Vehicle-mounted monitoring and early warning method and vehicle

Abstract

The invention discloses a vehicle-mounted monitoring and early warning method and a vehicle, the vehicle-mounted monitoring and early warning method is applied to the vehicle with a radar, and the vehicle-mounted monitoring and early warning method comprises the following steps: setting a warning area based on a radar view blind area; acquiring surrounding dynamic target information, and determining a dangerous target based on the dynamic target information and the warning area; based on the dangerous target information and the vehicle information, whether a dynamic target exists in a radar view blind area or not is judged; if the dynamic target exists in the radar view blind area, alarm information is sent out. According to the method, a warning area is set according to a radar view blind area, a dynamic target entering the warning area is determined as a dangerous target, and whether the dynamic target exists in the radar view blind area or not is judged according to dangerous target information and vehicle information; on the premise that hardware cost is not increased, whether a dynamic target exists in a radar view blind area or not is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-mounted BSD early warning systems, and in particular to a vehicle-mounted monitoring and early warning method and a vehicle. Background Art

[0002] The vehicle-mounted BSD warning system, or Blind Spot Detection System, is an advanced driver assistance system (ADAS) that is mainly used to monitor the blind spots on the side and rear of the vehicle to reduce the risk of collision accidents when the vehicle changes lanes. The system detects moving objects such as cars, motorcycles, bicycles, pedestrians, etc. in the blind spots through millimeter-wave radar sensors installed on both sides of the car. When a vehicle or other obstacle is detected entering the driver's blind spot, the system will send a warning signal through the receiving device on the edge of the rearview mirror, such as lighting up the cursor or flashing lights, and even accompanied by a sound warning or steering wheel vibration. However, due to the limited field of view of the radar, there is still a certain range of radar field of view blind spots on the side of the vehicle. When small dynamic targets such as motorcycles and bicycles are driving on the side of the vehicle, there is a possibility that they are completely in the radar field of view blind spots. Since the radar cannot detect dynamic targets at this time, the BSD system will determine that the target has disappeared at this time, and the warning will stop. If the vehicle changes lanes at this time, there is a risk of collision. Summary of the invention

[0003] The main purpose of the present invention is to provide a vehicle-mounted monitoring and early warning method, aiming to solve the BSD underreporting problem caused by the blind area of ​​the radar field of view.

[0004] To achieve the above object, the vehicle-mounted monitoring and early warning method proposed in the present invention is applied to a vehicle with a radar, and the vehicle-mounted monitoring and early warning method comprises:

[0005] Set warning areas based on radar blind spots;

[0006] Acquire surrounding dynamic target information, and determine dangerous targets based on the dynamic target information and the warning area;

[0007] Based on the dangerous target information and the vehicle information, determine whether there is a dynamic target in the radar blind spot;

[0008] If there is a dynamic target in the blind spot of the radar field of view, an alarm message will be issued.

[0009] Optionally, the setting of the warning area based on the radar blind area includes:

[0010] Calculate the vehicle's radar blind spot based on the vehicle's radar field of view, the radar's installation angle and location coordinates;

[0011] A warning area is set based on the size and position of the radar blind area; wherein the warning area includes the radar blind area.

[0012] Optionally, the set warning area is a rectangle, and one side of the set warning area is arranged to fit the side edge of the vehicle.

[0013] Optionally, the acquiring surrounding dynamic target information and determining the dangerous target based on the dynamic target information and the warning area includes:

[0014] Acquire dynamic target information around the vehicle; the dynamic target information at least includes position information;

[0015] Based on the position information and the warning area, any dynamic target that is partially within the warning area is regarded as a dangerous target.

[0016] Optionally, the dynamic target information also includes confidence and life cycle;

[0017] The method of treating any part of a dynamic target in the warning area as a dangerous target based on the position information and the warning area comprises:

[0018] Determining whether the dynamic target information is credible based on the confidence level and the life cycle;

[0019] If it is credible, the step of treating any dynamic target that is in the warning area as a dangerous target based on the position information and the warning area is executed.

[0020] Optionally, judging whether there is a dynamic target in the blind spot of the radar field of view based on the dangerous target information and the vehicle information includes:

[0021] Based on the position information of the dangerous target, the position of the dangerous target relative to the vehicle is obtained;

[0022] Based on the position of the dangerous target compared to the vehicle, the speed of the dangerous target, the speed of the vehicle and the confidence of the dangerous target, it is determined whether there is a dynamic target in the blind spot of the radar field of view.

