A method, apparatus, equipment and medium for detecting blind spots in automobiles.

Abstract

This application discloses a method, apparatus, device, and medium for detecting blind spots in vehicles. The method involves acquiring at least two sets of echo data received when a radar detection wave detects an area under test. The radar is installed at the rear of the vehicle under test. Beamforming is performed on the echo data in at least three preset lane directions behind the vehicle to obtain at least three main echo beams. Each main echo beam includes a correspondence between target distance and echo energy. Based on this correspondence, the speed information of the vehicle under test and the lane information of candidate target points in each frame of each main echo beam are determined. Each candidate target point is a target point corresponding to at least one peak point. Based on the speed information and lane information, a target vehicle entering the blind spot of the vehicle under test is identified. This technical solution enables accurate lane location determination for vehicles approaching from behind the vehicle under test, thereby accurately identifying vehicles within the vehicle's blind spot.

Description

Technical Field

[0001] This application relates to the field of sensor technology, and in particular to a method, device, equipment and medium for detecting blind spots in automobiles. Background Technology

[0002] A vehicle's blind spot refers to the area that a driver cannot directly observe when in a normal driving position because their view is obstructed by the vehicle body. Vehicle blind spots mainly include the front blind spot, rear blind spot, rearview mirror blind spot, A / B pillar blind spot, and driver-caused blind spot. Among these, traffic accidents caused by rearview mirror blind spots account for the majority, mostly due to drivers failing to notice nearby vehicles in time when overtaking or changing lanes due to inattention. Experiments have shown that if drivers could detect danger one second in advance and take necessary evasive action, the accident rate could be reduced by 90%. Therefore, research on vehicle blind spot monitoring systems is of great significance.

[0003] Currently, blind spot detection technologies mainly include: 1) Machine vision technology, which utilizes machine learning and image processing methods to capture road conditions in real time via a camera, then analyzes and learns from the captured images to identify vehicles and obstacles in blind spots. This method has high accuracy in identifying vehicles and obstacles, but it is highly dependent on the environment; its performance is significantly reduced in adverse conditions such as darkness, strong light, heavy fog, and heavy rain. 2) Ultrasonic monitoring technology, which calculates the distance between the sensor and the target by measuring the time it takes to emit sound waves and receive the reflected echoes. It has low hardware costs, strong signal penetration, and can work in all weather conditions, but it only provides single-dimensional distance information and only monitors in one direction, making it suitable only for blind spot monitoring of vehicles at low speeds. 3) Radar monitoring technology, which works by emitting electromagnetic waves and then analyzing and processing the echo signals. Radar sensors include lidar and millimeter-wave radar. Lidar has advantages such as high measurement accuracy, wide detection range and strong stability, but it is expensive and has insufficient anti-interference ability, and cannot be used in adverse weather conditions such as rain, snow and fog.

[0004] Therefore, how to provide a technical solution with strong anti-interference ability and accurate detection of blind spots in automobiles is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This application provides a method, device, equipment, and medium for detecting blind spots in vehicles, so as to accurately determine and locate the lane of vehicles approaching from behind the vehicle under test, and thus accurately identify vehicles in the blind spot.

[0006] According to one aspect of this application, a method for detecting blind spots in a vehicle is provided, the method comprising:

[0007] Acquire at least two sets of echo data received when the radar detection wave detects the area to be tested; wherein the radar is installed at the rear of the vehicle to be tested;

[0008] The echo data is beamformed in at least three preset lane directions behind the vehicle under test to obtain at least three main echo beams; wherein, the three preset lane directions include the lane direction where the vehicle under test is located, the lane direction to the left of the vehicle under test, and the lane direction to the right of the vehicle under test; each main echo beam includes at least one frame of main echo beam; the main echo beam includes the correspondence between target distance and echo energy; the target distance is the distance between the target point and the radar;

[0009] Based on the correspondence, the speed information of the vehicle under test and the lane information of the candidate target points in each frame of each echo main beam are determined; wherein, the candidate target point is the target point corresponding to at least one peak point;

[0010] Based on the speed information and the lane information, the target vehicle entering the blind spot of the vehicle under test is determined.

[0011] According to another aspect of this application, a vehicle blind spot detection device is provided, the device comprising:

[0012] The echo data acquisition module is used to acquire at least two sets of echo data received by the radar detection wave when detecting the area to be tested; wherein, the radar is installed at the rear of the vehicle to be tested;

[0013] A beamforming module is used to beamform the echo data in at least three preset lane directions behind the vehicle under test to obtain at least three main echo beams; wherein, the three preset lane directions include the lane direction where the vehicle under test is located, the lane direction to the left of the vehicle under test, and the lane direction to the right of the vehicle under test; each main echo beam includes at least one frame of main echo beam; the main echo beam includes the correspondence between target distance and echo energy; the target distance is the distance between the target point and the radar;

[0014] The lane positioning module is used to determine the speed information of the vehicle under test and the lane information of candidate target points in each frame of each echo main beam according to the correspondence; wherein, the candidate target point is the target point corresponding to at least one peak point;

[0015] The blind spot vehicle detection module is used to determine the target vehicle entering the blind spot of the vehicle under test based on the speed information and the lane information.

[0016] According to another aspect of this application, a vehicle blind spot detection device is provided, the device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] 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 vehicle blind spot detection method according to any embodiment of this application.

[0020] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle blind spot detection method according to any embodiment of this application.

