Vehicle automatic emergency braking judgment method and device based on target object recognition

Abstract

The invention provides a vehicle automatic emergency braking judgment method and device based on target object recognition. The method comprises the steps that image information in front of a vehicle is acquired, and the time distance between the vehicle and a target object is determined; setting a plurality of front detection areas according to the time interval; when the target object enters the first detection area, starting a front collision warning function; according to the triggering result of the front collision warning function, detecting whether a driver executes a predetermined operation, and judging whether an automatic emergency braking function is triggered or not according to the detection result; according to the triggering result of the front collision warning function and the execution condition of the driver on the preset operation, the cross section image of the target object is compared with the size of the second detection area, and in combination with the type of the target object, whether avoiding operation is executed or whether the automatic emergency braking function is directly triggered or not is judged. According to the method, the judgment process of automatic emergency braking of the vehicle can be simplified and accelerated, so that the probability of false triggering and missed triggering is reduced, and the driving safety of the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle technology, and in particular to a method and device for determining vehicle automatic emergency braking based on target object recognition. Background Art

[0002] As an important component of the Advanced Driver Assistance System (ADAS), the Automatic Emergency Braking System (AEB) has played a key role in actual road driving in recent years and has become one of the important technologies to improve driving safety. The function of AEB is to help drivers avoid or mitigate traffic accidents by detecting potential collision hazards ahead and automatically applying brakes. However, the AEB system still has problems with false triggering and missed triggering in actual applications, which may lead to potential traffic accidents.

[0003] Existing AEB systems mainly rely on sensors such as millimeter-wave radars and cameras to sense targets in front of the vehicle. However, in certain specific scenarios, the recognition capabilities of these sensors are insufficient, resulting in false triggering or missed triggering of the AEB system. For example, when a vehicle is traveling on a highway, a billboard on an overpass may be mistakenly identified as a stationary vehicle, which in turn causes a false triggering of the AEB, causing the vehicle to brake urgently and possibly causing a rear-end collision. Another typical scenario is that when there are stationary or slow-moving vehicles in front of the lane, the millimeter-wave radar may not be able to effectively identify these targets, causing the AEB system to fail to respond in time, thereby increasing the risk of a collision. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a vehicle automatic emergency braking determination method and device based on target object recognition to solve the problem in the prior art that the automatic emergency braking function is easily mistriggered or missed, resulting in reduced vehicle driving safety.

[0005] In a first aspect of an embodiment of the present application, a method for determining vehicle automatic emergency braking based on target object recognition is provided, comprising: acquiring image information in front of a vehicle and determining a time distance between the vehicle and the target object; according to the time distance, setting a plurality of detection areas in front, wherein the detection area includes at least a first detection area and a second detection area, which are respectively used to detect the target object under different time distance conditions; when the target object enters the first detection area, starting a forward collision warning function, and judging based on the image information whether the cross-sectional image of the target object continues to increase in the first detection area, so as to determine whether the relative distance between the vehicle and the target object decreases; according to the triggering result of the forward collision warning function, detecting whether the driver performs a predetermined operation, and judging whether to trigger the automatic emergency braking function according to the detection result; according to the triggering result of the forward collision warning function and the execution of the predetermined operation by the driver, comparing the cross-sectional image of the target object with the size of the second detection area, and judging whether to perform an avoidance operation or directly trigger the automatic emergency braking function in combination with the type of the target object.

[0006] According to a second aspect of an embodiment of the present application, a vehicle automatic emergency braking determination device based on target object recognition is provided, comprising: an acquisition module, configured to acquire image information in front of a vehicle and determine the time distance between the vehicle and the target object; a setting module, configured to set a plurality of detection areas in front according to the time distance, wherein the detection area includes at least a first detection area and a second detection area, which are respectively used to detect the target object under different time distance conditions; a determination module, configured to activate a forward collision warning function when the target object enters the first detection area, and determine whether the cross-sectional image of the target object continues to increase in the first detection area based on the image information, so as to determine whether the relative distance between the vehicle and the target object decreases; a detection module, configured to detect whether the driver performs a predetermined operation according to the trigger result of the forward collision warning function, and determine whether to trigger the automatic emergency braking function according to the detection result; a triggering module, configured to compare the cross-sectional image of the target object with the size of the second detection area according to the trigger result of the forward collision warning function and the execution of the predetermined operation by the driver, and determine whether to perform an avoidance operation or directly trigger the automatic emergency braking function in combination with the type of the target object.

[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the computer program.

[0008] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0009] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0010] By acquiring image information in front of the vehicle and determining the time distance between the vehicle and the target object; according to the time distance, setting multiple detection areas in front, wherein the detection area includes at least a first detection area and a second detection area, respectively used to detect the target object under different time distance conditions; when the target object enters the first detection area, the forward collision warning function is activated, and based on the image information, it is determined whether the cross-sectional image of the target object continues to increase in the first detection area to determine whether the relative distance between the vehicle and the target object is reduced; according to the triggering result of the forward collision warning function, it is detected whether the driver performs a predetermined operation, and it is determined whether to trigger the automatic emergency braking function according to the detection result; according to the triggering result of the forward collision warning function and the execution of the predetermined operation by the driver, the cross-sectional image of the target object is compared with the size of the second detection area, and combined with the type of the target object, it is determined whether to perform an avoidance operation or directly trigger the automatic emergency braking function. The present application can simplify and speed up the determination process of the vehicle's automatic emergency braking, so as to reduce the probability of false triggering and missed triggering, and improve the driving safety of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 It is a flow chart of a method for determining automatic emergency braking of a vehicle based on target object recognition provided in an embodiment of the present application;

[0013] Figure 2 is a schematic diagram of using a multifunctional camera to perform double-layer framing of time distance according to an embodiment of the present application;

[0014] Figure 3 This is a schematic diagram of the impact of billboards above a highway on vehicle driving provided by an embodiment of the present application;

[0015] Figure 4 This is a schematic diagram of the triggering logic of the automatic emergency braking function in a non-vehicle target scene provided by an embodiment of the present application;

[0016] Figure 5 It is a schematic diagram of the vehicle distance in a scene of a stationary or low-speed target ahead provided by an embodiment of the present application;

