A method and device for identifying fan interference in millimeter wave radar point cloud data

Abstract

The application discloses a kind of millimeter wave radar point cloud data in fan interference identification method and device, it is related to millimeter wave radar technical field.The method includes: continuously collecting the first point cloud data in specified time length, the spatial position coordinates and velocity information of all first point cloud data are extracted, the absolute value of the velocity of all point clouds in each grid is accumulated in state matrix Cumulative value;By velocity absolute value cumulative value, mark suspected interference area;For the suspected interference area marked, expand the detection range to its surrounding area, collect the second point cloud data of specified time length in this expanded area, using sliding window method to segment processing second point cloud data, the number of point clouds contained in each sliding window is counted, and the point cloud number sequence is obtained;The point cloud number sequence and velocity absolute value cumulative value are analyzed, and the determination of fan area is realized.The application effectively identifies fan interference by analyzing the velocity cumulative time sequence characteristics and quantity time sequence characteristics of point cloud data in space area.

Description

Technical Field

[0001] This invention relates to the field of millimeter-wave radar technology, and in particular to a method and apparatus for identifying fan interference in millimeter-wave radar point cloud data. Background Technology

[0002] In practical deployments, millimeter-wave radar used for human presence sensors suffers from low accuracy, sparseness, and significant multipath effects in its point cloud data. This results in the radar detecting not only real human bodies but also point cloud signals from common indoor objects such as curtains (slightly moving in the wind), green plants (such as swaying leaves), and rotating fans, leading to false alarms and greatly reducing the reliability of the detection system and the user experience. Fans, in particular, with their high speed and energy, have a more severe impact on human presence detection.

[0003] Existing technologies for handling fan interference in millimeter-wave radar point cloud data mainly include range segment shielding and machine learning classification. However, range segment shielding blocks areas where interference does not exist and requires continuous adjustments during use, failing to adapt to changing environments. Machine learning classification methods require a large number of labeled samples and have high hardware computing resource requirements, making them unsuitable for low-cost scenarios. Therefore, a simple and reliable scheme for identifying fan interference in millimeter-wave radar point cloud data is urgently needed. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and device for identifying fan interference in millimeter-wave radar point cloud data. By analyzing the velocity accumulation time-series characteristics and quantity time-series characteristics of point cloud data in a specific spatial region, fan interference can be effectively identified.

[0005] In a first aspect, the present invention provides a method for identifying fan interference in millimeter-wave radar point cloud data, comprising: State matrix construction process: This process involves uniformly dividing the two-dimensional space covered by the millimeter-wave radar detection range into grids and constructing a state matrix that corresponds one-to-one with each grid. Accumulation of absolute velocity: Continuously collect the first point cloud data within a specified time period, extract the spatial position coordinates and velocity information of all first point cloud data, and accumulate the cumulative absolute velocity value of all point clouds in each grid in the state matrix; Point cloud number sequence acquisition process: When the cumulative absolute value of velocity of a certain grid exceeds the threshold one, the grid position is marked as a suspected interference area; for the marked suspected interference area, the detection range is expanded to the surrounding area, and second point cloud data of a specified duration is collected in the expanded area. The second point cloud data is segmented using the sliding window method, and the number of point clouds contained in each sliding window is counted to obtain the point cloud number sequence. Fan region determination process: The fan region is determined by analyzing the sequence of point cloud counts and the cumulative absolute value of velocity.

[0006] Furthermore, the fan area determination process specifically includes: Oscillating fan region determination process: Calculate the correlation coefficient between the point cloud number sequence and its own delay k to obtain the autocorrelation coefficient sequence, and determine whether there is an oscillating fan in the suspected interference region based on the point cloud number sequence and the autocorrelation coefficient sequence; Non-oscillating fan region determination process: Calculate the mean and variance of the point cloud number sequence. If the mean of the point cloud number sequence is greater than threshold two and the variance is less than threshold three, then it is determined that a non-oscillating fan exists in the suspected interference region.

