Front vehicle detection method, vehicle-mounted millimeter wave radar, product and vehicle

Abstract

The invention provides a front vehicle detection method, a vehicle-mounted millimeter wave radar, a product and a vehicle, and the method comprises the steps: receiving an echo signal, and processing the echo signal to obtain point cloud data; target clustering is carried out on the point cloud data, and forward target information is determined; the forward target information comprises the number, the position and the shielding state of forward targets; determining whether a potential front vehicle exists or not according to the forward target information; if yes, whether the potential front vehicle meets a track starting condition or not is determined based on continuous multi-frame radar data, and the potential front vehicle meeting the track starting condition is determined as a target front vehicle; according to the relation between the running speed variable quantity of the target front vehicle and a speed change rate threshold value, the braking behavior of the target front vehicle is recognized, and braking early warning is conducted.

Description

Technical Field

[0001] The present application relates to the field of radar technology, and in particular to a method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar, a vehicle-mounted millimeter-wave radar, a computer program product, and a vehicle. Background Art

[0002] Millimeter-wave radar detects and tracks targets by emitting and receiving electromagnetic waves, and can simultaneously measure the distance, speed, and angle of the target. Compared with cameras and lidars, millimeter-wave radars have good environmental and weather adaptability, and can adapt to application scenarios such as strong light, night, heavy rain, fog, and dust. They have been widely used in vehicle-mounted ADAS (Advanced Driving Assistance System) assisted driving systems and vehicle-mounted AD (Autonomous Driving) automatic driving systems. Through the mutual integration of cameras, lidars, and millimeter-wave radars, the redundancy of intelligent decision-making can be improved, and the high reliability and safety of ADAS assisted driving or AD automatic driving can be achieved.

[0003] In vehicle-mounted application scenarios, as the number of vehicles increases, traffic accidents caused by vehicle collisions will often occur, causing a large amount of property damage and casualties. Especially on highways, there are even multiple vehicle collisions. Therefore, monitoring and predicting the driving status of the vehicle in front and the vehicle in front blocked by the vehicle in front through the vehicle-mounted assisted driving system can effectively improve vehicle safety. However, existing vehicle-mounted assisted driving systems usually only focus on detecting the motion status of vehicles in the field of vision, while in actual vehicle-mounted application scenarios, emergency braking of blocked vehicles or non-directly visible vehicles usually causes collisions of multiple consecutive vehicles. How to detect the emergency braking behavior of blocked vehicles or non-directly visible vehicles is of great significance to improving vehicle safety. Summary of the invention

[0004] In order to solve the existing technical problems, the present application provides a front vehicle detection method based on a vehicle-mounted millimeter-wave radar, a vehicle-mounted millimeter-wave radar and a computer program product that can detect the status of the front vehicle of the obstructing vehicle.

[0005] In a first aspect, a method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar is provided, comprising:

[0006] Receiving echo signals, and processing the echo signals to obtain point cloud data;

[0007] Performing target clustering on the point cloud data to determine forward target information; the forward target information includes the number, position and occlusion status of the forward targets;

[0008] Determining whether there is a potential preceding vehicle according to the forward target information;

[0009] If so, determine whether the potential preceding vehicle satisfies a track initiation condition based on the continuous multi-frame radar data, and determine the potential preceding vehicle that satisfies the track initiation condition as the target preceding vehicle.

[0010] In a second aspect, a vehicle-mounted millimeter-wave radar is provided, comprising a millimeter-wave radar processor and a memory, wherein the memory stores a computer program executable by the millimeter-wave radar processor;

[0011] When the computer program is executed by the millimeter-wave radar processor, the method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar as described in any embodiment of the present application is implemented.

[0012] In a third aspect, a vehicle is provided, including an on-board central control system and an on-board millimeter-wave radar interactively connected to the on-board central control system;

[0013] The vehicle-mounted millimeter-wave radar is used to perform the preceding vehicle detection method based on the vehicle-mounted millimeter-wave radar described in any embodiment of the present application;

[0014] The vehicle-mounted central control system is used to output corresponding auxiliary driving information according to the detection result of the millimeter-wave radar on the target vehicle in front.

[0015] In a fourth aspect, a computer program product is provided, including a computer program, which, when executed by a processor, implements the front vehicle detection method based on the vehicle-mounted millimeter-wave radar described in any embodiment of the present application.

[0016] The preceding vehicle detection method based on the vehicle-mounted millimeter-wave radar provided in the above-mentioned embodiment receives the echo signal, processes the echo signal to obtain point cloud data, performs target clustering on the point cloud data, determines the forward target information, and uses the forward target information to determine whether there is a potential preceding vehicle blocked by the preceding vehicle, and determines whether the track starting condition is met by target tracking of the potential preceding vehicle, and determines the potential preceding vehicle that meets the track starting condition as the target preceding vehicle. In this way, it is possible to accurately detect whether there is a blocked vehicle or a non-direct-view vehicle (target preceding vehicle) that may affect the driving safety of the vehicle, and improve the assisted driving performance according to the detection result of the target preceding vehicle, such as displaying the target preceding vehicle in the current assisted driving interface; for example, the driving status of the target preceding vehicle can be further monitored to identify the braking behavior of the target preceding vehicle and perform a braking warning. By monitoring the driving status of the preceding vehicle, the braking behavior of the blocked vehicle or the non-direct-view vehicle (the preceding vehicle) can be predicted in advance, reminding the driver to predict in advance and take measures to avoid the risk of vehicle collision caused by emergency braking, thereby effectively improving driving safety.