[0017] Figure 6This is a schematic diagram of a target object in a scene of a stationary or slow-moving target object in front provided by an embodiment of the present application;

[0018] Figure 7 This is a schematic diagram of the triggering logic of the automatic emergency braking function in the scenario of a stationary or slow-moving target object in front provided by an embodiment of the present application;

[0019] Figure 8 It is a structural schematic diagram of a vehicle automatic emergency braking determination device based on target object recognition provided in an embodiment of the present application;

[0020] Fig. 9 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0022] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0023] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0024] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0025] In recent years, AEB mis-triggering, as an important component of ADAS, has played an increasingly important role in actual road driving and is also one of the important technologies to ensure driving safety. However, the vehicle's incorrect perception and decision-making of the target in front will lead to the problem of AEB function misoperation, which in turn causes potential traffic accidents. The probability of AEB mis-triggering and missed triggering is very low, but once it occurs, it is easy to cause a traffic accident. How to reduce the possibility of AEB misoperation has become the focus of major automakers in research and development.

[0026] At present, there are two typical scenarios that still have the probability of misoperation. One is that if there is a vehicle billboard on the overpass of the highway, it is easy for the moving vehicles to mistakenly identify it as a stationary vehicle in front, thus causing the AEB to be falsely triggered. The other is that there is a stationary or slow-moving vehicle in front of the lane, but the millimeter-wave radar sometimes has insufficient recognition rate for stationary or slow-moving objects, resulting in the system being unable to slow down or change lanes, thus causing the AEB to be missed.

[0027] For these two typical scenarios, the multi-function camera needs to have the ability to independently identify and avoid the target ahead in addition to the millimeter-wave radar. For this, the multi-function camera needs to have a simple and direct method to determine the target ahead, so that it can escape danger more easily and quickly in high-speed driving scenarios on highways and expressways.

[0028] A vehicle anti-skid control method and device provided according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0029] Figure 1 FIG. 1 is a flow chart of a method for determining vehicle automatic emergency braking based on target object recognition provided by an embodiment of the present application. Figure 1 As shown, the vehicle automatic emergency braking determination method based on target object recognition may specifically include:

[0030] S101, acquiring image information in front of the vehicle and determining the time distance between the vehicle and the target object;

[0031] S102, according to the time distance, setting a plurality of detection areas ahead, wherein the detection areas include at least a first detection area and a second detection area, which are respectively used to detect the target under different time distance conditions;

[0032] S103, when the target object enters the first detection area, starting the forward collision warning function, and judging whether the cross-sectional image of the target object continues to increase in the first detection area based on the image information, so as to determine whether the relative distance between the vehicle and the target object decreases;

[0033] S104, detecting whether the driver performs a predetermined operation according to the triggering result of the forward collision warning function, and determining whether to trigger the automatic emergency braking function according to the detection result;

[0034] S105, based on the triggering result of the forward collision warning function and the driver's execution of the predetermined operation, the cross-sectional image of the target object is compared with the size of the second detection area, and combined with the type of the target object, it is determined whether to perform an avoidance operation or directly trigger the automatic emergency braking function.

[0035] In some embodiments, determining the time distance between the vehicle and the target object includes:

[0036] The time headway used for calculating the collision time between the vehicle and the target object is determined based on the current driving speed of the vehicle and a pre-configured mapping relationship between the vehicle driving speed and the minimum headway for triggering the forward collision warning function.

[0037] Specifically, this embodiment provides a method for determining the time-to-ground (TTC) between a vehicle and a target object, by combining the current driving speed of the vehicle with a preset mapping relationship to judge the potential collision time and trigger the corresponding forward collision warning (FCW) or automatic emergency braking (AEB) function.

[0038] First, the system obtains the current speed of the vehicle and determines the time to collision time calculation based on the pre-configured mapping relationship between the vehicle speed and the minimum headway for the forward collision warning (FCW) function. The time to collision time (TTC) represents the time required for the vehicle to collide with the target ahead at the current speed.

[0039] For example, in one example, the system uses a multi-function camera or millimeter-wave radar to monitor the target in front, and calculates the relative distance between the vehicle and the target in combination with the vehicle's speed. Based on the distance and the vehicle's speed, the system calculates the TTC value. For example, if the vehicle's current speed is 100km / h, the system determines the TTC threshold to be 4 seconds based on the preset mapping relationship, indicating that when the collision time corresponding to the distance between the vehicle and the target is 4 seconds or less, the system will further evaluate whether it is necessary to trigger the warning or braking function.

[0040] Furthermore, in order to improve the adaptability of the system, the TTC thresholds at different vehicle speeds are pre-configured mapping relationships. For example:

[0041] When the vehicle speed is between 100km / h and 130km / h, the system sets the minimum distance to 4 seconds; when the vehicle speed is between 80km / h and 100km / h, the minimum distance is 3 seconds; when the vehicle speed is less than 60km / h, the minimum distance is further shortened to 2 seconds or less.

[0042] This mapping relationship ensures that the system can accurately judge the collision risk between the vehicle and the target ahead at different speeds.

[0043] For example, in one example, assume that the vehicle is traveling at a speed of 120 km / h, and the system determines the minimum TTC distance to be 4 seconds based on the speed. When the multi-function camera detects a target in front, the system will calculate the TTC based on the current driving speed and the relative distance of the target. If the calculation result shows that the TTC is 4 seconds, the system will proceed to the next step to determine whether a forward collision warning (FCW) signal needs to be issued.

[0044] In this case, if the system further finds that the target is entering the vehicle's detection area A frame and TTC continues to shorten to less than 4 seconds, the system will prompt the driver to take necessary evasive action or slow down. If the driver does not respond and TTC continues to drop below 1.7 seconds, the system will trigger the AEB function to avoid a collision.

[0045] Through the method of the above embodiment, the system can accurately calculate the time distance between the vehicle and the target object, ensuring that the forward collision warning or automatic emergency braking function can be triggered in time under different speed conditions. This time distance determination method based on the mapping relationship between time distance and vehicle speed simplifies the system's response process and significantly improves the safety of the vehicle at high speeds.

