Method and device for determining drivable area, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a kind of determination method, device, electronic equipment and storage medium of travelable area, wherein the method comprises: obtaining at least two microwave radar images detected by microwave radar;Wherein, the position point of each microwave radar is in the plane of the midpoint of the rear axle of vehicle and perpendicular to the rear axle of vehicle;The gray value of each pixel point in the microwave radar image is used to reflect the signal strength of reflected wave when microwave radar scanning is carried out with microwave radar as origin;According to the gray value matrix corresponding to each microwave radar image, a clustering fusion point set is obtained;At least two scanning regions are determined, and according to the clustering fusion point set, the obstacle points matched with each scanning region are determined;According to the obstacle points matched with each scanning region, the travelable area of vehicle is determined.The technical scheme realizes the safety area detection in mine scene, and improves the safety factor of driving in mine area.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, and storage medium for determining a drivable area. Background Technology

[0002] With the rapid development of driver assistance technology, obstacle detection technology near vehicles has become relatively mature. Existing obstacle detection technologies near vehicles are usually based on panoramic imaging technology using LiDAR, which processes the obtained panoramic image of the vehicle's surroundings to determine whether obstacles exist.

[0003] However, in special environments such as mines, the dust in the vehicle's driving environment may obstruct the detection window of the LiDAR, thereby reducing the accuracy of obstacle detection or even causing the LiDAR to malfunction. Therefore, a new obstacle detection solution is needed in dusty environments such as mines. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for determining drivable areas, so as to realize safe area detection in mining scenarios and improve the safety factor of driving in mining areas.

[0005] According to one aspect of the present invention, a method for determining a drivable area is provided, the method comprising:

[0006] Acquire microwave radar images detected by at least two microwave radars; wherein the location of each microwave radar is on a plane passing through the midpoint of the rear axle of the vehicle and perpendicular to the rear axle of the vehicle;

[0007] The grayscale value of each pixel in the microwave radar image is used to reflect the signal strength of the reflected wave when the microwave radar is scanned with the microwave radar as the origin.

[0008] Based on the gray value matrix corresponding to each microwave radar image, a clustered fusion point set is obtained;

[0009] Identify at least two scanning regions, and determine the obstacle points that match each scanning region based on the clustered fusion point set;

[0010] The drivable area of ​​the vehicle is determined based on the obstacle points that match each scanned area.

[0011] According to another aspect of the present invention, a device for determining a drivable area is provided, comprising:

[0012] The image acquisition module is used to acquire microwave radar images detected by at least two microwave radars; wherein the position point of each microwave radar is located on a plane passing through the midpoint of the rear axle of the vehicle and perpendicular to the rear axle of the vehicle.

[0013] The grayscale value of each pixel in the microwave radar image is used to reflect the signal strength of the reflected wave when the microwave radar is scanned with the microwave radar as the origin.

[0014] The clustering fusion point set determination module is used to obtain the clustering fusion point set based on the gray value matrix corresponding to each microwave radar image;

[0015] The obstacle point determination module is used to determine at least two scanning regions and, based on the clustered fusion point set, determine the obstacle points that match each scanning region.

[0016] The drivable area determination module is used to determine the drivable area of ​​the vehicle based on the obstacle points that match each scanned area.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the method for determining the drivable area as described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for determining a drivable area as described in any embodiment of the present invention.

[0022] The technical solution of this application embodiment acquires microwave radar images detected by at least two microwave radars; obtains a clustered fusion point set based on the grayscale value matrix corresponding to each microwave radar image; determines at least two scanning areas; determines obstacle points matching each scanning area based on the clustered fusion point set; and determines the drivable area of ​​the vehicle based on the obstacle points matching each scanning area. This technical solution detects obstacles using microwave radar, avoiding interference from factors such as dust, and improves the accuracy and completeness of obstacle detection by employing at least two microwave radars, thus achieving safe area detection in mining scenarios and improving the safety factor of driving in mining areas.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a method for determining a drivable area according to Embodiment 1 of the present invention;

[0026] Figure 2 This is a schematic diagram of microwave radar location points for a method of determining a drivable area according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of the scanning area of ​​a method for determining a drivable area according to an embodiment of the present invention;

[0028] Figure 4 This is a flowchart of a method for determining a drivable area according to Embodiment 2 of the present invention;

[0029] Figure 5 This is a flowchart of a method for determining a drivable area according to Embodiment 3 of the present invention;

[0030] Figure 6 This is a microwave radar detection schematic diagram of a method for determining a drivable area according to an embodiment of the present invention;

[0031] Figure 7 This is a schematic diagram of adjacent position points in a method for determining a drivable area according to an embodiment of the present invention.

[0032] Figure 8 This is an interpolation diagram illustrating a method for determining a drivable area according to an embodiment of the present invention;

[0033] Figure 9 This is a schematic diagram of a device for determining a drivable area according to Embodiment 4 of the present invention;

[0034] Figure 10 This is a schematic diagram of the structure of an electronic device that implements a method for determining a drivable area according to an embodiment of the present invention. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0037] Example 1

[0038] Figure 1 This is a flowchart illustrating a method for determining a drivable area according to Embodiment 1 of the present invention. This embodiment is applicable to detecting safe areas in mining scenarios. The method can be executed by a drivable area determination device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0039] S110, acquire microwave radar images detected by at least two microwave radars; wherein the position point of each microwave radar is located on a plane passing through the midpoint of the rear axle of the vehicle and perpendicular to the rear axle of the vehicle.