[0017] The vehicle-mounted millimeter-wave radar, computer program product and vehicle provided in the above embodiments belong to the same concept as the corresponding embodiment of the front vehicle detection method based on the vehicle-mounted millimeter-wave radar, and thus have the same technical effect as the corresponding embodiment of the front vehicle detection method based on the vehicle-mounted millimeter-wave radar, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a diagram of optional application scenarios of a preceding vehicle detection method based on a vehicle-mounted millimeter-wave radar in one embodiment.

[0019] Figure 2 Schematic diagram of the working principle of a vehicle-mounted millimeter-wave radar in one embodiment.

[0020] Figure 3 Flowchart of a method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar in one embodiment.

[0021] Figure 4 This is a schematic diagram of a front vehicle detection scenario in an example.

[0022] Figure 5 for Figure 4 Schematic diagram of multipath propagation of electromagnetic waves in the front vehicle detection scenario in the example shown.

[0023] Figure 6 The figure is a flow chart of a preceding vehicle detection method based on a vehicle-mounted millimeter-wave radar in another embodiment.

[0024] Figure 7 A flowchart of a preceding vehicle detection method based on a vehicle-mounted millimeter-wave radar in an optional specific example.

[0025] Figure 8 A flowchart of the operation of a vehicle-mounted millimeter-wave radar in one embodiment.

[0026] Fig. 9 Schematic diagram of the structure of a vehicle-mounted millimeter-wave radar in one embodiment.

[0027] Fig.10 Schematic diagram of the structure of a vehicle in one embodiment. DETAILED DESCRIPTION

[0028] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments of the specification.

[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0030] In the following description, the expression "some embodiments" is involved, which describes a subset of all possible embodiments. It should be noted that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

[0031] In the following description, the terms "first, second, third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first, second, third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0032] Millimeter-wave radar signals have a multipath effect, and the signals can detect obscured objects through reflection, diffuse reflection, diffraction, and other methods. In the research on how to detect obscured vehicles or non-direct-view vehicles, and the detection of emergency braking behavior of detected obscured vehicles or non-direct-view vehicles, the inventors of this application proposed that this characteristic of millimeter-wave radar signals can be used to detect obscured vehicles or non-direct-view vehicles in vehicle driving scenes, and then to achieve emergency braking behavior warning. Millimeter-wave radar has irreplaceable advantages in addressing these problems that are difficult for other sensors to handle and have a high incidence of accidents.

[0033] See also Figure 1 , which is an optional application scenario diagram of the front vehicle detection method based on the vehicle-mounted millimeter wave radar provided in an embodiment of the present application applied to a vehicle. The vehicle-mounted millimeter wave radar 200 is usually installed on both sides of the front of the vehicle 100, and the common installation position is not limited to Figure 1 The forward position shown also includes the front corner, rear corner and rear corner positions, which are used to detect and perceive the surrounding environment targets (target 1, target 2, target 3).

[0034] See also Figure 2 , is a schematic diagram of the structure of the vehicle-mounted millimeter-wave radar. The vehicle-mounted millimeter-wave radar mainly consists of four functional parts:

[0035] 1) Antenna array, which consists of a transmitting array and a receiving array. Vehicle-mounted millimeter-wave radar generally adopts the MIMO (Multiple-Input Multiple-Output) working mode, and realizes the antenna array required for direction finding through the MIMO working mode between the unit antennas of the transmitting array.

[0036] 2) MRTR (Millimeter-wave Radar Transceiver, millimeter-wave radar transceiver module or chip), millimeter-wave radar transceiver functional module, mainly composed of transmitting components, receiving components and linear frequency modulation local oscillator source components. MRTR generates and transmits the working waveform signal of the millimeter-wave radar, receives and discretely samples the reflected waveform signal of the target, and sends the sampled reflected waveform signal to the MRP (Millimeter-wave Radar Processor) millimeter-wave radar processor.

[0037] 3) MRP (Millimeter-wave Radar Processor), millimeter-wave radar processor, receives the reflected waveform signal from MRTR and performs digital processing to obtain information such as the distance, speed and angle of environmental targets, clusters, identifies and tracks targets, and outputs point cloud-level detection results or target-level detection results. From the main functional division, MRP is mainly composed of distance measurement module, speed measurement module, angle measurement module and target clustering identification and tracking module. The above modules can be implemented through embedded software, FPGA (Field Programmable Gate Array) or AISC (Application Specific Integrated Circuit) application-specific integrated circuits.

[0038] 4) Readable and writable storage, used to store the working data of the vehicle-mounted millimeter-wave radar, including working parameter data and process data stored in advance. A typical example is that in the embodiment of the present application, during the implementation of the front vehicle detection method based on the vehicle-mounted millimeter-wave radar, the target parameters and motion state parameters of the front vehicle, the front front vehicle, etc. are identified, as well as the threshold parameters required for determining the emergency braking behavior of the front front vehicle.

[0039] The front vehicle detection method based on the vehicle-mounted millimeter-wave radar provided in the embodiment of the present application can be mainly completed in the target clustering recognition and tracking module. The implementation form, composition mode or module division mode of MRP does not affect the use of the front vehicle detection method based on the vehicle-mounted millimeter-wave radar provided in the embodiment of the present application.

[0040] 4) A read-write memory used to store the working data of the millimeter-wave radar, including working parameter data and process data stored in advance.

[0041] It should be noted that the configuration form or composition method of the functional parts of the above-mentioned vehicle-mounted millimeter-wave radar does not affect the use of the front vehicle detection method based on the vehicle-mounted millimeter-wave radar provided in the embodiment of the present application.

