Vehicle light control method, device and equipment and vehicle

Abstract

The embodiment of the invention provides a vehicle light control method, device and equipment and a vehicle. The method comprises the following steps: acquiring an image sequence acquired by a camera of a vehicle; performing identification processing on images in the image sequence to obtain an image identification result corresponding to the image sequence; wherein the image recognition result indicates an object recognition result and / or a light spot recognition result; determining new light spot information according to an object recognition result and / or a light spot recognition result indicated by the image recognition result; and according to the new light spot information, the light emitting state of the light of the vehicle is adjusted. According to the method, light spots can be output more quickly and stably, so that the vehicle lamp state is controlled in time, and external vehicles are prevented from flickering.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle lighting control method, device, equipment and vehicle. Background Art

[0002] At present, the Adaptive Driving Beam (ADB) system of the Advanced Driving Assistance System (ADAS) can control and turn off some of the lamps in the vehicle, so that external vehicles are in a dark area to avoid being disturbed by the vehicle's lights, thereby ensuring driving safety and comfort.

[0003] However, in the actual development of the ADB function, there may be inaccurate ADB dark zone control, which may cause the vehicle's lights to flash on external vehicles, thus affecting the safety and comfort of vehicle driving.

[0004] Therefore, how to control the vehicle lights more quickly and accurately has become an issue that needs to be addressed urgently. Summary of the invention

[0005] The embodiments of the present application provide a vehicle lighting control method, device, equipment and vehicle to solve the problem that the vehicle is prone to flashing external vehicles due to delayed light spot output.

[0006] In a first aspect, an embodiment of the present application provides a vehicle lighting control method, comprising:

[0007] Obtain an image sequence captured by a camera of a vehicle;

[0008] Performing recognition processing on the images in the image sequence to obtain an image recognition result corresponding to the image sequence; wherein the image recognition result indicates an object recognition result and / or a light spot recognition result;

[0009] Determine new light spot information according to the object recognition result indicated by the image recognition result and / or the light spot recognition result;

[0010] According to the new light spot information, the lighting state of the vehicle light is adjusted.

[0011] In a possible implementation, performing recognition processing on the images in the image sequence to obtain an object recognition result corresponding to the image sequence includes:

[0012] Performing object recognition processing on some images in the image sequence to obtain initial objects included in the image sequence;

[0013] According to the object category corresponding to each of the initial objects, identification processing is performed on each of the initial objects to obtain the object identification result.

[0014] In a possible implementation, performing recognition processing on the images in the image sequence to obtain the light spot recognition result corresponding to the image sequence includes:

[0015] Performing spot recognition processing on some images in the image sequence to obtain initial spot information included in the image sequence;

[0016] According to the light spot category corresponding to each piece of the initial light spot information, identification processing is performed on each piece of the initial light spot information to obtain the light spot identification result.

[0017] In a possible implementation, the image recognition result includes recognition attribute information; determining new light spot information according to the object recognition result indicated by the image recognition result and / or the light spot recognition result includes:

[0018] If the image recognition result indicates an object recognition result, the new light spot information is determined according to the recognition attribute information included in the object recognition result; otherwise, the new light spot information is determined according to the light spot recognition result.

[0019] In a possible implementation, adjusting the lighting state of the vehicle light according to the new light spot information includes:

[0020] Determine the area where the target object is located according to the new light spot information; wherein the target object indicates an object located within the illumination range of the vehicle's light;

[0021] The lights in the vehicle corresponding to the area where the target object is located are adjusted to turn off.

[0022] In a possible implementation manner, before determining the area where the target object is located according to the new light spot information, the method further includes:

[0023] The new light spot information is filtered to obtain filtered light spot information; wherein the filtered light spot information is used to determine the area where the target object is located.

[0024] In a possible implementation, the method further includes:

[0025] determining an initial state of lights of the vehicle;

[0026] When it is determined that the initial state indicates that the light of the vehicle is on, the lighting state of the light of the vehicle is adjusted according to the new light spot information.

[0027] In a second aspect, an embodiment of the present application provides a vehicle lighting control device, comprising:

[0028] An acquisition unit, used to acquire an image sequence captured by a camera of the vehicle;

[0029] An identification unit, configured to perform identification processing on the images in the image sequence to obtain an image identification result corresponding to the image sequence; wherein the image identification result indicates an object identification result and / or a light spot identification result;

[0030] a determination unit, configured to determine new light spot information according to an object recognition result indicated by the image recognition result and / or a light spot recognition result;

[0031] An adjustment unit is used to adjust the lighting state of the vehicle light according to the new light spot information.

