Vehicle ADB system and its control methods, storage media and vehicle

Abstract

This invention discloses a vehicle ADB system, its control method, storage medium, and a vehicle. The ADB system includes a camera, radar, and ADB headlights. The method includes: adjusting the confidence levels of the camera and radar according to vehicle operating conditions; the camera confidence level includes a spot confidence level and a first target confidence level, and the radar confidence level includes a second target confidence level; fusing image data of the front of the vehicle acquired by the camera and radar data of the front of the vehicle acquired by the radar according to the adjusted spot confidence level, first target confidence level, and second target confidence level to obtain a target object; and controlling the ADB headlights according to the target object. In this method, radar identification of obstacles is more accurate. By fusing radar data with camera image data, the system's lighting control is more accurate, effectively preventing glare from vehicle lights to road vehicles and pedestrians while ensuring clear visibility for the driver at night, thus reducing safety hazards.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a vehicle ADB system, its control method, storage medium, and vehicle. Background Technology

[0002] ADB (Adaptive Driving Beam) system typically consists of a forward-facing active safety camera (hereinafter referred to as the camera), a headlight controller, a light source module driver, a light source module, and transmission lines. The camera serves as the system's input sensor, responsible for collecting information on environmental conditions, road conditions, and vehicle / pedestrian status. When the vehicle's ambient lighting is insufficient and its speed exceeds a certain threshold, the ADB system is activated, automatically turning on the high beams to enhance ambient lighting and provide the driver with good visibility. Conversely, when the ADB system detects strong ambient light or low vehicle speed, it automatically turns off the high beams. When other road users are present in the driver's field of vision (e.g., when following or meeting oncoming traffic), the ADB system automatically detects their positions and dims or turns off the lights at those locations to avoid glare and ensure driving safety.

[0003] However, cameras are a type of visual sensor, and their performance is greatly affected by lighting conditions. Vehicle cameras generally have low resolution, and their accuracy drops significantly in low-light conditions such as rainy weather, nighttime, and tunnels. Furthermore, they are limited by their FOV (Field of View), resulting in a narrow field of view and a limited range of information that can be recognized. In addition, cameras struggle to accurately acquire three-dimensional information; when the shadows of nearby pedestrians are elongated and obstruct the view, the camera cannot reliably detect the target and the error is substantial. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, the purpose of this invention is to propose a vehicle ADB system and its control method, storage medium, and vehicle. This method, through the fusion of radar data and camera image data, enables more accurate lighting control of the ADB system. It can effectively prevent glare from vehicle lights to other vehicles and pedestrians on the road while ensuring clear visibility for the driver at night, thus reducing safety hazards.

[0005] To achieve the above objectives, a first aspect of the present invention provides a control method for a vehicle ADB system, the ADB system including a camera, a radar, and ADB headlights. The method includes: determining the operating condition of the vehicle and adjusting the confidence levels of the camera and the radar according to the operating condition, wherein the confidence level of the camera includes a spot confidence level and a first target confidence level, and the confidence level of the radar includes a second target confidence level; fusing image data of the front of the vehicle acquired by the camera and radar data of the front of the vehicle acquired by the radar according to the adjusted spot confidence level, the first target confidence level, and the second target confidence level to obtain a target object; and controlling the ADB headlights according to the target object.

[0006] In addition, the control method of the vehicle ADB system in the above embodiments of the present invention may also have the following additional technical features:

[0007] According to one embodiment of the present invention, the operating condition includes the road type of the road ahead of the vehicle, the type of the target object ahead of the vehicle, and the distance between the target object and the vehicle. Adjusting the confidence levels of the camera and the radar based on the operating condition includes: if the road type is a curve, increasing the confidence level of the light spot and the confidence level of the first target; if the road type is a straight road and the target object is a pedestrian, increasing the confidence level of the first target and decreasing the confidence level of the light spot and the confidence level of the second target; if the road type is a straight road and the target object is a vehicle, adjusting the confidence levels of the camera and the radar based on the distance between the target object and the vehicle.