[0046] In some embodiments, multiple detection areas ahead are set according to the time distance, including:

[0047] According to the minimum time distance, a first detection area and a second detection area are set in front of the vehicle respectively, wherein the sizes of the first detection area and the second detection area are associated with the driving speed of the vehicle, and the first detection area and the second detection area are used to monitor the target object in front of the vehicle to determine whether to trigger the forward collision warning function or the automatic emergency braking function.

[0048] Specifically, this embodiment provides a method for detecting an object in front of a vehicle based on a multifunctional camera, which is used to reduce the probability of false triggering of the AEB (automatic emergency braking system) in high-speed and expressway scenarios. The method mainly monitors the object in front of the vehicle by setting detection areas of different sizes, and determines whether to trigger the AEB function by combining the cross-sectional image of the object and the driving speed of the vehicle.

[0049] Figure 2 Schematic diagram of using a multifunctional camera to perform double-layer framing of time intervals provided in an embodiment of the present application. Figure 2As shown, for highway and expressway scenes, this embodiment uses a multifunctional camera to double-frame the time-to-distance (TTC) in front, that is, two detection areas are set in front of the vehicle, namely the first detection area (frame A) and the second detection area (frame B). The size of these detection areas is related to the vehicle's driving speed to ensure that the target in front can be effectively detected at different speeds.

[0050] For example, in one example, when the vehicle speed is 60 km / h, the TTC is set to 4 seconds, and the camera will monitor the range of about 67 meters in front of the vehicle. The size of frame A is set to 2.5 meters high and 3.5 meters wide, and the size of frame B is set to 1.8 meters high and 2 meters wide. The multifunctional camera uses the pixel framing method to monitor whether there is a target entering frame A or frame B, and decides whether to trigger the AEB function based on the position of the target in the two frames and the changes in its cross-sectional image.

[0051] As shown in Table 1, Table 1 is a mapping relationship table between the vehicle speed configured in some embodiments of the present application and the minimum time distance for triggering the forward collision warning function, which can also be called the camera frame TTC time distance table under different vehicle speeds.

[0052] Table 1 TTC time interval of camera frame at different vehicle speeds

[0053]

[0054] Figure 3 Schematic diagram of the impact of billboards on vehicles on highways provided in the embodiment of the present application. Figure 3 As shown, in a highway scenario, a vehicle may encounter a billboard above the highway, and such non-vehicle target may be mistakenly identified as a stationary vehicle ahead, thereby causing the AEB system to be falsely triggered. Therefore, this embodiment adopts a double-layer detection area to avoid such a situation.

[0055] For example, in one example, when the vehicle is traveling at a speed of 100km / h to 130km / h, the TTC is set to 4 seconds, and the detection distance of frame A and frame B extends from the front of the vehicle to at least 144.5 meters. Since billboards above the highway are usually set at a height of at least 4.5 meters, and the height of frame A is only 2.5 meters, when the billboard does not enter the range of frame A, the multi-function camera filters it out and does not trigger the AEB function.

[0056] In some embodiments, the system makes an AEB triggering decision by monitoring the changes in the cross-sectional image of the target object in the detection area. When the cross-sectional image of the target object enters frame A from outside frame A (for example, from the top or left and right sides) and further enters frame B, the system will determine whether the distance between the vehicle and the target object is decreasing, and determine whether to trigger the AEB function in combination with the TTC value.

[0057] In actual driving scenarios on highways or expressways, vehicles may encounter billboards set on overpasses or other structures in front of them. Since these billboards are usually suspended above the lanes and are large in size, traditional AEB systems may mistakenly identify them as obstacles ahead, thereby erroneously triggering emergency braking, causing unnecessary danger.

[0058] In some embodiments, by calculating the time-to-track distance (TTC) in front of the vehicle and setting the detection area in combination with a multi-function camera, these non-vehicle targets can be effectively identified and filtered to prevent the system from being triggered by mistake.

[0059] For example, when the vehicle is traveling at a higher speed, such as between 100km / h and 130km / h, the system sets the TTC to 4 seconds. At this time interval, the system sets two detection areas in front of the vehicle, namely frame A and frame B, according to the vehicle's driving speed. The size of frame A is 2.5 meters high and 3.5 meters wide, and the size of frame B is 1.8 meters high and 2 meters wide. The front edge of frame A and frame B is at least 144.5 meters away from the vehicle camera.

[0060] When the vehicle drives under the billboard, the system uses the multi-function camera to monitor the front detection area in real time. Assuming that the hanging height of the billboard is 4.5 meters or higher, the lower edge of the billboard exceeds the upper edge of the A frame (2.5 meters), so the billboard will not enter the detection range of the A frame.

[0061] According to the determination method of this embodiment, when there is no target object in the detection area in front of the vehicle that enters the A frame, that is, the billboard does not enter the A frame range, the system will identify the target object as a non-vehicle target, and according to the determination rules of the A frame and the B frame, the system will not trigger the AEB function. In this way, the system effectively filters out false triggering caused by overhead targets such as billboards, ensuring that the vehicle will not make erroneous emergency braking due to these interferences during driving.

[0062] It should be noted that the AEB trigger determination method provided in this embodiment is not only applicable to billboard scenarios, but can also be applied to the identification and filtering of other similar non-vehicle targets, such as signboards hanging at bridges and tunnel entrances, etc. In this way, the system can accurately distinguish between real vehicle targets and non-vehicle targets, avoid false triggering of AEB, and thus improve the safety and comfort of vehicle driving.

[0063] Through the method of the above embodiment, the method not only improves the detection accuracy of the system for the target in front, but also effectively reduces the AEB false triggering caused by non-vehicle targets (such as billboards), thereby enhancing the driving safety of vehicles in high-speed and expressway scenarios. This determination method based on multi-function cameras and double-layer detection areas, as a supplement to the fusion perception solution of millimeter-wave radar and laser radar, can independently make correct judgments in low-probability events, thereby improving the reliability of the AEB system.

