据；将雷达标准化数据进行聚类处理得到封装数据；将封装数据传输到应用系统,以便应用系统将其作为应用的输入事件。可见,本申请能够使用透视变换矩阵高效地对雷达原始数据进行矫正,通过标准化避免在后续的应用系统出现过多的冗余数据,并且通过聚类封装使传输到应用系统的数据为封装后的单一屏幕的触摸映射事件,从而本申请中传输至应用系统的封装数据能够更加准确地反映出触摸事件。(The application provides a radar data processing method, a radar data processing system and a computer storage medium. The processing method comprises the following steps: acquiring acquired radar raw data, wherein the raw data is generated by a touch event of a touch area; mapping by using a perspective transformation matrix to obtain radar correction data; standardizing the radar correction data to obtain radar standardized data; clustering radar standardized data to obtain encapsulated data; the encapsulated data is transmitted to the application system for the application system to use as input events for the application. Therefore, the radar original data can be efficiently corrected by using the perspective transformation matrix, excessive redundant data in a subsequent application system can be avoided through standardization, the data transmitted to the application system is a touch mapping event of a single encapsulated screen through clustering encapsulation, and therefore the encapsulated data transmitted to the application system can reflect the touch event more accurately.)

1. A method for processing radar data, comprising:

acquiring acquired radar raw data, wherein the raw data is generated by a touch event of a touch area;

mapping the radar original data by using the determined perspective transformation matrix to obtain radar correction data;

standardizing the radar correction data to obtain radar standardized data;

clustering the radar standardized data to obtain packaged data;

and transmitting the encapsulated data to an application system so that the application system can use the encapsulated data as an input event of the application.

2. The processing method according to claim 1, wherein the number of radars is 1, and the perspective transformation matrix is obtained by:

obtaining a translation estimation matrix and a rotation estimation matrix through maximum likelihood estimation based on the actual point coordinates of the touch area and the radar scanning coordinates represented by the radar original data;

and combining the translation estimation matrix and the rotation estimation matrix to obtain the perspective transformation matrix.

3. The processing method according to claim 1, wherein the number of radars is at least two, and the radar raw data is mapped by using the determined perspective transformation matrix to obtain radar correction data, and the method comprises:

performing boundary division on a radar scanning area to divide the radar scanning area into a plurality of sub-areas, wherein the number of the sub-areas is equal to the number of the radars;

determining a corresponding perspective transformation matrix for each radar and the corresponding sub-region;

mapping radar original data of each radar by using a corresponding perspective transformation matrix to obtain correction data corresponding to each radar;

and merging the correction data of the plurality of radars to obtain the radar correction data.

4. The processing method of claim 3, wherein combining the remediated data from the plurality of radars comprises:

and generating a splicing matrix by utilizing boundary fixed points existing in two radars to realize the combination of correction data of a plurality of radars.

5. The processing method according to claim 3 or 4, wherein the combining of the remediated data of the plurality of radars further comprises:

and for the combined data, weighting the data in the preset range by adopting a weighting algorithm to obtain a new point.

6. The processing method according to claim 1, wherein normalizing the radar correction data to obtain radar normalized data comprises:

taking the limit four-corner coordinates of the correction area where the radar correction data are located as limit boundary points to form a quadrilateral area;

taking the upper left corner of the quadrilateral area as a (0,0) point and the lower right corner as a (1,1) point, and mapping the radar correction data to a floating point data point set with a range of 0.0-1.0;

and discarding all data outside the region in the floating point data point set, and taking the data in the region as the radar standardized data.

7. The processing method of claim 1, wherein clustering the radar normalized data to obtain encapsulated data comprises:

clustering all radar standardized data by using a K-means clustering algorithm and taking a specific range distance as a boundary to form different clusters;

performing list tracking on the clusters obtained by clustering, and tracking each cluster by using a Kalman tracking formula;

and when a new cluster appears, the cluster is regarded as a touch start event, when the new cluster disappears, the cluster which is moving and confirmed by Kalman tracking is regarded as a touch moving event, and the like until the packaging is finished.