[0008] According to one embodiment of the present invention, adjusting the confidence levels of the camera and the radar based on the distance between the target and the vehicle includes: if the target is an oncoming vehicle or a vehicle traveling in the same direction, and the distance is less than a first preset distance, then increasing the second target confidence level and decreasing the spot confidence level based on the exposure of the camera; if the target is an oncoming vehicle or a vehicle traveling in the same direction, and the distance is greater than or equal to the first preset distance but less than a second preset distance, then keeping the current confidence levels of the camera and the radar unchanged; if the target is an oncoming vehicle, and the distance is greater than or equal to the second preset distance, then decreasing the first target confidence level and increasing the spot confidence level; if the target is a vehicle traveling in the same direction, and the distance is greater than or equal to the second preset distance, then decreasing the first target confidence level and the spot confidence level, and increasing the second target confidence level.

[0009] According to one embodiment of the present invention, the target object is determined based on a first target and a second target. The first target is obtained by target recognition of the image data, and the second target is obtained by target recognition of the radar data. The step of fusing the image data of the front of the vehicle acquired by the camera and the radar data of the front of the vehicle acquired by the radar to obtain the target object based on the adjusted spot confidence, the first target confidence, and the second target confidence includes: filtering the target object from the first target and the second target based on the adjusted spot confidence, the first target confidence, and the second target confidence.

[0010] According to an embodiment of the present invention, the step of selecting the target object from the first target and the second target based on the adjusted spot confidence, the first target confidence, and the second target confidence includes: comparing the position of each first target with the position of each second target respectively;

[0011] The first and second targets, whose distance is less than the distance threshold, are treated as the same target and denoted as the third target;

[0012] Based on the adjusted spot confidence, the first target confidence, and the second target confidence, a fourth target is selected from the remaining first and second targets, wherein the target objects include the third target and the fourth target.

[0013] According to an embodiment of the present invention, controlling the ADB headlights based on the target object includes: obtaining the object type of the target object within the target detection area; calculating a first distance between the vehicle and the target object whose object type is a preset type, and calculating a second distance between the vehicle and the target object whose object type is not the preset type and whose speed is greater than a second speed threshold, wherein the preset type is vehicle or pedestrian; sorting the first distance and the second distance in ascending order; and controlling the ADB headlights based on the target objects corresponding to the first K distances in the sorting, wherein K is greater than 0 and less than a third preset value.

[0014] According to one embodiment of the present invention, controlling the ADB headlights based on the first K distance-corresponding target objects includes: determining a target object of the preset type from the first K distance-corresponding target objects and denoting it as the final target; and performing zone control on the ADB headlights based on the position, object type, and movement speed of the final target.

[0015] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the above-described control method for a vehicle ADB system.

[0016] To achieve the above objectives, a third aspect of the present invention provides an ADB system, including a camera, radar, ADB headlights, and an ADB controller. The ADB controller includes a memory, a processor, and a computer program stored in the memory. When the computer program is executed by the processor, it implements the above-described control method for the vehicle ADB system.

[0017] To achieve the above objectives, a third aspect of the present invention provides a vehicle including the aforementioned ADB system.

[0018] The vehicle ADB system, its control method, storage medium, and vehicle of this invention, through the fusion of radar data and camera image data, enable more accurate lighting control of the ADB system. This can effectively prevent glare from vehicle lights to other vehicles and pedestrians on the road while ensuring clear visibility for the driver at night, thus reducing safety hazards. Attached Figure Description

[0019] Figure 1 This is a flowchart of the control method of the vehicle ADB system according to the first embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram of the recognition range of a radar and a camera according to an embodiment of the present invention;

[0021] Figure 3 This is a flowchart of the control method of the vehicle ADB system according to the second embodiment of the present invention;

[0022] Figure 4 This is a flowchart of the control method of the vehicle ADB system according to the third embodiment of the present invention;

[0023] Figure 5 This is a flowchart of the control method of the vehicle ADB system according to the fourth embodiment of the present invention;

[0024] Figure 6 This is a flowchart of the control method of the vehicle ADB system according to the fifth embodiment of the present invention;