[0023] Optionally, judging whether there is a dynamic target in the radar blind spot based on the position of the dangerous target compared to the vehicle, the speed of the dangerous target, the vehicle speed and the confidence of the dangerous target includes:

[0024] Calculating the relative speed of the dangerous target based on the speed of the dangerous target and the speed of the vehicle;

[0025] Determining whether the dangerous target is close to the ego vehicle based on the position of the dangerous target relative to the ego vehicle and the relative speed of the dangerous target;

[0026] If the dangerous target is close to the vehicle and the confidence of the dangerous target is lower than the confidence threshold, it is determined whether there is a dynamic target in the blind spot of the radar field of view.

[0027] Optionally, if there is a dynamic target in the radar blind spot, an alarm message is issued, and then the method further includes:

[0028] If a new dynamic target appears in the warning area, determine whether it is a dangerous target that is out of the radar blind spot according to the confidence and life cycle of the new dynamic target;

[0029] If the new dynamic target is a dangerous target that is out of the radar blind spot, and the new dynamic target is out of the warning area, stop sending the alarm information.

[0030] Optionally, judging whether the new dynamic target is a dangerous target out of the radar blind spot according to the confidence and life cycle of the new dynamic target includes:

[0031] comparing the confidence of the new dynamic target with the confidence threshold;

[0032] Compare the life cycle of the new dynamic goal with the set life cycle;

[0033] If the confidence of the new dynamic target is higher than or equal to the confidence threshold, and the life cycle of the new dynamic target is less than or equal to the set life cycle, the new dynamic target is determined to be a dangerous target that is out of the radar blind spot.

[0034] The present invention also proposes a vehicle, which includes a radar, a processor, a memory, and an on-board monitoring and early warning program stored in the memory and executable on the processor, wherein the on-board monitoring and early warning program is configured to implement the steps of the on-board monitoring and early warning method.

[0035] The present invention discloses a vehicle-mounted monitoring and early warning method and a vehicle, the vehicle-mounted monitoring and early warning method is applied to a vehicle with a radar, and the vehicle-mounted monitoring and early warning method includes: setting a warning area based on the radar blind area; obtaining surrounding dynamic target information, and determining dangerous targets based on the dynamic target information and the warning area; judging whether there are dynamic targets in the radar blind area based on the dangerous target information and the vehicle information; and issuing an alarm message if there are dynamic targets in the radar blind area. The present invention sets a warning area based on the radar blind area, identifies dynamic targets entering the warning area as dangerous targets, and then judges whether there are dynamic targets in the radar blind area based on the dangerous target information and the vehicle information; and realizes the function of obtaining whether there are dynamic targets in the radar blind area without increasing the hardware cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of a scene of an embodiment of a vehicle-mounted monitoring and early warning method of the present invention;

[0038] Figure 2 A schematic diagram of a scene of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0039] Figure 3 A schematic diagram of a scene of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0040] Figure 4 A schematic diagram of a process flow of an embodiment of a vehicle-mounted monitoring and early warning method of the present invention;

[0041] Figure 5 A schematic diagram of a flow chart of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0042] Figure 6 A schematic diagram of a flow chart of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0043] Figure 7 A schematic diagram of a flow chart of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0044] Figure 8 A schematic diagram of a flow chart of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0045] Fig. 9 A schematic diagram of a flow chart of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0046] Fig.10 A schematic diagram of a scene of an embodiment of a vehicle-mounted monitoring and early warning method of the present invention;

[0047] Fig.11 A schematic diagram of a scene of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0048] Fig.12 A schematic diagram of a scene of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention;

[0049] Fig.13 This is a scene diagram of another embodiment of the vehicle-mounted monitoring and early warning method of the present invention.