[0042] See also Figure 3, a front vehicle detection method based on a vehicle-mounted millimeter-wave radar provided in an embodiment of the present application includes the following steps:

[0043] S101, receiving an echo signal, and processing the echo signal to obtain point cloud data.

[0044] The radar echo signal refers to the signal received by the radar's receiving end after the electromagnetic wave emitted by the radar is reflected or scattered back after encountering the target. The radar echo signal usually contains radial distance, azimuth, pitch, radial velocity and other characteristic information about the target. By analyzing and processing these signals, the radar can obtain the spatial point cloud data at the current moment, and based on the point cloud data, it can realize target detection, tracking and identification functions. Point cloud data refers to the data set of spatial points obtained by radar scanning. Each point in the radar point cloud contains the polar coordinate information, velocity information and other attribute information of a certain position in the space, such as Rcs. By analyzing the spatial correlation between point clouds, more features and attributes about the target can be obtained.

[0045] S103, performing target clustering on the point cloud data to determine forward target information; the forward target information includes the number, position and occlusion status of the forward targets.

[0046] Target clustering refers to the process of grouping a large amount of point data generated by radar during target detection. These data points may represent multiple reflection points of the same target. Through clustering algorithms, these point data can be grouped into different groups to represent an independent target. Target clustering can also further include grouping multiple target points detected by radar according to their characteristics and positions for better target identification and tracking.

[0047] The forward target refers to the target in front of the vehicle. The occlusion status of the forward target is determined based on the number and position of the detected forward targets within the radial detection range of the radar. If there are two forward targets in front of the vehicle, and the two forward targets have similar azimuths relative to the vehicle but different distances, then for the vehicle, the forward target at the rear is occluded by the forward target at the front, and the occlusion status between the forward targets can be determined.

[0048] S105: Determine whether there is a potential preceding vehicle according to the forward target information.

[0049] According to the forward target information, when it is determined that there are multiple forward targets and there is an occlusion state between two forward targets, the occluded forward target of the two forward targets can be regarded as a potential preceding vehicle.

[0050] S107: If yes, determine whether the potential preceding vehicle satisfies a track starting condition based on the continuous multi-frame radar data, and determine the potential preceding vehicle that satisfies the track starting condition as the target preceding vehicle.

[0051] Track start conditions refer to the conditions that the radar must meet to establish the target's track when it detects that the target has entered its detection range. These conditions mainly include the accuracy of the position information and the association information with other tracks. The accuracy of the position information is usually determined by the accuracy of parameters such as distance, azimuth and pitch angle to provide reliable basic data for track start. The association information with other tracks refers to the use of algorithms and discrimination thresholds to determine whether the detected target is associated with an existing track, and to accumulate judgments over multiple frames to avoid generating false tracks.

[0052] According to the forward target information detected in the single-frame radar data, when the two forward targets in front and behind with an occlusion relationship are determined, the target that is farther away from the position of the vehicle is regarded as a potential preceding vehicle, and then the potential preceding vehicle is tracked. The clustering results containing the target identification of the potential preceding vehicle are associated with the target track of the potential preceding vehicle through continuous multi-frame radar data. By judging whether the track starting condition is met, it is confirmed that the potential preceding vehicle is a real target preceding vehicle.

[0053] The preceding vehicle detection method based on the vehicle-mounted millimeter-wave radar provided in the above-mentioned embodiment can accurately detect whether there is an obstructed vehicle or a non-directly-sighted vehicle (the target preceding vehicle) that may affect the driving safety of the vehicle by processing the radar echo signal. According to the detection result of the target preceding vehicle, the assisted driving performance is improved, such as displaying the target preceding vehicle in the current assisted driving interface; and the driving status of the target preceding vehicle can be further monitored to identify the braking behavior of the target preceding vehicle and perform a braking warning. By monitoring the driving status of the preceding vehicle, the braking behavior of the obstructed vehicle or the non-directly-sighted vehicle (the preceding vehicle) can be predicted in advance, reminding the driver to predict in advance and take measures to avoid the risk of vehicle collision caused by emergency braking, thereby effectively improving driving safety.

[0054] In some embodiments, step S105 includes:

[0055] According to the forward target information, determining whether the number of forward targets is greater than 1;

[0056] If the number of forward targets is greater than 1, determine whether the farther target is blocked by the closer target based on the forward target position;

[0057] If the farther target is blocked by the closer target, mark the closer target as the front vehicle and the farther target as the front-front vehicle, calculate the distance information between the front vehicle and the front-front vehicle, and determine whether the front-front vehicle detection condition is met;

[0058] If the preceding vehicle detection condition is met, the current preceding vehicle is determined to be a potential preceding vehicle.

[0059] When the number of forward targets is greater than 1, the front vehicle (closer target) and the front-front vehicle (farther target) can be determined according to the forward target positions, such as Figure 4 As shown, the number of targets ahead of the vehicle is greater than 1, the vehicle 100 is equipped with a radar, the closer target 101 is the preceding vehicle, and the farther target 102 is the preceding vehicle. The radar detects targets by using the echo signals reflected by the received targets as basic data for calculation and processing. In the radar field of view, the preceding vehicle that is blocked can be detected by the radar as a target, which requires certain detection conditions to be met. In this embodiment, the preceding vehicle detection condition is set based on the distance information between the preceding vehicle and the preceding vehicle. After the preceding vehicle and the preceding vehicle that are blocked are initially identified, the distance information between the preceding vehicle and the preceding vehicle is calculated and it is determined whether the preceding vehicle detection condition is met, so that false targets can be removed.