[0021] The technical solution provided in this application acquires at least two sets of echo data received when a radar detection wave detects an area under test. The radar is installed at the rear of the vehicle under test. The echo data is beamformed in at least three preset lane directions behind the vehicle to obtain at least three main echo beams. These three preset lane directions include the lane direction where the vehicle is located, the lane direction to the left of the vehicle, and the lane direction to the right of the vehicle. The main echo beams include a correspondence between target distance and echo energy. Based on this correspondence, the speed information of the vehicle under test and the lane information of candidate target points in each frame of each main echo beam are determined. The candidate target point is the target point corresponding to at least one peak point in the correspondence. Based on the speed information and lane information, the target vehicle entering the blind spot of the vehicle under test is identified. This technical solution enables accurate positioning of vehicles approaching from behind the vehicle under test, thereby accurately identifying vehicles in the vehicle's blind spot.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for detecting blind spots in a vehicle according to Embodiment 1 of the present invention;

[0025] Figure 2This is a schematic diagram of the formation of an echo main beam according to Embodiment 1 of the present invention;

[0026] Figure 3a This is a schematic diagram illustrating the correspondence of the main echo beams when the vehicle under test is traveling at high speed, as provided in Embodiment 1 of the present invention.

[0027] Figure 3b This is a schematic diagram of the correspondence between the main echo beams when the vehicle under test is traveling at low speed, as provided in Embodiment 1 of the present invention.

[0028] Figure 4 A flowchart illustrating a method for detecting blind spots in a vehicle, provided in Embodiment 2 of this application;

[0029] Figure 5 This is a schematic diagram of the structure of a vehicle blind spot detection device provided in Embodiment 3 of this application;

[0030] Figure 6 This is a schematic diagram of the structure of a device for implementing a vehicle blind spot detection method according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," "candidate," etc., used in the specification, claims, and accompanying drawings of this application 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 the embodiments of this application 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.

[0033] Example 1

[0034] Figure 1This is a flowchart of a method for detecting blind spots in a vehicle according to Embodiment 1 of the present invention. This embodiment is applicable to situations involving the detection of blind spots in vehicles. The method can be executed by a vehicle blind spot detection device, which can be implemented in hardware and / or software. This vehicle blind spot detection device can be configured in a device with data processing capabilities. Figure 1 As shown, the method includes:

[0035] S110. Acquire at least two sets of echo data received by the radar detection wave when detecting the area to be tested. The radar is installed at the rear of the vehicle under test.

[0036] The area to be detected can be the blind spot of the vehicle under test, such as the rear of the vehicle, the front of the vehicle, or the A and B pillars. In this embodiment of the invention, the radar can be installed at the rear of the vehicle under test to detect vehicles approaching from behind and identify vehicles entering the blind spot behind the vehicle under test.

[0037] Specifically, after the radar emits electromagnetic waves towards the rear of the vehicle under test, it receives at least two sets of echo data through at least two receiving antennas. For example, a dual-channel millimeter-wave radar with one transmitter and two receivers can be used to obtain two sets of echo data. Generally, N receiving antennas can detect N-1 targets, but by adopting the above technical solution, the shortcomings of dual-channel radar in complex road environments, which make it difficult to detect multiple target angles due to insufficient number of receiving antennas, can be overcome.

[0038] Optionally, after receiving the echo data, the echo data can be preprocessed to eliminate or reduce background clutter. For example, clutter suppression algorithms can be used to remove background clutter interference from the echo data. Specifically, multiple frequency-modulated continuous waves are continuously transmitted within each frame, and the echo data is subjected to a fast time-dimensional fast Fourier transform to obtain the range fast Fourier transform result. The average value is recorded as the background clutter, and the energy of each echo data is subtracted from the energy of the background clutter, which makes the target in the received echo data more visible.

[0039] S120. Beamforming is performed on the echo data in at least three preset lane directions behind the vehicle under test to obtain at least three main echo beams. The three preset lane directions include the lane direction where the vehicle under test is located, the lane direction to the left of the vehicle under test, and the lane direction to the right of the vehicle under test. Each main echo beam includes at least one frame of main echo beam. The main echo beam includes the correspondence between target distance and echo energy; the target distance is the distance between the target point and the radar.

[0040] The echo main beam can be beamformed from the echo data using a beamformer. Since a beamformer can amplify the signal in the directional direction and suppress signals in other directions, it can be used to beamform at least two preset lane directions behind the vehicle under test, so as to analyze the signals in different lane directions and reduce interference from strong targets.

[0041] The preset lane direction can be the lane where the vehicle under test is located and the adjacent lanes. In this embodiment of the invention, the angle pointing to the main echo beam can be determined based on the main lobe width of the echo main beam and the road width to ensure that the formed echo main beam can cover the preset lane range.

[0042] Specifically, the width of a motor vehicle lane is the standard width, for example, 3.5 meters per lane on urban roads and 3.75 meters per lane on trunk roads or expressways. The main lobe width of the echo beam can be determined using the following formula: Where Δθ is the main lobe width, M represents the number of array elements, θ represents the angle of the main echo beam, λ represents the wavelength, and d represents the spacing between array elements.

[0043] For example, Figure 2 This is a schematic diagram illustrating the formation of the echo main beam according to Embodiment 1 of the present invention. Figure 2 As shown, vehicle A is the vehicle under test. Beamforming is performed on the lane containing vehicle A and the two lanes to its left and right using the echo data received by the radar installed at the rear of vehicle A, resulting in three main echo beams pointing to θ0, θ1, and θ2. Each sector represents the main lobe width range of each main echo beam; for example, the main lobe width range of the main echo beam pointing to θ0 is Δθ0. β1 represents the angle between the line connecting the centers of vehicles A and B and the lane containing vehicle A. β1 increases as vehicle B approaches, therefore, when... At that time, it is clear that vehicle B is within the main lobe width range of the echo main beam pointing to θ2. Therefore, the echo energy of vehicle B in the echo main beam pointing to θ2 is increased, and its energy is relatively high. The echo energy in the echo main beam pointing to θ0 is suppressed, and its energy is relatively low.

[0044] S130. Based on the correspondence, determine the speed information of the vehicle under test and the lane information of candidate target points in each frame of each echo main beam. The candidate target point is the target point corresponding to at least one peak point in the correspondence.

