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

Abstract

The application provides a front vehicle detection method, a vehicle-mounted millimeter wave radar, a product and a vehicle. The method comprises the following steps: receiving a return signal, processing the return signal to obtain point cloud data; performing target clustering on the point cloud data to determine front target information; the front target information comprises a front target quantity, a position and an occlusion state; determining whether there is a potential front vehicle according to the front target information; if yes, determining whether the potential front vehicle meets a track initiation condition based on continuous multiple frames of radar data, and determining the potential front vehicle meeting the track initiation condition as a target front vehicle; and identifying a braking behavior of the target front vehicle and performing a braking warning according to a relationship between a driving speed variation of the target front vehicle and a speed variation rate threshold.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of radar, in particular to a front-front vehicle detection method based on a vehicle-mounted millimeter wave radar, a vehicle-mounted millimeter wave radar, a computer program product and a vehicle. BACKGROUND

[0002] The millimeter wave radar can measure the distance, speed and angle of a target by emitting and receiving electromagnetic waves. Compared with a camera and a laser radar, the millimeter wave radar has good environmental adaptability and weather adaptability, and can adapt to application scenarios such as strong light, night, heavy rain, heavy fog and dust, and has been widely used in vehicle-mounted ADAS (Advanced Driving Assistance System) auxiliary driving systems and vehicle-mounted AD (Autonomous Driving) automatic driving systems. Through the mutual fusion of the camera, the laser radar and the millimeter wave radar, the redundancy of intelligent decision-making can be improved, and the high reliability and high safety of the ADAS auxiliary driving or the AD automatic driving can be realized.

[0003] In a vehicle-mounted application scenario, as the number of vehicles increases, traffic accidents caused by vehicle collisions also occur from time to time, causing a large amount of property loss and casualties. In particular, on a highway, even multiple vehicle collisions occur. Therefore, monitoring and predicting the driving state of a front vehicle and a front-front vehicle hidden by the front vehicle through a vehicle-mounted auxiliary driving system can effectively improve the safety of the vehicle. However, the existing vehicle-mounted auxiliary driving system usually only focuses on detecting the motion state of a vehicle in the line of sight, and in an actual vehicle-mounted application scenario, an emergency brake of a hidden vehicle or a non-straight-view vehicle usually causes a collision of multiple consecutive vehicles. How to detect the emergency brake behavior of the hidden vehicle or the non-straight-view vehicle is of great significance to improving the safety of the vehicle. SUMMARY

[0004] To solve the existing technical problems, the present application provides a front-front vehicle detection method based on a vehicle-mounted millimeter wave radar, a vehicle-mounted millimeter wave radar and a computer program product, which can detect the state of a front-front vehicle hidden by a vehicle.

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

[0006] receiving a return signal, processing the return signal to obtain point cloud data;

[0007] target clustering is performed on the point cloud data to determine forward target information; the forward target information includes the number, position and shielding state of the forward target;

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

[0009] If yes, determining, based on continuous radar data, whether the potential preceding preceding vehicle meets a track initiation condition, and determining the potential preceding preceding vehicle meeting the track initiation condition as a target preceding preceding vehicle.

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

[0011] The computer program, when executed by the millimeter wave radar processor, implements the preceding preceding vehicle detection method based on a vehicle-mounted millimeter wave radar according to any of the embodiments.

[0012] In a third aspect, a vehicle is provided, comprising a vehicle-mounted central control system and a vehicle-mounted millimeter wave radar connected to the vehicle-mounted central control system;

[0013] The vehicle-mounted millimeter wave radar is configured to execute the preceding preceding vehicle detection method based on a vehicle-mounted millimeter wave radar according to any of the embodiments.

[0014] The vehicle-mounted central control system is configured to output corresponding auxiliary driving information according to the detection result of the target preceding preceding vehicle by the millimeter wave radar.

[0015] In a fourth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the preceding preceding vehicle detection method based on a vehicle-mounted millimeter wave radar according to any of the embodiments.