[0025] Figure 7 This is a flowchart of the control method of the vehicle ADB system according to the sixth embodiment of the present invention;

[0026] Figure 8 This is a flowchart of the control method of the vehicle ADB system according to the seventh embodiment of the present invention;

[0027] Figure 9 This is a schematic diagram illustrating the final objective of one embodiment of the present invention;

[0028] Figure 10 This is a structural block diagram of an ADB system according to an embodiment of the present invention;

[0029] Figure 11 This is a structural block diagram of an ADB controller according to an embodiment of the present invention;

[0030] Figure 12 This is a structural block diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0031] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0032] The following is a reference appendix. Figure 1 -Appendix Figure 12 This invention describes a vehicle ADB system and its control method, storage medium, and vehicle according to embodiments of the present invention.

[0033] Figure 1 This is a flowchart of a control method for a vehicle ADB system according to an embodiment of the present invention.

[0034] In this embodiment, the ADB system includes a camera, radar, and ADB headlights, see [link / reference]. Figure 1 The methods include:

[0035] S11, determine the vehicle's operating condition, and adjust the confidence levels of the camera and radar according to the operating condition. The confidence level of the camera includes the confidence level of the light spot and the confidence level of the first target, and the confidence level of the radar includes the confidence level of the second target.

[0036] Specifically, when the ADB system is activated, it acquires image data of the area in front of the vehicle through one or more front-facing cameras and radar data of the area in front of the vehicle through one or more front-facing radars. It should be noted that this method is not executed when the vehicle's low beam headlights are on.

[0037] S12, based on the adjusted spot confidence, first target confidence and second target confidence, the image data of the front of the vehicle acquired by the camera and the radar data of the front of the vehicle acquired by the radar are fused to obtain the target object.

[0038] In this embodiment, the control cycle is longer than the data acquisition cycle, and both image data and radar data can be time-series data, that is, multiple data arranged according to the acquisition time.

[0039] S13, control the ADB headlights according to the target object.

[0040] Specifically, after receiving the ADB headlight switch activation signal, the ADB system uses radar and a camera to simultaneously identify the target. Based on the adjusted beam confidence, the first target confidence, and the second target confidence, the system fuses the identified targets to obtain the target object, which is then output to the ADB controller. The ADB controller combines information such as vehicle speed to perform zoned control of the headlights. For example, when the vehicle speed is less than 60 km / h, the ADB headlights are controlled according to the target object to avoid illuminating it; when the vehicle speed is greater than or equal to 60 km / h, the high beams can be directly activated to ensure the driver can clearly see the road ahead at high speeds, ensuring driving safety.

[0041] The vehicle ADB system control method of this invention fuses radar data and camera image data, making the ADB system's lighting control more accurate. It can effectively prevent the vehicle's lights from glaring at road vehicles and pedestrians while ensuring the driver's clear vision at low speeds at night, thus reducing safety hazards.

[0042] In some embodiments, such as Figure 3 As shown, the operating conditions include the road type ahead of the vehicle, the type of target object ahead of the vehicle, and the distance between the target object and the vehicle. The confidence levels of the camera and radar are adjusted according to these operating conditions, including:

[0043] S31, if the road type is a curve, increase the confidence of the light spot and the confidence of the first target.

[0044] S32, if the road type is a straight road and the target object is a pedestrian, then increase the confidence of the first target and decrease the confidence of the light spot and the confidence of the second target.

[0045] S33. If the road type is a straight road and the target is a vehicle, the confidence level of the camera and radar is adjusted according to the distance between the target and the vehicle.

[0046] In some embodiments, such as Figure 4 As shown, the confidence levels of the camera and radar are adjusted based on the distance between the target and the vehicle, including:

[0047] S41, if the target is an oncoming vehicle or a vehicle traveling in the same direction, and the distance is less than the first preset distance, then increase the confidence of the second target and decrease the confidence of the light spot according to the exposure of the camera.

[0048] S42, if the target is an oncoming vehicle or a vehicle traveling in the same direction, and the distance is greater than or equal to the first preset distance but less than the second preset distance, then the current confidence level of the camera and radar remains unchanged.