[0050] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0055] The vehicle-mounted BSD warning system, or Blind Spot Detection System, is an advanced driver assistance system (ADAS) that is mainly used to monitor the blind spots on the side and rear of the vehicle to reduce the risk of collision accidents when the vehicle changes lanes. The system uses millimeter-wave radar sensors installed on both sides of the car to detect moving objects such as cars, motorcycles, bicycles, pedestrians, etc. in the blind spots. When a vehicle or other obstacle is detected entering the driver's blind spot, the system will send a warning signal through the receiving device on the edge of the rearview mirror, such as lighting up the cursor or flashing lights, and even accompanied by sound warnings or steering wheel vibrations. Figure 1 As shown in the figure, due to the limited field of view of the radar, there is still a certain range of radar blind spots on the side of the vehicle. When small dynamic targets such as motorcycles and bicycles are driving on the side of the vehicle, there is a possibility that they are completely in the radar blind spot. Since the radar cannot detect the dynamic target at this time, the BSD system will determine that the target has disappeared and the warning will stop. If the vehicle changes lanes at this time, there is a risk of collision. This is a limitation of the BSD system. Without increasing the hardware configuration, there is no mature solution relying solely on millimeter-wave radar. The widely used solution is to add a camera and integrate it with the millimeter-wave radar perception to make up for the problem of the radar blind spot. Its layout structure is as follows Figure 2 As shown. For target detection, the controller will fuse radar point cloud data and visual data to improve the accuracy and precision of target detection and classify target types. The use of camera field of view can make up for the blind spot of millimeter-wave radar field of view, thereby avoiding the BSD underreporting problem. However, the solution of adding cameras will increase hardware costs. First, the cost of the camera itself, and second, to perform perception fusion, the controller computing power needs to be improved, the controller hardware cost is increased, and the software complexity is increased, resulting in an overall increase in system cost and complexity.

[0056] This method aims to solve the BSD underreporting problem caused by the radar blind spot without increasing the hardware cost. Specifically, the present invention proposes a vehicle-mounted monitoring and early warning method, which is applied to a vehicle with a radar, and the vehicle-mounted monitoring and early warning method includes:

[0057] Step S10: setting a warning area based on the radar blind area;

[0058] It should be noted that this solution is applied to vehicles with radar blind spots, wherein the number of radars and the arrangement of radars in the vehicle are not limited by this solution. Accordingly, the shape of the radar blind spot is not limited by this solution.

[0059] In one example, a radar is arranged at each of the four corners of the vehicle, such as Figure 1 As shown, Figure 1Taking the side of a vehicle as an example, the radar blind area on the side of the vehicle is displayed. In this example, the radar blind area is a triangle.

[0060] This solution sets a warning area based on a specific radar blind area. The warning area set based on the radar blind area includes:

[0061] Step S110, calculating the radar blind spot of the vehicle based on the vehicle-mounted radar field of view angle, the radar installation angle and the position coordinates;

[0062] Step S120: setting a warning area based on the size and position of the radar blind area; wherein the warning area includes the radar blind area.

[0063] It is easy to understand that the purpose of setting the warning area is to analyze whether the dynamic target enters or leaves a specific area of ​​the radar blind area; the warning area needs to cover the radar blind area.

[0064] In addition, it is easy to understand that the detection distance and field of view of a single radar are limited, and the combination of multiple radars may form a radar field of view blind spot. In one example, the self-vehicle includes 4 angular millimeter-wave radars, which are arranged at the right front, right rear, left front and left rear positions of the vehicle body, with a horizontal field of view of about 150°, a vertical field of view of about 12°, and a detection distance of about 0.3m to 110m. By processing the electromagnetic wave signal, the distance, speed, angle and other information of the target are obtained. It should be noted that the self-vehicle represents the vehicle to which the vehicle-mounted monitoring and early warning method is applied. In order to distinguish it from other vehicles on the road, the self-vehicle will be used to refer to it later.

[0065] Reference Figure 1 , the radar blind area of ​​the vehicle can be calculated based on the field of view angle of the vehicle-mounted radar, the installation angle of the radar and the position coordinates. It should be noted that the field of view angle of the vehicle-mounted radar includes the horizontal field of view angle and the vertical field of view angle of the radar. The position coordinates of the radar depend on the installation position of the radar on the vehicle. It is easy to understand that the installation angle of the radar, the field of view angle of the radar and the position coordinates of the radar determine the detection area of ​​a single radar. The horizontal detection field of view of a single millimeter-wave radar is about 150°. Based on the current layout scheme, the detection range of the millimeter-wave radar cannot completely cover the side vision of the vehicle. There is still a large blind area of ​​vision on the side of the vehicle. For small dynamic targets, such as bicycles, motorcycles or pedestrians, they can be completely in the radar blind area. If the dynamic target enters the radar blind area and keeps the same speed as the vehicle for a long time, the BSD function will stop the alarm because the radar cannot detect the dynamic target, resulting in BSD underreporting, which poses a safety hazard.