[0060] It should be noted that in the front vehicle detection conditions, the distance information between the front vehicle and the front vehicle refers to the distance condition that needs to be met so that the echo signal reflected by the front vehicle can be received by the radar. Here, it can include the distance condition of the front vehicle relative to the vehicle itself, and also the distance condition of the front vehicle relative to the front vehicle.

[0061] In the above embodiment, the distance information between the front vehicle and the front vehicle is used to set the front vehicle detection condition, and the distance information between the front vehicle and the front vehicle is calculated to determine whether the front vehicle detection condition is met, so as to screen and determine the potential front vehicle. This can reduce the amount of calculation required for further identifying and confirming the real front vehicle through target tracking, and ensure the recognition accuracy of the real front vehicle target.

[0062] In some embodiments, the calculating the distance information between the preceding vehicle and the preceding vehicle and determining whether the preceding vehicle detection condition is satisfied includes:

[0063] Obtaining the parameters of the preceding vehicle, calculating the distance between the preceding vehicle and the vehicle according to the radar installation height and the preceding vehicle parameters, and determining whether the distance between the preceding vehicle and the vehicle meets the minimum detection distance boundary; the preceding vehicle parameters include the chassis height and the length of the preceding vehicle;

[0064] If the minimum detection distance boundary is met, the cluster centroid height of the preceding vehicle is calculated based on the radar measurement pitch angle, radar installation height, and radial distance of the preceding vehicle;

[0065] If the cluster centroid height meets the preset conditions, the distance between the preceding vehicle and the preceding vehicle is calculated according to the radial distance between the preceding vehicle, the distance between the preceding vehicle and the vehicle, and the length of the preceding vehicle;

[0066] Whether the front vehicle detection condition is met is determined according to whether the distance between the front vehicle and the front vehicle is within the front vehicle detection range.

[0067] The front vehicle is a directly visible vehicle within the radar field of view. Therefore, the front vehicle chassis height and the front vehicle length in the front vehicle parameters can be calculated by direct radar detection; or, the radar can identify the target category of the front vehicle based on the target detection results. For example, the preset target categories include cars and trucks, which are determined based on the target category of the front vehicle.

[0068] The minimum detection distance boundary refers to the minimum condition that the distance between the front vehicle and the vehicle must meet. For example, if the distance between the front vehicle and the vehicle is less than the minimum detection distance boundary, it means that the echo signal reflected by the front vehicle cannot pass through the space between the front vehicle and the vehicle and be received by the radar. Therefore, in the front vehicle detection condition, the first judgment item is to judge whether the distance between the front vehicle and the vehicle meets the minimum detection distance boundary. Please refer to Figure 5 In the radar field of view, the target recognition result related to the front vehicle is equivalent to the target recognition result of the position of the front vehicle's mirror image relative to the ground (regarded as the target 102'). Therefore, the second judgment condition in the front vehicle detection condition is to calculate the cluster centroid height of the front vehicle, and judge whether the cluster centroid of the front target in the two forward targets is below the ground according to whether the cluster centroid height is less than 0. Thirdly, the front vehicle is the target blocked by the front vehicle, and the reflected echo signal needs to be able to be reflected by the ground in the space under the chassis of the front vehicle. Therefore, combined with the characteristics of the front vehicle parameters, the distance between the front vehicle and the front vehicle also needs to meet certain conditions. Therefore, the third judgment condition in the front vehicle detection condition is whether the distance between the front vehicle and the front vehicle is within the detection range of the front vehicle.

[0069] In the above embodiment, in the method for preliminary identification of the front vehicle of the target in the target clustering result, three judgment conditions, namely the minimum detection distance boundary, the cluster centroid height and the front vehicle detection range, are set in sequence to ensure the accuracy of the preliminary identification of whether there is a front vehicle.

[0070] In some embodiments, the length of the preceding vehicle is a1, the height of the preceding vehicle chassis is h1, the radar installation height is h0, and the distance between the preceding vehicle and the vehicle is l1. It is determined whether the distance between the preceding vehicle and the vehicle satisfies the minimum detection distance boundary, as shown in the following formula 1:

[0071]

[0072] The distance between the preceding vehicle and the preceding vehicle is l2, and l2 is calculated as shown in the following formula 2:

[0073] l2=l-a1-l1 (Formula 2)

[0074] Whether the distance l2 between the preceding vehicle and the preceding vehicle is within the preceding vehicle detection range is as shown in the following formula 3-5:

[0075] R2≤l2≤R1; (Formula 3)

[0076]

[0077] Where R1 and R2 represent the distance range of the vehicle ahead that the radar can detect at the current moment without considering the radar transmission power. Figure 4 and Figure 5 , h0 is the radar installation height, h1 is the chassis height of the front vehicle, a1 is the length of the front vehicle, and h2 is the measured height of the front vehicle (the cluster centroid height detected by the radar). h1 and a1 can be obtained by radar detection, and parameters can also be preset according to the target recognition type. For example, if the radar recognizes the front vehicle as a car, the reference car length standard a1 is preset to 5m, and the chassis height h1 is preset to 0.3m. If the radar recognizes the front vehicle as a truck, the reference truck length standard a1 is preset to 8m, and the chassis height h1 is preset to 0.5m. The preset values ​​of a1 and h1 will affect the range of distance that the radar can detect the front vehicle, but the error is within the allowable range. l1 is the distance between the radar vehicle and the front vehicle, which is detected by the radar, and l2 is the distance between the front vehicle and the front vehicle.