8. The processing method of claim 1, wherein transmitting the encapsulated data to an application system comprises:

and transmitting the encapsulated data to the application system through a data transmission module according to the command setting obtained by the communication module.

9. A system for processing radar data, comprising:

the data collection module is used for acquiring acquired radar raw data, wherein the raw data is generated by touch events of a touch area;

a data processing module to:

mapping the radar original data by using the determined perspective transformation matrix to obtain radar correction data;

standardizing the radar correction data to obtain radar standardized data;

clustering the radar standardized data to obtain packaged data;

and transmitting the encapsulated data to an application system so that the application system can use the encapsulated data as an input event of the application.

10. A computer storage medium on which a computer program is stored, characterized in that the computer program, when being executed by a computer or a processor, carries out the steps of the method according to any one of claims 1 to 8.

Technical Field

The present invention relates to the field of data processing, and in particular, to a radar data processing method, a radar data processing system, and a computer storage medium.

Background

In a scenario such as a game, the user is more inclined to use the way of touch. For example, a user may touch on the touch plane as an input to a game.

In the process of converting the touch of the user into a digital form, various methods such as a sensor may be used to collect data, but due to the influence of the installation precision, the collection precision, and the like of the data collection system, the collected data may not accurately reflect the touch input of the user.

Disclosure of Invention

The invention provides a radar data processing method, a radar data processing system and a computer storage medium, which can process collected radar data so that the collected radar data can reflect touch input more accurately.

According to a first aspect of the present application, there is provided a radar data processing method, including:

acquiring acquired radar raw data, wherein the raw data is generated by a touch event of a touch area;

mapping the radar original data by using the determined perspective transformation matrix to obtain radar correction data;

standardizing the radar correction data to obtain radar standardized data;

clustering the radar standardized data to obtain packaged data;

and transmitting the encapsulated data to an application system so that the application system can use the encapsulated data as an input event of the application.

In one embodiment, the number of the radars is 1, and the perspective transformation matrix is obtained by:

obtaining a translation estimation matrix and a rotation estimation matrix through maximum likelihood estimation based on the actual point coordinates of the touch area and the radar scanning coordinates represented by the radar original data;

and combining the translation estimation matrix and the rotation estimation matrix to obtain the perspective transformation matrix.

In one embodiment, the number of the radars is at least two, and the mapping of the radar raw data by using the determined perspective transformation matrix to obtain radar correction data includes:

performing boundary division on a radar scanning area to divide the radar scanning area into a plurality of sub-areas, wherein the number of the sub-areas is equal to the number of the radars;

determining a corresponding perspective transformation matrix for each radar and the corresponding sub-region;

mapping radar original data of each radar by using a corresponding perspective transformation matrix to obtain correction data corresponding to each radar;

and merging the correction data of the plurality of radars to obtain the radar correction data.

In one embodiment, combining the remediated data of multiple radars comprises: and generating a splicing matrix by utilizing boundary fixed points existing in two radars to realize the combination of correction data of a plurality of radars.

In one embodiment, the combining the remediated data of the plurality of radars further comprises: and for the combined data, weighting the data in the preset range by adopting a weighting algorithm to obtain a new point.

In one embodiment, normalizing the radar correction data to obtain radar normalized data includes:

taking the limit four-corner coordinates of the correction area where the radar correction data are located as limit boundary points to form a quadrilateral area;

taking the upper left corner of the quadrilateral area as a (0,0) point and the lower right corner as a (1,1) point, and mapping the radar correction data to a floating point data point set with a range of 0.0-1.0;

and discarding all data outside the region in the floating point data point set, and taking the data in the region as the radar standardized data.