[0007] Furthermore, in the process of determining the fan region, determining whether an oscillating fan exists in the suspected interference region based on the point cloud count sequence and the autocorrelation coefficient sequence specifically includes: determining whether the point cloud count sequence and the autocorrelation coefficient sequence simultaneously satisfy the following conditions: Condition 1: The maximum difference between the peak-to-peak values ​​of the point cloud number sequence is less than D1; Condition 2: The peak-to-peak values ​​of the point cloud number sequence exhibit periodicity at corresponding time points; Condition 3: The first two local maxima of the autocorrelation coefficient sequence are greater than 0.5, and the first two local minima are less than -0.5; If the conditions are met, it is determined that there is an oscillating fan in the suspected interference area.

[0008] Furthermore, the fan area determination process also includes: High-speed fan region determination process: When the cumulative absolute value of velocity exceeds threshold four, it is determined that there is a fan in the region, and no further point cloud number sequence analysis is required. The threshold four is greater than threshold one.

[0009] Furthermore, it also includes the continuous monitoring process of the fan area: Set a preset monitoring cycle and a fifth threshold, which is less than the first threshold. Within each monitoring cycle, only the areas identified as fans are counted for their cumulative absolute speed values. If the cumulative absolute speed value is greater than the fifth threshold, it indicates that the fan is still running, and the fan identification result is maintained.

[0010] Secondly, the present invention provides a device for identifying fan interference in millimeter-wave radar point cloud data, comprising: The state matrix construction module is used to divide the two-dimensional space covered by the millimeter-wave radar detection range into uniform grids and construct a state matrix that corresponds one-to-one with the divided grids. The absolute velocity accumulation module is used to continuously collect the first point cloud data within a specified time period, extract the spatial position coordinates and velocity information of all the first point cloud data, and accumulate the cumulative absolute velocity value of all point clouds in each grid in the state matrix. The point cloud number sequence acquisition module marks the location of a grid as a suspected interference area when the cumulative absolute value of the velocity of a certain grid exceeds a threshold. For the marked suspected interference area, the detection range is expanded to the surrounding area, and second point cloud data of a specified duration is collected in the expanded area. The second point cloud data is segmented using the sliding window method, and the number of point clouds contained in each sliding window is counted to obtain the point cloud number sequence. The fan region determination module determines the fan region based on the point cloud number sequence and the cumulative absolute value of velocity.

[0011] Furthermore, the fan area determination module specifically includes: The oscillating fan region determination submodule is used to calculate the correlation coefficient between the point cloud number sequence and its own delay k to obtain the autocorrelation coefficient sequence, and to determine whether there is an oscillating fan in the suspected interference region based on the point cloud number sequence and the autocorrelation coefficient sequence; The non-oscillating fan area determination submodule is used to calculate the mean and variance of the point cloud number sequence. If the mean of the point cloud number sequence is greater than threshold two and the variance is less than threshold three, then it is determined that there is a non-oscillating fan in the suspected interference area.

[0012] Furthermore, in the process of determining the fan region, determining whether an oscillating fan exists in the suspected interference region based on the point cloud count sequence and the autocorrelation coefficient sequence specifically includes: determining whether the point cloud count sequence and the autocorrelation coefficient sequence simultaneously satisfy the following conditions: Condition 1: The maximum difference between the peak-to-peak values ​​of the point cloud number sequence is less than D1; Condition 2: The peak-to-peak values ​​of the point cloud number sequence exhibit periodicity at corresponding time points; Condition 3: The first two local maxima of the autocorrelation coefficient sequence are greater than 0.5, and the first two local minima are less than -0.5; If the conditions are met, it is determined that there is an oscillating fan in the suspected interference area.

[0013] Furthermore, the fan area determination module also includes: The high-speed moving fan area determination submodule is used to determine that a fan exists in the area when the cumulative absolute value of the speed exceeds threshold four, without the need for subsequent point cloud number sequence analysis. The threshold four is greater than threshold one.

[0014] Furthermore, it also includes a fan area continuous monitoring module, which is used to set a preset monitoring cycle and a fifth threshold, which is less than the first threshold. In each monitoring cycle, only the area that has been identified as a fan is counted for its cumulative absolute speed value. If the cumulative absolute speed value is greater than the fifth threshold, it means that the fan is still running, and the fan identification result is maintained.

[0015] The technical solutions provided in the embodiments of the present invention have at least the following technical effects: 1. Wide adaptability: By analyzing the velocity accumulation time series characteristics and quantity time series characteristics of point cloud data in a specific spatial area, fan interference can be effectively identified without the need to manually shield the fan location in advance. It adaptively detects and locates the fan position. If the fan position changes, there is no need to manually adjust the parameters, making it more applicable.