[0064] In some embodiments, when the target object enters the first detection area, the forward collision warning function is activated, including:

[0065] Using a multifunctional camera to monitor a first detection area in front of the vehicle in real time;

[0066] When it is detected that the target object enters the first detection area and the time distance of the target object is less than or equal to the preset time distance threshold, it is determined whether there is an identified target object in the second detection area;

[0067] If a target object is detected in the first detection area and no target object is detected in the second detection area, the forward collision warning function is activated and a warning signal is sent to notify the driver of a potential collision risk ahead.

[0068] Specifically, this embodiment also provides a determination method for a forward collision warning (FCW) and automatic emergency braking (AEB) system based on target object recognition, which is used to make timely warnings and responses to potential collision risks ahead during vehicle driving.

[0069] Figure 4 1 is a schematic diagram of the triggering logic of the automatic emergency braking function in the non-vehicle target scene provided by the embodiment of the present application. Figure 4 As shown, when the vehicle is in motion, the system uses a multifunctional camera to monitor the first detection area (frame A) in front of the vehicle in real time. The detection area is determined according to the vehicle's driving speed and a preset collision time (TTC) threshold. For example, in this embodiment, when the vehicle's TTC is less than or equal to 4 seconds, the system will pay close attention to the situation where the target in front enters frame A.

[0070] Furthermore, when the multi-function camera detects that a target object enters the first detection area (frame A) and the TTC of the target object is less than or equal to 4 seconds, the system will further determine whether there is an identified target object in the second detection area (frame B). For example, if a target object is detected in frame A but not in frame B (for example, a vehicle in front of the side lane merges or there is a suspected obstacle above the lane), the system will trigger the forward collision warning (FCW) function.

[0071] Furthermore, when the FCW function is triggered, the system will send a warning signal to inform the driver that there is a potential collision risk ahead. At this time, the driver can make corresponding driving operations according to the warning signal, such as slowing down or changing lanes, to avoid possible collisions.

[0072] Furthermore, after the FCW function is triggered, the system will continue to monitor the position change of the target in frame A and frame B, especially whether the cross-sectional image of the target continues to increase in frame A. This process is used to determine whether the distance between the vehicle and the target is further decreasing.

[0073] Next, the system detects whether the driver decelerates or brakes:

[0074] If the driver slows down or brakes after the warning and the target object does not enter the B frame, the system determines that the current collision risk is reduced and the vehicle will continue to maintain the current speed.

[0075] If the driver does not take any action and the target object enters the B frame when the TTC is less than or equal to 1.7 seconds, the system will issue a speed reduction command through the electronic control unit (ECS) and trigger the automatic emergency braking (AEB) function to prevent a possible collision.

[0076] Through the above method of this embodiment, the system of this embodiment monitors the detection area in front of the vehicle in real time through a multifunctional camera, and dynamically determines whether to trigger the forward collision warning (FCW) or automatic emergency braking (AEB) function according to the time distance, cross-sectional image and driver's operation of the target object. This determination method can effectively reduce false triggering situations, and at the same time ensure that the vehicle can make a correct response in time in high-risk situations, thereby improving driving safety.

[0077] In some embodiments, when the target object is a non-vehicle target, detecting whether the driver performs a predetermined operation according to the triggering result of the forward collision warning function, and determining whether to trigger the automatic emergency braking function according to the detection result include:

[0078] When the forward collision warning function is triggered and the target object enters the first detection area, the multi-function camera is used to continuously monitor the movement state of the target object and the relative distance between the vehicle and the target object;

[0079] Determine whether the target object has entered the second detection area, and confirm whether the target object is a non-vehicle target based on the size and relative position change of the cross-sectional image of the target object;

[0080] When the target object is confirmed to be a non-vehicle target, detecting whether the driver performs a deceleration or braking operation;

[0081] If the driver does not perform deceleration or braking operations, and the target object does not enter the second detection area, the vehicle maintains its current driving state and does not trigger the automatic emergency braking function;

[0082] When the target object enters the second detection area when the time distance is less than or equal to the preset time distance, and the driver does not perform deceleration or braking operations, a deceleration command is issued and the automatic emergency braking function is triggered.

[0083] Specifically, during the driving process of the vehicle, the system monitors the road ahead in real time through a multi-function camera. When the target enters the first detection area (frame A) and triggers the forward collision warning function (FCW), the system begins to closely track the movement state of the target, focusing on the relative distance between the vehicle and the target. If the time to time (TTC) of the target is less than or equal to the preset time to time threshold, such as 4 seconds, the system will further analyze the characteristics of the target.

[0084] As described in this embodiment, when the target enters the first detection area, the system uses the multifunctional camera to continuously monitor the cross-sectional image of the target, and determines whether the target is a non-vehicle target by comparing the size with the second detection area (frame B). Specifically, the system monitors whether the cross-sectional image of the target continues to increase in frame A. This process is used to determine whether the distance between the vehicle and the target is continuously decreasing.

[0085] Furthermore, if the cross-sectional image of the target object in frame A increases and does not enter the range of frame B, the system preliminarily determines that the target object may be a non-vehicle target, such as a billboard hanging at a high place, a bridge structure or a road sign.

[0086] Furthermore, when the target object is confirmed to be a non-vehicle target, the system will detect whether the driver performs a predetermined deceleration or braking operation:

[0087] If the driver slows down or brakes after triggering FCW, and the target object does not enter the B frame, the system determines that the current collision risk is low, the vehicle maintains the current driving state, and the automatic emergency braking function is not triggered.

[0088] If the driver does not slow down or brake, and the target enters the second detection area (frame B) when TTC is less than or equal to 1.7 seconds, the system will issue a speed reduction command and automatically trigger the AEB function to avoid potential collision risks.

[0089] For example, in one example, when the vehicle is driving on the highway, the system detects a billboard hanging at a height of 4.5 meters in front of it, and its cross-sectional image enters the A frame. At this time, the FCW function is triggered, and the system prompts the driver that there may be a risk of collision ahead. However, after further analysis by the system, the billboard has not entered the B frame range, and after confirming that the billboard is a non-vehicle target, the system will not automatically trigger the AEB function. If the driver does not take deceleration action, and the cross-sectional image of the billboard does not further increase when approaching the B frame, the system will maintain the current driving state.