[0078] In this embodiment, three specific calculation formulas for the front vehicle detection conditions are provided. However, it can be understood that these calculation formulas are specific technical solutions obtained under the corresponding technical concepts provided by the inventors of this application, which can verify the feasibility of implementation and the better technical effects that can be obtained. Under the technical guidance given in the embodiments of this application, those skilled in the art can also adjust the parameters in the specific calculation formulas within some preset proportions so that the calculation results are within the allowable error range, and the corresponding technical solutions can still be implemented to achieve preliminary identification of whether there is a front vehicle. Therefore, the provision of these specific calculation formulas should not be used as a limitation on the maximum protection scope of this application.

[0079] In some embodiments, in step S107, determining whether the potential preceding vehicle meets the track starting condition based on the continuous multiple frames of radar data includes:

[0080] If the distance between the preceding vehicle and the vehicle is greater than the minimum detection distance boundary, determine whether the potential preceding vehicle meets the following first track starting conditions based on continuous multi-frame radar data: the azimuth angle is less than a preset value, the difference between the azimuth angle of the clustering result corresponding to the potential preceding vehicle and the azimuth angle of the tracking target is greater than the azimuth angle threshold, the difference between the distance of the clustering result corresponding to the potential preceding vehicle and the distance of the intermediate vehicle target is greater than the distance threshold, and the average signal-to-noise ratio of the clustering result corresponding to the potential preceding vehicle is greater than the signal-to-noise ratio threshold;

[0081] If the distance between the preceding vehicle and the vehicle is equal to the minimum detection distance boundary, determine whether the potential preceding vehicle meets the following second track starting condition based on continuous multiple frames of radar data: the azimuth angle is less than a preset value, the sum of the distance between the preceding vehicle and the preceding vehicle, the distance between the preceding vehicle and the vehicle, and the length of the preceding vehicle is approximately equal to the radial distance between the preceding vehicle and the radar, and the average signal-to-noise ratio of the clustering results corresponding to the potential preceding vehicle is greater than the signal-to-noise ratio threshold.

[0082] In this embodiment, whether the potential preceding vehicle satisfies the track starting condition is distinguished based on whether the distance l1 between the preceding vehicle and the vehicle is relatively greater than or equal to the minimum detection distance boundary.

[0083] When l1>a1(h0-h1) / 2h1, the starting conditions of the front vehicle track reflected by the ground include: 1. The corresponding clustering result has a target identifier of the potential front vehicle; 2. The azimuth is less than the preset value; 3. clusterAzimuth-targetAzimuth>angleThre; 4. clusterSnr>snrThre; where clusterAzimuth is the azimuth of the clustering result, clusterRange is the distance of the clustering result, targetAzimut is the azimuth of the tracking target, targetRange is the distance of the tracking target, angleThre is the azimuth, and rangeThre is the distance threshold. clusterSnr is the average signal-to-noise ratio of the clustering result, and snrThre is the signal-to-noise ratio threshold.

[0084] When l1=a1(h0-h1) / 2h1, the starting conditions of the preceding vehicle track reflected from the ground include: 1. The corresponding clustering result has a target identification of a potential preceding vehicle; 2. The azimuth angle is less than the preset value; 3. l≈l1+l2+a1; 4. The signal-to-noise ratio threshold clusterSnr>snrThre is met.

[0085] The target track is associated with the clustering result of the potential preceding vehicle, and the target track is updated. The target track that meets the track starting condition is executed with track starting, track merging and separation, and the target track that meets the track extinction condition is executed with track extinction.

[0086] See also Figure 6In some embodiments, after step S107, the method further includes:

[0087] S109, identifying the braking behavior of the target vehicle ahead and issuing a braking warning according to the relationship between the speed change of the target vehicle ahead and the speed change rate threshold.

[0088] Monitor the driving status of the target vehicle in front. Usually, the speed of the vehicle will decrease rapidly during braking. By monitoring the change in the driving speed of the target vehicle in front, and based on the relationship between the speed change amount of the target vehicle in front and the speed change rate threshold, whether the target vehicle in front is currently performing braking behavior is detected in real time to identify the braking behavior of the target vehicle in front and issue a braking warning.

[0089] Braking warning can be a reminder message in the form of text and / or images in the display interface of the vehicle-mounted central control system through the auxiliary driving system, indicating that the vehicle in front is braking; it can also be a reminder message in the form of an indicator light and / or a speaker in the auxiliary driving system, indicating that the vehicle in front is braking. In some embodiments, braking warning can also include various reminder methods that can remind the driver to know and identify that the target vehicle in front is braking, such as sending a warning message to an associated terminal device, a reminder message to enable the maximum speed limit control for the vehicle, etc.

[0090] It should be noted that the vehicle-mounted central control system can detect the vehicle's driving environment through various sensor elements such as vehicle-mounted cameras and speed sensors. In this embodiment, the vehicle-mounted millimeter-wave radar can be used as a sensor element of the vehicle-mounted central control system to accurately detect whether there is an obscured target vehicle in front that may affect the driving safety of the vehicle. The vehicle-mounted central control of the vehicle-mounted system predicts the driving safety risk based on the detection results of the vehicle-mounted millimeter-wave radar to improve the assisted driving performance.

[0091] In some embodiments, the preceding vehicle detection method based on the vehicle-mounted millimeter-wave radar further includes:

[0092] For the potential preceding vehicle that meets the track starting condition, the spatial position information of the preceding vehicle is restored according to the following formula 6:

[0093]

[0094] Among them, azimuth is the azimuth of the front vehicle, elev is the pitch angle of the front vehicle, R2 is the radial distance of the front vehicle, h0 is the radar installation height, x, y, z is the Cartesian coordinate of the front vehicle.