[0016] 2. High detection accuracy: Oscillating fans and non-oscillating fans are classified and detected separately. Different judgment conditions are designed for the motion characteristics of the two types of fans. At the same time, autocorrelation analysis is introduced to extract periodic features, which improves the recognition accuracy of different types of fans. Through multi-threshold collaborative judgment, the false judgment rate is further reduced.

[0017] 3. Reduced computational load: No machine learning classification is required; fan interference areas can be determined through point cloud data analysis. While ensuring accuracy in the initial rigorous determination, the computational load of subsequent monitoring is reduced, while ensuring continuous identification of fans.

[0018] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] Figure 1 This is a flowchart illustrating the overall process of the method in Embodiment 1 of the present invention. Figure 2 This is a flowchart illustrating the specific execution process in Embodiment 1 of the present invention; Figure 3 This is a schematic diagram of the cumulative absolute velocity value and suspected interference area in Embodiment 1 of the present invention. Figure 4 This is a schematic diagram of the point cloud number sequence obtained by the sliding window method in Embodiment 1 of the present invention; Figure 5 This is a schematic diagram of the autocorrelation coefficient sequence in Embodiment 1 of the present invention; Figure 6 This is a schematic diagram of the device in Embodiment 2 of the present invention. Detailed Implementation

[0021] This invention provides a method and apparatus for identifying fan interference in millimeter-wave radar point cloud data. By analyzing the velocity accumulation time-series characteristics and quantity time-series characteristics of point cloud data within a specific spatial region, fan interference can be effectively identified.

[0022] The overall concept of the technical solutions in the embodiments of the present invention is as follows: 1. Inventive concept: The continuous rotation of fan blades accumulates stable high-velocity values ​​in radar point clouds; simultaneously, the inherent periodicity or steady-state nature of its mechanical motion produces statistical characteristics in the time series of point cloud data that differ from human activity. By analyzing the temporal characteristics of velocity accumulation and quantity in point cloud data within a specific spatial region, fan interference can be effectively identified.

[0023] 2. Algorithm Implementation Principle 2.1 Millimeter-wave radar data acquisition; 2.2 Divide the two-dimensional detection space into a grid with a preset resolution and construct a state matrix; 2.3 Collect millimeter-wave radar point cloud data within 1 minute, record the cumulative absolute value of the velocity of the point cloud at each grid location in the state matrix, and mark the location as a suspected interference area if the value exceeds the threshold. 2.4 Collect all point cloud data within 1 minute around the suspected interference area, and use a sliding window with a length of 5 seconds and a step of 1 second to count the number of point clouds in each sliding window to obtain the point cloud count sequence; 2.5 Judgment based on point cloud number sequence: If the sequence has obvious periodicity, it is judged as an oscillating fan; if the mean of the sequence is greater than threshold two and the variance is less than threshold three, it is judged as a non-oscillating fan; if the cumulative absolute value of velocity in the suspected interference area exceeds threshold four, it is directly judged as a fan.

[0024] 2.6 Subsequent lenient judgment. Based on the initial strict judgment to ensure accuracy, subsequent judgments only require that the cumulative absolute value of the speed exceeds threshold five and that threshold five is less than threshold one, thus ensuring continuous recognition of the fan. Example 1

[0025] This embodiment provides a method for identifying fan interference in millimeter-wave radar point cloud data, such as... Figure 1 As shown, including; S1. State matrix construction process: This is used to divide the two-dimensional space covered by the millimeter-wave radar detection range into uniform grids and construct a state matrix that corresponds one-to-one with the divided grids. S2, Accumulation of absolute velocity: Continuously collect the first point cloud data within a specified time period, extract the spatial position coordinates and velocity information of all first point cloud data, and accumulate the cumulative absolute velocity value of all point clouds in each grid in the state matrix. S3. Point cloud number sequence acquisition process: If the cumulative absolute value of the velocity of a certain grid exceeds the threshold, it indicates that there is a continuously moving object at the grid location, and the grid location is marked as a suspected interference area; for the marked suspected interference area, the detection range is expanded to the surrounding area, and second point cloud data of a specified duration is collected in the expanded area. The second point cloud data is segmented using the sliding window method, and the number of point clouds contained in each sliding window is counted to obtain the point cloud number sequence; S4. Fan Region Determination Process: The fan region is determined by analyzing the sequence of point cloud counts and the cumulative absolute value of velocity.