In one embodiment, clustering the radar normalized data to obtain encapsulated data includes:

clustering all radar standardized data by using a K-means clustering algorithm and taking a specific range distance as a boundary to form different clusters;

performing list tracking on the clusters obtained by clustering, and tracking each cluster by using a Kalman tracking formula;

and when a new cluster appears, the cluster is regarded as a touch start event, when the new cluster disappears, the cluster which is moving and confirmed by Kalman tracking is regarded as a touch moving event, and the like until the packaging is finished.

In one embodiment, transmitting the encapsulated data to an application system comprises: and transmitting the encapsulated data to the application system through a data transmission module according to the command setting obtained by the communication module.

According to a second aspect of the present application, there is provided a radar data processing system comprising:

the data collection module is used for acquiring acquired radar raw data, wherein the raw data is generated by touch events of a touch area;

a data processing module to:

mapping the radar original data by using the determined perspective transformation matrix to obtain radar correction data;

standardizing the radar correction data to obtain radar standardized data;

clustering the radar standardized data to obtain packaged data;

and transmitting the encapsulated data to an application system so that the application system can use the encapsulated data as an input event of the application.

According to a third aspect of the present application, there is provided a computer storage medium having a computer program stored thereon, wherein the computer program is adapted to perform the steps of the method according to the first aspect or any of the embodiments described above when executed by a computer or processor.

Therefore, the radar data processing method provided by the embodiment of the invention can efficiently correct radar original data by using the perspective transformation matrix, avoid excessive redundant data from appearing in a subsequent application system through standardization, and enable data transmitted to the application system to be a touch mapping event of a single encapsulated screen through clustering encapsulation, so that the encapsulated data transmitted to the application system in the embodiment of the invention can more accurately reflect the touch event.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.

FIG. 1 is a schematic block diagram of a radar data processing system of an embodiment of the present application;

FIG. 2 is another schematic block diagram of a radar data processing system of an embodiment of the present application;

FIG. 3 is a schematic flow chart diagram of a method of processing radar data in accordance with an embodiment of the present application;

FIG. 4 is a schematic diagram of an actual coordinate system and a desired coordinate system of an embodiment of the present application;

FIG. 5 is a schematic view of a scan area of a radar of an embodiment of the present application;

FIG. 6 is a schematic illustration of an embodiment of the present application including a correction point;

FIG. 7 is a schematic diagram of mapping using a perspective transformation matrix according to an embodiment of the present application;

fig. 8 is a schematic block diagram of a radar data processing apparatus according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. It is to be understood, however, that features of the following examples and embodiments may be combined with each other without conflict.

The hardware part of the radar is divided into a plurality of modules, namely, the data collection, the data rectification, the data processing, the key feature extraction and the data standardization. A set of complete flow can ensure that radar hardware can be conveniently used by the current mainstream interaction system, and has corresponding confidentiality and expansibility. The entire data transfer will go through: fig. 1 shows an example of a system for processing radar data. Illustratively, it may further include a data display module and a data usage module, as shown in fig. 2, which is another example of a processing system of radar data.

The data collection module may obtain hardware data from various different hardware and then use different Software Development Kits (SDKs) according to the different hardware to obtain the raw data. It can be understood that different SDKs corresponding to different hardware are stored in the data collection module, and the SDKs can be continuously expanded as the number of connected hardware (e.g., manufacturer, model, etc.) increases.

In the present application, the data collection module may obtain radar raw data from a radar sensor (e.g., a millimeter wave radar sensor or other type of radar sensor).

The data processing module may include a local data processing module and optionally may include a cloud data processing module. Illustratively, the data processing module may obtain raw data from the data collection module and process the data.

Specifically, the data collection and correction part is completed by the interaction of the data collection module and the data processing module, the data collection module provides original data to the data processing module, the data processing module simultaneously collects data with corresponding precision by using different commands according to different requirements, and the display content is matched with the content of the data collection module through the data display module to complete the correction process.