[0066] The radar blind area of ​​the vehicle can be calculated specifically based on the field of view angle of each radar on the vehicle, the installation angle and position coordinates of the radar. It is easy to understand that the radar blind area refers to the area that cannot be detected by any radar on the vehicle. When a dynamic target is in the radar blind area, the vehicle cannot obtain information about the target in the radar blind area through the radar.

[0067] Furthermore, in order to avoid the situation where dynamic targets are missed from entering the radar blind area, the warning area needs to cover the radar blind area, that is, the warning area includes the radar blind area. Correspondingly, the warning area needs to be set according to the size and position of the radar blind area.

[0068] Specifically, based on the vehicle-mounted millimeter-wave radar field of view, the installation angle and position coordinates on the vehicle, the corner coordinates, longitudinal distance H and lateral distance L of the radar visual triangular blind area on the side of the vehicle are calculated. Then, according to the size and position of the radar visual triangular blind area, a warning area is set, which will cover the visual blind area and be used to analyze whether a dynamic target enters or leaves a specific area of ​​the blind area.

[0069] In one example, if Figure 3 As shown, the area is set as a rectangle, the length of which must be greater than the longitudinal distance H of the radar blind spot, the width of which must be greater than the lateral distance L, the side edges must fit the side edges of the vehicle (excluding the rearview mirror), and the three corner points of the radar blind spot must be included.

[0070] Step S20, obtaining surrounding dynamic target information, and determining dangerous targets based on the dynamic target information and the warning area;

[0071] It should be noted that the vehicle obtains information about surrounding dynamic targets based on the radar mounted thereon, which is hereinafter referred to as surrounding dynamic target information.

[0072] Dangerous targets refer to dynamic targets that may enter but have not yet entered the radar blind spot, making them undetectable by the radar. Dynamic targets include four-wheeled vehicles, two-wheeled vehicles, and pedestrians. After a dangerous target is identified, its ID is stored and a calculation is performed to determine whether it has entered the radar blind spot.

[0073] The position information in the dynamic target information is compared with the warning area. If any part of the dynamic target is within the warning area, the dynamic target can be regarded as a dangerous target.

[0074] In one example, the acquiring surrounding dynamic target information and determining the dangerous target based on the dynamic target information and the warning area includes:

[0075] Step S210, obtaining dynamic target information around the vehicle; the dynamic target information at least includes position information;

[0076] Step S220: Based on the position information and the warning area, any dynamic target that is in the warning area is regarded as a dangerous target.

[0077] It should be noted that the ultimate goal of the vehicle-mounted BSD warning system is to prevent the vehicle from colliding with other dynamic targets on the road. The position information of the dynamic target and the vehicle can be used to determine whether the two may collide. The range within a certain distance around the vehicle can be set as a warning area, and the position information of the dynamic target can be used to determine whether the dynamic target has entered the warning area. In one example, the range of the warning area is 3m from the lateral distance of the vehicle, and the longitudinal distance is a rectangular area from the eyeline to 3m behind the rear bumper, which is symmetrical on the left and right. When any part of the dynamic target (vehicle, two-wheeled vehicle, pedestrian, etc.) enters the alarm area, an alarm message is issued to remind the driver.

[0078] In another example, in order to avoid excessive sensitivity of the system and excessive burden on computing resources, the dynamic target information also includes confidence and life cycle;

[0079] The method of treating any part of a dynamic target in the warning area as a dangerous target based on the position information and the warning area comprises:

[0080] Determining whether the dynamic target information is credible based on the confidence level and the life cycle;

[0081] If it is credible, the step of treating any dynamic target that is in the warning area as a dangerous target based on the position information and the warning area is executed.