[0016] The preceding preceding vehicle detection method based on a vehicle-mounted millimeter wave radar provided by the above embodiments can receive a return signal, process the return signal to obtain point cloud data, perform target clustering on the point cloud data, determine forward target information, determine whether there is a potential preceding preceding vehicle obscured by a preceding vehicle using the forward target information, determine whether a track initiation condition is met by performing target tracking on the potential preceding preceding vehicle, and determine the potential preceding preceding vehicle meeting the track initiation condition as a target preceding preceding vehicle. In this way, it can accurately detect whether there is an obscured vehicle or a non-direct-view vehicle (target preceding preceding vehicle) that may affect the driving safety of the vehicle. According to the detection result of the target preceding preceding vehicle, the auxiliary driving performance can be improved, for example, the target preceding preceding vehicle can be displayed in the current auxiliary driving interface; for another example, the driving state of the target preceding preceding vehicle can be further monitored to identify the braking behavior of the target preceding preceding vehicle and perform braking warning. By monitoring the driving state of the preceding preceding vehicle, the braking behavior of the obscured vehicle or non-direct-view vehicle (preceding preceding vehicle) can be predicted in advance, reminding the driver to make an early prediction and take measures to avoid the risk of emergency braking causing vehicle collision, thereby effectively improving driving safety.

[0017] The vehicle-mounted millimeter wave radar, the computer program product and the vehicle provided by the above embodiments belong to the same concept as the corresponding front vehicle detection method based on the vehicle-mounted millimeter wave radar, and have the same technical effects as the corresponding front vehicle detection method based on the vehicle-mounted millimeter wave radar. Details are not repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 An optional application scenario diagram of the front vehicle detection method based on the vehicle-mounted millimeter wave radar in an embodiment.

[0019] Figure 2 A working principle diagram of the vehicle-mounted millimeter wave radar in an embodiment.

[0020] Figure 3 A flowchart of the front vehicle detection method based on the vehicle-mounted millimeter wave radar in an embodiment.

[0021] Figure 4 A front vehicle detection scenario diagram in an example.

[0022] Figure 5 A front vehicle detection scenario diagram in an example. Figure 4 A multi-path propagation diagram of electromagnetic waves in the front vehicle detection scenario in the example shown.

[0023] Figure 6 A flowchart of the front vehicle detection method based on the vehicle-mounted millimeter wave radar in another embodiment.

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

[0025] Figure 8 A working flowchart of the vehicle-mounted millimeter wave radar in an embodiment.

[0026] Figure 9 A structural diagram of the vehicle-mounted millimeter wave radar in an embodiment.

[0027] Figure 10 A structural diagram of the vehicle in an embodiment. DETAILED DESCRIPTION

[0028] The technical solutions of the present application will be further described in detail below in combination with the accompanying drawings and specific embodiments.

[0029] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0030] In the following description, the expression "some embodiments" refers to a subset of all possible embodiments, and it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other as long as there is no conflict.

[0031] In the following description, the terms "first", "second", "third" are merely used to distinguish similar objects, and do not represent a specific order of the objects. Understandably, "first", "second", "third" can be interchanged in a specific order or sequence as long as it is allowed, so that the embodiments of the 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. The signals can detect the occluded objects through reflection, diffuse reflection, diffraction, and bending, etc. In the research on how to detect the occluded vehicles or non-direct-view vehicles and detect the emergency braking behavior of the detected occluded vehicles or non-direct-view vehicles, the inventors of the present application propose that this characteristic of millimeter wave radar signals can be used to realize the detection of occluded vehicles or non-direct-view vehicles in a vehicle driving scene, and further realize the emergency braking behavior warning. Millimeter wave radar has irreplaceable advantages for problems that other sensors are difficult to handle and accidents occur frequently.

[0033] Please refer to Figure 1 The optional application scene diagram of the front vehicle detection method based on vehicle-mounted millimeter wave radar provided by an embodiment of the present application is applied to a vehicle. The vehicle-mounted millimeter wave radar 200 is usually installed on both sides of the front of the vehicle 100. The common installation positions are not limited to the front position shown in the figure, but also include front corners, rear positions, and rear corners, etc. for detecting and perceiving the surrounding environment targets (target 1, target 2, target 3). Figure 1

[0034] Please refer to Figure 2 The structure diagram of the vehicle-mounted millimeter wave radar. The vehicle-mounted millimeter wave radar mainly consists of four functional parts:

[0035] 1) Antenna array, consisting of transmitting array and receiving array. The vehicle-mounted millimeter wave radar generally adopts MIMO (Multiple-Input Multiple-Output) working mode. Through the MIMO working mode between each unit antenna of the transmitting array, the antenna array required for direction finding is realized.

[0036] ​2) MRTR (Millimeter-wave Radar Transceiver), millimeter-wave radar transceiver function module, mainly composed of a transmitting component, a receiving component, and a linear frequency modulation local oscillator component. The MRTR generates and transmits millimeter-wave radar working waveform signals, and receives and discretely samples target reflected waveform signals, and sends the sampled reflected waveform signals to the MRP (Millimeter-wave Radar Processor).