The data processing and standardization process is carried out by the data processing module, and after the data are corrected, the corrected data are summarized, key data are extracted, and the like, so that the data are preprocessed. Then, the preprocessed data are standardized for a data use module (such as an application system) and finally the standardized content is transmitted to the interactive software through a communication protocol. The application system may be software and/or hardware of a development program or system, such as an application engine.

An embodiment of the process performed by the data processing module in the present application will be described below with reference to fig. 3 to 7. Fig. 3 is a schematic flow chart of a radar data processing method in the present application. The method shown in fig. 3 comprises:

s110, acquiring acquired radar original data, wherein the original data is generated by a touch event of a touch area;

s120, mapping the radar original data by using the determined perspective transformation matrix to obtain radar correction data;

s130, standardizing the radar correction data to obtain radar standardized data;

s140, clustering the radar standardized data to obtain encapsulated data;

s150, transmitting the encapsulated data to an application system so that the application system can use the encapsulated data as an input event of the application.

In the present application, a plane on which a user performs touch input may be a touch plane. Also, the touch plane includes a touch area, and generally, data within the touch area is considered valid input, while data outside the touch area is considered invalid input, which is discarded.

S110 may include: the data processing module acquires radar raw data from the data collection module. The radar raw data is collected by a data collection module through a radar sensor and the like. Alternatively, the radar raw data may be obtained after the data collection module collects the data and uses the corresponding SDK.

Also, it will be appreciated that one or more numbers of radars may be installed for collecting touch data of a user. That is, the number of radars is not limited in this application.

For radar, angle and distance data are provided as radar raw data, but due to installation reasons, a scanning plane and a wall surface are difficult to be perfectly consistent with a touch plane, and the vertical angle of the radar is difficult to be adjusted to be perfectly matched during installation. Therefore, a set of algorithm is needed to complete the matching correction of the actual input touch plane of the radar.

From root cause analysis, the reason influencing the radar coordinate deviation is mainly installation accuracy, which is reflected in the deviation between a radar scanning coordinate system and an actual physical coordinate system, but a simple four-corner correction interpolation algorithm cannot solve the problem well, and when the area is large, the four-corner correction interpolation algorithm can generate the condition that four corners are well matched, but the middle deviation is large.

The elimination method needs to be started from the original mode, namely the deviation of the coordinate axes, but the radar does not actually calibrate any high-precision correction method on the shell, so that the acquired data is needed to be corrected by combining the touch plane. Wherein the deviation of the actual coordinate system of the raw data from the desired coordinate system is shown in fig. 4. Shown in fig. 4 by a dashed box is the touch plane, which corresponds to the desired coordinate system, the origin of which may be located in the upper left corner of the touch plane. The actual coordinate system of the raw data is determined by the installation position and the installation accuracy of the radar, the origin of the actual coordinate system may be the center of the radar, and the y-axis of the actual coordinate system is the direction of the rotation angle of 0 degree when the radar is installed.

Referring to fig. 4, it can be seen that the radar may have a deviation between the actual coordinate system scanned by the radar and the expected coordinate system of the actual touch plane due to the lack of guarantee of the installation angle and the installation level, and therefore, the radar needs to be corrected.

Specifically, the present application maps radar raw data of a scan plane of a radar to a touch plane through a perspective transformation matrix in S120, thereby obtaining radar correction data. It is understood that even if the number of radars is plural, there is a corresponding perspective transformation matrix for each radar, and mapping can be achieved. In one implementation, the perspective transformation matrix may also be referred to as a projective transformation matrix, which is not limited in this application.

The following describes an embodiment of S120 by taking the number of radars as 1 as an example. The perspective transformation matrix may be decomposed into a rotation matrix and a translation matrix. When the number of radars is 1, the perspective transformation matrix can be obtained by: obtaining a translation estimation matrix and a rotation estimation matrix through maximum likelihood estimation based on actual point coordinates of the touch area and radar scanning coordinates represented by radar original data; and combining the translation estimation matrix and the rotation estimation matrix to obtain a perspective transformation matrix.