[0082] It should be noted that the confidence level is the credibility level of the target detection, tracking, identification and other results based on the radar observation data. For example, if the radar detects a suspected aircraft target in a certain airspace, a high confidence level means that the system has a high confidence in determining that the detection result is a real target; conversely, a low confidence level implies that the detection result is likely to be a false alarm or error interference. It can be determined by multiple factors such as the strength of the radar signal, the stability of the signal, the noise characteristics, and the degree of feature matching of the target. For example, the stronger the echo signal received by the radar, the more stable the signal, and the higher the degree of fit with the preset target radar cross section and other features, the higher the corresponding confidence level will be.

[0083] The life cycle is the length of time that the radar can continuously detect the target. Generally speaking, the higher the confidence, the more credible the dynamic target information; the longer the generation cycle, the more credible the dynamic target information.

[0084] A confidence threshold and a life cycle threshold can be set. Compare the confidence corresponding to the dynamic target with the confidence threshold, and compare the generation cycle corresponding to the dynamic target with the life cycle threshold. If the confidence is higher than or equal to the confidence threshold, and the generation cycle is greater than or equal to the life cycle threshold, it can be determined that the dynamic target information is credible. It should be noted that the confidence threshold and the life cycle threshold are set by R&D personnel.

[0085] After determining the dangerous target, determine whether there is a dynamic target in the radar blind area. It is easy to understand that this solution regards the dynamic target in the warning area as a dangerous target and gives it an ID number accordingly to facilitate identification and management. Since the warning area includes the radar blind area, the dynamic target entering the radar blind area must be a dangerous target.

[0086] Step S30: Based on the dangerous target information and the vehicle information, determine whether there is a dynamic target in the radar blind spot;

[0087] It should be noted that the dangerous target information includes the confidence, life cycle, location information and speed of the dangerous target. It is easy to understand that in the process of the dangerous target entering the blind spot of the radar field of view, the radar point cloud reflected by the dangerous target gradually decreases, and its confidence decreases accordingly. In addition, this scheme also determines whether the dangerous target enters the blind spot of the radar field of view by the orientation of the dangerous target and the relative speed of the dangerous target compared to the vehicle. If the relative speed of the dangerous target makes the dangerous target move closer to the vehicle, and the confidence of the dangerous target gradually decreases, it can be considered that the dangerous target is entering the blind spot of the radar field of view.

[0088] In one embodiment, judging whether there is a dynamic target in the radar blind spot based on the dangerous target information and the vehicle information includes:

[0089] Step S310: based on the position information of the dangerous target, obtain the position of the dangerous target relative to the vehicle;

[0090] Step S320: Based on the position of the dangerous target compared to the vehicle, the speed of the dangerous target, the vehicle speed and the confidence of the dangerous target, determine whether there is a dynamic target in the radar blind spot.

[0091] Since the radars are all installed on the ego vehicle, the ego vehicle can be regarded as a whole compared to other dynamic targets. After obtaining the position information of the dangerous target, the direction of the dangerous target compared to the ego vehicle can be obtained based on the position information.

[0092] It should be noted that if the dangerous target (assuming ID_1) is in front of the vehicle, and the relative longitudinal speed (vehicle longitudinal speed - dangerous target longitudinal speed) > 0, there is a possibility that the dangerous target passively enters the radar blind spot. When the dangerous target gradually enters the radar blind spot, the reflected radar point cloud gradually decreases, and its confidence decreases accordingly. When the confidence is lower than the confidence threshold, it is determined that the dangerous target has entered the radar blind spot. The alarm signal flag is set to 1, indicating that there is a dynamic target in the blind spot. At this time, the BSD will keep the alarm without interruption.

[0093] If the dangerous target (assuming ID_1) is behind the vehicle, and the relative longitudinal speed (vehicle longitudinal speed - dangerous target longitudinal speed) is less than 0, the dangerous target may actively enter the radar blind spot. When the dangerous target gradually enters the radar blind spot, the reflected radar point cloud gradually decreases, and its confidence decreases accordingly. When the confidence is lower than the confidence threshold, it is determined that the dangerous target has entered the radar blind spot. The alarm signal flag is set to 1, indicating that there is a dynamic target in the blind spot. At this time, the BSD will keep the alarm without interruption.