[0037] 3) MRP (Millimeter-wave Radar Processor), millimeter-wave radar processor, receiving reflected waveform signals from the MRTR and performing digital processing to obtain distance, speed, and angle information of environmental targets, and realizing clustering, identification, and track tracking of targets, and outputting point cloud level detection results or target level detection results. According to the main function division, the MRP is mainly composed of a ranging module, a speed measurement module, an angle measurement module, and a target clustering identification and tracking module, and the above modules can be realized by embedded software, FPGA (Field Programmable Gate Array), or ASIC (Application Specific Integrated Circuit).

[0038] 4) Readable and writable storage, used for storing working data of the vehicle-mounted millimeter-wave radar, including pre-stored working parameter data and process data. In the embodiment of the present application, the target parameters and motion state parameters of the preceding vehicle and the front vehicle are identified, and the threshold parameters required for judging the emergency braking behavior of the front vehicle are also included.

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

[0040] 4) Readable and writable storage, used for storing working data of the millimeter-wave radar, including pre-stored working parameter data and process data.

[0041] It should be noted that the composition form or composition method of each functional part of the 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 by the embodiment of the present application.

[0042] Please refer to Figure 3A front-front vehicle detection method based on a vehicle-mounted millimeter wave radar is provided for an embodiment of the present application, and includes the following steps:

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

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

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

[0046] Target clustering can refer to that when the radar performs target detection, a large amount of point data will be generated, and these data points may represent multiple reflection points of the same target. Through a clustering algorithm, these point data can be grouped into different groups to represent an independent target. Target clustering can further include grouping multiple target points detected by the radar according to their characteristics and positions to better perform target identification and tracking.

[0047] The forward target refers to the target in front of the vehicle. The occlusion state of the forward target in the radial detection range of the radar can be determined according to the number and position of the detected forward target. If there are two forward targets in front of the vehicle, the azimuth angles of the two forward targets relative to the vehicle are similar, and the distances are different. Therefore, the forward target behind the position is occluded by the forward target in front of the position, and the occlusion state between the forward targets can be determined.

[0048] S105, determining whether there is a potential front-front 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 in the two forward targets can be regarded as a potential front-front vehicle.

[0050] S107, if yes, determining whether the potential preceding preceding vehicle meets a track initiation condition based on the continuous multiple frames of radar data, and determining the potential preceding preceding vehicle meeting the track initiation condition as a target preceding preceding vehicle.

[0051] The track initiation condition refers to conditions required to be met by a radar when detecting a target entering its detection range in order to establish a track of the target. These conditions can mainly include accuracy of position information and association information with other tracks. The accuracy of position information is usually determined by the accuracy of parameters such as distance, azimuth angle and pitch angle to determine the position of the target, so as to provide reliable basic data for track initiation. The association information with other tracks refers to determining whether the detected target is associated with an existing track through an algorithm and a discrimination threshold, and is determined through multi-frame accumulation to avoid false tracks.

[0052] According to the forward target information detected in the single frame of radar data, when the two forward targets in a shielding relationship are determined to exist, the target farther away from the position of the vehicle among the two forward targets is regarded as a potential preceding preceding vehicle. Target tracking is performed on the potential preceding preceding vehicle. The clustering result containing the target identification of the potential preceding preceding vehicle is associated with the target track of the potential preceding preceding vehicle through continuous multiple frames of radar data. Whether the track initiation condition is met is determined to confirm that the potential preceding preceding vehicle is a real target preceding preceding vehicle.

[0053] The preceding vehicle detection method based on the vehicle-mounted millimeter wave radar provided in the above embodiments can accurately detect whether there is a shielded vehicle or a non-direct-view vehicle (target preceding preceding vehicle) that can affect the driving safety of the vehicle by processing the echo signal of the radar. According to the detection result of the target preceding preceding vehicle, the assisted driving performance is improved. For example, the target preceding preceding vehicle can be displayed in the current assisted driving interface. For another example, the driving state of the target preceding preceding vehicle can be further monitored to identify the braking behavior of the target preceding preceding vehicle and to perform braking warning. By monitoring the driving state of the preceding preceding vehicle, the braking behavior of the shielded vehicle or non-direct-view vehicle (preceding preceding vehicle) can be predicted in advance. The driver can be reminded to make a prediction in advance and take measures to avoid the risk of vehicle collision caused by emergency braking, thereby effectively improving the driving safety.

[0054] In some embodiments, step S105 comprises:

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

[0056] If the number of forward targets is greater than 1, it is determined whether the farther target is shielded by the closer target according to the position of the forward target;

[0057] If a distant target is obscured by a nearby target, the nearby target is marked as the vehicle in front and the distant target is marked as the vehicle ahead. The distance information between the vehicle in front and the vehicle ahead is calculated and it is determined whether the conditions for detecting the vehicle ahead are met.