[0049] S43, if the target is an oncoming vehicle and the distance is greater than or equal to the second preset distance, then reduce the confidence of the first target and increase the confidence of the light spot.

[0050] S44, if the target is a vehicle traveling in the same direction and the distance is greater than or equal to the second preset distance, then reduce the confidence of the first target and the confidence of the light spot, and increase the confidence of the second target.

[0051] In some embodiments, the target object is determined based on a first target and a second target. The first target is obtained by target recognition of image data, and the second target is obtained by target recognition of radar data. The target object is obtained by fusing image data of the front of the vehicle acquired by the camera and radar data of the front of the vehicle acquired by the radar, based on the adjusted spot confidence level, the first target confidence level, and the second target confidence level.

[0052] Based on the adjusted confidence level of the light spot, the confidence level of the first target, and the confidence level of the second target, target objects are selected from the first target and the second target.

[0053] As an example, both the first and second objectives can be considered as targets.

[0054] In some embodiments, to improve processing speed, when performing fusion processing on image data and radar data, such as... Figure 5 As shown, the target object is obtained by fusing image data and radar data, including:

[0055] S51 performs target identification on image data to obtain the first target, and performs target identification on radar data to obtain the second target.

[0056] S52, select target objects from the first target and the second target.

[0057] Specifically, the camera categorizes the light emitted by other vehicles (large vehicles, small vehicles, two-wheeled vehicles, etc.) and strong reflective points (signs, puddles, streetlights, etc.) as light source targets. It then uses a built-in model to identify vehicles and pedestrians on the road ahead (i.e., the primary target). The camera integrates the speed and coordinate information of the primary target with the detection results from the millimeter-wave radar to comprehensively determine the target type and location. It then filters out the five largest and closest targets (including vehicles with single headlights, vehicles with dual headlights, and pedestrians) and outputs this information to the ADB controller. Based on this information, the ADB controller controls the headlight shut-off area to reduce glare to other road users while ensuring the driver has good visibility, thus guaranteeing driving safety.

[0058] If the ADB system detects more than 5 objects with strong reflections, the system will output the nearest object (based on the coordinates detected by the radar) in an iterative manner to ensure that the number of objects does not exceed 5.

[0059] In some embodiments, the image data includes multiple time-series images, and target recognition is performed on the image data to obtain a first target, including: performing target recognition on each frame of the image, and taking the target identified in all N frames of the image as the first target, wherein N is greater than a first preset value; the radar data includes multiple time-series radar signals, and target recognition is performed on each radar signal, and taking the target identified in all M radar signals as the second target, wherein M is greater than a second preset value.

[0060] The first preset value can be 10, and the second preset value can be 30.

[0061] In some embodiments, such as Figure 6 As shown, based on the adjusted spot confidence level, the first target confidence level, and the second target confidence level, target objects are selected from the first target and the second target, including:

[0062] S61, compare the position of each first target with the position of each second target.

[0063] Specifically, the camera converts the coordinate information of the first and second targets into a unified coordinate system and compares the differences between the coordinate points.

[0064] S62, the first target and the second target whose distance is less than the distance threshold are treated as the same target and denoted as the third target.

[0065] If the distance is greater than the distance threshold, the type is determined based on the confidence levels of the first and second targets, and it is recorded as the third target.

[0066] S63, based on the adjusted spot confidence, the first target confidence and the second target confidence, select the fourth target from the remaining first target and second target, wherein the target objects include the third target and the fourth target.

[0067] The remaining first and second objectives are the objectives obtained by removing the third objective from the initial first and second objectives. A fourth objective can be selected from the remaining first and second objectives based on its confidence level. For example, the objective with a confidence level greater than a confidence threshold (which could be the initial confidence level) can be selected as the fourth objective.

[0068] In some embodiments, selecting a fourth target from the remaining first and second targets based on road type includes: if the road type is a straight road, then selecting the remaining second target as the fourth target; if the road type is a curve, then selecting the remaining first target as the fourth target.