[0095] After the track of the preceding vehicle starts, the distance and spatial position of the preceding vehicle are restored according to the radar installation information and the preceding vehicle information, and the Cartesian coordinates of the preceding vehicle are calculated to describe the spatial position of the preceding vehicle.

[0096] Optionally, step S109 includes:

[0097] Monitoring the driving state of the target vehicle in front of the vehicle, and determining whether the change in the driving speed of the target vehicle in front of the vehicle is greater than a speed change rate threshold;

[0098] If the speed is greater than the speed change rate threshold, increase the confidence of the braking behavior of the target vehicle in front;

[0099] If the confidence of the braking behavior of the target vehicle in front is greater than the confidence threshold, it is confirmed that the target vehicle in front currently has a braking behavior and a braking warning is issued.

[0100] After confirming the target vehicle in front, the driving status of the target vehicle in front is monitored, which reduces the amount of calculation for tracking the target vehicle in front and can also improve the accuracy of monitoring the driving status of the target vehicle in front.

[0101] Optionally, increasing the confidence of the braking behavior of the target vehicle in front includes:

[0102] If the change in the speed of the vehicle in front of the target is detected to be greater than the speed change rate threshold according to multiple consecutive frames of radar data, the confidence level is increased by a preset proportion for each frame;

[0103] The speed change rate threshold is determined according to the current driving speed.

[0104] For each current frame data, the speed change can be calculated based on the change in the spatial position of the target vehicle in front of the current frame data relative to the spatial position of the target vehicle in front of the previous frame data, and it is determined whether the speed change Δv is greater than the speed change rate threshold vThreshold. If Δv>vThreshold, the confidence of the braking behavior of the front vehicle is increased. In a specific example, the radar refresh rate is 20hz, and the speed change Δv of 8 consecutive frames of radar data can be counted by sliding the window. If Δv>6m / s, the confidence is increased by 10% for each frame. If the confidence is increased by 10% for more than 8 consecutive frames, the confidence corresponding to the 8 frames of data is 80%. At this time, it can be considered that the vehicle has braked, and a braking warning of the front vehicle is issued.

[0105] In order to have a more organized understanding of the front vehicle detection method based on vehicle-mounted millimeter-wave radar, please refer to Figure 7 and Figure 8 ,by Figure 2Taking the structure of the vehicle-mounted millimeter-wave radar shown in the figure as an example, the main working process of the vehicle-mounted millimeter-wave radar and the process of the front vehicle detection method based on the vehicle-mounted millimeter-wave radar are explained.

[0106] S11, the millimeter wave radar processes the echo signal received by the front end to obtain multiple detection points.

[0107] S12, preprocessing the detection points. The preprocessing includes eliminating invalid point cloud data, compensating for installation errors and performing coordinate system conversion.

[0108] S13, clustering the detection points. Performing target clustering on the point cloud data to obtain a target cluster set. Using a recognition algorithm, performing target recognition and preliminary recognition of the preceding vehicle on the target cluster set.

[0109] Among them, target recognition and preliminary recognition of the preceding vehicle may include:

[0110] S141, determining whether the number of targets in the target cluster set in the forward direction of the radar is greater than 1.

[0111] If satisfied, execute S142. Specifically, the azimuth angle can be detected to verify whether the two targets are in front of the radar, the closer one is marked as the front vehicle, the farther one is marked as the front front vehicle, and the object not in front of the radar is marked as others.

[0112] S142, determining whether the farther target is blocked by the closer target among the two targets in front of the radar, if the closer target is marked as the front vehicle and the farther target is marked as the front-front vehicle, target recognition is performed on the front vehicle target type.

[0113] Among them, the distance between the front vehicle and the vehicle itself, the distance between the front front vehicle and the front vehicle, the length of the front vehicle a1, and the height of the chassis of the front vehicle h1 can be obtained. The corresponding a1 and h1 can be set according to the target type of the front vehicle, and the distance l1 between the radar vehicle and the front vehicle and the radial distance l of the farther target relative to the radar are measured by the radar. The height h2 of the farther target is calculated according to the pitch angle measured by the radar and the radial distance l, that is, the cluster centroid height h2 corresponding to the front front vehicle.

[0114] S145, determining whether the distance between the preceding vehicle and the vehicle satisfies the minimum detection distance boundary.

[0115] According to the installation height h0 of the radar relative to the ground, the length a1 of the front vehicle, and the chassis height h1 of the front vehicle, as shown in the above formula 1, it is determined that l1>a1(h0-h1) / 2h1 or l1=a1(h0-h1) / 2h1. If satisfied, execute S146.

[0116] S146, judging whether the centroid of the cluster of the distant target is below the ground (h2<0) according to the radar installation height. If satisfied, executing S147.

[0117] S147, whether the distance between the front vehicle and the front vehicle meets the detection range. If so, execute S15.

[0118] The distance between the front vehicle and the front vehicle is l2, and the judgment condition is as shown in the previous formula 2-5. If it is satisfied, it is marked as a potential front vehicle clustering result, and if it is not satisfied, it is a multipath false target.

[0119] S15, tracking the vehicle in front.

[0120] The target track is associated with the clustering result. If there is a track of the preceding vehicle, the preceding vehicle is associated with the clustering result with the potential identifier of the preceding vehicle, and the target track is updated.

[0121] Determine whether the track start conditions are met, and execute track elimination and starting, as well as track merging and separation for the target track that meets the elimination or starting conditions. After the preceding vehicle track starts, the distance and spatial position of the preceding vehicle are restored according to the radar installation information and the preceding vehicle information, as shown in the above formula 6.