[0058] If the conditions for detecting the preceding vehicle are met, then the current preceding vehicle is identified as a potential preceding vehicle.

[0059] When the number of forward targets is greater than 1, the preceding vehicle (closer target) and the vehicle before that (farther target) can be determined based on the position of the forward targets. Figure 4 As shown, the number of forward targets for this vehicle is greater than one. The vehicle with the radar installed is this vehicle 100, the closer target 101 is the vehicle in front, and the farther target 102 is the vehicle in front of that vehicle. Radar detection of targets is based on the received echo signals reflected back from the targets. For an obstructed vehicle in front to be detected by the radar within its field of view, certain detection conditions must be met. In this embodiment, the distance information between the vehicle in front and the vehicle in front of that vehicle is used as the condition for setting the detection conditions for the vehicle in front of that vehicle. After initially identifying the vehicles in front and the vehicle in front of that vehicle with an obstruction relationship, the distance information between them is calculated, and it is determined whether the detection conditions for the vehicle in front of that vehicle are met, thus eliminating false targets.

[0060] It should be noted that in the preceding vehicle detection conditions, the distance information between the preceding vehicle and the preceding vehicle refers to the distance conditions that need to be met based on the fact that the echo signal reflected by the preceding vehicle can be received by the radar. Here, it can include the distance conditions between the preceding vehicle and the current vehicle, or the distance conditions between the preceding vehicles.

[0061] In the above embodiments, the distance information between the preceding vehicle and the vehicle before that is used to set the preceding vehicle detection conditions. By calculating the distance information between the preceding vehicle and the vehicle before that, it is determined whether the preceding vehicle detection conditions are met, so as to screen and identify potential preceding vehicles. This can reduce the amount of computation required for subsequent target tracking to identify and confirm the real preceding vehicle, and ensure the accuracy of identifying the real preceding vehicle target.

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

[0063] The system acquires parameters of the preceding vehicle, calculates the distance between the preceding vehicle and the current vehicle based on the radar installation height and the preceding vehicle parameters, and determines whether the distance between the preceding vehicle and the current vehicle meets the minimum detection distance boundary. The preceding vehicle parameters include the chassis height and length of the preceding vehicle.

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

[0065] If the cluster center height meets the preset condition, the distance between the front vehicle and the front front vehicle is calculated according to the front front vehicle radial distance, the distance between the front vehicle and the vehicle, and the length of the front vehicle.

[0066] According to whether the distance between the front front vehicle and the front vehicle is within the front front vehicle detection range, it is determined whether the front front vehicle detection condition is met.

[0067] The front vehicle is a directly visible vehicle in the radar field of view, and therefore, the front vehicle chassis height and the front vehicle length in the front vehicle parameters can be directly detected and calculated by the radar, or can be identified by the radar according to the target detection result to determine the target category to which the front vehicle belongs, such as a preset target category including a car and a large truck.

[0068] The minimum detection distance boundary refers to the minimum condition required for the distance between the front vehicle and the vehicle, for example, if the distance between the front vehicle and the vehicle is less than the minimum detection distance boundary, it can be indicated that the echo signal reflected by the front front vehicle cannot be received by the radar after being reflected by the ground and passing through the space between the front vehicle and the vehicle. Therefore, the first judgment condition in the front front vehicle detection condition is to determine 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 front vehicle is equivalent to the position of the mirror image of the front front vehicle relative to the ground (the target recognition result of the position 102'), and therefore, the second judgment condition in the front front vehicle detection condition is to calculate the cluster center height of the front front vehicle, and to determine whether the cluster center height of the front target in the front target is below the ground according to whether the cluster center height is less than 0. Again, as a target blocked by the front vehicle, the echo signal reflected by the front front vehicle needs to be reflected by the ground in the space below the chassis of the front vehicle, and therefore, in combination with the characteristics of the front vehicle parameters, the distance between the front front vehicle and the front vehicle also needs to meet certain conditions, and therefore, the third judgment condition in the front front vehicle detection condition is whether the distance between the front front vehicle and the front vehicle is within the front front vehicle detection range.

[0069] In the above embodiment, the three judgment conditions of the minimum detection distance boundary, the cluster center height, and the front front vehicle detection range are sequentially set in the front front vehicle preliminary identification method of the target in the target clustering result, to ensure the accuracy of the preliminary identification of whether the front front vehicle exists.