[0069] Specifically, when a vehicle is cornering, due to the radar beam's limitation of only being able to transmit and receive in a straight line, the confidence levels of the camera (Kcl, the weight for light source recognition, and Kco, the target confidence level) are considered higher. Therefore, these confidence levels are increased while the radar confidence level (Kr) is decreased, with camera information being the primary basis for target identification. Based on this, when the road ahead is curved, targets identified using camera data can be used as the fourth target. Similarly, when the road ahead is straight, the confidence level (Kr) is higher than both Kcl and Kco, and targets identified using radar data can be used as the fourth target.

[0070] In some embodiments, according to Figure 7 As shown, controlling the ADB headlights according to the target object includes:

[0071] S71, Obtain the object type of the target object within the target detection area.

[0072] Among them, the target detection area can be defined as follows: Figure 2 As shown, the lateral range Sx is 6m to the left and right of the vehicle's centerline, and the longitudinal range Sy is 15m to 150m from the front of the vehicle.

[0073] Specifically, when the camera determines that the target object is within the target detection area of ​​the ADB system, the camera classifies the target object, including large vehicles, small vehicles, pedestrians, or two-wheeled vehicles.

[0074] S72, calculate the first distance between the target object of the preset type and the vehicle, and calculate the second distance between the target object of the preset type and the vehicle whose speed is greater than the second speed threshold. The preset types are vehicle and pedestrian.

[0075] The second speed threshold can be 10 km / h.

[0076] S73, sort the first distance and the second distance in ascending order.

[0077] S74, control the ADB headlights according to the K target objects corresponding to the distances in the sorted order, where K is greater than 0 and less than the third preset value.

[0078] Where K can be 5.

[0079] In some embodiments, such as Figure 8As shown, the ADB headlights are controlled based on the K target objects corresponding to the distances of the first K objects in the sorted sequence, including:

[0080] S81, determine the target object with the preset type from the K target objects corresponding to the distances in the sorted order, and denot it as the final target.

[0081] For ease of understanding, regarding the above Figure 3 and Figure 4 The embodiments shown are described as follows:

[0082] In the process of fusing image data and radar data to obtain the target object, the performance characteristics of radar and camera can be comprehensively considered. Under different operating conditions, the confidence scores of the camera (Kcl, the recognition weight for light sources), target (Kco, the recognition weight for vehicles, pedestrians, positions, speeds, etc.), and radar (Kr, the recognition weight for vehicles, pedestrians, positions, speeds, etc.) can be dynamically adjusted to comprehensively determine the target's type, position, and other information. When the radar and camera detect a negative absolute speed of the target, the target is considered to be traveling in the opposite direction; conversely, when the absolute speed is positive, the target is considered to be traveling in the same direction.

[0083] Specifically, when identifying the first target from image data and the second target from radar data, the confidence levels Kcl and Kco for each first target can be adjusted, and the confidence level Kr for each second target can also be adjusted. The initial values ​​for the three confidence levels can be the same. The confidence level adjustment strategies under different operating conditions are as follows:

[0084] (1) Oncoming vehicles

[0085] a. The distance between the target and the vehicle is relatively small, such as 15m to 50m.

[0086] When driving at close range, the headlights of oncoming vehicles can overexpose the vehicle's camera, affecting its ability to recognize light spots. Therefore, under these conditions, the system will adjust the camera's confidence level (Kcl) and increase the radar's confidence level (Kr) based on the exposure.

[0087] b. The target object is relatively far from the vehicle, such as 50m to 100m.

[0088] Within this range, both radar and camera recognition of targets are relatively stable, and the confidence levels can be maintained at their initial values.

[0089] c. The distance between the target object and the vehicle is large, such as greater than 100m.

[0090] Because cameras are less stable in recognizing distant targets, but still significantly better at recognizing distant light spots than radar, in this case, the camera target confidence Kco will be reduced and the camera light spot confidence Kcl will be increased. This allows for the fusion of target data by combining radar information.

[0091] (2) Vehicles traveling in the same direction

[0092] a. The distance between the target and the vehicle is relatively small, such as 15m to 50m.