[0032] In a possible implementation, the identification unit is used to:

[0033] Performing object recognition processing on some images in the image sequence to obtain initial objects included in the image sequence;

[0034] According to the object category corresponding to each of the initial objects, identification processing is performed on each of the initial objects to obtain the object identification result.

[0035] In a possible implementation, the identification unit is used to:

[0036] Performing spot recognition processing on some images in the image sequence to obtain initial spot information included in the image sequence;

[0037] According to the light spot category corresponding to each piece of the initial light spot information, identification processing is performed on each piece of the initial light spot information to obtain the light spot identification result.

[0038] In a possible implementation manner, the image recognition result includes recognition attribute information; in this case, the determination unit is configured to:

[0039] If the image recognition result indicates an object recognition result, the new light spot information is determined according to the recognition attribute information included in the object recognition result; otherwise, the new light spot information is determined according to the light spot recognition result.

[0040] In a possible implementation manner, the adjustment unit is configured to:

[0041] Determine the area where the target object is located according to the new light spot information; wherein the target object indicates an object located within the illumination range of the vehicle's light;

[0042] The lights in the vehicle corresponding to the area where the target object is located are adjusted to turn off.

[0043] In a possible implementation, the device further includes a filtering unit, which is used to:

[0044] Before determining the area where the target object is located according to the new light spot information, the new light spot information is filtered to obtain filtered light spot information; wherein the filtered light spot information is used to determine the area where the target object is located.

[0045] In a possible implementation, the device is also used for:

[0046] determining an initial state of lights of the vehicle;

[0047] When it is determined that the initial state indicates that the light of the vehicle is on, the lighting state of the light of the vehicle is adjusted according to the new light spot information.

[0048] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0049] The memory stores computer-executable instructions;

[0050] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0051] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising the electronic device described in the third aspect.

[0052] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0053] In a sixth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0054] The vehicle lighting control method, device, equipment and vehicle provided in the embodiment of the present application can first obtain the image sequence collected by the camera of the vehicle, and then obtain the image recognition result corresponding to the image sequence by identifying the images in the image sequence; wherein the image recognition result indicates the object recognition result and / or the light spot recognition result. Afterwards, new light spot information can be determined according to the object recognition result indicated by the image recognition result and / or the light spot recognition result, so that the new light spot information can be integrated with the object recognition result and the light spot recognition result, so that not only the new light spot information can determine the light spot target in a larger range in front of the vehicle, but also more stable and accurate light spot information can be determined, so that the ADB function of the vehicle can be used better in the curve scene. Afterwards, according to the new light spot information, the luminous state of the vehicle's lights is adjusted, which can make the adjustment of the luminous state of the vehicle's lights more timely and accurate, thereby avoiding the flashing of the vehicle's lights on external vehicles and improving driving safety and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0056] Figure 1 A schematic diagram of an application scenario of an ADB function provided in an embodiment of the present application;

[0057] Figure 2 A schematic diagram of a general vehicle lighting control process provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of a flow chart of controlling the lighting state of a vehicle light according to the above-mentioned general vehicle light control method provided in an embodiment of the present application;

[0059] Figure 4 A schematic diagram of a vehicle lighting control method provided in an embodiment of the present application;

[0060] Figure 5 A schematic diagram of a flow chart of another vehicle lighting control method provided in an embodiment of the present application;

[0061] Figure 6 A schematic diagram of an implementation flow of a vehicle lighting control method provided in an embodiment of the present application;

[0062] Figure 7 A schematic diagram of the structure of a vehicle lighting control device provided in an embodiment of the present application;

[0063] Figure 8 A schematic diagram of the structure of another vehicle lighting control device provided in an embodiment of the present application;

[0064] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0065] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0066] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0067] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0068] First, the terms involved in the embodiments of the present application are explained:

[0069] LED: Lighting Emitting Diode, light-emitting diode;

[0070] FLC: Front Looking Camera, front-looking camera;

[0071] FOV: Field of view, field of view.

[0072] With the development of automobile technology, the application of smart matrix headlights is becoming more and more widespread. At this time, the ADB function in the vehicle ADAS can control the shutdown of one or more LED lamp beads in the vehicle's smart matrix headlights, so that the vehicle target within the FOV of the vehicle's FLC is in a dark area, thereby avoiding external vehicles from being disturbed by the vehicle's high beams while illuminating other areas except external vehicles, thereby ensuring the safety and comfort of the vehicle / external vehicle driving.