[0040] Microwave radar images, in particular, are images formed when a radar transmitter emits radio waves into a detection area, and a receiver receives the scattered echoes. Microwave radar images essentially reflect the intensity data at various locations within the radar detection area. The microwave radar image corresponds to the detection area, and each pixel corresponds to a sub-region within that area. The position and grayscale value of each pixel reflect information about that sub-region. For example, obstacles in the detection area will cause the radar reflected wave signal intensity at that location to differ from that in an unobstructed area. The signal intensity of the radar reflected wave is represented by the grayscale value of the pixel; therefore, microwave radar images can reflect obstacle information within the detection area.

[0041] In this embodiment, obstacles are detected using at least two microwave radars, improving the comprehensiveness of obstacle detection and avoiding missed detections. The grayscale value of each pixel in the microwave radar image reflects the signal strength of the reflected wave when the microwave radar is scanned with the origin as the microwave radar. The positions of the at least two microwave radars should be at different locations on the vehicle to detect obstacles from different directions. For example, the plane formed by the positions of the at least two microwave radars and the midpoint of the vehicle's rear axle is perpendicular to the rear axle of the vehicle. Figure 2 As shown, the location of the microwave radar can be the square parts on the roof and under the vehicle.

[0042] S120: Based on the gray value matrix corresponding to each microwave radar image, a clustered fusion point set is obtained.

[0043] In this embodiment, the grayscale values ​​of each pixel in the microwave radar image are extracted into a grayscale matrix. If the microwave radar image contains P rows and Q columns of pixels, then...

[0044]

[0045] Where F is the gray value matrix, f pq F represents the grayscale value of the pixel at position (p, q). It can be mapped to a rectangular region of PΔ×QΔ, where each pixel corresponds to a square region with a side length of Δ meters in actual space.

[0046] Furthermore, since obstacles have a certain volume, they usually correspond to multiple pixels in microwave radar images. Clustering can be performed on each gray value matrix to obtain the cluster point set corresponding to each gray value matrix. The distribution of this cluster point set in the microwave radar image can reflect the actual location of the obstacle. The cluster point sets corresponding to each microwave radar image are then merged to obtain the cluster fusion point set. The practical significance of this cluster fusion point set is to integrate the obstacles detected by each microwave radar together, which facilitates subsequent calculations.

[0047] S130, determine at least two scanning regions, and determine the obstacle points that match each scanning region based on the clustered fusion point set.

[0048] The scanning area can be part of the microwave radar detection area, and all scanning areas can form the radar detection area. An obstacle point refers to the location of the nearest obstacle to the vehicle within each scanning area.

[0049] Specifically, the radar detection area is divided into at least two scanning areas. Obstacles in each scanning area are determined based on the clustered fusion point set. The distance to the nearest obstacle to the vehicle is calculated, and obstacle points matching each scanning area are determined.

[0050] S140, determine the drivable area of ​​the vehicle based on the obstacle points that match each scanned area.

[0051] The drivable area refers to an area with fewer obstacles, where vehicles have greater room to maneuver. For example, in a mining area, driving near obstacles is inconvenient and unsafe; vehicles can be driven away from obstacles to improve driving safety. It should be noted that if an obstacle point in a scanned area is close to a vehicle, adjacent areas of that scanned area should be avoided from appearing in the drivable area as much as possible.

[0052] The technical solution of this application embodiment acquires microwave radar images detected by at least two microwave radars; obtains a clustered fusion point set based on the grayscale value matrix corresponding to each microwave radar image; determines at least two scanning areas; determines obstacle points matching each scanning area based on the clustered fusion point set; and determines the drivable area of ​​the vehicle based on the obstacle points matching each scanning area. This technical solution detects obstacles using microwave radar, avoiding interference from factors such as dust, and improves the accuracy and completeness of obstacle detection by employing at least two microwave radars, thus achieving safe area detection in mining scenarios and improving the safety factor of driving in mining areas.

[0053] Example 2

[0054] Figure 4 This is a flowchart of a method for determining a drivable area provided in Embodiment 2 of the present invention. This embodiment optimizes the clustering and fusion process based on the above embodiment.

[0055] like Figure 4 As shown, the method in this embodiment specifically includes the following steps:

[0056] S210, acquire microwave radar images detected by at least two microwave radars; wherein, the position point of each microwave radar is located on a plane passing through the midpoint of the rear axle of the vehicle and perpendicular to the rear axle of the vehicle; the microwave radar images include a roof microwave radar image and a bottom microwave radar image.

[0057] S220, based on the scene noise grayscale value, perform activation function mapping on the grayscale value matrix corresponding to each microwave radar image; the scene noise grayscale value is the mode of each grayscale value in the grayscale value matrix corresponding to the roof microwave radar image.