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

[0071]

[0072] The front-front vehicle and front vehicle distance is l2, and l2 is calculated according to formula 2 as shown below:

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

[0074] Whether the front-front vehicle and front vehicle distance l2 is within the front-front vehicle detection range is shown in formulas 3-5 as follows:

[0075] R2≤l2≤R1; (formula 3)

[0076]

[0077] Wherein, R1 and R2 respectively represent the distance range within which the radar can detect the front-front vehicle at the current time without considering the radar transmitting power. Please refer to Figure 4 and Figure 5 , h0 is the radar installation height, h1 is the front vehicle chassis height, a1 is the front vehicle length, and h2 is the front-front vehicle measurement height (the cluster center height detected by the radar). h1 and a1 can be detected by the radar, or can be preset according to the target recognition type, for example, if the radar recognition result of the front vehicle is a car, then the reference car length standard a1 is preset to 5m, and the chassis height h1 is preset to 0.3m. If the radar recognition result of the front vehicle is a truck, then 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 distance range within which the radar can detect the front-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-front vehicle.

[0078] In this embodiment, specific calculation formulas of three judgment conditions are provided for the front-front vehicle detection condition. However, it can be understood that these calculation formulas are specific technical solutions obtained under the corresponding technical concepts provided by the inventors of the present application, and the feasibility of implementation and the better technical effects that can be obtained are verified. Under the technical teaching given in the embodiments of the present application, the person skilled in the art can also make some adjustments to the parameters in the specific calculation formulas within a certain preset proportion range, so that the calculation results are within the allowable error range, and the corresponding technical solutions can still be implemented to preliminarily identify whether there is a front-front vehicle. Therefore, the provision of these specific calculation formulas should not be regarded as a limitation on the maximum protection scope of the present application.

[0079] In some embodiments, in step S107, the determination of whether the potential front-front vehicle satisfies the track initiation condition based on the continuous multiple frames of radar data comprises:

[0080] If the distance between the preceding vehicle and the vehicle is greater than the minimum detection distance boundary, it is determined, based on continuous multi-frame radar data, whether the potential preceding preceding vehicle satisfies the following first track initiation condition: the azimuth angle is less than a preset value, the difference between the azimuth angle of the cluster result corresponding to the potential preceding preceding vehicle and the azimuth angle of the tracked target is greater than the azimuth angle threshold, the difference between the distance of the cluster result corresponding to the potential preceding 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 cluster result corresponding to the potential preceding 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, it is determined, based on continuous multi-frame radar data, whether the potential preceding preceding vehicle satisfies the following second track initiation condition: the azimuth angle is less than a preset value, the sum of the distance between the preceding 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 preceding vehicle and the radar, and the average signal-to-noise ratio of the cluster result corresponding to the potential preceding preceding vehicle is greater than the signal-to-noise ratio threshold.

[0082] In this embodiment, the judgment of whether the potential preceding preceding vehicle satisfies the track initiation condition is distinguished according to whether the distance l1 between the preceding vehicle and the vehicle is greater than or equal to the minimum detection distance boundary.

[0083] When l1 > a1 (h0-h1) / 2h1, the track initiation condition for the ground-reflected preceding preceding vehicle includes: 1. The target identification corresponding to the cluster result has a potential preceding preceding vehicle; 2. The azimuth angle is less than a preset value; 3. clusterAzimuth-targetAzimuth > angleThre; 4. clusterSnr > snrThre; where clusterAzimuth is the azimuth angle of the cluster result, clusterRange is the distance of the cluster result, targetAzimut is the azimuth angle of the tracked target, targetRange is the distance of the tracked target, angleThre is the azimuth angle threshold, rangeThre is the distance threshold, clusterSnr is the average signal-to-noise ratio of the cluster result, and snrThre is the signal-to-noise ratio threshold.

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

[0085] The target track is associated with the cluster result of the potential preceding preceding vehicle, and the target track update is performed. The target track that satisfies the track initiation condition is subjected to track initiation, track merging and separation, and the target track that satisfies the track extinction condition is subjected to track extinction.

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

[0087] S109, identifying the braking behavior of the target front-front vehicle and giving a braking warning according to the relationship between the change in the driving speed of the target front-front vehicle and the speed change rate threshold.

[0088] The driving state of the target front-front vehicle is monitored. Generally, the speed of the vehicle will decrease rapidly during braking. By monitoring the change in the driving speed of the target front-front vehicle, the real-time detection of whether the target front-front vehicle is currently performing the braking behavior of braking is performed according to the relationship between the change in the driving speed of the target front-front vehicle and the speed change rate threshold, so as to identify the braking behavior of the target front-front vehicle and give a braking warning.