[0045] Among them, speed information is used to indicate whether the vehicle under test is at high or low speed, and lane information is used to indicate that the candidate target point is located in the lane where the vehicle under test is located or in the adjacent lane.

[0046] Furthermore, since the detection targets are located in the blind spots of vehicles, the candidate target points can be selected from those closest to the vehicle under test. Specifically, the candidate target points can be the target points corresponding to at least one peak point in the correspondence relationship that is closest to the vehicle under test. Candidate target points can be categorized according to different echo main beams and stored in frame order.

[0047] It should be noted that, due to the reflection of electromagnetic waves upon impact with the ground, when the vehicle under test is at low speed, there is no relative change between the radar and the ground in a short period of time. Therefore, multiple echo data within a single frame will not show significant differences in the reflected signals from the ground. However, when the vehicle under test is at high speed, the relative change between the radar and the ground is more likely to occur in a short period of time due to the high speed. Therefore, after background clutter suppression, it is clear that multiple echo data within a short period of time show significant differences. Thus, background clutter suppression methods cannot remove the ground background when the vehicle under test is at high speed. Consequently, this provides a characteristic point, or prominent point, for determining the speed information of the vehicle under test.

[0048] Therefore, when the vehicle under test is at a low speed, the candidate target point can be at least one peak point in the correspondence that is closest to the vehicle under test; when the vehicle under test is at a high speed, the candidate target point can be at least one peak point in the correspondence that is closest to the vehicle under test, excluding the prominent point.

[0049] As an optional but non-limiting implementation, the speed information of the vehicle under test is determined based on the aforementioned correspondence, including but not limited to the following steps A1-A2:

[0050] Step A1: Determine the echo energy of the prominent points according to the correspondence. The prominent points are the points obtained by ground reflection in each frame of the main echo beam.

[0051] Specifically, based on the correspondence between target distance and echo energy in the main echo beam, the echo energy corresponding to the range with significant differences in the correspondence is determined.

[0052] For example, Figure 3a This is a schematic diagram illustrating the correspondence between the main beam echoes of a vehicle under test traveling at high speed, as provided in Embodiment 1 of the present invention. Figure 3b This is a schematic diagram illustrating the correspondence between the main beam echoes of a vehicle under test traveling at low speed, as provided in Embodiment 1 of the present invention. Figure 3a As shown, when the vehicle under test is traveling at high speed, distinct features appear within a radar distance of 1 to 3 meters. Based on the correspondence on the right, the echo energy of these distinct features is 250. (As shown...) Figure 3bAs shown, when the vehicle under test is traveling at low speed, the output of the main echo beam does not show any significant differences.

[0053] Step A2: Determine the speed information of the vehicle under test based on the echo energy of the special point and the third threshold.

[0054] The third threshold can be a threshold obtained from a large number of experimental tests. Specifically, the third threshold is th3. If the echo energy L3 of the salient point is greater than th3, the vehicle under test is determined to be in a high-speed condition; otherwise, the vehicle under test is determined to be in a low-speed condition.

[0055] Furthermore, depending on the speed of the vehicle under test, subsequent parameters can be adjusted, such as the position parameter association threshold or the minimum length threshold of the real target trajectory, thereby improving the accuracy and robustness of vehicle blind spot monitoring under different road conditions.

[0056] As an optional but non-limiting implementation, the lane information of candidate target points in each frame of each echo main beam is determined according to the correspondence, including but not limited to the following steps B1-B3:

[0057] Step B1: Based on the aforementioned correspondence, determine the moving average amplitude value corresponding to each target distance in each frame of each echo main beam. The moving average amplitude value is the weighted average of the moving average amplitude value of the previous frame corresponding to the same target distance for each echo main beam and the echo energy of the current frame.

[0058] Specifically, the moving average amplitude value of the current frame = α × the moving average amplitude value of the previous frame + (1-α) × the echo energy of the current frame; where α ranges from (0, 1), and α is the weighting coefficient of the moving average amplitude value of the previous frame. For example, the moving average amplitude value of the current frame can be the sum of 30% of the moving average amplitude value of the previous frame and 70% of the echo energy of the current frame.

[0059] By performing a moving average on the amplitude value of each frame, the amplitude value of the candidate target point can be made relatively smooth and stable in each frame.

[0060] Step B2: Based on the moving average amplitude values, generate new correspondences for each frame of each echo main beam, and select at least one target point corresponding to a peak point from the new correspondences as a candidate target point.

[0061] Step B3: For each candidate target point corresponding to the same frame, determine the lane information of the candidate target point corresponding to the maximum moving average amplitude value based on the target distance corresponding to the maximum moving average amplitude value in the main beam of each echo and the first threshold value.

[0062] Specifically, lane information for a candidate target point can be determined by comparing the distances corresponding to the maximum moving average amplitude values ​​of the same candidate target point in the main echo beams pointing to different preset lane directions with a first threshold value. For example, the lane corresponding to the maximum value of the maximum moving average amplitude values ​​of the candidate target point in each main echo beam can be used as the lane information of the candidate target point.

[0063] As an optional but non-limiting implementation, for each candidate target point in the same frame, the lane information corresponding to the candidate target point with the maximum moving average amplitude value is determined based on the target distance corresponding to the maximum moving average amplitude value in the main beam of each echo and a first threshold value. This includes, but is not limited to, the following steps C1-C4:

[0064] Step C1: For each candidate target point in the same frame, determine the difference in target distance corresponding to the maximum moving average amplitude value in the main beams of two adjacent echoes, and determine the first comparison result between each difference and the first threshold.

[0065] To ensure that the generated echo main beam can completely cover the blind spot behind the vehicle under test, the echo main beams generated behind the vehicle under test will intersect in pairs. That is, the two adjacent echo main beams will have a common coverage area. When a vehicle behind the vehicle under test enters this range, the two adjacent echo main beams can detect the target with a high amplitude value, and therefore cannot determine the lane of the vehicle behind.