[0058] The activation function can remove scene noise, which reflects background noise. In this embodiment, each microwave radar image includes obstacles and scene noise, requiring scene noise removal. Specifically, let the activation function be f. act (),

[0059]

[0060] Where baseline represents the scene's noise level in grayscale values. The grayscale matrix of the roof-mounted microwave radar image is denoted as F. high The grayscale matrix of the microwave radar image under the vehicle is denoted as F. low , will F high and F low By substituting the activation function into the activation function mapping, we get:

[0061] F′ low ={f act (x)|x in F low}

[0062] F′ high ={f act (x)|x in F high}

[0063] Among them, F′ low F′ refers to the grayscale matrix of the microwave radar image under the vehicle after activation function mapping. high This refers to the grayscale matrix of the under-vehicle microwave radar image after activation function mapping, x in F low This refers to: using each element of the grayscale matrix of the microwave radar image under the vehicle as x, where x ∈ F high This refers to using each element of the grayscale matrix of the roof-mounted microwave radar image as x.

[0064] S230, transform each gray value matrix after the activation function mapping into Cartesian coordinates to obtain a set of Cartesian coordinate points that match each gray value matrix.

[0065] The Cartesian coordinates can be a two-dimensional rectangular coordinate system, defined by two mutually perpendicular coordinate axes, referred to as the x-axis and y-axis. In this embodiment, since the elements in each grayscale value matrix after activation function mapping are in numerical form and do not reflect the correspondence with the actual position, the grayscale value matrices after activation function mapping are transformed into Cartesian coordinates to obtain a set of Cartesian coordinate points that match each grayscale value matrix.

[0066] Specifically, the actual length corresponding to each pixel is set as Δ meters. A Cartesian coordinate system is established with the microwave radar as the origin, and F′ is... low and F′ high The Cartesian coordinate point set obtained by mapping from the pixel coordinate system to the Cartesian coordinate system and matching each gray value matrix is ​​denoted as P. low and P high ,

[0067]

[0068]

[0069] Among them, F′ low and F′ high A matrix of size P*Q. Represents coordinates in the Cartesian coordinate system. in F′ low Representing F′ low The elements in in F′ high Representing F′ high The elements in.

[0070] S240, cluster and merge the Cartesian coordinate point set that matches each gray value matrix to obtain the clustered and merged point set.

[0071] In this embodiment of the application, optionally, the Cartesian coordinate point set matching each gray value matrix is ​​clustered and fused to obtain a clustered and fused point set, including steps A1-A3:

[0072] Step A1: Perform density-based nonparametric clustering on the Cartesian coordinate point sets that match each gray value matrix to obtain the outlier point sets that match each Cartesian coordinate point set.

[0073] Density-based nonparametric clustering involves grouping closely packed points in a Cartesian coordinate set that matches each grayscale matrix together, and marking points located in low-density regions as outliers. These outliers form an outlier set. Specifically, density-based nonparametric clustering pre-sets the minimum number of points required to form a cluster region: `minPts`, and the neighborhood value: `∈`. Clustering begins with any unvisited point, checking if any other points exist within the `∈` range of that point. If so, and the total number of points is greater than or equal to `minPts`, a cluster region is formed; otherwise, it is identified as an outlier. Further, outliers may be found within the `∈` neighborhood of other points. If the number of points in this neighborhood is greater than or equal to `minPts`, the outlier is added to this cluster region, forming a larger cluster region. This process is repeated, and the final outliers form the outlier set. For example, `minPts = 2`, `∈` = 2Δ.

[0074] Step A2: After removing outlier points from each Cartesian coordinate point set, merge them to obtain a Cartesian coordinate fused point set.

[0075] The Cartesian coordinate fusion point set includes the Cartesian coordinate point set corresponding to the roof microwave radar image after removing outliers, and the Cartesian coordinate point set corresponding to the under-vehicle microwave radar image after removing outliers. For example, the line connecting the roof and under-vehicle microwave radars is perpendicular to the horizontal plane, and the roof and under-vehicle microwave radars can be the origin of the same Cartesian coordinate system. Therefore, each Cartesian coordinate point set can be marked in the same Cartesian coordinate system. After removing outliers from each Cartesian coordinate point set, they are merged to obtain the Cartesian coordinate fusion point set.

[0076] Specifically, the outlier set corresponding to the under-vehicle microwave radar and the roof microwave radar is denoted as: P′ low and P′ high .

[0077] L = P low -P′ low

[0078] H = P high -P′ high ;

[0079] Where L represents the Cartesian coordinate point set of the under-vehicle microwave radar after removing outliers, and H represents the Cartesian coordinate point set of the roof microwave radar after removing outliers. The fused Cartesian coordinate point set is denoted as P′. U ,but:

[0080] P′ U =L∪H.

[0081] It is obvious that if the location points of microwave radar are randomly distributed, the Cartesian coordinate system of each microwave radar can be translated to merge the Cartesian coordinate systems. Then, after removing outlier points from each Cartesian coordinate set, they can be merged to obtain the Cartesian coordinate fused set.

[0082] Step A3: Perform polar coordinate transformation on the Cartesian coordinate fusion point set to obtain the clustered fusion point set.