[0026] like Figure 2 As shown, in a specific embodiment, the implementation steps are as follows: Step 1: Divide the two-dimensional detection space and construct the state matrix. Based on the detection range of the millimeter-wave radar, its covered two-dimensional space is divided into uniform grids with a resolution of 0.1m, with each grid corresponding to a unique spatial coordinate. A state matrix is ​​constructed that corresponds one-to-one with the grid division. Each element of the state matrix records the cumulative absolute velocity value of the point cloud at the corresponding grid location. The state matrix maintains the point cloud data received within 1 minute, assigning and recording it to the corresponding position in the state matrix, while removing point clouds that have exceeded the timeout period (recording time greater than 1 minute).

[0027] Step 2: Calculate the cumulative absolute value of velocity over 1 minute. In top-mounted mode, point cloud information of the current environment is acquired in real time. The point cloud information includes spatial three-dimensional coordinates, radial velocity, and energy value. The millimeter-wave radar is controlled to continuously acquire point cloud data within 1 minute (i.e., the first point cloud data). Each point cloud data is preprocessed to extract its spatial position coordinates and velocity information. Based on the spatial position coordinates of the point cloud, it is matched to the corresponding grid divided in step 1. The absolute velocity values ​​of all point clouds at the grid position are accumulated in the state matrix to obtain the cumulative absolute velocity value of each grid position over 1 minute.

[0028] Step 3: Mark suspected interference areas A preset threshold is set. The cumulative absolute velocity value of each grid is compared with the threshold. If the cumulative value of a grid exceeds the threshold, it indicates that there is a continuously moving object at that location, and the grid location is marked as a suspected interference area. Figure 3As shown, the area within the red box can be marked as a suspected interference area. The purpose of threshold one is to initially filter out areas with continuous motion characteristics and exclude interference from small-amplitude human movements.

[0029] Step 4: Obtain the sequence of point cloud counts in the suspected region. For the suspected interference area marked in step 3, the detection range is expanded to its surrounding area (N grids outward from the suspected interference area as the center), and all point cloud data (i.e., the second point cloud data) within this expanded area for 1 minute are collected. The 1-minute point cloud data is segmented using a sliding window method, with a sliding window length of 5 seconds and a sliding window step of 1 second. That is, starting from the first second, a 5-second segment of point cloud data is collected every 1 second, resulting in a total of 56 sliding windows (1 minute = 60 seconds, 60 - 5 + 1 = 56). The number of point clouds contained in each sliding window is counted, and these point cloud counts are arranged in sliding window order to obtain a point cloud count sequence. The 5-second sliding window length was chosen because the fan's rotation cycle is usually within a few seconds, and the 5-second duration allows the data to be as smooth as possible, making it easier to extract periodic features later; the 1-second step ensures the continuity of the time series and avoids missing key features.

[0030] Step 5: Initial Determination of Fan Area Based on the point cloud number sequence obtained in step 4 and the cumulative absolute value of velocity in step 2, the fan area is accurately identified through the following three judgment conditions, which facilitates the subsequent masking of the area when detecting the presence of human beings.

[0031] a) Oscillating Fan Region Determination Process: During the rotation of an oscillating fan, the spatial range swept by its blades changes periodically, causing the number of point clouds within different sliding windows to fluctuate periodically. Autocorrelation analysis is performed on the acquired point cloud number sequence. Autocorrelation analysis measures the similarity of sequences at different time delays. If the sequence exhibits periodicity, a peak in the correlation coefficient will appear at a delay that is an integer multiple of the period.

[0032] In practice, this can be achieved by calculating the correlation coefficient between the point cloud number sequence and its own delay k. , Obtain the autocorrelation coefficient sequence The presence of an oscillating fan in the suspected interference area can be determined based on the point cloud count sequence and autocorrelation coefficient sequence. Specifically, this can be achieved by determining whether the point cloud count sequence and autocorrelation coefficient sequence simultaneously satisfy the following conditions: Condition 1: The maximum difference between the peak-to-peak values ​​of the point cloud number sequence is less than D1 (e.g., Figure 4 As shown, D1 is a manually set and adjustable threshold. ; Condition 2: Peak-to-peak value of the point cloud number sequence corresponding to the time point It has a periodicity; Condition 3: The first two local maxima of the autocorrelation coefficient sequence are greater than 0.5, and the first two local minima are less than -0.5, i.e. ,like Figure 5 As shown; If the above conditions are met, it is determined that there is an oscillating fan in the suspected interference area.