[0066] In view of the above problems, the embodiments of the present invention calculate the difference between the distances corresponding to the maximum moving average amplitude values ​​of the candidate target points in the two adjacent echo main beams, and further determine the first comparison result between the difference and the first threshold.

[0067] For example, with Figure 2 Taking an example, the difference can be determined using the following formula:

[0068]

[0069]

[0070] in, This represents the target distance corresponding to the maximum moving average amplitude of the main beam echoing the lane where the vehicle under test is located. This represents the target distance corresponding to the maximum moving average amplitude of the main echo beam pointing towards the right lane of the vehicle under test. L1 represents the target distance corresponding to the maximum moving average amplitude value of the echo main beam pointing to the left lane of the vehicle under test. L2 represents the difference between the distances corresponding to the maximum moving average amplitude value when the echo main beam points to the lane of the vehicle under test and when the echo main beam points to the right lane.

[0071] Furthermore, the comparison result can be the difference between the difference and the first threshold value.

[0072] Step C2: Determine whether the candidate target points in each echo main beam are the same target based on the first comparison result.

[0073] Specifically, if the difference L1 or L2 is less than the first threshold th1, then the candidate target points in each of the echo main beams can be determined to be the same target; otherwise, the candidate target points in each of the echo main beams can be determined to be different targets.

[0074] Step C3: If it is the same target, then the lane information of the candidate target point is determined according to the second comparison result of the ratio of the sliding average amplitude value of the candidate target point in each echo main beam and the second threshold value.

[0075] If the target is the same object and it lies within the intersection of two adjacent echo main beams, then the lane information of the candidate target point needs to be further determined. In this embodiment of the invention, the lane information of the candidate target point is determined by further comparing the ratio of the moving average amplitude value of the candidate target point in each frame of each echo main beam with a second threshold.

[0076] Specifically, when If th2 is true, then the candidate target point is considered to be more biased towards the right lane of the vehicle being tested; otherwise, it is considered to be more biased towards the lane where the vehicle is located. Here, th2 is the second threshold value. If the distance is equal to the distance between the two lanes, the candidate target point is considered to be more inclined towards the left lane of the vehicle being tested; otherwise, it is considered to be more inclined towards the lane where the vehicle is located. This represents the sliding average amplitude value of the candidate target point in the main echo beam pointing towards the lane where the vehicle under test is located. This represents the sliding average amplitude value of the candidate target point in the main echo beam pointing to the right lane of the vehicle under test. This represents the sliding average amplitude value of the candidate target point in the main echo beam pointing to the left lane of the vehicle under test.

[0077] Optionally, after determining the lane information of the candidate target point, the candidate target point in the echo main beam corresponding to the lane information can be used as the target to be tracked, and the other candidate target point can be eliminated.

[0078] Step C4: If they are different targets, the lane where the echo main beam of the candidate target point is located is taken as the lane information of the candidate target point.

[0079] Specifically, if the targets are different, the candidate target points detected in the echo main beams pointing to different preset lane directions are determined to be from different targets. Therefore, the lane where the echo main beam corresponding to the candidate target point is located is taken as the lane information of the candidate target point.

[0080] Optionally, after determining the lane information of the candidate target points, the candidate target points in each echo main beam are taken as the targets to be tracked.

[0081] The beneficial effect of the above technical solution is that it enables accurate lane positioning of targets approaching the test vehicle in complex road environments.

[0082] S140. Based on the speed information and the lane information, determine the target vehicle that has entered the blind spot of the vehicle under test.

[0083] Specifically, the current road conditions and parameter settings of each frame of radar echo data received can be determined based on the speed information of the vehicle under test to identify whether a candidate target point entering the blind spot of the vehicle under test is a vehicle. Candidate target points can be classified according to lane information to determine their trajectory information. Then, based on the candidate target points identified as vehicles and their trajectory information, they are tracked to identify the target vehicle entering the blind spot of the vehicle under test.

[0084] This invention provides a method for detecting blind spots in vehicles. The method acquires at least two sets of echo data received when a radar detection wave detects an area under test. The radar is installed at the rear of the vehicle under test. The echo data is beamformed in at least three preset lane directions behind the vehicle to obtain at least three main echo beams. The three preset lane directions include the lane direction where the vehicle is located, the lane direction to the left of the vehicle, and the lane direction to the right of the vehicle. The main echo beams include a correspondence between target distance and echo energy. Based on this correspondence, the speed information of the vehicle under test and the lane information of candidate target points in each frame of each main echo beam are determined. The candidate target point is the target point corresponding to at least one peak point in the correspondence. Based on the speed information and lane information, the target vehicle entering the blind spot of the vehicle under test is determined. This technical solution enables accurate positioning of the lane of vehicles approaching from behind the vehicle under test, thereby accurately identifying vehicles in the vehicle's blind spot.

[0085] Example 2

[0086] Figure 4 This is a flowchart of a method for detecting blind spots in a vehicle according to Embodiment 2 of this application. This embodiment is an optimization based on the above embodiment. Figure 4 As shown, the method in this embodiment specifically includes the following steps:

[0087] S210. Acquire at least two sets of echo data received by the radar detection wave when detecting the area to be tested. The radar is installed at the rear of the vehicle under test.

[0088] S220. Beamforming is performed on the echo data in at least three preset lane directions behind the vehicle under test to obtain at least three main echo beams. The three preset lane directions include the lane direction where the vehicle under test is located, the lane direction to the left of the vehicle under test, and the lane direction to the right of the vehicle under test. Each main echo beam includes at least one frame of main echo beam. The main echo beam includes the correspondence between target distance and echo energy; the target distance is the distance between the target point and the radar.

[0089] S230. Based on the correspondence, determine the speed information of the vehicle under test and the lane information of candidate target points in each frame of each echo main beam. The candidate target point is the target point corresponding to at least one peak point in the correspondence.