[0083] Polar coordinate transformation refers to representing the Cartesian coordinate fusion point set in polar coordinates. The polar coordinate system containing the clustered fusion point set has the midpoint of the vehicle's rear axle as the pole, the vehicle's driving direction as the polar axis, and takes clockwise angles as positive.

[0084] Specifically, the cluster fusion point set is denoted as P. U ,but:

[0085]

[0086] Where (x,y)in P′ U Represents P′ U The Cartesian coordinates of each element in the equation.

[0087] This scheme obtains clustered point sets matching obstacles by performing density-based nonparametric clustering on the Cartesian coordinate point sets that match each grayscale value matrix and removing outlier points. This removes interference from other factors. After removing outlier points from each Cartesian coordinate point set, the sets are merged into a single Cartesian coordinate system, which facilitates the determination of obstacle positions. Furthermore, polar coordinate transformation is performed on the merged Cartesian coordinate point set, which facilitates the determination of obstacle points matching each scanning area in subsequent steps.

[0088] S250 defines a circular detection area with the center of the vehicle's rear axle and the radius of the preset maximum detection distance.

[0089] It is obvious that the center of the circular detection area can be any position. The embodiment of this application takes the midpoint of the rear axle of the vehicle as the center, which is only a specific implementation method. The embodiment of this application does not limit the specific position of the center.

[0090] S260, the circular detection area is divided into scanning areas according to the preset number of segments; wherein, the area of ​​each scanning area is equal.

[0091] The specific value of the preset number of fragments can be determined according to the actual situation, and this application embodiment does not limit it. For example, as shown in the figure... Figure 3 As shown, the circular detection area is divided into multiple sector areas, and each sector area is a scanning area.

[0092] S270, based on the clustered fusion point set, determine the obstacle points that match each scanned region.

[0093] In this embodiment of the application, optionally, determining the obstacle points matching each scanning area based on the cluster fusion point set includes: determining the obstacle distance scanning value based on the cluster fusion point set for the target scanning area; if it is determined that the difference between the obstacle distance scanning value and the obstacle distance state value is less than a preset threshold, then updating the obstacle distance state value based on the obstacle distance scanning value, the obstacle distance state value, and the number of times the obstacle distance state value is continuously updated.

[0094] The target scanning area refers to the area within each scanning area where obstacle distance scanning is performed. The obstacle distance scanning value can be the distance to the nearest obstacle to the midpoint of the vehicle's rear axle in the target scanning area obtained during each radar scan. The obstacle distance status value is used to represent the distance to the nearest obstacle to the midpoint of the vehicle's rear axle in the target scanning area at the current moment. The preset threshold can be determined according to actual conditions, and this application embodiment does not limit it.

[0095] In this embodiment, the distance between the vehicle and the obstacle is determined through multiple scans to avoid inaccurate scan data in a single scan. Specifically, during the initial radar scan of the target scanning area, the obtained obstacle distance scan value is used as the obstacle distance state value. Subsequently, during each radar scan, it is determined whether the difference between the obtained obstacle distance scan value and the obstacle distance state value is less than a preset threshold. If it is less, the obstacle distance state value is updated based on the obstacle distance scan value, the obstacle distance state value, and the number of consecutive updates to the obstacle distance state value.

[0096] In this embodiment of the application, optionally, the obstacle distance status value is updated based on the obstacle distance scan value, the obstacle distance status value, and the number of consecutive updates of the obstacle distance status value, including steps B1-B4:

[0097] Step B1: If it is determined that the number of consecutive updates of the obstacle distance status value is less than the first value, then the first weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the first weight is used as the weight of the obstacle distance status value, and the obstacle distance status value is updated.

[0098] Step B2: If it is determined that the number of consecutive updates of the obstacle distance status value is greater than or equal to the first value and less than the second value, then the second weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the second weight is used as the weight of the obstacle distance status value, and the obstacle distance status value is updated.

[0099] Step B3: If it is determined that the number of consecutive updates of the obstacle distance status value is greater than or equal to the third value and less than the fourth value, then the third weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the third weight is used as the weight of the obstacle distance status value, and the obstacle distance status value is updated.

[0100] Step B4: If it is determined that the number of consecutive updates of the obstacle distance status value is greater than or equal to the fourth value, then the obstacle distance status value is updated based on the average of the obstacle distance scan value and the obstacle distance status value.

[0101] Wherein, the first value is less than the second value, the second value is less than the third value, and the third value is less than the fourth value; the first weight is less than the second weight, and the second weight is less than the third weight. The specific values ​​of the first value, the second value, the third value, the fourth value, the first weight, the second weight, and the third weight can be determined according to the actual situation, and this application embodiment does not limit them.

[0102] In this scheme, the obstacle distance status value is only updated when the difference between the obstacle distance scan value and the obstacle distance status value is less than a preset threshold. Therefore, if the obstacle distance status value is updated infrequently, it indicates that there is significant uncertainty in the obstacle distance status value obtained from each scan. In this case, when updating the obstacle distance status value, a lower weight is assigned to the obstacle distance scan value, and a higher weight is assigned to the obstacle distance status value. The obstacle distance status value is updated by weighted summation of the obstacle distance scan value and the obstacle distance status value. If the obstacle distance status value is updated frequently, it indicates that the update status of the obstacle distance status value is becoming more stable. In this case, when updating the obstacle distance status value, the weight of the original obstacle distance scan value should be increased, and the weight of the obstacle distance status value should be decreased.