[0033] b) Determination process for non-oscillating fan areas: The blade rotation range of a non-oscillating fan is fixed, and the number of point clouds generated per unit time is relatively stable. Therefore, the mean of its point cloud number sequence is large (indicating high point cloud density) and the variance is small (indicating small fluctuation in the number of point clouds). In this embodiment, by calculating the mean and variance of the point cloud number sequence, if the mean of the point cloud number sequence is greater than threshold two and the variance is less than threshold three, then it is determined that a non-oscillating fan exists in the suspected interference area.

[0034] c) High-speed moving fan area determination process: Preset threshold four (threshold four is greater than threshold one). If the cumulative absolute value of the speed of the suspected interference area in step S2 exceeds threshold four, it indicates that there is a high-speed continuously moving object in the area. Since the speed of human activity is usually lower than the rotation speed of the fan blades, it can be directly determined that there is a fan in the area without the need for subsequent sequence analysis, thus improving detection efficiency.

[0035] Step 5: Continuous monitoring of the fan area: Once a fan is identified based on any of the conditions a), b), or c) above, this embodiment switches to a continuous fan area monitoring mode to improve detection efficiency. A preset monitoring period and a fifth threshold (value 5) are set, where the fifth threshold is less than the first threshold. Within each monitoring period, only the cumulative absolute speed value of the identified fan area is calculated. If this cumulative absolute speed value is greater than the fifth threshold, it indicates that the fan is still running, and the fan identification result is maintained. The core purpose of setting a more lenient subsequent judgment is to reduce the computational load of subsequent monitoring while ensuring continuous fan identification, based on the initial strict judgment guaranteeing accuracy.

[0036] Based on the same inventive concept, this application also provides an apparatus corresponding to the method in Embodiment 1, as detailed in Embodiment 2. Example 2

[0037] This embodiment provides a device for identifying fan interference in millimeter-wave radar point cloud data, such as... Figure 6 As shown, it includes: The state matrix construction module is used to divide the two-dimensional space covered by the millimeter-wave radar detection range into uniform grids and construct a state matrix that corresponds one-to-one with the divided grids. The absolute velocity accumulation module is used to continuously collect the first point cloud data within a specified time period, extract the spatial position coordinates and velocity information of all the first point cloud data, and accumulate the cumulative absolute velocity value of all point clouds in each grid in the state matrix. The point cloud number sequence acquisition module marks the location of a grid as a suspected interference area when the cumulative absolute value of the velocity of a certain grid exceeds a threshold. For the marked suspected interference area, the detection range is expanded to the surrounding area, and second point cloud data of a specified duration is collected in the expanded area. The second point cloud data is segmented using the sliding window method, and the number of point clouds contained in each sliding window is counted to obtain the point cloud number sequence. The fan region determination module determines the fan region based on the point cloud number sequence and the cumulative absolute value of velocity.

[0038] Preferably, the fan area determination module specifically includes: The oscillating fan region determination submodule is used to calculate the correlation coefficient between the point cloud number sequence and its own delay k to obtain the autocorrelation coefficient sequence, and to determine whether there is an oscillating fan in the suspected interference region based on the point cloud number sequence and the autocorrelation coefficient sequence; The non-oscillating fan area determination submodule is used to calculate the mean and variance of the point cloud number sequence. If the mean of the point cloud number sequence is greater than threshold two and the variance is less than threshold three, then it is determined that there is a non-oscillating fan in the suspected interference area.

[0039] Preferably, in the process of determining the fan region, determining whether there is an oscillating fan in the suspected interference region based on the point cloud count sequence and the autocorrelation coefficient sequence specifically includes: determining whether the point cloud count sequence and the autocorrelation coefficient sequence simultaneously satisfy the following conditions: Condition 1: The maximum difference between the peak-to-peak values ​​of the point cloud number sequence is less than D1; Condition 2: The peak-to-peak values ​​of the point cloud number sequence exhibit periodicity at corresponding time points; Condition 3: The first two local maxima of the autocorrelation coefficient sequence are greater than 0.5, and the first two local minima are less than -0.5; If the conditions are met, it is determined that there is an oscillating fan in the suspected interference area.