[0090] Through the above-mentioned method of this embodiment, this embodiment can, when the target object is not a vehicle, combine the driver's actual operating behavior to reasonably judge whether it is necessary to trigger the automatic emergency braking function, avoid unnecessary emergency braking due to misjudgment of non-vehicle targets, thereby improving the vehicle's driving safety and driving experience.

[0091] In some embodiments, when the target object is a stationary target or a low-speed moving target ahead, detecting whether the driver performs a predetermined operation based on the triggering result of the forward collision warning function, and determining whether to trigger the automatic emergency braking function based on the detection result include:

[0092] When the forward collision warning function is not triggered and the target object enters the first detection area, the multi-function camera is used to monitor the state of the target object in real time and calculate the time distance between the vehicle and the target object;

[0093] When it is detected that the driver performs braking or steering operations, the automatic emergency braking function is not triggered; when it is detected that the driver does not perform braking or steering operations, and the size of the cross-sectional image of the target object in the second detection area continues to increase, and the time distance is lower than the preset time distance threshold, the automatic emergency braking function is triggered.

[0094] Specifically, this embodiment also provides a method for determining an automatic emergency braking (AEB) system for a stationary target or a low-speed target in front. The method uses a multi-function camera combined with the triggering result of the forward collision warning (FCW) function and the driver's operating behavior to reasonably determine whether to trigger the AEB function, and is particularly suitable for processing targets that the sensor fails to identify under the condition of "static clutter filtering".

[0095] Figure 5 Schematic diagram of the distance between vehicles in the case of a stationary or slow-moving target ahead provided by an embodiment of the present application. Figure 5As shown in the figure, when the vehicle is driving, the multi-function camera monitors the target in front of the lane in real time. In the initial stage, the target may be stationary or moving at a low speed, and the distance between the vehicle and the target is far. Since the millimeter-wave radar may not be able to effectively identify these stationary or slow-moving targets, the system relies on the multi-function camera to determine whether there is a potential collision risk.

[0096] When the camera detects an object in front of it, it determines the potential danger by calculating the collision time (TTC) between the vehicle and the object. When the TTC reaches 4 seconds, the system begins to pay close attention to the changes in the cross-sectional image of the object in the detection area.

[0097] Figure 6 Schematic diagram of a target object in a scene of a stationary or slow-moving target object in front provided by an embodiment of the present application. Figure 6 As shown, when TTC is equal to 4 seconds, if the system still does not trigger the forward collision warning (FCW) function, the system will continue to monitor the status of the target object and detect whether the driver has performed a predetermined braking or steering operation.

[0098] Furthermore, if the system detects that the driver has performed braking or steering operations, the system determines that the driver has taken appropriate evasive measures to the target ahead, and therefore will not trigger the AEB function, and the vehicle will continue to drive according to the driver's operating instructions.

[0099] Furthermore, AEB judgment without operation: If the driver does not perform any braking or steering operation, and the size of the cross-sectional image of the target in frame B continues to increase, it indicates that the distance between the vehicle and the target is decreasing rapidly. In this case, the system further detects the TTC value. When the TTC is lower than the preset threshold (such as 1.7 seconds), the system will automatically trigger the AEB function to avoid a possible collision.

[0100] The above-mentioned embodiment is particularly suitable for dealing with situations that occur in the "static clutter filtering" scenario. Since the millimeter-wave radar may filter out the signals of stationary or low-speed target objects, the system uses the camera alone to identify and determine the target object. For example, when the vehicle encounters a stationary commercial vehicle in front of it during driving, although the millimeter-wave radar fails to identify it, the multi-function camera can monitor the cross-sectional image of the target object. When the TTC drops to less than 1.7 seconds, if the driver still does not take any action, the system will give priority to triggering the AEB function or performing emergency avoidance operations when possible.

[0101] Through the above-mentioned method of this embodiment, this embodiment effectively makes up for the shortcomings of millimeter-wave radar in detecting stationary or low-speed targets, ensures that the vehicle can respond in time in situations where there may be high risks, and enhances driving safety.

[0102] In some embodiments, according to the triggering result of the forward collision warning function and the execution of the predetermined operation by the driver, the cross-sectional image of the target object is compared with the size of the second detection area, and combined with the type of the target object, it is determined whether to perform an avoidance operation or directly trigger the automatic emergency braking function, including:

[0103] When the forward collision warning function is triggered or detects that the driver is not braking or steering, the multi-function camera monitors the cross-sectional image of the target object;

[0104] Comparing the cross-sectional image of the target object with the size of the second detection area in real time to determine whether the actual size of the target object exceeds the range of the second detection area;

[0105] When the cross-sectional image of the target object is larger than the second detection area and the time distance is within the preset time distance range, the automatic emergency braking function is triggered;

[0106] When the cross-sectional image of the target object is smaller than the second detection area, or the target object does not continue to increase in size within the preset time range, the automatic emergency braking function is not triggered.

[0107] Specifically, this embodiment also provides a trigger determination method for an automatic emergency braking (AEB) system based on a multifunctional camera, which is particularly suitable for scenarios where there is a stationary or slow-moving target in front. The method combines the trigger result of the forward collision warning (FCW) function and the driver's operation, and determines whether to perform an avoidance operation or directly trigger the AEB function by monitoring the cross-sectional image of the target object in real time.

[0108] Figure 7 1 is a schematic diagram of the triggering logic of the automatic emergency braking function in the scenario of a stationary or slow-moving target ahead provided by an embodiment of the present application. Figure 7 As shown in the figure, during the vehicle's driving process, the system first calculates the collision time (TTC) between the vehicle and the target in front, and monitors the position and size changes of the target in the first detection area (frame A) and the second detection area (frame B) in real time. When the TTC reaches 4 seconds, if the system triggers the forward collision warning (FCW) function, or detects that the driver does not perform braking or steering operations, the system will further analyze the cross-sectional image of the target.

[0109] Once the FCW function is triggered or the driver does not take corresponding evasive action, the system will monitor the cross-sectional image of the target through the multi-function camera and compare it with the size of the second detection area (B frame) in real time. This step is used to determine whether the actual size of the target exceeds the range of the B frame to determine the type of target ahead and the potential risk.