[0103] For example, the number of consecutive updates to the obstacle distance state value is placed in the array `counter`, and the obstacle distance state value is placed in the array `state`. k In this context, the obstacle distance scan values ​​are placed in the array range.

[0104] If |range i -state k,i If |<ε, then it is considered a related continuous update, let counter i Increment by 1. Otherwise, consider it an irrelevant update and set the counter to 1. i Set to 1, state k =(range i +state k-1,i ×7)÷8, proceed to the next scan area update. Here, ε can be set according to specific circumstances, typically less than 20 times the radar data acquisition interval. The subscript i represents the scan area, state... k-1,i and state k These represent the previously determined obstacle distance scan value and the newly determined obstacle distance scan value, respectively.

[0105] If 1 ≤ counter i If the value is less than 3, the associated continuous update is considered to be in the initial stage, and the obstacle distance state value is updated at a moderate rate. k =(range i +state k-1,i ×3)÷4.

[0106] If 3 ≤ counter i If the value is less than 5, the associated continuous updates are considered to be leveling off, and the obstacle distance state value is updated at a faster rate. k =(range i +statek-1,i ×2)÷3.

[0107] If counter i If the value is ≥5, the associated continuous update is considered stable, and the obstacle distance state value is updated to state at the fastest speed. k =(range i +state k-1,i )÷2,。

[0108] Furthermore, by traversing all scanned areas, obstacle points are identified. It should be noted that if the radius of the circular detection area occupied by the scanned area is small, the updated obstacle distance state value for the current scanned area is considered to affect adjacent areas. Therefore, a range function is added to the updates of the two adjacent detection areas i-1 and i+1. i ,Right now:

[0109] range i-1 =min(range) i-1 ,range i );

[0110] range i+1 =min(range) i+1 ,range i ).

[0111] S280 determines the drivable area of ​​the vehicle based on the obstacle points that match each scanned area.

[0112] The technical solution of this application embodiment removes scene noise through activation function. After removing outlier point sets, a clustered fusion point set in Cartesian coordinates is obtained, and the point set is converted into polar coordinates to obtain the position distribution of obstacles in polar coordinates.

[0113] Example 3

[0114] Figure 5 This is a flowchart of a microwave radar image determination method for target detection provided in Embodiment 3 of the present invention. This embodiment optimizes the microwave radar image determination process based on the above embodiment.

[0115] like Figure 5 As shown, the method in this embodiment specifically includes the following steps:

[0116] S310: Obtain the signal strength of each reflected wave at different distances from the microwave radar when the microwave radar is rotated and scanned at a preset azimuth angle with the microwave radar as the origin.

[0117] The technical solution of this application embodiment detects targets using microwave radar, the location of which is as follows: Figure 6As shown, this can be a single-transmitter, single-receiver mechanically scanning microwave radar. The radar rotates around its center, continuously transmitting and receiving frequency-modulated radio waves. The divergent dashed lines emitted by the radar represent the radar's detection signals; the directions corresponding to two adjacent detection signals are adjacent detection directions; the angle between two adjacent detection signals is a preset azimuth angle; and adjacent position points are points equidistant from the radar along adjacent detection directions. Figure 7 Points A and B in the diagram.

[0118] A reflected wave is the echo of a radar signal that has been reflected back to the radar and received by the radar. The signal strength of the reflected wave can be detected by microwave radar. The signal strength of the reflected wave corresponding to a certain location in the environment can indicate whether an obstacle exists at that location, and the location, size, and shape of the obstacle can be determined based on the signal strength of the reflected wave. The detection direction of each radar signal transmission can be characterized by an azimuth angle, which is the horizontal angle between the radar's north direction line and the detection direction in a clockwise direction. When the radar detects each azimuth angle, a corresponding reflected wave signal strength is obtained at each location point at a different distance from the radar at that azimuth angle. Each azimuth angle corresponds to multiple signal strengths, resulting in a one-dimensional signal strength. As the radar rotates and scans once, a two-dimensional signal strength corresponding to each location point can be formed in polar coordinates.

[0119] S320 performs interpolation processing on the signal intensity of each reflected wave.

[0120] In this embodiment, different weights can be selected based on the signal strength of adjacent locations to determine the signal strength at the interpolation location. For example, the signal strength of adjacent locations is S. A and S B Let their weights be ω1 and ω2, and the signal strength at the interpolation point be S. C Then S C =S A ×ω1+S B ×ω2.