[0040] Preferably, the fan area determination module further includes: The high-speed moving fan area determination submodule is used to determine that a fan exists in the area when the cumulative absolute value of the speed exceeds threshold four, without the need for subsequent point cloud number sequence analysis. The threshold four is greater than threshold one.

[0041] Preferably, it also includes a fan area continuous monitoring module, which is used to set a preset monitoring cycle and a fifth threshold, the fifth threshold being less than the first threshold; within each monitoring cycle, only the area identified as a fan is counted for its cumulative absolute speed value. If the cumulative absolute speed value is greater than the fifth threshold, it indicates that the fan is still running, and the fan identification result is maintained.

[0042] Since the apparatus described in Embodiment 2 of the present invention is an apparatus used to implement the method of Embodiment 1 of the present invention, those skilled in the art can understand the specific structure and variations of the apparatus based on the method described in Embodiment 1 of the present invention, and therefore will not be described again here. All apparatuses used in the method of Embodiment 1 of the present invention fall within the scope of protection of the present invention.

[0043] The technical solutions provided in the embodiments of the present invention have at least the following technical effects: 1. Wide adaptability: By analyzing the velocity accumulation time series characteristics and quantity time series characteristics of point cloud data in a specific spatial area, fan interference can be effectively identified without the need to manually shield the fan location in advance. It adaptively detects and locates the fan position. If the fan position changes, there is no need to manually adjust the parameters, making it more applicable.

[0044] 2. High detection accuracy: Oscillating fans and non-oscillating fans are classified and detected separately. Different judgment conditions are designed for the motion characteristics of the two types of fans. At the same time, autocorrelation analysis is introduced to extract periodic features, which improves the recognition accuracy of different types of fans. Through multi-threshold collaborative judgment, the false judgment rate is further reduced.

[0045] 3. Reduced computational load: No machine learning classification is required; fan interference areas can be determined through point cloud data analysis. While ensuring accuracy in the initial rigorous determination, the computational load of subsequent monitoring is reduced, while ensuring continuous identification of fans.

[0046] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0047] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0048] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0049] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0050] While specific embodiments of the present invention have been described above, those skilled in the art should understand that the specific embodiments described are merely illustrative and not intended to limit the scope of the present invention. Equivalent modifications and variations made by those skilled in the art in accordance with the spirit of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying fan interference in millimeter-wave radar point cloud data, characterized in that, include: State matrix construction process: This process involves uniformly dividing the two-dimensional space covered by the millimeter-wave radar detection range into grids and constructing a state matrix that corresponds one-to-one with each grid. Accumulation of absolute velocity: Continuously collect the first point cloud data within a specified time period, extract the spatial position coordinates and velocity information of all first point cloud data, and accumulate the cumulative absolute velocity value of all point clouds in each grid in the state matrix; Point cloud number sequence acquisition process: When the cumulative absolute value of velocity of a certain grid exceeds the threshold one, the grid position is marked as a suspected interference area; for the marked suspected interference area, the detection range is expanded to the surrounding area, and second point cloud data of a specified duration is collected in the expanded area. The second point cloud data is segmented using the sliding window method, and the number of point clouds contained in each sliding window is counted to obtain the point cloud number sequence. Fan region determination process: The fan region is determined by analyzing the sequence of point cloud counts and the cumulative absolute value of velocity.

2. The method according to claim 1, characterized in that: The fan area determination process specifically includes: Oscillating fan region determination process: Calculate the correlation coefficient between the point cloud number sequence and its own delay k to obtain the autocorrelation coefficient sequence, and determine whether there is an oscillating fan in the suspected interference region based on the point cloud number sequence and the autocorrelation coefficient sequence; Non-oscillating fan region determination process: Calculate the mean and variance of the point cloud number sequence. If the mean of the point cloud number sequence is greater than threshold two and the variance is less than threshold three, then it is determined that a non-oscillating fan exists in the suspected interference region.