[0122] S16, monitoring the driving state of the preceding vehicle, determining whether the change in the driving speed of the preceding vehicle between frames is greater than a speed change rate threshold, and if so, increasing the confidence of the braking behavior of the preceding vehicle.

[0123] S17, determining whether the confidence level of the braking behavior of the preceding vehicle is greater than a confidence level threshold, and if so, issuing a braking warning for the preceding vehicle.

[0124] The preceding vehicle detection method based on the vehicle-mounted millimeter-wave radar provided in the above-mentioned embodiment is based on the ground multipath reflection echo signal of the vehicle-mounted millimeter-wave radar, and the point cloud information of the scene is obtained through signal processing. Through the clustering, association, tracking and target recognition methods in data processing, the position and speed of the preceding vehicle target blocked by the preceding vehicle can be accurately calculated, its driving state can be monitored, the braking behavior of the preceding vehicle can be identified, and an early warning can be issued. Without adding millimeter-wave radar hardware equipment, the unique characteristic of the millimeter-wave radar signal having the multipath effect can be used to monitor the driving state of the preceding vehicle and issue an early warning of the braking behavior of the preceding vehicle.

[0125] Among them, the typical workflow of the vehicle-mounted millimeter-wave radar using the front vehicle detection method based on the vehicle-mounted millimeter-wave radar proposed in the embodiment of the present application is as follows: Figure 8 As shown, the following steps are included:

[0126] S211, the vehicle-mounted millimeter-wave radar is powered on and initialized, and the working parameters are read and sent down.

[0127] S212, the vehicle-mounted millimeter-wave radar receives an instruction to start working.

[0128] S213, the MRTR chip linear frequency modulation local oscillator source component generates a linear frequency modulation waveform local oscillator signal according to the waveform parameters, and transmits it to the transmitting component and the receiving component.

[0129] S214, the MRTR chip transmitting component generates a transmitting signal according to the linear frequency modulation waveform local oscillator signal, and radiates the transmitting signal through the transmitting antenna array.

[0130] S215, the receiving antenna array receives the waveform signal reflected by the target and transmits it to the MRTR chip receiving component.

[0131] S216, the MRTR chip performs discrete ADC sampling on the waveform signal reflected by the received target.

[0132] S217, the MRP chip ranging module performs ranging processing on the discrete ADC signal from the MRTR chip.

[0133] S218, the MRP chip speed measurement module performs speed measurement processing.

[0134] S219, the MRP chip angle measurement module performs angle measurement processing.

[0135] S220, the MRP chip target clustering association tracking module performs target-level data processing.

[0136] S221, MRP chip target recognition and event recognition processing.

[0137] S222, the MRP chip outputs point cloud-level detection results or target-level detection results.

[0138] S223, completing scene target detection in a loop until a condition for stopping operation is met.

[0139] Among them, the front vehicle detection method based on the vehicle-mounted millimeter-wave radar proposed in the embodiment of the present application can be executed by the millimeter-wave radar chip, and can be specifically completed in step S220.

[0140] On the other hand, please refer to Figure 2 and Fig. 9 , a vehicle-mounted millimeter-wave radar is also provided, including a millimeter-wave radar processor 201 and a memory 202. The memory 202 stores a computer program that can be executed by the millimeter-wave radar processor 201; when the computer program is executed by the millimeter-wave radar processor 201, the front vehicle detection method based on the vehicle-mounted millimeter-wave radar described in any embodiment of the present application is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0141] On the other hand, please refer to Fig.10, provides a vehicle, including an on-board central control system and an on-board millimeter-wave radar interactively connected to the on-board central control system; the on-board millimeter-wave radar is used to execute the front vehicle detection method based on the on-board millimeter-wave radar described in any embodiment of the present application; the on-board central control system is used to output corresponding auxiliary driving information according to the detection result of the millimeter-wave radar on the target front vehicle.

[0142] Among them, the assisted driving information can be the detection result of the target vehicle in front by the on-board central control system using the on-board millimeter-wave radar, and the assisted driving information output after calculating the prediction of driving safety risks, such as including but not limited to real-time updates and displays of the driving trajectory of the vehicle in front, the braking behavior warning of the vehicle in front, and the lane change and overtaking reminder of the vehicle in front on the on-board assisted driving screen.

[0143] On the other hand, an embodiment of the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the front vehicle detection method based on the vehicle-mounted millimeter-wave radar of any embodiment of the present application, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0144] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned front vehicle detection method embodiment based on the vehicle-mounted millimeter-wave radar are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0145] The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0146] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0147] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0148] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar, characterized in that: include: Receiving echo signals, and processing the echo signals to obtain point cloud data; Performing target clustering on the point cloud data to determine forward target information; The forward target information includes the number, position and occlusion status of the forward targets; Determining whether there is a potential preceding vehicle according to the forward target information; If so, determine whether the potential preceding vehicle satisfies a track initiation condition based on the continuous multi-frame radar data, and determine the potential preceding vehicle that satisfies the track initiation condition as the target preceding vehicle.

2. The method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar according to claim 1, characterized in that: The determining whether there is a potential preceding vehicle according to the forward target information includes: According to the forward target information, determining whether the number of forward targets is greater than 1; If the number of forward targets is greater than 1, determine whether the farther target is blocked by the closer target based on the forward target position; If the farther target is blocked by the closer target, mark the closer target as the front vehicle and the farther target as the front-front vehicle, calculate the distance information between the front vehicle and the front-front vehicle, and determine whether the front-front vehicle detection condition is met; If the preceding vehicle detection condition is met, the current preceding vehicle is determined to be a potential preceding vehicle.