[0093] When driving at close range, the taillights of vehicles traveling in the same direction can expose the vehicle's camera, affecting its ability to recognize light spots. Therefore, under this condition, the system will reduce the camera's confidence level (Kcl) for light spots and increase the radar's confidence level (Kr) based on the exposure. This information can then be combined with the camera's target confidence level (Kco) to perform data fusion.

[0094] b. The target object is relatively far from the vehicle, such as 50m to 100m.

[0095] Within this range, both radar and camera identification of targets are relatively stable, maintaining each confidence level at its initial value, and comprehensively considering and fusing the detection information from both.

[0096] c. The distance between the target object and the vehicle is large, such as greater than 100m.

[0097] Because the taillight illumination of vehicles traveling in the same direction is low, the camera's ability to recognize this type of light spot is reduced, resulting in poor stability. Radar, on the other hand, has a better ability to detect moving objects than cameras. Therefore, in this situation, the radar confidence level Kr will be increased, while the camera confidence levels Kcl and Kco will be decreased. In this case, the information identified by the radar can be prioritized for data fusion.

[0098] (3) Pedestrians

[0099] Because pedestrians are small and non-metallic, radar reflects them at fewer points, resulting in relatively poor stability. Therefore, pedestrian identification requires increasing the target confidence level Kco of the camera while decreasing the radar confidence level Kr and the camera spot confidence level Kcl, and then fusing the identified information.

[0100] Meanwhile, considering the characteristics of pedestrians being small targets and moving slowly (e.g., <8km / h), the stable recognition range for pedestrians is 15m to 40m.

[0101] (4) Curve

[0102] When a vehicle is cornering, due to the characteristic that radar beams can only transmit and receive in a straight line, in this scenario, the confidence levels of the camera (Kcl and Kco) are considered to be higher. Therefore, the confidence levels of both cameras will be increased, while the radar confidence level (Kr) will be decreased. The target object will be output based primarily on the camera information.

[0103] (5) Stationary target

[0104] When the ambient light is greater than 80 lux (referencing the street light standard of 89 lux), if the camera detects the light spot information but the radar cannot detect the relevant object, then the light spot is considered invalid (e.g., considered to be a distant light source).

[0105] Based on the adjusted confidence levels mentioned above, when selecting target objects from the first and second targets, the confidence levels corresponding to the first and second targets can be combined to filter the identified information for target objects.

[0106] For example, if the distance between the first target and the second target is less than a distance threshold, and the confidence scores corresponding to both the first and second targets are greater than the first confidence threshold, then the first target and the second target are considered as the same target. If the distance between the first target and the second target is less than a distance threshold, and the confidence score corresponding to the first target is greater than the first confidence threshold, while the confidence score corresponding to the second target is less than the first confidence threshold, then the first target is considered as the third target, and the second target is eliminated. If the distance between the first target and the second target is less than a distance threshold, and the confidence score corresponding to the second target is greater than the first confidence threshold, while the confidence score corresponding to the first target is less than the first confidence threshold, then the second target is considered as the third target, and the first target is eliminated. The first confidence threshold can be set as needed; for example, the initial confidence value is 0.5, and the first confidence threshold can be set within the range of 0.2-0.5.

[0107] For example, if the distance between the first target and the second target is greater than or equal to a distance threshold, then the remaining first targets with a confidence level greater than the second confidence threshold are designated as the fourth target, and the remaining second targets with a confidence level greater than the second confidence threshold are designated as the fourth target. The second confidence threshold can be set as needed; for example, the initial confidence level is 0.5, and the second confidence threshold can be set within the range of 0.5-0.7.

[0108] S82 performs zoned control of the ADB headlights based on the location, object type, and speed of the final target.