[0121] Specifically, intensity interpolation between adjacent location points can be performed by interpolating along an arc centered on the radar and with the adjacent location points as endpoints, to obtain the interpolated location points. For example... Figure 8 As shown. Interpolation point C and interpolation point D are located within a circle centered on the radar. This is obtained by interpolation. The intervals between the interpolation points can be equal or unequal. For example... Figure 8 As shown, points A and B are adjacent locations, and points C and D are interpolation points located between points A and B. The distances from A, B, C, and D to the radar are the same. Therefore, the signal strength at point C is... Signal strength at point D

[0122] S330: Based on the interpolated signal strengths and the predetermined mapping relationship between signal strengths and grayscale values, the grayscale values ​​of each pixel in the microwave radar image to be identified are obtained.

[0123] For example, if using This represents the signal strength matrix obtained from the Weibo radar, where M represents the Mth azimuth angle and N represents the Nth sample number. The signal strength matrix obtained after interpolation using the method in S320 is as follows:

[0124]

[0125] in `%` indicates rounding down, `%` indicates the remainder operation, and `round()` rounds to the nearest integer. After interpolation, the angular interval between two adjacent beams is... At points at the same distance from the microwave radar, the angular interval between adjacent beams is also equal.

[0126] The microwave radar image F to be identified is represented as a gray value matrix with P rows and Q columns:

[0127]

[0128] Among them, f pq This represents the grayscale value of the pixel at position (p, q).

[0129] The process of determining the mapping relationship between signal intensity and grayscale value can be as follows: determine the size of the scanning area and the area size corresponding to the pixel in the microwave radar image to be identified; determine the mapping relationship between the pixel coordinates and Cartesian coordinates of the pixel in the microwave radar image to be identified based on the size of the scanning area and the area size corresponding to the pixel; determine the mapping relationship between the grayscale value of the pixel in the microwave radar image to be identified and each signal intensity based on the mapping relationship between the pixel coordinates and Cartesian coordinates, and the mapping relationship between Cartesian coordinates and polar coordinates.

[0130] Wherein, the size of the scanning area is denoted as PΔ×QΔ, the region corresponding to the pixel is denoted as a square region with a side length of Δ meters, and the mapping relationship between the pixel coordinates of the pixel in the microwave radar image to be identified and the coordinates in the Cartesian coordinate system can be expressed as:

[0131]

[0132] Where (x,y) are Cartesian coordinates and (p,q) are pixel coordinates.

[0133] The mapping relationship between Cartesian coordinates and polar coordinates can be expressed as:

[0134]

[0135]

[0136] Where (r,θ) are polar coordinates, and || represents an OR relationship.

[0137] Finally, the mapping relationship between the grayscale values ​​of pixels in the microwave radar image to be identified and the signal intensities can be obtained:

[0138]

[0139] Therefore, based on the signal intensity matrix obtained during microwave radar scanning, the gray values ​​of each pixel in the microwave radar image to be identified can be determined according to the pre-determined mapping relationship between the gray values ​​of the pixels and each signal intensity.

[0140] S340, based on the gray value matrix corresponding to each microwave radar image, obtain the clustered fusion point set.

[0141] S350, determine at least two scanning regions, and determine obstacle points that match each scanning region based on the clustered fusion point set.

[0142] S360 determines the drivable area of ​​the vehicle based on obstacle points that match each scanned area.

[0143] The technical solution of this application involves acquiring the signal intensity of reflected waves at different distances from the microwave radar during a rotating microwave radar scan with a preset azimuth angle as the origin; interpolating the signal intensity of each reflected wave; and obtaining the grayscale value of each pixel in the microwave radar image to be identified based on the interpolated signal intensity and a pre-determined mapping relationship between signal intensity and grayscale value. This technical solution determines the signal intensity at more locations through interpolation, improving radar detection density. Furthermore, the pre-determined mapping relationship between signal intensity and grayscale value allows for the rapid determination of the signal intensity corresponding to each pixel in the microwave radar image to be identified.

[0144] Example 4

[0145] Figure 9 This is a schematic diagram of a device for determining a drivable area according to Embodiment 4 of the present invention. This device can execute the method for determining a drivable area provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. For example... Figure 9 As shown, the device includes:

[0146] The image acquisition module 410 is used to acquire microwave radar images detected by at least two microwave radars; wherein the position point of each microwave radar is located on a plane passing through the midpoint of the rear axle of the vehicle and perpendicular to the rear axle of the vehicle.

[0147] The grayscale value of each pixel in the microwave radar image is used to reflect the signal strength of the reflected wave when the microwave radar is scanned with the microwave radar as the origin.

[0148] The clustering fusion point set determination module 420 is used to obtain the clustering fusion point set based on the gray value matrix corresponding to each microwave radar image;

[0149] The obstacle point determination module 430 is used to determine at least two scanning regions and, based on the clustered fusion point set, determine the obstacle points that match each scanning region.

[0150] The drivable area determination module 440 is used to determine the drivable area of ​​the vehicle based on the obstacle points that match each scanned area.

[0151] Optionally, the image acquisition module 410 includes:

[0152] The signal strength acquisition unit is used to acquire the signal strength of each reflected wave at different distances from the microwave radar when the microwave radar is rotated and scanned at a preset azimuth angle with the microwave radar as the origin.

[0153] An interpolation processing unit is used to interpolate the signal intensity of each reflected wave;

[0154] The grayscale value determination unit is used to obtain the grayscale value of each pixel in the microwave radar image to be identified based on the interpolated signal strengths and the pre-determined mapping relationship between signal strengths and grayscale values.