[0073] For example, see Figure 1 , Figure 1A schematic diagram of an application scenario of an ADB function provided in an embodiment of the present application, such as Figure 1 As shown, the application scenario includes a self-vehicle 101, an external vehicle 102, and a road 103, wherein the self-vehicle includes a matrix headlight 1011. At this time, if the ADB function of the self-vehicle 101 is activated, the matrix headlight 1011 will form a bright area in the road 103. At this time, in order to prevent the external vehicle 102 from being affected by the matrix headlight 1011 of the self-vehicle 101, some of the lamp beads of the matrix headlight 1011 can be controlled to turn off, thereby forming a dark area in the area where the external vehicle 102 is located, so as to prevent the matrix headlight 1011 from flashing the external vehicle 102.

[0074] However, in the actual development of ADB functions, due to differences in the target perception performance of cameras, the ADB dark area control may be inaccurate and the dark area may be reflected late, causing the vehicle to flash outside vehicles, thus affecting driving safety and comfort. The ADB function flashing phenomenon is particularly serious in curved road scenarios such as ramps and roundabouts.

[0075] Moreover, in some regions, regulations prohibit the ADB function of a vehicle from flashing external vehicles. At this time, if a vehicle has the problem of flashing external vehicles, it will affect the sales of the vehicle in the region, thereby causing certain economic losses.

[0076] For example, Figure 2 A general vehicle lighting control process diagram provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the FLC of the vehicle usually recognizes the light spots of the headlights / taillights of external vehicles, and determines the dark area based on the recognized light spots, so that the electronic control unit in the vehicle controls the lamp beads corresponding to the dark area in the matrix headlights to turn off, thereby activating the ADB function while avoiding the vehicle from flashing external vehicles.

[0077] In a curved road scenario, an external vehicle is likely to leave the FOV area of the host vehicle's FLC. After the external vehicle leaves the FOV area of the FLC and then re-enters the FOV area of the host vehicle's FLC, the host vehicle's FLC needs to re-identify the light spot of the external vehicle. At this time, it takes a certain amount of time for the FLC to identify the light spot. And to ensure the accuracy of light spot identification, the FLC usually outputs the light spot after the light spot lasts for a certain period of time, which leads to a certain amount of time required for the FLC to output the light spot, denoted as T1. Assume that the time required for the host vehicle to activate the ADB function is denoted as T2. Then, when T2 < T1, the ADB function of the host vehicle will be activated first and the high beam will be turned on. At this time, the high beam of the host vehicle will shine on the external vehicle. After the time reaches T1, the FLC starts to output the identified light spot target of the external vehicle, and controls the light beads corresponding to the dark area in the matrix headlight to turn off according to the determined dark area and the electronic control unit, so as to form a dark area in the area where the external vehicle is located. At this time, there will be a problem that the ADB function of the host vehicle flashes the external vehicle.

[0078] Exemplarily, refer to Figure 3 , Figure 3 which is a schematic flowchart of controlling the light emission state of the vehicle's lights according to the above general vehicle light control method provided by an embodiment of the present application. As Figure 3 shown, starting from time 1, the external vehicle leaves the FOV area of the FLC, and the ADB function of the host vehicle meets the activation requirements and is activated. Starting from time 2, the external vehicle re-enters the FOV area of the host vehicle's FLC. However, the host vehicle starts to output the light spot at time 3 ( Figure 3 The light spot shown is only schematic. For example, Figure 3 the light spot shown can represent the light spot angle), and controls some light beads of the vehicle's matrix headlight to turn off according to the output light spot to form a dark area. This leads to a problem that the matrix headlight of the host vehicle flashes the external vehicle during the time period between time 2 and time 3.

[0079] The vehicle light control method provided by the present application combines the detection result of the vehicle control target with the detection result of the light spot to determine the output light spot, so as to make up for the problem of traditional light spot output delay, so that T1 < T2 can be always maintained, thereby solving the above technical problems.

[0080] The following uses specific embodiments to elaborate in detail on the technical solution of the present application and how the technical solution of the present application solves the above technical problems. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0081] Figure 4A flow chart of a vehicle lighting control method provided in an embodiment of the present application is shown as follows: Figure 4 As shown, the method includes:

[0082] S101. Acquire an image sequence captured by a camera of a vehicle.

[0083] In one example, the camera of the vehicle can be understood as the front-view camera FLC of the vehicle. At this time, multiple frames of images located in front of the vehicle can be collected according to the FLC to obtain an image sequence. At this time, the number of frames of images included in the image sequence can be 30 frames, or 50 frames, etc., and the number of images included in the image sequence collected by the FLC is not limited here.