[0090] S240. Based on the lane information, cluster each candidate target point in each frame of the same lane and determine the position parameters of each candidate target point in each frame.

[0091] Specifically, candidate target points can be classified according to lane information. A sliding window with a window length of k is set, and the candidate target points in the k-frame echo main beam of the same lane are density clustered. Through clustering, different vehicles and road obstacles are divided into independent targets. The cluster center point of each class after clustering is used as the position parameter of each independent target, that is, the position parameter of each candidate target point in each frame.

[0092] S250. Establish an association matrix based on the location parameters. The association matrix includes location parameters for the same candidate target point, used to represent the trajectory information of each candidate target point.

[0093] Specifically, the position parameters of candidate target points that first enter the radar detection area can be used as the initial values ​​of the trajectory. As time progresses, new candidate target points will be obtained through the echo main beam, forming new cluster centers. Data can be correlated based on position parameter information and lane positioning information to establish a correlation matrix R(i,j), where R(i,j) = abs(Rnew -R t (i,j)), R new R represents the location parameter corresponding to the new cluster center. t (i,j) represents the position parameter of the latest end of the i-th known trajectory (i.e., the j-th position parameter associated with the i-th known trajectory).

[0094] The correlation of each position parameter in the correlation matrix R(i,j) can be determined as follows. Because for candidate target points under the same driving conditions, the changes in position parameters of the candidate target points obtained from consecutive frames of the echo main beam differ depending on whether the vehicle under test is at high speed or low speed. For example, when the vehicle under test is at high speed, the changes in position parameters of the same candidate target point in each frame of the echo main beam may be large, while when the vehicle under test is at low speed, the changes in position parameters of the same candidate target point in each frame of the echo main beam may be small. Therefore, a position parameter correlation threshold R_Thre can be determined based on the speed information of the vehicle under test, and the correlation of each position parameter in the correlation matrix R(i,j) can be determined through this position parameter correlation threshold. Specifically, if min(R(i,j)) > R_Thre, the difference between the position parameters of each candidate target point in the next frame and the position parameter at the end of the current correlation matrix is ​​calculated to obtain the position change parameter for two consecutive frames. If this position change parameter is greater than the position parameter correlation threshold, it indicates that the candidate target point is not associated with the current correlation matrix, but may be a road obstacle or a newly entered radar detection range. In this case, the position parameter of the candidate target point can be used as the trajectory starting value of the correlation matrix. Otherwise, it is added to the correlation matrix.

[0095] S260. Determine the type of each candidate target point based on the correlation matrix. The types of candidate target points include vehicles and roadblocks.

[0096] Since this embodiment of the invention targets blind spot detection for vehicles, specifically targets targets within the blind spot of the vehicle under test that tend to approach the vehicle. When the vehicle under test is moving forward, if a target is approaching the vehicle in the blind spot, the type of the target can be preliminarily determined to be a vehicle. If a target is moving away from the vehicle in the blind spot, the type of the target can be preliminarily determined to be a road obstacle. Specifically, the movement trend of candidate target points can be determined by the difference between the first and last position parameters in the correlation matrix.

[0097] As an optional but non-limiting implementation, determining the type of the candidate target point based on the correlation matrix includes, but is not limited to, the following steps D1-D2:

[0098] Step D1: Based on the correlation matrix, determine the difference in the first and last position parameters of each candidate target point in the correlation matrix and the number of associated frames. The number of associated frames refers to the number of position parameters in the correlation matrix.

[0099] In R(i,j), j represents the number of associated frames. The difference can be the value of the candidate target point's position parameter at the end of the association matrix minus the value of the first position parameter.

[0100] Step D2: Determine the type of the candidate target point based on the difference and the number of associated frames.

[0101] As an optional but non-limiting implementation, the type of the candidate target point is determined based on the difference and the number of associated frames, including but not limited to the following steps E1-E2:

[0102] Step E1: Select the candidate target points with a difference less than zero as candidate vehicles.

[0103] Specifically, when the difference is less than zero, the movement trend of the candidate target point is approaching, and its type can be preliminarily determined to be a vehicle; conversely, when the difference is greater than zero, the movement trend of the candidate target point is moving away, and its type can be preliminarily determined to be a roadblock.

[0104] Step E2: If the absolute value of the difference between the candidate vehicles is greater than a preset difference and the number of associated frames for the candidate vehicles is greater than a preset number of frames, then the type of the candidate vehicle is determined to be a vehicle. The preset difference and preset number of frames are determined based on the speed information.

[0105] Due to the existence of some special road obstacles, such as guardrails, their characteristics are similar to those of vehicles, and they cannot be accurately distinguished by step E1 alone, which can easily lead to false alarms.

[0106] In view of the above problems, embodiments of the present invention determine a preset difference and a preset number of frames based on speed information to accurately distinguish between special road obstacles and vehicles. The preset difference can be the minimum length threshold L_Thre of the vehicle trajectory, and the preset number of frames can be... Here, α is a threshold parameter that can be adjusted based on actual data analysis, and v is a parameter set based on speed information. If the absolute value of the difference between candidate vehicles is greater than a preset difference and the number of associated frames for a candidate vehicle is greater than a preset number of frames, then the candidate vehicle is determined to be a vehicle; otherwise, it is determined to be a roadblock.

[0107] S270. The candidate target point is determined as a candidate target point of a vehicle as the vehicle to be tracked, and the distance between the vehicle to be tracked and the vehicle to be tested is determined.

[0108] Specifically, candidate target points identified as vehicles are continuously tracked, and their distance to the vehicle under test is determined in real time.

[0109] S280. If the distance between the vehicle to be tracked and the vehicle to be tested is less than the warning distance, then the vehicle to be tracked is determined to be the target vehicle that has entered the blind spot of the vehicle to be tested.