[0089] The braking warning can be a warning information indicating that the front-front vehicle is braking, which is sent by the auxiliary driving system in the display interface of the vehicle-mounted central control system; or the warning information indicating that the front-front vehicle is braking can be sent by the indicator light and / or the loudspeaker in the auxiliary driving system. In some embodiments, the braking warning can further include various reminding ways capable of reminding the driver to timely know that the target front-front vehicle is braking, such as sending an alarm prompt information to the associated terminal device, sending a reminder information for enabling the maximum speed control of the vehicle, and the like.

[0090] It should be noted that the vehicle-mounted central control system can detect the driving environment of the vehicle through various sensing elements such as vehicle-mounted cameras and speed sensors. In the present embodiment, the vehicle-mounted millimeter wave radar can be used as a sensing element of the vehicle-mounted central control system to accurately detect whether there is a blocked target front-front vehicle that may affect the driving safety of the vehicle. The vehicle-mounted central control system predicts the driving safety risk according to the detection result of the vehicle-mounted millimeter wave radar, and improves the auxiliary driving performance.

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

[0092] For the potential front-front vehicle satisfying the track initiation condition, the spatial position information of the front-front vehicle is restored according to the following formula 6:

[0093]

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

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

[0096] Optionally, step S109 comprises:

[0097] The driving state of the target front vehicle is monitored to determine whether the speed change amount of the target front vehicle is greater than a speed change rate threshold value;

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

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

[0100] After confirming the target front vehicle, the driving state of the target front vehicle is monitored, the calculation amount for tracking the target front vehicle is reduced, and the accuracy of monitoring the driving state of the target front vehicle is improved.

[0101] Optionally, the confidence of the braking behavior of the target front vehicle is increased, comprising:

[0102] According to the fact that the speed change amount of the target front vehicle is greater than the speed change rate threshold value is detected in the continuous multiple frames of radar data, the confidence is increased by a preset proportion for each frame;

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

[0104] For each current frame data, the speed change amount can be calculated according to the change of the spatial position of the target front vehicle in the current frame data relative to the spatial position of the target front vehicle in the previous frame data, and it is determined whether the speed change amount Δv is greater than the speed change rate threshold value 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, the speed change amount Δv of the continuous 8 frames of radar data can be statistically calculated by sliding 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 frames, the confidence corresponding to the 8 frames of data is 80%, at this time, it can be considered that it has a braking behavior, and a front vehicle braking warning is performed.

[0105] In order to have a more comprehensive understanding of the front vehicle detection method based on the vehicle-mounted millimeter wave radar, please refer to Figure 7 and Figure 8 to Figure 2The structure of the vehicle-mounted millimeter wave radar is shown as an example to illustrate 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.

[0106] S11, the millimeter wave radar performs signal processing on the echo signal received at the front end to obtain a plurality of detection points.

[0107] S12, preprocessing the detection points. The preprocessing includes invalidation elimination of the point cloud data and coordinate system conversion for compensating installation errors.

[0108] S13, clustering the detection points. Target clustering is performed on the point cloud data to obtain a target clustering set. The target recognition algorithm is used to perform target recognition and preliminary identification of the front vehicle in the target clustering set.

[0109] The target recognition and preliminary identification of the front vehicle can include:

[0110] S141, determining whether the number of targets in the front direction of the radar is greater than 1.

[0111] If the condition is met, S142 is executed. Specifically, the two targets can be verified by detecting the azimuth angle to determine whether they are in the front direction of the radar. The one with a shorter distance is marked as the front vehicle, and the one with a longer distance is marked as the front vehicle. The object not in the front direction of the radar is marked as other.

[0112] S142, determining whether the farther target is blocked by the closer target among the two targets in the front direction of the radar. If the condition is met, the closer target is marked as the front vehicle, and the farther target is marked as the front vehicle. The target type of the front vehicle is identified.

[0113] The distance between the front vehicle and the vehicle, the distance between the front vehicle and the front vehicle, the length of the front vehicle a1, and the height of the front vehicle chassis h1 can be obtained. The corresponding a1 and h1 can be set according to the target type to which the front vehicle belongs. The distance l1 between the radar and the front vehicle is measured by the radar. The radial distance l of the farther target relative to the radar is calculated based on the radar measurement of the pitch angle and the radial distance l. The height h2 of the farther target, i.e. the clustering centroid height h2 of the front vehicle, is calculated.

[0114] S145, determining whether the distance between the front 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 of the front vehicle a1, and the height of the front vehicle chassis h1, it is determined whether l1 > a1 (h0-h1) / 2h1 or l1 = a1 (h0-h1) / 2h1. If the condition is met, S146 is executed.