[0109] In some examples, such as Figure 9 As shown, the origin of the coordinate axis represents the center point of the rear axle of the vehicle, the vertical axis represents the longitudinal distance, and the horizontal axis represents the lateral distance. Figure 9This includes radar-identified target 2, camera-identified target 71, and final target 70, with final target 70 located in area 2. ADB headlights are controlled in zones, either by turning off the headlights corresponding to area 2 or by displaying preset information in areas 2 or 3. For example, if the final target is a pedestrian, a zebra crossing image can be displayed at the pedestrian location in area 2 to remind pedestrians to cross first; the display time is negatively correlated with pedestrian speed. If the final target is a vehicle traveling in the same direction, and the speed of the vehicle traveling in the same direction is greater than the vehicle's speed but less than a preset speed (e.g., 40 m / s), the vehicle's speed can be projected onto the ground in the vehicle's lane in area 3, so that drivers of vehicles traveling in the same direction in adjacent lanes (i.e., the final target) are aware of their vehicle's speed, facilitating subsequent safe vehicle control, such as lane changing or overtaking. If the final target is an oncoming vehicle, the headlights corresponding to area 2 can be turned off; the turning-off time is negatively correlated with the sum of the speeds of the vehicle and the oncoming vehicle, where the oncoming vehicle's speed must be less than the preset speed (e.g., 40 m / s).

[0110] For ease of understanding, Table 1 below lists the signal information involved in the method of this invention:

[0111] Table 1

[0112]

[0113] Information for each target object is shown in Table 1, including: camera status, radar status, object type signal, object's lateral distance, object's longitudinal distance, object's longitudinal absolute velocity, and the number of objects. Among these, camera status and radar status are used to determine whether they can properly support the ADB system; the object type signal describes the type of object (large vehicle, small vehicle, two-wheeled vehicle, pedestrian, etc.); the object's lateral distance is... Figure 2 The length 'a' of the object is [value]. Figure 2 The length b is used to define the target detection area; the longitudinal absolute velocity of the object is between -40m / s and 40m / s, that is, for the final target with a velocity outside of -40m / s and 40m / s, it can be ignored; the final target may not exist, and there are a maximum of 5.

[0114] In summary, the vehicle ADB system control method of this invention, through the fusion of radar data and camera image data, makes the lighting control of the ADB system more accurate. It can effectively prevent the vehicle's lights from dazzling other vehicles and pedestrians on the road while ensuring clear visibility for the driver at night, thus reducing safety hazards. The introduction of confidence level can effectively avoid the disadvantages of sensors, give full play to the advantages of each sensor, and make target recognition more accurate and reliable.

[0115] Based on the control method of the vehicle ADB system in the above embodiments, the present invention also proposes a computer-readable storage medium.

[0116] In this embodiment, a computer program is stored on a computer-readable storage medium. When the computer program is executed by a processor, it implements the control method of the vehicle ADB system described above.

[0117] Figure 10 This is a structural block diagram of an ADB system according to an embodiment of the present invention.

[0118] like Figure 10 As shown, the ADB system 800 includes a camera 801, a radar 802, an ADB headlight 803, and an ADB controller 900.

[0119] In some embodiments, such as Figure 11 As shown, the ADB controller 900 includes a processor 901 and a memory 903. The processor 901 and the memory 903 are connected, for example, via a bus 902. Optionally, the ADB controller 900 may also include a transceiver 904. It should be noted that in practical applications, the transceiver 904 is not limited to one type, and the structure of this ADB controller 900 does not constitute a limitation on the embodiments of the present invention.

[0120] Processor 901 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 901 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0121] Bus 902 may include a pathway for transmitting information between the aforementioned components. Bus 902 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 502 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0122] The memory 903 stores the control method of the vehicle ADB system according to the above embodiments of the present invention. This computer program is executed under the control of the processor 901. The processor 901 executes the computer program stored in the memory 903 to implement the content shown in the foregoing method embodiments.

[0123] Figure 11 The ADB controller 900 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0124] Figure 12 This is a structural block diagram of a vehicle according to an embodiment of the present invention.

[0125] like Figure 12 As shown, vehicle 1000 includes ADB system 800.