[0110] Specifically, if the distance between the vehicle to be tracked and the vehicle to be tested is less than the warning distance, the vehicle to be tracked is determined to be the target vehicle entering the blind spot of the vehicle to be tested, and the corresponding indicator light or voice prompt is controlled to remind the driver.

[0111] This invention provides a method for detecting blind spots in vehicles. The method acquires at least two sets of echo data received by a radar detector when detecting an area under test. The radar is installed at the rear of the vehicle under test. The echo data is beamformed in at least three preset lane directions behind the vehicle to obtain at least three main echo beams. The three preset lane directions include the lane direction where the vehicle is located, the lane direction to the left of the vehicle, and the lane direction to the right of the vehicle. Each main echo beam includes at least one frame of the main echo beam. The main echo beam includes a correspondence between target distance and echo energy. The target distance is the distance between the target point and the radar. Based on the correspondence, the speed information of the vehicle under test and the lane information of candidate target points in each frame of each main echo beam are determined. In this system, candidate target points are those with the largest amplitude value and the closest distance in the corresponding relationships. Based on lane information, each candidate target point in each frame within the same lane is clustered to determine its position parameters in each frame. An association matrix is ​​established based on these position parameters, including the position parameters of the same candidate target point to represent its trajectory information. The type of each candidate target point is determined based on the association matrix, including vehicles and road obstacles. Candidate target points classified as vehicles are identified as the vehicles to be tracked, and the distance between the tracked vehicle and the vehicle being tracked is determined. If the distance between the tracked vehicle and the vehicle being tracked is less than the warning distance, the tracked vehicle is identified as the target vehicle entering the blind spot of the vehicle being tracked. This technical solution achieves accurate identification of vehicles and road obstacles and judges the speed information of the vehicle being tracked, making it applicable to various road environments and improving the accuracy of vehicle blind spot detection.

[0112] Example 3

[0113] Figure 5 This is a schematic diagram of a vehicle blind spot detection device provided in Embodiment 3 of this application. Figure 5 As shown, the device includes:

[0114] The echo data acquisition module 310 is used to acquire at least two sets of echo data received by the radar detection wave when detecting the area to be tested; wherein, the radar is installed at the rear of the vehicle to be tested;

[0115] The beamforming module 320 is used to beamform the echo data in at least three preset lane directions behind the vehicle under test to obtain at least three main echo beams; wherein, the three preset lane directions include the lane direction where the vehicle under test is located, the lane direction to the left of the vehicle under test, and the lane direction to the right of the vehicle under test; each main echo beam includes at least one frame of main echo beam; the main echo beam includes the correspondence between target distance and echo energy; the target distance is the distance between the target point and the radar;

[0116] The lane positioning module 330 is used to determine the speed information of the vehicle under test and the lane information of candidate target points in each frame of each echo main beam according to the correspondence relationship; wherein, the candidate target point is the target point corresponding to at least one peak point in the correspondence relationship;

[0117] The blind spot vehicle detection module 340 is used to determine the target vehicle entering the blind spot of the vehicle to be tested based on the speed information and the lane information.

[0118] This invention provides a vehicle blind spot detection device. The device acquires at least two sets of echo data received when a radar detection wave detects an area under test. The radar is installed at the rear of the vehicle under test. Beamforming is performed on the echo data in at least three preset lane directions behind the vehicle to obtain at least three main echo beams. Each main echo beam includes a correspondence between target distance and echo energy. Based on this correspondence, the speed information of the vehicle under test and the lane information of candidate target points in each frame of each main echo beam are determined. Each candidate target point is a target point corresponding to at least one peak point in the correspondence. Based on the speed information and lane information, a target vehicle entering the blind spot of the vehicle under test is determined. This technical solution enables accurate lane location determination for vehicles approaching from behind the vehicle under test, thereby accurately identifying vehicles in the vehicle's blind spot. Further, a lane positioning module 330 includes:

[0119] The moving average amplitude determination unit is used to determine the moving average amplitude value corresponding to each target distance in each frame of each echo main beam according to the correspondence; wherein, the moving average amplitude value is the weighted average of the moving average amplitude value of the previous frame corresponding to the same target distance of each echo main beam and the echo energy of the current frame.

[0120] The candidate target point determination unit is used to generate new correspondences for each frame of each echo main beam based on each of the moving average amplitude values, and select at least one target point corresponding to a peak point from the new correspondences as a candidate target point.

[0121] The lane positioning unit is used to determine the lane information of the candidate target point corresponding to the maximum moving average amplitude value for each candidate target point in the same frame, based on the target distance corresponding to the maximum moving average amplitude value in the main beam of each echo and a first threshold value.

[0122] Furthermore, the lane positioning unit includes:

[0123] The first comparison result determination subunit is used to determine the difference in distances between the candidate target points in the two adjacent echo main beams for each candidate target point in the same frame, based on the maximum moving average amplitude value of the candidate target point, and to determine the first comparison result between each difference and the first threshold.

[0124] The same target determination subunit is used to determine whether the candidate target points in each echo main beam are the same target based on the first comparison result.

[0125] The first lane positioning subunit is used to determine the lane information of the candidate target point based on the second comparison result of the ratio of the sliding average amplitude value of the candidate target point in each echo main beam and the second threshold if the target is the same.

[0126] The second lane positioning subunit is used to take the lane where the echo main beam of the candidate target point is located as the lane information of the candidate target point if the target is different.

[0127] Furthermore, the lane positioning module 330 also includes:

[0128] The first target determination unit is used to determine the candidate target points as the target to be tracked if, after determining the lane information of the candidate target points, they are the same target.

[0129] The second target determination unit is used to identify candidate target points in each echo main beam as targets to be tracked if they are different targets.

[0130] Furthermore, the lane positioning module 330 includes:

[0131] The prominent point amplitude determination unit is used to determine the echo energy of the prominent point according to the correspondence; wherein, the prominent point is the point obtained by ground reflection in each frame of the echo main beam;

[0132] The vehicle speed determination unit is used to determine the speed information of the vehicle under test based on the echo energy of the special point and the third threshold.