The actual point coordinates of the touch area are coordinate values in a desired coordinate system corresponding to the touch plane. The radar scanning coordinate represented by the radar raw data is a coordinate value in an actual coordinate system of the radar. In the present application, a translation matrix and a rotation matrix may be calculated by using 3 points as a group. The existing points (e.g. tens or even hundreds) can be divided into several groups of 3 points, so that several translation matrices and several rotation matrices can be calculated in a one-to-one correspondence. Carrying out maximum likelihood estimation on a plurality of translation matrixes to obtain a translation estimation matrix; and performing maximum likelihood estimation on a plurality of rotation matrixes to obtain a rotation estimation matrix. In one embodiment of the present application, performing maximum likelihood estimation may include: the contingency matrix is removed and a new average approximation matrix is established.

Specifically, by measuring observed data (including radar feedback coordinates corresponding to an actual position, radar data corresponding to boundary data of an actual touch area, and an approximate rotation angle at the time of radar installation), the observed data is converted into a two-dimensional coordinate system (i.e., an actual coordinate system as shown in fig. 4) with the radar as a center origin and the rotation angle of 0 degrees as a positive direction of a y-axis according to angle and distance information, and world coordinates are corrected for the first time by the approximate angle at which the radar is rotated at the time of radar installation, so that it is ensured that an installation relationship between a scanning area and the radar is consistent with a virtual relationship corresponding to collected data, as shown in fig. 5.

This has the advantage that correct matching information can be collected without finding corresponding points, but only by finding correction points nearby, as shown in fig. 6.

Therefore, scanning data corresponding to correction points required to correspond can be obtained, radar original data (angle/distance data) collected by the data collection module are transmitted to the data processing module, a set of unique perspective transformation matrix can be obtained according to actual point coordinates and radar scanning coordinates of a touch area, and after the matrix passes through, points which are not collected can also find a unique mapping relation through the function, as shown in fig. 7.

According to the perspective principle, a unique perspective transformation matrix can be found out according to the known pattern of the graph and the pattern after perspective transformation, so that coordinates of a point set after transformation can be obtained after all point sets on the original graph are mapped by the perspective transformation matrix. However, there is an error in the actual situation, and the data of both of them have an error due to the accuracy in measurement and the accuracy of the display content.

Therefore, aiming at the acquired radar original data and the standard positions of the points needing to be mapped corresponding to the acquired radar original data, all possible perspective transformation matrixes are sequentially calculated by taking 3 points as a unit, the obtained matrixes are subjected to likelihood estimation, unexpected matrixes are removed, a new average approximate matrix is established as a basis, and the whole mapping process is completed.

In one example, the calculation flow may include the following steps: 1. the perspective transformation matrix comprises two parts, one part is a rotation matrix, the other part is a translation matrix, and the perspective transformation matrix needs to be decomposed. 2. And respectively carrying out maximum likelihood estimation on the rotation matrix and the perspective matrix to obtain an estimation matrix. 3. And (3) combining the estimation matrixes obtained in the step (2), and combining the rotation matrixes and the translation matrixes after the maximum likelihood estimation to generate a new perspective transformation matrix.

Therefore, after the data collection of the data collection module and the mapping correction of the data processing module, the correction of the original data of the single radar is completed, and the radar correction data are obtained.

The following describes an embodiment of S120 by taking the number of radars as at least two as an example. S120 may include: performing boundary division on a radar scanning area to divide the radar scanning area into a plurality of sub-areas, wherein the number of the sub-areas is equal to the number of the radars; determining a corresponding perspective transformation matrix for each radar and the corresponding sub-region; mapping radar original data of each radar by using a corresponding perspective transformation matrix to obtain correction data corresponding to each radar; and merging the correction data of the plurality of radars to obtain the radar correction data.