[0094] If the dangerous target (assuming ID_1) is on the right side of the vehicle, the relative longitudinal speed is 0, but the relative lateral speed (lateral speed of the vehicle - lateral speed of the dangerous target) is greater than 0, the dangerous target will gradually approach the vehicle and may enter the radar blind spot. When the dangerous target gradually enters the radar blind spot, the reflected radar point cloud gradually decreases, and its confidence decreases accordingly. When the confidence is lower than the confidence threshold, it is determined that the dangerous target has entered the radar blind spot. The alarm signal flag is set to 1, indicating that there is a dynamic target in the blind spot. At this time, the BSD will keep the alarm without interruption.

[0095] If the dangerous target (assuming ID_1) is on the left side of the vehicle, the relative longitudinal speed is 0, but the relative lateral speed (lateral speed of the vehicle - lateral speed of the dangerous target) is less than 0, the dangerous target will gradually approach the vehicle and may enter the radar blind spot. When the dangerous target gradually enters the radar blind spot, the reflected radar point cloud gradually decreases, and its confidence decreases accordingly. When the confidence is lower than the confidence threshold, it is determined that the dangerous target has entered the radar blind spot. The alarm signal flag is set to 1, indicating that there is a dynamic target in the blind spot. At this time, the BSD will keep the alarm without interruption.

[0096] The determining whether there is a dynamic target in the radar blind spot based on the position of the dangerous target compared to the vehicle, the speed of the dangerous target, the vehicle speed and the confidence of the dangerous target includes:

[0097] Step S3210, calculating the relative speed of the dangerous target based on the speed of the dangerous target and the vehicle speed;

[0098] Step S3220: judging whether the dangerous target is close to the vehicle based on the position of the dangerous target compared to the vehicle and the relative speed of the dangerous target;

[0099] Step S3230: If the dangerous target is close to the vehicle and the confidence of the dangerous target is lower than the confidence threshold, determine whether there is a dynamic target in the blind spot of the radar field of view.

[0100] Step S40: If there is a dynamic target in the radar blind spot, an alarm message is issued.

[0101] It should be noted that if it is determined that there is a dynamic target in the blind spot of the radar field of view, an alarm message will be continuously issued to solve the problem in the prior art that when the dynamic target is in the blind spot of the radar field of view and the radar cannot detect the dynamic target, the BSD system determines that the target has disappeared and the warning stops, which may cause the risk of vehicle lane change collision.

[0102] The present invention discloses a vehicle-mounted monitoring and early warning method and a vehicle, the vehicle-mounted monitoring and early warning method is applied to a vehicle with a radar, and the vehicle-mounted monitoring and early warning method includes: setting a warning area based on the radar blind area; obtaining surrounding dynamic target information, and determining dangerous targets based on the dynamic target information and the warning area; judging whether there are dynamic targets in the radar blind area based on the dangerous target information and the vehicle information; and issuing an alarm message if there are dynamic targets in the radar blind area. The present invention sets a warning area based on the radar blind area, identifies dynamic targets entering the warning area as dangerous targets, and then judges whether there are dynamic targets in the radar blind area based on the dangerous target information and the vehicle information; and realizes the function of obtaining whether there are dynamic targets in the radar blind area without increasing the hardware cost.

[0103] It is easy to understand that a dangerous target may enter or leave the radar blind spot of the vehicle. Considering the actual situation, if we only handle the dangerous target entering the radar blind spot but not the dangerous target leaving the radar blind spot, after a dangerous target enters the radar blind spot, no matter whether the dangerous target leaves the radar blind spot later, the alarm information will continue to be issued.

[0104] In order to solve the above problem, in one embodiment of the present invention, if there is a dynamic target in the radar blind spot, an alarm message is issued, and then the following is further included:

[0105] Step S50: If a new dynamic target appears in the warning area, determine whether it is a dangerous target that is out of the radar blind spot according to the confidence and life cycle of the new dynamic target;

[0106] Step S60: If the new dynamic target is a dangerous target that is out of the radar blind spot, and the new dynamic target is out of the warning area, stop sending the alarm information.

[0107] It should be noted that since the warning area covers the radar blind area, after the dangerous target escapes from the radar blind area, it will enter the warning area again and be detected by the radar. However, it is easy to understand that the radar blind area is generally connected to one side of the vehicle. When the dangerous target escapes from the radar blind area, the emitted radar point cloud is stronger, the echo signal received by the radar is stronger, the signal is stable, and the corresponding confidence is high. However, after the dangerous target escapes from the radar blind area, the survival period of the dangerous target in the warning area is recalculated, and the survival period is smaller.