[0116] S146, determining whether the clustering centroid of the farther target is below the ground (h2 < 0) according to the installation height of the radar. If the condition is met, S147 is executed.

[0117] S147, whether the distance between the preceding preceding vehicle and the preceding vehicle meets the detection range. If yes, S15 is executed.

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

[0119] S15, target tracking is performed on the preceding preceding vehicle.

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

[0121] It is judged whether the track starting condition is met, and the target track that meets the death or starting condition is executed track death and starting, and track merging and separation. After the preceding preceding vehicle track is started, the distance and spatial position of the preceding preceding vehicle are restored according to the radar installation information and the preceding vehicle information. As shown in the previous formula 6.

[0122] S16, the driving state of the preceding preceding vehicle is monitored, and it is judged whether the inter-frame driving speed change of the preceding preceding vehicle is greater than the speed change rate threshold. If it is met, the braking behavior confidence of the preceding preceding vehicle is increased.

[0123] S17, it is judged whether the braking behavior confidence of the preceding preceding vehicle is greater than the confidence threshold. If it is greater, the preceding preceding vehicle braking warning is performed.

[0124] The preceding preceding vehicle detection method based on the vehicle-mounted millimeter wave radar provided in the above embodiment is based on the ground multi-path 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 preceding vehicle target blocked by the preceding vehicle can be accurately calculated, the driving state thereof is monitored, the braking behavior of the preceding preceding vehicle is identified, and warning is performed. Without increasing the hardware equipment of the millimeter wave radar, the unique characteristics of the millimeter wave radar signal with multi-path effect are used to monitor the driving state of the preceding preceding vehicle and to warn the braking behavior of the preceding preceding vehicle.

[0125] The typical working process of the vehicle-mounted millimeter wave radar using the preceding preceding vehicle detection method based on the vehicle-mounted millimeter wave radar proposed in the embodiments of the present application is shown in FIG. 1, which includes the following steps: Figure 8

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

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

[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 parameter, and transmits the linear frequency modulation waveform local oscillator signal 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 a target reflected waveform signal, and transmits the target reflected waveform signal to the MRTR chip receiving component.

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

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

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

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

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

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

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

[0138] S223, the cycle completes the scene target detection until the condition of stopping working is met.

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

[0140] In another aspect of the embodiment of the application, please refer to Figure 2 and Figure 9 The application further provides a vehicle-mounted millimeter wave radar, which comprises a millimeter wave radar processor 201 and a memory 202. The memory 202 stores a computer program which 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 is realized, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0141] In another aspect of the embodiment of the application, please refer to Figure 10In some embodiments, a vehicle is provided, which includes a vehicle-mounted central control system and a vehicle-mounted millimeter wave radar connected to the vehicle-mounted central control system. The vehicle-mounted millimeter wave radar is configured to perform the method for detecting a front vehicle in front of a target vehicle based on a vehicle-mounted millimeter wave radar according to any of the embodiments of the present application. The vehicle-mounted central control system is configured to output corresponding auxiliary driving information according to the detection result of the target vehicle in front of the vehicle by the millimeter wave radar.

[0142] The auxiliary driving information can be the auxiliary driving information output by the vehicle-mounted central control system through calculation of the driving safety risk prediction based on the detection result of the target vehicle in front of the vehicle by the vehicle-mounted millimeter wave radar, such as but not limited to real-time updating and displaying the driving track of the front vehicle in front of the vehicle, the brake behavior warning of the front vehicle in front of the vehicle, the lane changing and overtaking reminder of the front vehicle in front of the vehicle, etc.

[0143] In another aspect, the embodiments of the present application also provide a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for detecting a front vehicle in front of a target vehicle based on a vehicle-mounted millimeter wave radar according to any of the embodiments of the present application is implemented, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0144] In another aspect, the embodiments of the present application also provide a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, each process of the method for detecting a front vehicle in front of a target vehicle based on a vehicle-mounted millimeter wave radar according to the above embodiments is implemented, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

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

[0146] It should be noted that, in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or apparatus including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or apparatus. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or apparatus including the element.

[0147] Those skilled in the art can clearly understand the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, can also be through hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solutions of the present application essentially or say the part of the prior art contribution can be embodied in the form of software products, the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disc, optical disc), including a number of instructions to make a terminal (may be a mobile phone, computer, server, or network equipment, etc.) executes the method described in various embodiments of the present application.