The determination manner of the perspective transformation matrix of each of the plurality of radars may refer to the above embodiment taking 1 radar as an example, and will not be described again here. The merging process may be an automatic alignment mode or a manual adjustment mode.

That is to say, when a plurality of radars are enabled simultaneously, the problem of data merging of the plurality of radars, that is, the problem of radar array, is handled, and then merging and correcting are performed in a data splicing manner.

Firstly, boundary division is needed to be carried out on a scanning area, namely, the whole area needing to be scanned is divided averagely according to the number of radars; secondly, generating a perspective transformation matrix corresponding to each radar and the scanning area used for rectification of each radar, and remapping all radar data by using the perspective transformation matrix. And thirdly, combining all the radar data, and adjusting the splicing matrix of the whole point set according to the distance position between the radar position and the feedback numerical value.

In one embodiment, the correction data of a plurality of radars can be merged by generating a splicing matrix by using the boundary fixed points divided by the two radars. The embodiment can be regarded as an automatic alignment mode, namely a rough splicing matrix is generated by directly utilizing boundary fixed points existing in two radars to realize data merging. However, the method needs the radar feedback points as accurate as possible, and the volume difference caused by different positions of the reflector and the radar does not exist, so that the scheme of manually adjusting the splicing matrix can be adopted in another embodiment, and fine correction is convenient to carry out. It can be understood that the automatic alignment mode may also be combined with the manual adjustment mode, for example, a preliminary mosaic matrix may be generated by using boundary fixed points existing in two radars, and then the preliminary mosaic matrix may be manually adjusted by using the manual adjustment mode to obtain the mosaic matrix.

Optionally, the method may further include: and for the combined data, weighting the data in the preset range by adopting a weighting algorithm to obtain a new point. Wherein the rule of the weighting process may include at least one of: averaging and taking a median value to generate a new point; discarding the weighted value over small points; a plurality of dots is retained.

For the merged data, due to the accuracy problem of the hardware device, the farther the distance is, the more difficult the identification accuracy is to accurately identify, so that all points need to be weighted and judged, that is, two points of two radars appearing at a certain approaching position will appear in the following three situations according to the weighted value: averaging and taking a median value to generate a new point; discarding the weighted value over small points; a plurality of dots is retained. The specific weighting algorithm rules are as follows:

in the first case, averaging takes the median to generate a new point:

the preset range may refer to: the difference between the distance between any two points in the plurality of points and the radar center is not more than 20% of the total distance, namely the weights of the two points in the two radar scanning ranges are basically the same, the distance between any two points in the plurality of points is less than 5mm, and no other points exist in the diameter range of 10mm by taking the generated center point as the center of a circle. The point set is directly merged into 1 point. For example, the center of the circumscribed circle of the points may be taken as the new point. It can be seen that in this case, the new point may not be any of the original plurality of points.

In the second case, discard weight over-dot:

if a plurality of points are more biased to one side from the center of the radar, i.e. the distances differ by more than 20% of the total distance, the points with longer distances are discarded, and the remaining points are new points. It can be seen that in this case, the new point is a partial point among the original points.

In a third case, a number of points are reserved:

if the difference between the distances between the multiple points and the radar center is not more than 20% of the total distance, and other points exist in the range of 10mm, keeping point data; or if the distance of the plurality of points exceeds the set sensitive distance range, namely the point set belongs to the points which are not easy to acquire by the radar, correcting the points as far as possible, and ensuring the data presentation. It can be seen that in this case, the new points are the original points.

It follows that, irrespective of the number of radars, corrections can be made by means of embodiments of the present application.

Illustratively, S130 may include: taking the limit four-corner coordinates of the correction area where the radar correction data are located as limit boundary points to form a quadrilateral area; taking the upper left corner of the quadrilateral area as a (0,0) point and the lower right corner as a (1,1) point, and mapping the radar correction data to a floating point data point set with a range of 0.0-1.0; and discarding all data outside the region in the floating point data point set, and taking the data in the region as the radar standardized data.