[0108] When a new dynamic target appears in the warning area, if the confidence of the new dynamic target is high and the life cycle is short, the new dynamic target can be determined as a dangerous target that has escaped from the blind spot of the radar field of view.

[0109] In one example, judging whether the new dynamic target is a dangerous target out of the radar blind spot according to the confidence and life cycle of the new dynamic target includes:

[0110] comparing the confidence of the new dynamic target with the confidence threshold;

[0111] Compare the life cycle of the new dynamic goal with the set life cycle;

[0112] If the confidence of the new dynamic target is higher than or equal to the confidence threshold, and the life cycle of the new dynamic target is less than or equal to the set life cycle, the new dynamic target is determined to be a dangerous target out of the radar blind spot. The set life cycle is determined by the R&D personnel.

[0113] It is easy to understand that this solution numbers each dynamic target that enters the warning area. When a new dynamic target is determined to be a dangerous target that has left the radar blind spot, the number of the dangerous target that has entered the radar blind spot is used to re-reference the new dynamic target. The new dynamic target is continuously monitored. If the new dynamic target leaves the warning area, the alarm message is stopped. It should be pointed out that in order to improve safety, this solution proposes an embodiment. In this embodiment, the count number of dangerous targets entering the radar blind spot is recorded; when the dangerous target leaves the radar blind spot, the count number is reduced by one; when the dangerous target enters the radar blind spot, the count number is increased by one. The alarm message is stopped only when the count number is zero and there is no dangerous target in the warning area.

[0114] To facilitate understanding, the following embodiments are provided.

[0115] In the first embodiment, the vehicle actively overtakes. Fig.10 As shown, there is a triangular blind spot on the right side of the vehicle, and the warning area covers the blind spot. When the dynamic target is in position 1, part of its body has entered the warning area. If its confidence and life cycle are greater than the corresponding threshold, it will be judged as a dangerous target. It is currently in front of the vehicle. If its speed is lower than the speed of the vehicle, that is, the relative longitudinal speed (longitudinal speed of the vehicle - longitudinal speed of the dangerous target)>0, it will then enter the radar blind spot. As the point cloud feedback decreases, the confidence will decrease, and it is judged that it has entered the radar blind spot and is in position 2. Therefore, when the dangerous target meets the following conditions:

[0116] Located in front of the vehicle, with a relative longitudinal speed > 0, when the confidence level is lower than the confidence level threshold or the target disappears, it is determined to have entered the blind spot and the alarm signal flag is set to 1.

[0117] like Fig.11 As shown in the figure, when it moves from position 2 to position 3, a new ID appears in the warning area. When its confidence is greater than or equal to the confidence threshold and its life cycle is less than or equal to the set life cycle, it is determined to be a dangerous target that has left the blind spot, and the alarm signal flag is set to 0.

[0118] In the second embodiment, the vehicle performs passive overtaking. Fig.12 As shown in the figure, the passive overtaking scenario is similar to the active overtaking scenario. The dangerous target is originally located behind the vehicle and gradually enters the radar blind spot. When it is at position 1, it is judged as a dangerous target by confidence and life cycle. The relative longitudinal speed is less than 0, and it gradually enters the radar blind spot. When the confidence is lower than the confidence threshold or the target disappears, it is judged to have entered the blind spot, and the alarm signal flag is set to 1.

[0119] like Fig.13 As shown in the figure, when the target moves from position 2 to position 3, a new ID appears in the warning area. When its confidence is greater than or equal to the confidence threshold and its life cycle is less than or equal to the set life cycle, it is determined to be a dangerous target that has left the blind spot, and the alarm signal flag is set to 0.

[0120] The present invention also proposes a vehicle, comprising a radar, a processor, a memory, and an on-board monitoring and early warning program stored in the memory and executable on the processor, wherein the on-board monitoring and early warning program is configured to implement the steps of the on-board monitoring and early warning method. The specific steps of the on-board monitoring and early warning method refer to the above-mentioned embodiments. Since the present subject two adopts all the technical solutions of all the above-mentioned embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be described one by one here. The above is only an optional embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural transformations made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A vehicle-mounted monitoring and early warning method, characterized in that: The vehicle-mounted monitoring and early warning method is applied to a vehicle with a radar, and the vehicle-mounted monitoring and early warning method includes: Set warning areas based on radar blind spots; Acquire surrounding dynamic target information, and determine dangerous targets based on the dynamic target information and the warning area; Based on the dangerous target information and the vehicle information, determine whether there is a dynamic target in the radar blind spot; If there is a dynamic target in the blind spot of the radar field of view, an alarm message will be issued.