3. The method according to claim 1, characterized in that, In the process of determining the fan region, determining whether there is an oscillating fan in the suspected interference region based on the point cloud count sequence and the autocorrelation coefficient sequence specifically includes: determining whether the point cloud count sequence and the autocorrelation coefficient sequence simultaneously satisfy the following conditions: Condition 1: The maximum difference between the peak-to-peak values ​​of the point cloud number sequence is less than D1; Condition 2: The peak-to-peak values ​​of the point cloud number sequence exhibit periodicity at corresponding time points; Condition 3: The first two local maxima of the autocorrelation coefficient sequence are greater than 0.5, and the first two local minima are less than -0.5; If the conditions are met, it is determined that there is an oscillating fan in the suspected interference area.

4. The method according to claim 1, characterized in that, The fan area determination process also includes: High-speed fan region determination process: When the cumulative absolute value of velocity exceeds threshold four, it is determined that there is a fan in the region, and no further point cloud number sequence analysis is required. The threshold four is greater than threshold one.

5. The method according to claim 1 or 4, characterized in that, This also includes continuous monitoring of the fan area: Set a preset monitoring cycle and a fifth threshold, which is less than the first threshold. Within each monitoring cycle, only the areas identified as fans are counted for their cumulative absolute speed values. If the cumulative absolute speed value is greater than the fifth threshold, it indicates that the fan is still running, and the fan identification result is maintained.

6. A device for identifying fan interference in millimeter-wave radar point cloud data, characterized in that, include: The state matrix construction module is used to divide the two-dimensional space covered by the millimeter-wave radar detection range into uniform grids and construct a state matrix that corresponds one-to-one with the divided grids. The absolute velocity accumulation module is used to continuously collect the first point cloud data within a specified time period, extract the spatial position coordinates and velocity information of all the first point cloud data, and accumulate the cumulative absolute velocity value of all point clouds in each grid in the state matrix. The point cloud number sequence acquisition module marks the location of a grid as a suspected interference area when the cumulative absolute value of the velocity of a certain grid exceeds a threshold. For the marked suspected interference area, the detection range is expanded to the surrounding area, and second point cloud data of a specified duration is collected in the expanded area. The second point cloud data is segmented using the sliding window method, and the number of point clouds contained in each sliding window is counted to obtain the point cloud number sequence. The fan region determination module determines the fan region based on the point cloud number sequence and the cumulative absolute value of velocity.

7. The apparatus according to claim 6, characterized in that: The fan area determination module specifically includes: The oscillating fan region determination submodule is used to calculate the correlation coefficient between the point cloud number sequence and its own delay k to obtain the autocorrelation coefficient sequence, and to determine whether there is an oscillating fan in the suspected interference region based on the point cloud number sequence and the autocorrelation coefficient sequence; The non-oscillating fan area determination submodule is used to calculate the mean and variance of the point cloud number sequence. If the mean of the point cloud number sequence is greater than threshold two and the variance is less than threshold three, then it is determined that there is a non-oscillating fan in the suspected interference area.

8. The apparatus according to claim 6, characterized in that, In the process of determining the fan region, determining whether there is an oscillating fan in the suspected interference region based on the point cloud count sequence and the autocorrelation coefficient sequence specifically includes: determining whether the point cloud count sequence and the autocorrelation coefficient sequence simultaneously satisfy the following conditions: Condition 1: The maximum difference between the peak-to-peak values ​​of the point cloud number sequence is less than D1; Condition 2: The peak-to-peak values ​​of the point cloud number sequence exhibit periodicity at corresponding time points; Condition 3: The first two local maxima of the autocorrelation coefficient sequence are greater than 0.5, and the first two local minima are less than -0.5; If the conditions are met, it is determined that there is an oscillating fan in the suspected interference area.

9. The apparatus according to claim 6, characterized in that, The fan area determination module also includes: The high-speed moving fan area determination submodule is used to determine that a fan exists in the area when the cumulative absolute value of the speed exceeds threshold four, without the need for subsequent point cloud number sequence analysis. The threshold four is greater than threshold one.

10. The apparatus according to claim 6 or 9, characterized in that: It also includes a fan area continuous monitoring module, which is used to set a preset monitoring cycle and a fifth threshold, which is less than the first threshold. In each monitoring cycle, only the area that has been identified as a fan is counted for its cumulative absolute speed value. If the cumulative absolute speed value is greater than the fifth threshold, it means that the fan is still running and the fan identification result is maintained.

Images