[0126] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0127] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0128] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0129] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0130] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0131] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0132] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0133] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A control method for a vehicle ADB system, characterized in that, The ADB system includes a camera, radar, and ADB headlights, and the method includes: The operating condition of the vehicle is determined, and the confidence levels of the camera and the radar are adjusted according to the operating condition. The confidence level of the camera includes a spot confidence level and a first target confidence level, and the confidence level of the radar includes a second target confidence level. Based on the adjusted spot confidence, the first target confidence, and the second target confidence, the image data of the front of the vehicle acquired by the camera and the radar data of the front of the vehicle acquired by the radar are fused to obtain the target object. The ADB headlights are controlled according to the target object; The operating conditions include the road type ahead of the vehicle, the type of the target object ahead of the vehicle, and the distance between the target object and the vehicle. Adjusting the confidence levels of the camera and the radar based on the operating conditions includes: If the road type is a curve, then increase the confidence level of the light spot and the confidence level of the first target; if the road type is a straight road and the target is a pedestrian, then increase the confidence level of the first target and decrease the confidence level of the light spot and the confidence level of the second target; if the road type is a straight road and the target is a vehicle, then adjust the confidence levels of the camera and the radar according to the distance between the target and the vehicle. The target object is determined based on a first target and a second target. The first target is obtained by target recognition of the image data, and the second target is obtained by target recognition of the radar data. The step of fusing the image data of the front of the vehicle acquired by the camera and the radar data of the front of the vehicle acquired by the radar, based on the adjusted spot confidence level, the first target confidence level, and the second target confidence level, to obtain the target object includes: The target object is selected from the first target and the second target based on the adjusted spot confidence, the first target confidence, and the second target confidence.

2. The control method for a vehicle ADB system according to claim 1, characterized in that, The step of adjusting the confidence levels of the camera and the radar based on the distance between the target and the vehicle includes: If the target is an oncoming vehicle or a vehicle traveling in the same direction, and the distance is less than a first preset distance, then the confidence level of the second target is increased, and the confidence level of the light spot is decreased according to the exposure of the camera. If the target is an oncoming vehicle or a vehicle traveling in the same direction, and the distance is greater than or equal to the first preset distance but less than the second preset distance, then the current confidence levels of the camera and the radar remain unchanged. If the target is an oncoming vehicle and the distance is greater than or equal to the second preset distance, then the confidence level of the first target is reduced and the confidence level of the light spot is increased. If the target is a vehicle traveling in the same direction, and the distance is greater than or equal to the second preset distance, then the confidence level of the first target and the confidence level of the light spot are reduced, and the confidence level of the second target is increased.

3. The control method for a vehicle ADB system according to claim 2, characterized in that, The step of selecting the target object from the first target and the second target based on the adjusted spot confidence, the first target confidence, and the second target confidence includes: The positions of each first target and each second target are compared respectively; The first and second targets, whose distance is less than the distance threshold, are treated as the same target and denoted as the third target; Based on the adjusted spot confidence, the first target confidence, and the second target confidence, a fourth target is selected from the remaining first and second targets, wherein the target objects include the third target and the fourth target.

4. The control method for a vehicle ADB system according to claim 1, characterized in that, The step of controlling the ADB headlights according to the target object includes: Obtain the object type of the target object within the target detection area; The first distance between a target object of a preset type and the vehicle is calculated, and the second distance between a target object of a different type and the vehicle whose speed is greater than a speed threshold is calculated, wherein the preset type is vehicle or pedestrian; Sort the first distance and the second distance in ascending order; The ADB headlights are controlled based on the K target objects corresponding to the first K distances in the sorting, where K is greater than 0 and less than a third preset value.

5. The control method for a vehicle ADB system according to claim 4, characterized in that, The step of controlling the ADB headlights based on the K target objects corresponding to the first K distances in the sorting includes: From the K target objects corresponding to the first distances in the sorting, determine the target object whose object type is the preset type, and denot it as the final target; The ADB headlights are controlled in zones based on the location, object type, and movement speed of the final target.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the control method of the vehicle ADB system according to any one of claims 1-5.

7. An ADB system, characterized in that, The system includes a camera, radar, ADB headlights, and an ADB controller. The ADB controller includes a memory, a processor, and a computer program stored in the memory. When the computer program is executed by the processor, it implements the control method for the vehicle ADB system according to any one of claims 1-5.

8. A vehicle, characterized in that, Including the ADB system according to claim 7.

Images