Specifically, the raw radar data after being rectified by S120 is a set of points, which may collect partial profile data of the scanned object, but if the rectified data is directly processed by the application system, a large amount of redundant data beyond expectation may be generated, and since each application needs to extract key elements repeatedly, a large amount of repeated codes may be generated in each application content, which is also not beneficial for simultaneous collection of multiple applications. Therefore, the original data is processed at the data processing end, so that the data processing end has the function of data preprocessing, and the processing of the data in the application can be reduced or replaced.

It is understood that the specific type, specific implementation manner, and the like of the application are not limited in the present application, and for example, the application may be a game or the like using a touch event as an input.

The description of the location of the interactive content is generally: relative coordinate position represents the percentage of the coordinate relative to the screen size; the absolute position represents the position of a specific pixel on the screen; both of the two are inconsistent with a millimeter distance coordinate system which can be provided by the radar, and in order to avoid carrying out secondary resolution adaptation on the radar, standardization and unification are needed, and standardized data are provided for a data use module.

When the relative position mapping relation is calculated during standardization, all data need to be segmented and mapped by utilizing boundary points and grid points aiming at the corrected data, and the mapping accuracy is ensured.

In one embodiment, assuming a radar count of 1, the normalization process may include: 1. and forming a quadrilateral area by taking the limit four-corner coordinates of the correction area as limit boundary points. 2. And mapping all data into a floating point data point set with the range of 0.0-1.0 by taking the upper left corner as a (0,0) point and the lower right corner as a (1,1) point. 3. And discarding all data outside the region, and taking the data in the region as radar standardized data.

In one embodiment, assuming that the number of radars is plural (at least two), the normalization process may include: 1. perspective rectification is performed on all radars and all raw data is merged (i.e., S120 above for the multi-radar case). 2. And taking the four-corner coordinates of the limits in all correction areas as limit boundary points, taking all data as (0,0) points at the upper left corner and (1,1) points at the lower right corner, and mapping all data into floating point data in the range of 0.0-1.0. 3. And discarding all data outside the region, and taking the data in the region as radar standardized data.

Exemplarily, S140 may include: clustering all radar standardized data by using a K-means clustering algorithm and taking a specific range distance as a boundary to form different clusters; performing list tracking on the clusters obtained by clustering, and tracking each cluster by using a Kalman tracking formula; and when a new cluster appears, the cluster is regarded as a touch start event, when the new cluster disappears, the cluster which is moving and confirmed by Kalman tracking is regarded as a touch moving event, and the like until the packaging is finished.

For example, the specific range may be a range of 100 mm. One skilled in the art will appreciate that the specific range may be set according to other requirements, such as the accuracy requirements of the application, and the application is not limited thereto.

The method comprises the steps of dividing data into K groups in advance, randomly selecting K objects as initial clustering centers, calculating the distance between each object and each seed clustering center, and allocating each object to the nearest clustering center. The cluster centers and the objects assigned to them represent a cluster. The cluster center of a cluster is recalculated for each sample assigned based on the objects existing in the cluster. This process will be repeated until some termination condition is met. The termination condition may be that no (or minimum number) objects are reassigned to different clusters, no (or minimum number) cluster centers are changed again, and the sum of squared errors is locally minimal.

Since touch events are generally used as input events of an application in an application system, radar data needs to be packaged into android or windows general touch events by adopting the current general standardized events. That is, the radar-normalized data needs to be clustered in a data processing chip.

Performing feature extraction on the radar standardized data standard, and completing encapsulation of the touch event by using a clustering theory according to the following rules: and (3) clustering all data by taking the range distance of 100mm as a boundary by using a mature K-means clustering algorithm to form different clusters. And tracking the list of each clustered cluster, and tracking each cluster by using a Kalman tracking formula. When a new cluster appears, the cluster is regarded as a touch start (touchstart) event, when the cluster disappears, the cluster is regarded as a touch end (touchnd) event, the moving cluster confirmed by Kalman tracking is regarded as a touch move (touchmove) event, and the like, and the cluster is packaged into a general touch event.