[0084] In one example, the range captured by the vehicle's camera can be a range of 500 meters in front of the vehicle, or a range of 300 meters in front of the vehicle. The acquisition range corresponding to the image sequence is not specifically limited here, and is based on actual needs. For example, when the curve is short and the bending angle is large, multiple frames of images within 300 meters in front of the vehicle can be collected to obtain an image sequence; when the curve is long and the bending angle is small, multiple frames of images within 500 meters in front of the vehicle can be collected to obtain an image sequence, etc.

[0085] In one example, the number of cameras of a vehicle can be one or more. In this case, if the number of cameras of a vehicle is more than one, different cameras of the vehicle can be used to obtain image sequences of different distances. For example, if the number of cameras of a vehicle is two, camera 1 can be used to collect multiple frames of images within a range of 0-200 meters to obtain a first image sequence, and camera 2 can be used to obtain multiple frames of images within a range of 200-500 meters to obtain a second image sequence. In this case, the first image sequence and the second image sequence are combined to obtain the above image sequence.

[0086] S102: Perform recognition processing on the images in the image sequence to obtain image recognition results corresponding to the image sequence.

[0087] The image recognition result indicates an object recognition result and / or a light spot recognition result.

[0088] In one example, each frame image included in the image sequence may include one or more vehicle control targets. In this case, the object recognition result can be obtained by identifying each vehicle control target included in the image. The vehicle control targets here mainly refer to vehicles and pedestrians, such as same-direction vehicles, oncoming vehicles, oncoming pedestrians, etc.

[0089] In one example, when performing recognition processing on each image in the image sequence, the light spot in the image can also be recognized to obtain a light spot recognition result. At this time, the light spot recognition result can be used to determine the type of light source corresponding to the light spot, for example, the type of the light source can be a vehicle, a reflective object, etc.

[0090] In a possible implementation, the image sequence may be input into a pre-trained object recognition model, so that the vehicle control targets of various object categories included in the image sequence are identified according to the pre-trained object recognition model. For example, the object categories of the vehicle control targets may include but are not limited to: cars, trucks, off-road vehicles, pedestrians, etc. At the same time, the image sequence is input into a pre-trained light spot recognition model, so that the light spot targets included in the image sequence are identified according to the pre-trained light spot recognition model. At this time, the light spot categories corresponding to the light spot targets may include but are not limited to: split-type categories, through-type categories, etc.

[0091] In another possible implementation, the image sequence may be first input into a pre-trained category recognition model, and the object category (or light spot category) included in the images in the image sequence may be identified based on the pre-trained category recognition model. Then, based on the identified object category (or light spot category), the image sequence may be input into an object recognition model that matches the object category (or light spot category) for recognition processing. In this way, different object recognition models may be trained according to different categories for recognition processing, thereby improving the accuracy and reliability of image recognition, and thereby improving the accuracy of image recognition results.

[0092] In one example, the object recognition result indicated by the image recognition result may include but is not limited to: object category, object distance, object driving speed, object driving direction, object driving acceleration, etc. The light spot recognition result indicated by the image recognition result at least indicates the light spot distance, light spot direction, light spot angle, etc.

[0093] S103: Determine new light spot information according to the object recognition result indicated by the image recognition result and / or the light spot recognition result.

[0094] In one example, the object recognition result indicated by the image recognition function and / or the light spot recognition result may be fused to obtain new light spot information.

[0095] In specific implementation, since the recognition distance of the light spot target is farther than the recognition distance corresponding to the object recognition result, when the light spot recognition result is included in the image recognition result, the new light spot information can be determined based on the light spot recognition result first, and the light spot recognition result can be supplemented based on the object recognition result, thereby ensuring the distance of light spot target recognition while ensuring the stability of the light spot output.

[0096] At the same time, since the distance of the object recognition result is short and the accuracy is high, the light spot recognition result can be further supplemented by the object recognition result to determine new light spot information, thereby compensating for the problem of light spot output delay, thereby improving the speed and efficiency of light spot recognition and avoiding the vehicle flashing external vehicles.

[0097] S104: Adjust the lighting state of the vehicle's lights according to the new light spot information.

[0098] In one example, the dark area position can be determined according to the position corresponding to the new light spot information, so as to adjust the lighting state of the vehicle's lights according to the dark area position to avoid flashing external vehicles.