[0110] Large object size: If the cross-sectional image of the object is larger than the B frame range and the TTC is within the preset range (1.7 seconds ≤ TTC ≤ 4 seconds), the system will determine that the object ahead may be a large vehicle (such as a commercial vehicle). At this time, the system will further observe the situation in the adjacent lane. If there are feasible lane change conditions in the adjacent lane, the system will give priority to lateral lane change to avoid potential collision risks.

[0111] The target object is small in size: If the cross-sectional image of the target object does not exceed the range of the B frame, or the target object does not continue to increase within the preset TTC range, the system determines that the target in front is a small vehicle or other low-risk object. At this time, the system will not trigger the automatic emergency braking function, and the vehicle will continue to maintain the current driving state.

[0112] When the system determines that the target ahead is a commercial vehicle and the cross-sectional image continues to grow, and the TTC further drops below 1.7 seconds, the system will directly trigger the AEB function to avoid a possible collision. In this case, the vehicle will automatically perform emergency braking to reduce the risk of collision.

[0113] This embodiment provides a detailed logic flow for determining whether the AEB function should be triggered or an evasive maneuver should be performed in the case of a stationary or slow-moving target ahead. By combining the comparative analysis of the cross-sectional image of the target and the detection area, as well as the rapid identification of the target type, the system can make the most appropriate response in different driving scenarios to ensure the safety of vehicle driving and the comfort of the driver.

[0114] This method is particularly suitable for the design of driving safety systems in complex road environments. It can effectively improve the system's recognition accuracy for different types of targets and provide a variety of response strategies in emergency situations, further improving the reliability of the autonomous driving system and user experience.

[0115] In some embodiments, judging whether to perform an avoidance operation or directly trigger an automatic emergency braking function in combination with the type characteristics of the target object includes:

[0116] The target object is characterized to determine its type. When the distance is within the preset distance range and the type of the target object is the target vehicle type, when it is identified that the adjacent lane meets the lane change conditions, the vehicle is controlled to change lanes laterally to perform an avoidance operation; when the distance is less than the preset distance range, the automatic emergency braking function is triggered.

[0117] Specifically, this embodiment also proposes a method for determining whether to perform an evasive maneuver or directly trigger an automatic emergency braking (AEB) function by combining the characteristics of the target type. The method uses a multi-function camera to identify the characteristics of the target in front, and decides the best response strategy based on the type, relative position and time distance (TTC) of the target to ensure driving safety.

[0118] When the vehicle is driving, the system first uses the multi-function camera to identify the features of the target in the front detection area. By analyzing the size and shape characteristics of the cross-sectional image of the target, the system can quickly determine the type of the target, such as whether it is a passenger car, commercial vehicle or other type of obstacle.

[0119] As described in the above technical solution, the system further determines the actual type of the target by comparing the cross-sectional image of the target with the size of the second detection area (B frame). If the cross-sectional image of the target is larger than the B frame range, the system tends to think that the target is a commercial vehicle, while if the cross-sectional image is smaller, the system may judge it as a passenger car or other low-risk target.

[0120] Once the type of target is determined, the system will combine the time to reach (TTC) to determine the best response strategy:

[0121] When the TTC is between 1.7 seconds and 4 seconds, and the system determines that the target ahead is a commercial vehicle, the system will give priority to performing a lateral lane change to avoid the potential dangers brought by the commercial vehicle. Before performing the lane change, the system will detect the traffic conditions of the adjacent lanes. If the adjacent lanes meet the lane change conditions and there are no vehicles blocking them, the system will control the vehicle to perform a lateral lane change to ensure safe passage of the commercial vehicle.

[0122] When TTC is further shortened to less than 1.7 seconds, the system will directly trigger the automatic emergency braking (AEB) function, especially when the lane change conditions are not met. This operation is designed to minimize the risk of collision between the vehicle and commercial vehicles or other large objects through emergency braking.

[0123] For example, in one example, a commercial truck appears in front of the vehicle on the highway. The system detects through the multi-function camera that the cross-sectional image of the truck is larger than the B frame range and confirms that the target object is a commercial vehicle. At this time, the TTC calculated by the system is between 1.7 seconds and 4 seconds. The system first checks whether the adjacent lane has the conditions for safe lane change. If the lane change conditions are met, the system will control the vehicle to perform a lane change operation to bypass the truck and avoid a possible collision.

[0124] If the distance between the vehicle and the truck decreases rapidly when the TTC is less than 1.7 seconds, and the adjacent lane does not have the conditions for safe lane change, the system will immediately trigger the AEB function and cause the vehicle to brake urgently to prevent a collision.

[0125] Through the above logic, this embodiment realizes the rapid identification of the type of the target ahead, and decides whether to perform a lane change or trigger emergency braking based on the time interval and road conditions. This method can effectively deal with complex situations in various road scenarios, ensuring that the vehicle can make the most reasonable response strategy in the face of potential dangers, thereby improving driving safety.

[0126] According to the technical solution provided in the embodiments of the present application, the technical solution of the present application has at least the following advantages:

[0127] This application provides a more accurate and simplified method for avoiding the misapplication of the automatic emergency braking system (AEB) in high-speed scenarios. By introducing a collaborative judgment mechanism of a multi-function camera and a millimeter-wave radar in key driving scenarios (such as billboards on overpasses on highways, stationary or slow-moving vehicles ahead, etc.), the system can effectively reduce the mis-triggering and missed triggering of AEB caused by misidentification.

[0128] First of all, the technical solution of the present application is optimized for the above-mentioned typical scenarios to ensure that when the millimeter-wave radar fails to sense the target in front, the multi-function camera can independently complete the accurate identification and classification of the target in front, and make reasonable response decisions based on the preset time-to-course (TTC) and target type, such as performing avoidance operations or triggering the AEB function.

[0129] In addition, the technical solution of this application not only improves the judgment accuracy of the AEB system in complex scenarios, but also simplifies the decision-making process of the system, effectively reducing the possibility of misjudgment. Although the probability of AEB misoperation is low, through continuous optimization of the system, this application can significantly improve driving safety and reduce the potential risks caused by system mis-triggering, thereby providing drivers with a safer and more reliable driving experience.