Exemplarily, S150 may include: and transmitting the encapsulated data to the application system through a data transmission module according to the command setting obtained by the communication module.

Specifically, the encapsulated touch event may be transmitted to the data using module through the data transmission module according to the command setting obtained by the communication module. The data usage module includes an application system, so that the transmitted packaged touch event is used as an input event of the application in the application system.

Based on the technical scheme, the radar data processing method can efficiently correct radar original data of a radar plane; aiming at the situation of multiple radars, a simple splicing and synthesizing method is provided, and partial data of a fusion part is corrected through an auxiliary weighting algorithm; and excessive redundant data of a subsequent application system is avoided through standardization; and through clustering packaging, the data transmitted to the application system is a packaged single-screen touch mapping event.

In addition, as shown in fig. 8, an embodiment of the present invention further provides a radar data processing apparatus, which includes a processor and a memory, where the memory stores computer instructions, and when the computer instructions are executed by the processor, the steps of the method shown in fig. 3 can be implemented.

The memory may be a Read Only Memory (ROM), a static memory device, a dynamic memory device, or a Random Access Memory (RAM).

The processor may be a general-purpose Central Processing Unit (CPU), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits, and is configured to execute the relevant programs to implement the methods of the embodiments of the present application.

The processor may also be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the method of the present application may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The processor may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory, and performs functions required to be performed by units included in the apparatus according to the embodiments of the present application or performs the method according to the embodiments of the present application in combination with hardware thereof.

Optionally, the apparatus may further comprise a communication interface and a bus. Wherein the communication interface enables communication with other devices or networks using transceiver means such as, but not limited to, a transceiver. For example, raw data may be acquired through a communication interface, processed data may be transmitted through a communication interface, and so on. A bus may include a pathway that transfers information between various components of the device (e.g., memory, processor, communication interface).

It is understood that the apparatus in fig. 8 may be the data processing module described above, or may be a processing system of the radar data described above.

In addition, the embodiment of the invention also provides a computer storage medium, and the computer storage medium is stored with the computer program. When executed by a computer or processor, may implement the steps of the method described above in connection with fig. 3. For example, the computer storage medium is a computer-readable storage medium.

In one embodiment, the computer program instructions, when executed by a computer or processor, cause the computer or processor to perform the steps of: acquiring acquired radar raw data, wherein the raw data is generated by a touch event of a touch area; mapping the radar original data by using the determined perspective transformation matrix to obtain radar correction data; standardizing the radar correction data to obtain radar standardized data; clustering the radar standardized data to obtain packaged data; and transmitting the encapsulated data to an application system so that the application system can use the encapsulated data as an input event of the application.

The computer storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a portable compact disc read only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

In addition, an embodiment of the present invention further provides a computer program product, which contains instructions that, when executed by a computer, cause the computer to perform the steps of the method described above in conjunction with fig. 3.

Therefore, the embodiment of the invention provides a radar data processing method, a radar data processing system and a computer storage medium, which can efficiently correct radar original data by using a perspective transformation matrix, avoid excessive redundant data from appearing in a subsequent application system through standardization, and enable data transmitted to the application system to be a touch mapping event of a packaged single screen through cluster packaging. In addition, the method provides a simple splicing and synthesizing method for the situation of multiple radars, and corrects partial data of the fusion part through an auxiliary weighting algorithm. Therefore, the packaging data transmitted to the application system in the embodiment of the invention can reflect the touch event more accurately.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the foregoing illustrative embodiments are merely exemplary and are not intended to limit the scope of the invention thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the scope or spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as set forth in the appended claims.