[0133] Furthermore, the blind spot vehicle detection module 340 includes:

[0134] The target point location parameter determination unit is used to cluster each candidate target point in each frame of the same lane according to the lane information, and determine the location parameters of each candidate target point in each frame.

[0135] The target point trajectory determination unit is used to establish an association matrix based on the position parameters; wherein, the association matrix includes position parameters of the same candidate target point, which are used to represent the trajectory information of each candidate target point;

[0136] The target point type determination unit is used to determine the type of each candidate target point according to the correlation matrix; wherein, the types of candidate target points include vehicles and roadblocks;

[0137] The vehicle to be tracked unit is used to determine the type of the candidate target point as a candidate target point of a vehicle as the vehicle to be tracked, and to determine the distance between the vehicle to be tracked and the vehicle to be tested;

[0138] The blind spot vehicle detection unit is used to determine that the vehicle to be tracked is a target vehicle entering the blind spot of the vehicle to be tested if the distance between the vehicle to be tracked and the vehicle to be tested is less than the warning distance.

[0139] Furthermore, the target point type determination unit includes:

[0140] The correlation matrix parameter determination subunit is used to determine the difference between the first and last position parameters of each candidate target point in the correlation matrix and the number of correlation frames, based on the correlation matrix; wherein, the number of correlation frames is the number of position parameters in the correlation matrix;

[0141] The target point type determination subunit is used to determine the type of the candidate target point based on the difference and the associated frame number.

[0142] Furthermore, the target point type determines the sub-unit, specifically used for:

[0143] Candidate target points with a difference less than zero are selected as candidate vehicles;

[0144] If the absolute value of the difference between the candidate vehicles is greater than a preset difference and the number of associated frames of the candidate vehicles is greater than a preset number of frames, then the type of the candidate vehicle is determined to be a vehicle; wherein the preset difference and the preset number of frames are determined based on the speed information.

[0145] The blind spot detection device for automobiles provided in this application embodiment can execute the blind spot detection method for automobiles provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the method.

[0146] Example 4

[0147] Figure 6 A schematic diagram of the structure of a device 10 that can be used to implement embodiments of this application is shown. The 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 device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as 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 application described and / or claimed herein.

[0148] like Figure 6 As shown, device 10 includes at least one processor 11 and a memory, such as read-only memory (ROM) 12, random access memory (RAM) 13, etc., communicatively connected to at least one processor 11. The memory stores computer programs executable by 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 device 10. The processor 11, ROM 12, and RAM 13 are interconnected via bus 14. Input / output (I / O) interface 15 is also connected to bus 14.

[0149] Multiple components in 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 monitors, 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 device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0150] 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 methods for detecting blind spots in automobiles.

[0151] In some embodiments, the vehicle blind spot detection method 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 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 vehicle blind spot detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle blind spot detection method by any other suitable means (e.g., by means of firmware).

[0152] 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.

[0153] Computer programs used to implement the methods of this application 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.

[0154] In the context of this application, 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 can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on a device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the 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 haptic feedback); and input from the user can be received in any form (including sound input, voice input, or haptic input).

[0156] 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.

[0157] 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.

[0158] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0159] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. 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 application should be included within the scope of protection of this application.

Claims

1. A method of detecting a blind area of an automobile, characterized by, The method comprises: obtaining at least two groups of echo data received by radar detection waves when detecting a to-be-detected area; wherein the radar is installed at the tail of a to-be-detected vehicle; performing beamforming on the echo data in at least three preset lane directions behind the to-be-detected vehicle to obtain at least three echo main beams; wherein the three preset lane directions include a lane direction of the to-be-detected vehicle, a lane direction on the left side of the to-be-detected vehicle, and a lane direction on the right side of the to-be-detected vehicle; each echo main beam includes at least one frame of echo main beam; the echo main beam includes a corresponding relationship between a target distance and echo energy; the target distance is the distance between a target point and the radar; determining speed information of the to-be-detected vehicle and lane information of candidate target points in each frame of each echo main beam according to the corresponding relationship; wherein the candidate target points are target points corresponding to at least one peak point in the corresponding relationship; determining a target vehicle entering a blind area of the to-be-detected vehicle according to the speed information and the lane information; wherein the determination of the lane information of the candidate target points in each frame of each echo main beam according to the corresponding relationship comprises: determining a sliding average amplitude value corresponding to each target distance in each frame of each echo main beam according to the corresponding relationship; wherein the sliding average amplitude value is a weighted average value of a sliding average amplitude value of a previous frame corresponding to the same target distance and a current frame echo energy; generating a new corresponding relationship of each frame of each echo main beam according to each sliding average amplitude value, and selecting a target point corresponding to at least one peak point from the new corresponding relationship as a candidate target point; for each candidate target point corresponding to the same frame, determining the lane information of the candidate target point corresponding to the maximum sliding average amplitude value in each echo main beam according to the target distance corresponding to the maximum sliding average amplitude value and a first threshold value; wherein the determination of the lane information of the candidate target point corresponding to the maximum sliding average amplitude value in each echo main beam according to the target distance corresponding to the maximum sliding average amplitude value and the first threshold value for each candidate target point corresponding to the same frame comprises: for each candidate target point corresponding to the same frame, determining a difference value of the target distances corresponding to the maximum sliding average amplitude values in adjacent two echo main beams, and determining a first comparison result of each difference value and the first threshold value; determining whether the candidate target points in each echo main beam are the same target according to the first comparison result; if they are the same target, determining the lane information of the candidate target point according to a second comparison result of a ratio of the sliding average amplitude values of the candidate target point in each echo main beam and a second threshold value; if they are different targets, taking the lane of the echo main beam corresponding to the candidate target point as the lane information of the candidate target point; wherein the determination of the target vehicle entering the blind area of the to-be-detected vehicle according to the speed information and the lane information comprises: According to the lane information, each candidate target point in each frame is clustered respectively, and position parameters of each candidate target point in each frame are determined respectively; An association matrix is established according to the position parameters; wherein the association matrix includes position parameters of the same candidate target point, and is used to represent trajectory information of each candidate target point; Types of each candidate target point are determined according to the association matrix; wherein the types of the candidate target point include a vehicle and a roadblock; A candidate target point whose type is determined as a vehicle is taken as a to-be-tracked vehicle, and a distance between the to-be-tracked vehicle and the to-be-measured vehicle is determined; If the distance between the to-be-tracked vehicle and the to-be-measured vehicle is less than a pre-warning distance, the to-be-tracked vehicle is determined as a target vehicle entering a blind area of the to-be-measured vehicle.