[0155] Optionally, the microwave radar images include roof-mounted microwave radar images and under-vehicle microwave radar images; the clustering and fusion point set determination module 420 includes:

[0156] The function mapping unit is used to perform activation function mapping on the gray value matrix corresponding to each microwave radar image based on the scene noise gray value; the scene noise gray value is the mode of each gray value in the gray value matrix corresponding to the roof microwave radar image.

[0157] The Cartesian coordinate point set determination unit is used to transform each gray value matrix after the activation function mapping into a Cartesian coordinate system to obtain a Cartesian coordinate point set that matches each gray value matrix.

[0158] The clustering fusion unit is used to cluster and fuse the Cartesian coordinate point set that matches each gray value matrix to obtain the clustered fusion point set.

[0159] Optionally, the cluster fusion point set determination module 420 includes:

[0160] The outlier set determination unit is used to perform density-based nonparametric clustering on the Cartesian coordinate point sets that match each gray value matrix to obtain the outlier point sets that match each Cartesian coordinate point set.

[0161] The fusion point set determination unit is used to merge the Cartesian coordinate point sets after removing outlier points to obtain the Cartesian coordinate fusion point set.

[0162] The coordinate transformation unit is used to perform polar coordinate transformation on the Cartesian coordinate fusion point set to obtain the clustered fusion point set;

[0163] The polar coordinate system in which the clustered fusion point set is located has the midpoint of the rear axle of the vehicle as the pole, the direction of vehicle travel as the polar axis, and takes the clockwise angle as positive.

[0164] Optionally, defining at least two scan regions can specifically include:

[0165] A circular detection area is determined with the center of the rear axle of the vehicle as the center and the preset maximum detection distance as the radius;

[0166] The circular detection area is divided into scanning areas according to the preset number of segments; wherein the area of ​​each scanning area is equal.

[0167] Optionally, the obstacle point determination module 430 includes:

[0168] The scan value determination unit is used to determine the obstacle distance scan value for the target scan area based on the clustered fusion point set.

[0169] The status value update unit is used to update the obstacle distance status value based on the obstacle distance scan value, the obstacle distance status value, and the number of consecutive updates of the obstacle distance status value if the difference between the obstacle distance scan value and the obstacle distance status value is less than a preset threshold.

[0170] The obstacle distance status value is used to represent the distance of the nearest obstacle to the midpoint of the vehicle's rear axle in the target scan area at the current moment.

[0171] Optionally, the state value update unit includes:

[0172] The first state value update subunit is used to update the obstacle distance state value if the number of consecutive updates of the obstacle distance state value is less than a first value. The first weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the first weight is used as the weight of the obstacle distance state value.

[0173] The second state value update subunit is used to update the obstacle distance state value if the number of consecutive updates of the obstacle distance state value is greater than or equal to the first value and less than the second value. The second weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the second weight is used as the weight of the obstacle distance state value.

[0174] The third state value update subunit is used to update the obstacle distance state value if the number of consecutive updates of the obstacle distance state value is greater than or equal to the third value and less than the fourth value. The third weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the third weight is used as the weight of the obstacle distance state value.

[0175] The fourth state value update subunit is used to update the obstacle distance state value based on the average of the obstacle distance scan value and the obstacle distance state value if the number of consecutive updates of the obstacle distance state value is greater than or equal to the fourth value.

[0176] Among them, the first value is less than the second value, the second value is less than the third value, and the third value is less than the fourth value; the first weight is less than the second weight, and the second weight is less than the third weight.

[0177] The device for determining a drivable area provided in this embodiment of the invention can execute a method for determining a drivable area provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0178] Example 5

[0179] Figure 10 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0180] like Figure 10As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0181] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0182] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining a drivable area.

[0183] In some embodiments, the method for determining the drivable area may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the drivable area described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the drivable area by any other suitable means (e.g., by means of firmware).

[0184] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0185] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0186] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0187] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0188] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0189] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0190] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0191] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of determining a drivable area, characterized by, include: Acquire microwave radar images detected by at least two microwave radars; wherein the location of each microwave radar is on a plane passing through the midpoint of the rear axle of the vehicle and perpendicular to the rear axle of the vehicle; The grayscale value of each pixel in the microwave radar image is used to reflect the signal strength of the reflected wave when the microwave radar is scanned with the microwave radar as the origin. Based on the gray value matrix corresponding to each microwave radar image, a clustered fusion point set is obtained; Identify at least two scanning regions, and determine the obstacle points that match each scanning region based on the clustered fusion point set; The drivable area of ​​the vehicle is determined based on the obstacle points that match each scanned area; The microwave radar images include roof microwave radar images and under-vehicle microwave radar images. Based on the grayscale value matrix corresponding to each microwave radar image, a clustered fusion point set is obtained, including: Based on the scene noise grayscale value, an activation function is applied to the grayscale matrix corresponding to each microwave radar image; the scene noise grayscale value is the mode of each grayscale value in the grayscale matrix corresponding to the roof microwave radar image. The gray value matrices mapped by the activation function are transformed into Cartesian coordinates to obtain a set of Cartesian coordinate points that match each gray value matrix. Clustering and merging of the Cartesian coordinate point set that matches each gray value matrix yields a clustered and merged point set.