[0130] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0131] Figure 8 Schematic diagram of the structure of the vehicle automatic emergency braking determination device based on target object recognition provided by the embodiment of the present application. Figure 8 As shown, the vehicle automatic emergency braking determination device based on target object recognition includes:

[0132] The acquisition module 801 is configured to acquire image information in front of the vehicle and determine the time distance between the vehicle and the target object;

[0133] The setting module 802 is configured to set a plurality of detection areas ahead according to the time distance, wherein the detection areas at least include a first detection area and a second detection area, which are respectively used to detect the target under different time distance conditions;

[0134] The determination module 803 is configured to start the forward collision warning function when the target object enters the first detection area, and determine whether the cross-sectional image of the target object continues to increase in the first detection area based on the image information to determine whether the relative distance between the vehicle and the target object decreases;

[0135] The detection module 804 is configured to detect whether the driver performs a predetermined operation according to the triggering result of the forward collision warning function, and determine whether to trigger the automatic emergency braking function according to the detection result;

[0136] The trigger module 805 is configured to determine whether to perform an avoidance operation or directly trigger the automatic emergency braking function based on the trigger result of the forward collision warning function and the driver's execution of the predetermined operation, by comparing the cross-sectional image of the target object with the size of the second detection area, and in combination with the type of the target object.

[0137] In some embodiments, Figure 8 The acquisition module 801 determines the time headway for calculating the collision time between the vehicle and the target object according to the current driving speed of the vehicle and the pre-configured mapping relationship between the vehicle driving speed and the minimum headway for triggering the forward collision warning function.

[0138] In some embodiments, Figure 8 The setting module 802 sets the first detection area and the second detection area in front of the vehicle according to the minimum time distance, wherein the sizes of the first detection area and the second detection area are associated with the driving speed of the vehicle, and the first detection area and the second detection area are used to monitor the target object in front of the vehicle to determine whether to trigger the forward collision warning function or the automatic emergency braking function.

[0139] In some embodiments, Figure 8 The determination module 803 uses a multi-function camera to monitor the first detection area in front of the vehicle in real time; when a target object is detected entering the first detection area and the time distance of the target object is less than or equal to a preset time distance threshold, it is determined whether there is an identified target object in the second detection area; if a target object is detected in the first detection area and no target object is detected in the second detection area, the forward collision warning function is activated and a warning signal is sent to notify the driver of a potential collision risk ahead.

[0140] In some embodiments, when the target object is a non-vehicle target, Figure 8 When the forward collision warning function is triggered and the target object enters the first detection area, the detection module 804 uses a multi-function camera to continuously monitor the movement state of the target object and the relative distance between the vehicle and the target object; determines whether the target object enters the second detection area, and confirms whether the target object is a non-vehicle target based on the size of the cross-sectional image of the target object and the relative position change; when it is confirmed that the target object is a non-vehicle target, detects whether the driver performs a deceleration or braking operation; if the driver does not perform a deceleration or braking operation, and the target object does not enter the second detection area, maintains the current driving state of the vehicle and does not trigger the automatic emergency braking function; when the target object enters the second detection area when the time distance is less than or equal to the preset time distance, and the driver does not perform a deceleration or braking operation, issues a speed reduction command and triggers the automatic emergency braking function.

[0141] In some embodiments, when the target object is a stationary target or a slow-moving target in front, Figure 8 When the forward collision warning function is not triggered and the target object enters the first detection area, the detection module 804 uses a multi-function camera to monitor the state of the target object in real time and calculates the time distance between the vehicle and the target object; when it is detected that the driver performs a braking or steering operation, the automatic emergency braking function is not triggered; when it is detected that the driver does not perform a braking or steering operation, and the size of the cross-sectional image of the target object in the second detection area continues to increase, and the time distance is lower than a preset time distance threshold, the automatic emergency braking function is triggered.

[0142] In some embodiments, when the front collision warning function is triggered, or when it is detected that the driver has not performed braking or steering operations, the trigger module 805 uses a multi-function camera to monitor the cross-sectional image of the target object; compares the cross-sectional image of the target object with the size of the second detection area in real time to determine whether the actual size of the target object exceeds the range of the second detection area; when the cross-sectional image of the target object is larger than the second detection area and the time distance is within a preset time distance range, the automatic emergency braking function is triggered; when the cross-sectional image of the target object is smaller than the second detection area, or the target object does not continue to increase within the preset time distance range, the automatic emergency braking function is not triggered.

[0143] In some embodiments, the trigger module 805 performs feature recognition on the target object to determine the type of the target object. When the distance is within a preset time distance range and the type of the target object is the target vehicle type, when it is identified that the adjacent lane meets the lane change conditions, the vehicle is controlled to change lanes laterally to perform an avoidance operation; when the distance is less than the preset time distance range, the automatic emergency braking function is triggered.

[0144] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0145] Fig. 9 Schematic diagram of the structure of the electronic device 9 provided in the embodiment of the present application. Fig. 9 As shown, the electronic device 9 of this embodiment includes: a processor 901, a memory 902, and a computer program 903 stored in the memory 902 and executable on the processor 901. When the processor 901 executes the computer program 903, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 901 executes the computer program 903, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0146] Exemplarily, the computer program 903 may be divided into one or more modules / units, which are stored in the memory 902 and executed by the processor 901 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 903 in the electronic device 9.

[0147] The electronic device 9 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 9 may include, but is not limited to, a processor 901 and a memory 902. Those skilled in the art will appreciate that Fig. 9 It is only an example of the electronic device 9 and does not constitute a limitation of the electronic device 9. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0148] The processor 901 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0149] The memory 902 may be an internal storage unit of the electronic device 9, for example, a hard disk or memory of the electronic device 9. The memory 902 may also be an external storage device of the electronic device 9, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 9. Further, the memory 902 may also include both an internal storage unit of the electronic device 9 and an external storage device. The memory 902 is used to store computer programs and other programs and data required by the electronic device. The memory 902 may also be used to temporarily store data that has been output or is to be output.