2. The method of claim 1, wherein, After the lane information of the candidate target point is determined, the method further includes: If the same target, a candidate target point in a main echo beam corresponding to the lane information is taken as a to-be-tracked target; If different targets, candidate target points in each road main echo beam are taken as to-be-tracked targets respectively.

3. The method of claim 1, wherein, According to the corresponding relationship, speed information of the to-be-measured vehicle is determined, including: According to the corresponding relationship, echo energy of a special point is determined; wherein the special point is a point obtained by ground reflection in each frame of the main echo beam; According to the echo energy of the special point and a third threshold, speed information of the to-be-measured vehicle is determined.

4. The method of claim 1, wherein, According to the association matrix, types of the candidate target point are determined, including: According to the association matrix, a difference value between head and tail position parameters and an association frame number of each candidate target point in the association matrix are determined; wherein the association frame number is the number of position parameters in the association matrix; According to the difference value and the association frame number, types of the candidate target point are determined.

5. The method of claim 4, wherein, According to the difference value and the association frame number, types of the candidate target point are determined, including: The candidate target point with the difference value less than zero is taken as a candidate vehicle; If an absolute value of the difference value of the candidate vehicle is greater than a preset difference value and the association frame number of the candidate vehicle is greater than a preset frame number, the type of the candidate vehicle is determined as a vehicle; wherein the preset difference value and the preset frame number are determined according to the speed information.

6. A blind area detection device for a vehicle, characterized by comprising: The device includes: An echo data acquisition module is configured to acquire at least two groups of echo data received when a radar detection wave detects a to-be-measured region; wherein the radar is installed at a tail of a to-be-measured vehicle; A beam forming module is configured to perform beam forming on the echo data in at least three preset lane directions behind the to-be-measured vehicle to obtain at least three main echo beams; wherein the three preset lane directions include a lane direction of the to-be-measured vehicle, a lane direction on a left side of the to-be-measured vehicle, and a lane direction on a right side of the to-be-measured vehicle; each main echo beam includes at least one frame of main echo beam; the main echo beam includes a corresponding relationship between a target distance and echo energy; the target distance is a distance between a target point and the radar; The lane positioning module is configured to determine speed information of the to-be-tested vehicle and lane information of candidate target points in each frame of each echo main beam according to the correspondence relationship. The blind area vehicle detection module is configured to determine a target vehicle entering a blind area of the to-be-tested vehicle according to the speed information and the lane information. The lane positioning module includes: The sliding average amplitude determination unit is configured to determine a sliding average amplitude value corresponding to each target distance in each frame of each echo main beam according to the correspondence relationship; the sliding average amplitude value is a weighted average value of a sliding average amplitude value of a previous frame and echo energy of a current frame corresponding to a same target distance of each echo main beam. The candidate target point determination unit is configured to generate a new correspondence relationship for each frame of each echo main beam according to each sliding average amplitude value, and select a target point corresponding to at least one peak value point from the new correspondence relationship as a candidate target point. The lane positioning unit is configured to determine lane information of a candidate target point corresponding to a maximum sliding average amplitude value according to the target distance corresponding to the maximum sliding average amplitude value and a first threshold value for each candidate target point corresponding to a same frame. The lane positioning unit includes: The first comparison result determination subunit is configured to determine a difference value of distances corresponding to maximum sliding average amplitude values in adjacent two echo main beams for each candidate target point corresponding to a same frame, and determine a first comparison result of each difference value and a first threshold value. The same target determination subunit is configured to determine whether the candidate target points in each echo main beam are a same target according to the first comparison result. The first lane positioning subunit is configured to determine lane information of the candidate target point according to a second comparison result of a ratio of sliding average amplitude values of the candidate target point in each echo main beam and a second threshold value if the candidate target points are a same target. The second lane positioning subunit is configured to respectively take a lane where an echo main beam corresponding to the candidate target point is located as lane information of the candidate target point if the candidate target points are different targets. The blind area vehicle detection module includes: The target point position parameter determination unit is configured to cluster each candidate target point in each frame in a same lane, and determine a position parameter of each candidate target point in each frame according to the lane information. The target point trajectory determination unit is configured to establish an association matrix according to the position parameters; the association matrix includes position parameters of a same candidate target point, and is used to represent trajectory information of each candidate target point. The target point type determination unit is configured to determine a type of each candidate target point according to the association matrix; the type of the candidate target point includes a vehicle and a roadblock. The to-be-tracked vehicle determination unit is configured to take a candidate target point whose type is determined as a vehicle as a to-be-tracked vehicle, and determine a distance between the to-be-tracked vehicle and the to-be-tested vehicle. The blind area vehicle detection unit is configured to determine that the to-be-tracked vehicle is a target vehicle entering a blind area of the to-be-detected vehicle if a distance between the to-be-tracked vehicle and the to-be-detected vehicle is less than a pre-warning distance.

7. An electronic device, comprising: The device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the vehicle blind area detection method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to implement the vehicle blind area detection method of any one of claims 1-5 when executed.

Images