[0148] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited to this, any skilled in the art within the scope of the technology disclosed in the present application, can easily think of changes or replacement, should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for detecting a preceding vehicle based on a vehicle-mounted millimeter wave radar, characterized by, Comprising: receiving echo signals, processing the echo signals to obtain point cloud data; target clustering on the point cloud data to determine forward target information; the forward target information includes the number, position and occlusion state of forward targets; determining whether there is a potential front car according to the forward target information; if yes, determining whether the potential front car meets the track initiation condition based on continuous multi-frame radar data, and determining the potential front car meeting the track initiation condition as a target front car; wherein, the determination of whether the potential front car meets the track initiation condition based on continuous multi-frame radar data comprises: if the distance between the front car and the host vehicle is greater than the minimum detection distance boundary, determining whether the potential front car meets the following first track initiation condition 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 front car 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 front car and the distance of the intermediate car target is greater than the distance threshold, and the average signal-to-noise ratio of the clustering result corresponding to the potential front car is greater than the signal-to-noise ratio threshold; if the distance between the front car and the host vehicle is equal to the minimum detection distance boundary, determining whether the potential front car meets the following second track initiation condition based on continuous multi-frame radar data: the azimuth angle is less than a preset value, the distance between the front car and the host vehicle, the sum of the distance between the front car and the host vehicle and the length of the front car is approximately equal to the distance between the front car and the radar radial distance, and the average signal-to-noise ratio of the clustering result corresponding to the potential front car is greater than the signal-to-noise ratio threshold. 2.The car millimeter wave radar based front front vehicle detection method according to claim 1, characterized in that, The determination of whether there is a potential front car according to the forward target information comprises: determining whether the number of forward targets is greater than 1 according to the forward target information; if the number of forward targets is greater than 1, determining whether the far target is occluded by the near target according to the position of the forward target; if the far target is occluded by the near target, marking the near target as the front car and the far target as the front car, calculating the distance information of the front car and the front car, and determining whether the front car detection condition is met; if the front car detection condition is met, determining the current front car as a potential front car. 3.The vehicle-mounted millimeter wave radar-based preceding vehicle detection method according to claim 2, characterized in that, The calculation of the distance information of the front car and the front car and the determination of whether the front car detection condition is met comprise: obtaining front car parameters, calculating the distance between the front car and the host vehicle according to the radar installation height and the front car parameters, and determining whether the distance between the front car and the host vehicle meets the minimum detection distance boundary; the front car parameters include the front car chassis height and the front car length; if the minimum detection distance boundary is met, calculating the clustering centroid height of the front car according to the radar measurement pitch angle, the radar installation height and the radial distance of the front car; if the clustering centroid height meets the preset condition, calculating the distance between the front car and the front car according to the radial distance of the front car, the distance between the front car and the host vehicle, and the length of the front car; determining whether the front car detection condition is met according to whether the distance between the front car and the front car is within the front car detection range. 4.The vehicle-mounted millimeter wave radar-based preceding vehicle detection method according to claim 3, characterized in that, a length of the front vehicle is , a height of the front vehicle chassis is , a radar installation height is , and a distance between the front vehicle and the ego vehicle is . Whether the distance between the front vehicle and the ego vehicle satisfies a minimum detection distance boundary is determined according to the following calculation formula: ； The front-to-front vehicle distance is , and the calculation formula is as follows: ； The front-to-front vehicle distance Whether in the front-to-front vehicle detection range, the calculation formula is as follows: ； ； ； wherein, with respectively represent the distance range of the radar capable of detecting the car in front at the current time without considering the radar transmitting power; measuring the height of the car in front. 5.The vehicle-mounted millimeter wave radar-based preceding vehicle detection method according to claim 1, characterized in that, After determining the target front car, it further comprises: identifying the braking behavior of the target front car according to the relationship between the speed change amount of the target front car and the speed change rate threshold, and performing brake warning. 6.The vehicle-mounted millimeter wave radar-based preceding vehicle detection method according to claim 5, characterized in that, Further comprising: According to the following formula, the spatial position information of the pre-preceding vehicle is restored: ； wherein, is a front front vehicle azimuth angle, is a front front vehicle pitch angle, is a front front vehicle radial distance, is a radar mounting height, , , is a Cartesian coordinate of the front front vehicle.

7. The vehicle-mounted millimeter wave radar-based preceding vehicle detection method according to claim 6, characterized in that, The braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and the speed change rate threshold, and the braking behavior of the target pre-preceding vehicle is identified and braking warning is given according to the relationship between the speed change amount of the target pre-preceding vehicle and ​ ​ ​ 8. A vehicle mounted millimeter wave radar characterized by comprising: ​ ​ 9. A vehicle characterized by comprising: ​ ​ ​ 10. A computer program product comprising a computer program, characterized in that, ​

Images