3. The method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar according to claim 2, characterized in that: The calculating the distance information between the front vehicle and the front-front vehicle and judging whether the front-front vehicle detection condition is met includes: Obtaining the parameters of the preceding vehicle, calculating the distance between the preceding vehicle and the vehicle according to the radar installation height and the preceding vehicle parameters, and determining whether the distance between the preceding vehicle and the vehicle meets the minimum detection distance boundary; the preceding vehicle parameters include the chassis height and the length of the preceding vehicle; If the minimum detection distance boundary is met, the cluster centroid height of the preceding vehicle is calculated based on the radar measurement pitch angle, radar installation height, and radial distance of the preceding vehicle; If the cluster centroid height meets the preset conditions, the distance between the preceding vehicle and the preceding vehicle is calculated according to the radial distance between the preceding vehicle, the distance between the preceding vehicle and the vehicle, and the length of the preceding vehicle; Whether the front vehicle detection condition is met is determined according to whether the distance between the front vehicle and the front vehicle is within the front vehicle detection range.

4. The method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar according to claim 3, characterized in that: The length of the preceding vehicle is a1, the height of the preceding vehicle chassis is h1, the radar installation height is h0, and the distance between the preceding vehicle and the vehicle is l1. The calculation formula for determining whether the distance between the preceding vehicle and the vehicle satisfies the minimum detection distance boundary is as follows: The distance between the front vehicle and the front vehicle is l2, and the calculation formula is as follows: l2＝l-a1-l1； Whether the distance l2 between the preceding vehicle and the preceding vehicle is within the preceding vehicle detection range is calculated as follows: R2≤l2≤R1; 5. The method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar according to claim 1, characterized in that: The determining whether the potential preceding vehicle meets the track starting condition based on the continuous multiple frames of radar data includes: If the distance between the preceding vehicle and the vehicle is greater than the minimum detection distance boundary, determine whether the potential preceding vehicle meets the following first track starting conditions based on continuous multi-frame radar data: the azimuth angle is less than a preset value, the difference between the azimuth angle of the clustering result corresponding to the potential preceding vehicle and the azimuth angle of the tracking target is greater than the azimuth angle threshold, the difference between the distance of the clustering result corresponding to the potential preceding vehicle and the distance of the intermediate vehicle target is greater than the distance threshold, and the average signal-to-noise ratio of the clustering result corresponding to the potential preceding vehicle is greater than the signal-to-noise ratio threshold; If the distance between the preceding vehicle and the vehicle is equal to the minimum detection distance boundary, determine whether the potential preceding vehicle meets the following second track starting condition based on continuous multiple frames of radar data: the azimuth angle is less than a preset value, the sum of the distance between the preceding vehicle and the preceding vehicle, the distance between the preceding vehicle and the vehicle, and the length of the preceding vehicle is approximately equal to the radial distance between the preceding vehicle and the radar, and the average signal-to-noise ratio of the clustering results corresponding to the potential preceding vehicle is greater than the signal-to-noise ratio threshold.

6. The method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar according to claim 1, characterized in that: After determining the target vehicle in front, it also includes: According to the relationship between the driving speed change amount of the target preceding vehicle and the speed change rate threshold, the braking behavior of the target preceding vehicle is identified and a braking warning is issued.

7. The method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar according to claim 6, characterized in that: Also includes: For the potential preceding vehicle that meets the track starting condition, the spatial position information of the preceding vehicle is restored according to the following formula: Among them, azimuth is the azimuth of the front vehicle, elev is the pitch angle of the front vehicle, R2 is the radial distance of the front vehicle, h0 is the radar installation height, x, y, z is the Cartesian coordinate of the front vehicle.

8. The method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar according to claim 7, characterized in that: The method of identifying the braking behavior of the target vehicle in front of the target and performing a braking warning according to the relationship between the speed change amount of the target vehicle in front of the target and the speed change rate threshold comprises: Monitoring the driving state of the target vehicle in front of the vehicle, and determining whether the change in the driving speed of the target vehicle in front of the vehicle is greater than a speed change rate threshold; If multiple frames of radar data are detected to have a speed change of the vehicle in front of the target that is greater than a speed change rate threshold, a preset confidence level is increased for each frame; wherein the speed change rate threshold is determined according to the current vehicle speed; If the confidence level of the braking behavior of the target vehicle in front is greater than the confidence level threshold, it is confirmed that the target vehicle in front is currently braking and a braking warning is issued.

9. A vehicle-mounted millimeter wave radar, characterized in that: The invention comprises a millimeter wave radar processor and a memory, wherein the memory stores a computer program executable by the millimeter wave radar processor; When the computer program is executed by the millimeter-wave radar processor, the method for detecting a preceding vehicle based on a vehicle-mounted millimeter-wave radar as claimed in any one of claims 1 to 8 is implemented.

10. A vehicle, characterized in that: It includes a vehicle-mounted central control system and a vehicle-mounted millimeter-wave radar interactively connected to the vehicle-mounted central control system; The vehicle-mounted millimeter-wave radar is used to perform the front vehicle detection method based on the vehicle-mounted millimeter-wave radar as described in any one of claims 1 to 8; The vehicle-mounted central control system is used to output corresponding auxiliary driving information according to the detection result of the millimeter-wave radar on the target vehicle in front.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the preceding vehicle detection method based on a vehicle-mounted millimeter-wave radar as claimed in any one of claims 1 to 8 is implemented.

Images