2. The vehicle-mounted monitoring and early warning method according to claim 1, characterized in that: The setting of the warning area based on the radar blind area includes: Calculate the vehicle's radar blind spot based on the vehicle's radar field of view, the radar's installation angle and location coordinates; A warning area is set based on the size and position of the radar blind area; wherein the warning area includes the radar blind area.

3. The vehicle-mounted monitoring and early warning method according to claim 2, characterized in that: The set warning area is rectangular, and one side of the set warning area is arranged to fit the side edge of the vehicle.

4. The vehicle-mounted monitoring and early warning method according to claim 2, characterized in that: The acquiring of surrounding dynamic target information and determining a dangerous target based on the dynamic target information and the warning area includes: Acquire dynamic target information around the vehicle; the dynamic target information at least includes position information; Based on the position information and the warning area, any dynamic target that is partially within the warning area is regarded as a dangerous target.

5. The vehicle-mounted monitoring and early warning method according to claim 4, characterized in that: The dynamic target information also includes confidence and life cycle; The method of treating any part of a dynamic target in the warning area as a dangerous target based on the position information and the warning area comprises: Determining whether the dynamic target information is credible based on the confidence level and the life cycle; If it is credible, the step of treating any dynamic target that is in the warning area as a dangerous target based on the position information and the warning area is executed.

6. The vehicle-mounted monitoring and early warning method according to any one of claims 1 to 5, characterized in that: The determining whether there is a dynamic target in the radar blind spot based on the dangerous target information and the vehicle information includes: Based on the position information of the dangerous target, the position of the dangerous target relative to the vehicle is obtained; Based on the position of the dangerous target compared to the vehicle, the speed of the dangerous target, the speed of the vehicle and the confidence of the dangerous target, it is determined whether there is a dynamic target in the blind spot of the radar field of view.

7. The vehicle-mounted monitoring and early warning method according to claim 6, characterized in that: The determining whether there is a dynamic target in the radar blind spot based on the position of the dangerous target compared to the vehicle, the speed of the dangerous target, the vehicle speed and the confidence of the dangerous target includes: Calculating the relative speed of the dangerous target based on the speed of the dangerous target and the speed of the vehicle; Determining whether the dangerous target is close to the ego vehicle based on the position of the dangerous target relative to the ego vehicle and the relative speed of the dangerous target; If the dangerous target is close to the vehicle and the confidence of the dangerous target is lower than the confidence threshold, it is determined whether there is a dynamic target in the blind spot of the radar field of view.

8. The vehicle-mounted monitoring and early warning method according to any one of claims 1 to 5, characterized in that: If there is a dynamic target in the radar blind spot, an alarm message is issued, and then the following steps are also included: If a new dynamic target appears in the warning area, determine whether it is a dangerous target that is out of the radar blind spot according to the confidence and life cycle of the new dynamic target; If the new dynamic target is a dangerous target that is out of the radar blind spot, and the new dynamic target is out of the warning area, stop sending the alarm information.

9. The vehicle-mounted monitoring and early warning method according to claim 8, characterized in that: The step of judging whether the new dynamic target is a dangerous target out of the radar blind spot according to the confidence and life cycle of the new dynamic target includes: comparing the confidence of the new dynamic target with the confidence threshold; Compare the life cycle of the new dynamic goal with the set life cycle; If the confidence of the new dynamic target is higher than or equal to the confidence threshold, and the life cycle of the new dynamic target is less than or equal to the set life cycle, the new dynamic target is determined to be a dangerous target that is out of the radar blind spot.

10. A vehicle, characterized in that: The vehicle includes a radar, a processor, a memory, and an on-board monitoring and early warning program stored in the memory and executable on the processor, wherein the on-board monitoring and early warning program is configured to implement the steps of the on-board monitoring and early warning method as described in any one of claims 1 to 9.

Images