[0150] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0151] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0152] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0153] In the embodiments provided in the present application, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. Multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0157] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A vehicle automatic emergency braking determination method based on target recognition, It is characterized in that include: Acquire image information in front of the vehicle and determine the time distance between the vehicle and the target object; According to the time interval, a plurality of detection areas ahead are set, wherein the detection areas at least include a first detection area and a second detection area, which are respectively used to detect the target under different time interval conditions; When the target object enters the first detection area, a forward collision warning function is activated, and based on the image information, it is determined whether the cross-sectional image of the target object continues to increase in the first detection area to determine whether the relative distance between the vehicle and the target object decreases; Based on the triggering result of the forward collision warning function, detecting whether the driver performs a predetermined operation, and determining whether to trigger the automatic emergency braking function based on the detection result; Based on the triggering result of the forward collision warning function and the driver's execution of the predetermined operation, the cross-sectional image of the target object is compared with the size of the second detection area, and combined with the type of the target object, it is determined whether to perform an avoidance operation or directly trigger the automatic emergency braking function.

2. The method according to claim 1, It is characterized in that Determining the time distance between the vehicle and the target object includes: The time headway for calculating the collision time between the vehicle and the target object is determined according to the current driving speed of the vehicle and a preconfigured mapping relationship between the vehicle driving speed and the minimum headway for triggering the forward collision warning function.

3. The method according to claim 2, It is characterized in that The step of setting a plurality of detection areas ahead according to the time interval includes: According to the minimum time distance, a first detection area and a second detection area are set in front of the vehicle respectively, wherein the sizes of the first detection area and the second detection area are associated with the driving speed of the vehicle, and the first detection area and the second detection area are used to monitor the target object in front of the vehicle to determine whether to trigger the forward collision warning function or the automatic emergency braking function.

4. The method according to claim 1, It is characterized in that When the target object enters the first detection area, starting the forward collision warning function includes: Using a multifunctional camera to monitor a first detection area in front of the vehicle in real time; When a target object is detected entering the first detection area and the time distance of the target object is less than or equal to a preset time distance threshold, determining whether there is an identified target object in the second detection area; If a target object is detected in the first detection area and no target object is detected in the second detection area, the forward collision warning function is activated and a warning signal is sent to notify the driver of a potential collision risk ahead.

5. The method according to claim 1, It is characterized in that When the target object is a non-vehicle target, detecting whether the driver performs a predetermined operation according to the triggering result of the forward collision warning function, and determining whether to trigger the automatic emergency braking function according to the detection result, includes: When the forward collision warning function is triggered and the target object enters the first detection area, the multi-function camera is used to continuously monitor the movement state of the target object and the relative distance between the vehicle and the target object; Determine whether the target object has entered the second detection area, and confirm whether the target object is a non-vehicle target according to the size and relative position change of the cross-sectional image of the target object; In the case where the target object is confirmed to be a non-vehicle target, detecting whether the driver performs a deceleration or braking operation; If the driver does not perform a deceleration or braking operation and the target object does not enter the second detection area, the current driving state of the vehicle is maintained and the automatic emergency braking function is not triggered; When the target object enters the second detection area when the time distance is less than or equal to the preset time distance, and the driver does not perform deceleration or braking operations, a deceleration command is issued and the automatic emergency braking function is triggered.

6. The method according to claim 1, It is characterized in that When the target object is a stationary target or a low-speed moving target ahead, the method of detecting whether the driver performs a predetermined operation according to the triggering result of the forward collision warning function, and determining whether to trigger the automatic emergency braking function according to the detection result, includes: When the forward collision warning function is not triggered and the target object enters the first detection area, the state of the target object is monitored in real time by using a multifunctional camera, and the time distance between the vehicle and the target object is calculated; When it is detected that the driver performs braking or steering operations, the automatic emergency braking function is not triggered; when it is detected that the driver does not perform braking or steering operations, and the size of the cross-sectional image of the target object in the second detection area continues to increase, and the time interval is lower than a preset time interval threshold, the automatic emergency braking function is triggered.

7. The method according to claim 1, It is characterized in that According to the triggering result of the forward collision warning function and the execution of the predetermined operation by the driver, the cross-sectional image of the target object is compared with the size of the second detection area, and combined with the type of the target object, whether to perform an avoidance operation or directly trigger the automatic emergency braking function includes: When the forward collision warning function is triggered or it is detected that the driver does not perform braking or steering operations, using the multi-function camera to monitor the cross-sectional image of the target object; Comparing the cross-sectional image of the target object with the size of the second detection area in real time to determine whether the actual size of the target object exceeds the range of the second detection area; When the cross-sectional image of the target object is larger than the second detection area and the time interval is within a preset time interval range, an automatic emergency braking function is triggered; When the cross-sectional image of the target object is smaller than the second detection area, or the target object does not continue to increase in size within the preset time range, the automatic emergency braking function is not triggered.

8. The method according to claim 7, It is characterized in that The determining whether to perform an avoidance operation or directly trigger an automatic emergency braking function in combination with the type characteristics of the target object includes: The target object is feature-recognized to determine its type. When the time distance is within a preset time distance range and the type of the target object is the target vehicle type, and when it is identified that the adjacent lane meets the lane change conditions, the vehicle is controlled to change lanes laterally to perform an avoidance operation. When the time distance is less than the preset time distance range, the automatic emergency braking function is triggered.

9. A vehicle automatic emergency braking determination device based on target recognition, It is characterized in that include: An acquisition module is configured to acquire image information in front of the vehicle and determine a time distance between the vehicle and a target object; A setting module is configured to set a plurality of detection areas ahead according to the time interval, wherein the detection areas at least include a first detection area and a second detection area, which are respectively used to detect the target under different time interval conditions; a determination module configured to activate a forward collision warning function when the target object enters the first detection area, and determine whether a cross-sectional image of the target object continues to increase in the first detection area based on the image information to determine whether a relative distance between the vehicle and the target object decreases; a detection module configured to detect whether the driver performs a predetermined operation according to a trigger result of the forward collision warning function, and determine whether to trigger the automatic emergency braking function according to the detection result; The trigger module is configured to determine whether to perform an avoidance operation or directly trigger the automatic emergency braking function based on the trigger result of the forward collision warning function and the driver's execution of a predetermined operation, according to the cross-sectional image of the target object and the size of the second detection area, and in combination with the type of the target object.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images