2. The method of claim 1, wherein, Acquire microwave radar images obtained from at least two microwave radar detectors, including: The signal strength of each reflected wave at different distances from the microwave radar is obtained when the microwave radar is rotated and scanned at a preset azimuth angle with the microwave radar as the origin. Interpolation processing is performed on the signal intensity of each reflected wave; Based on the interpolated signal strengths and the predetermined mapping relationship between signal strengths and grayscale values, the grayscale values ​​of each pixel in the microwave radar image to be identified are obtained.

3. The method of claim 1, wherein, Clustering and merging of the Cartesian coordinate point sets matching each grayscale value matrix yields a clustered and merged point set, including: Density-based nonparametric clustering is performed on the Cartesian coordinate point sets that match each gray value matrix to obtain the outlier point sets that match each Cartesian coordinate point set. After removing outlier points from each Cartesian coordinate point set, they are merged to obtain a Cartesian coordinate fused point set. Perform polar coordinate transformation on the Cartesian coordinate fusion point set to obtain the clustered fusion point set; The polar coordinate system in which the clustered fusion point set is located has the midpoint of the rear axle of the vehicle as the pole, the direction of vehicle travel as the polar axis, and takes the clockwise angle as positive.

4. The method of claim 3, wherein, Identify at least two scan regions, including: A circular detection area is determined with the center of the rear axle of the vehicle as the center and the preset maximum detection distance as the radius; The circular detection area is divided into scanning areas according to a preset number of segments; wherein each scanning area has an equal area.

5. The method of claim 3, wherein, Based on the clustered fusion point set, obstacle points matching each scanned region are determined, including: For the target scanning area, the obstacle distance scanning value is determined based on the clustered fusion point set; If it is determined that the difference between the obstacle distance scan value and the obstacle distance status value is less than a preset threshold, then the obstacle distance status value is updated according to the obstacle distance scan value, the obstacle distance status value, and the number of consecutive updates of the obstacle distance status value; The obstacle distance status value is used to represent the distance of the nearest obstacle to the midpoint of the vehicle's rear axle in the target scan area at the current moment.

6. The method according to claim 5, characterized in that, The obstacle distance status value is updated based on the obstacle distance scan value, the obstacle distance status value, and the number of consecutive updates to the obstacle distance status value, including: If it is determined that the number of consecutive updates of the obstacle distance status value is less than the first value, then the first weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the first weight is used as the weight of the obstacle distance status value, and the obstacle distance status value is updated. If it is determined that the number of consecutive updates of the obstacle distance status value is greater than or equal to the first value and less than the second value, then the second weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the second weight is used as the weight of the obstacle distance status value, and the obstacle distance status value is updated accordingly. If it is determined that the number of consecutive updates of the obstacle distance status value is greater than or equal to the third value and less than the fourth value, then the third weight is used as the weight of the obstacle distance scan value, and the value of 1 minus the third weight is used as the weight of the obstacle distance status value, and the obstacle distance status value is updated accordingly. If it is determined that the number of consecutive updates to the obstacle distance status value is greater than or equal to the fourth value, then the obstacle distance status value is updated based on the average of the obstacle distance scan value and the obstacle distance status value. Among them, the first value is less than the second value, the second value is less than the third value, and the third value is less than the fourth value; the first weight is less than the second weight, and the second weight is less than the third weight.

7. A device for determining a drivable area, characterized in that, include: The image acquisition module is used to acquire microwave radar images detected by at least two microwave radars; wherein the position point of each microwave radar is located on a plane passing through the midpoint of the rear axle of the vehicle and perpendicular to the rear axle of the vehicle. The grayscale value of each pixel in the microwave radar image is used to reflect the signal strength of the reflected wave when the microwave radar is scanned with the microwave radar as the origin. The clustering fusion point set determination module is used to obtain the clustering fusion point set based on the gray value matrix corresponding to each microwave radar image; The obstacle point determination module is used to determine at least two scanning regions and, based on the clustered fusion point set, determine the obstacle points that match each scanning region. The drivable area determination module is used to determine the drivable area of ​​the vehicle based on the obstacle points that match each scanned area. The microwave radar images include roof-mounted microwave radar images and under-vehicle microwave radar images; the clustering and fusion point set determination module includes: The function mapping unit is used to perform activation function mapping on the gray value matrix corresponding to each microwave radar image based on the scene noise gray value; the scene noise gray value is the mode of each gray value in the gray value matrix corresponding to the roof microwave radar image. The Cartesian coordinate point set determination unit is used to transform each gray value matrix after the activation function mapping into a Cartesian coordinate system to obtain a Cartesian coordinate point set that matches each gray value matrix. The clustering fusion unit is used to cluster and fuse the Cartesian coordinate point set that matches each gray value matrix to obtain the clustered fusion point set.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the method for determining the drivable area according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining a drivable area as described in any one of claims 1-6.

Images