[0099] It can be seen from the above description that the embodiment of the present application can first obtain the image sequence collected by the camera of the vehicle, and then obtain the image recognition result corresponding to the image sequence by identifying the images in the image sequence; wherein the image recognition result indicates the object recognition result and / or the light spot recognition result. Afterwards, new light spot information can be determined according to the object recognition result indicated by the image recognition result and / or the light spot recognition result, so that the new light spot information can be integrated with the object recognition result and the light spot recognition result, so that not only the new light spot information can determine the light spot target in a larger range in front of the vehicle, but also more stable and accurate light spot information can be determined, so that the ADB function of the vehicle can be used better in the curve scene. Afterwards, according to the new light spot information, the luminous state of the vehicle's lights is adjusted, which can make the adjustment of the luminous state of the vehicle's lights more timely and accurate, thereby avoiding the flashing of the vehicle's lights on external vehicles and improving driving safety and comfort.

[0100] Figure 5 A flow chart of another vehicle lighting control method provided in an embodiment of the present application is shown as follows: Figure 5 As shown, in this embodiment Figure 4 Based on the provided embodiment, a vehicle light control method is described in detail, and the method includes:

[0101] S201: Acquire an image sequence captured by a camera of a vehicle.

[0102] In an example, this step can refer to the content described in the above S101, and will not be described in detail here.

[0103] After the image sequence is acquired, the image recognition result corresponding to the image sequence can be obtained by performing recognition processing on the images in the image sequence, wherein the image recognition result indicates the object recognition result and / or the light spot recognition result.

[0104] At this time, since the recognition distances corresponding to the object recognition result and the light spot recognition result are different, the images in the image sequence need to be divided into two parts, one part is used to determine the object recognition result, and the other part is used to determine the light spot recognition result. The two parts of the image may have an intersection.

[0105] Based on this, the two parts of the image can be processed for recognition respectively to obtain an object recognition result and / or a light spot recognition result, thereby obtaining an image recognition result.

[0106] In specific implementation, the images in the image sequence are recognized and processed to obtain the object recognition results corresponding to the image sequence, which can be seen from the steps described below:

[0107] S202: Perform object recognition processing on some images in the image sequence to obtain initial objects included in the image sequence.

[0108] S203 , performing recognition processing on each initial object according to the object category corresponding to each initial object to obtain an object recognition result.

[0109] In one example, a portion of the images in the image sequence used for object recognition processing may indicate that the camera of the vehicle acquires images within the range S1 to S2 in front of the vehicle, where S1 and S2 are natural numbers greater than 0, and the value of S2 is greater than the value of S1. For example, the value of S1 may be 50 meters, and the value of S2 may be 200 meters.

[0110] In one example, when the initial objects included in the image sequence are determined, the images in the image sequence can be cropped according to the location of each initial object to obtain images containing a single initial object, and recognition processing can be performed on each image containing a single initial object according to the object category of each initial object to obtain an object recognition result.

[0111] In another example, if the number of initial objects included in the image is large and there is overlap between different initial objects, then the single initial image included in the cropped image may be an incomplete object. At this time, the incomplete object can be supplemented first, and after obtaining the complete initial object, the initial object can be recognized.

[0112] In another example, if it is determined that the image sequence includes multiple initial objects, the initial object closest to the vehicle may be identified to obtain an object recognition result.

[0113] When performing recognition processing according to the object category of the initial object, each initial object can be recognized according to a pre-trained network model for recognizing different object categories. The model structure of each network model used to recognize the initial object is not specifically limited here, subject to what can be implemented.

[0114] In the above implementation, object recognition processing can be performed on some images in the image sequence, thereby reducing the complexity of image recognition and improving recognition efficiency. At the same time, after the initial object is recognized, recognition processing is performed according to the object category of the initial object, which can improve the accuracy of object recognition and thus improve the precision of the object recognition result.

[0115] In specific implementation, the images in the image sequence are recognized and processed to obtain the light spot recognition results corresponding to the image sequence. The process described below can be referred to:

[0116] S204: Perform light spot recognition processing on part of the images in the image sequence to obtain initial light spot information included in the image sequence.

[0117] S205 , performing identification processing on each piece of initial light spot information according to the light spot category corresponding to each piece of initial light spot information, to obtain a light spot identification result.

[0118] In one example, part of the images in the image sequence used for spot recognition processing can instruct the vehicle's camera to obtain images within the range of S3 to S4 in front of the vehicle, where S3 and S4 are natural numbers greater than 0, and the value of S4 is greater than the value of S3. For example, the value of S3 can be 50 meters, and the value of S2 can be 400 meters, or the value of S3 can be 100 meters, and the value of S2 can be 500 meters, etc.

[0119] When identifying and processing the light spot category corresponding to the initial light spot information, each initial light spot information can be identified and processed according to a pre-trained network model for identifying different light spot categories. The model structure of each network model used to identify the initial light spot information is not specifically limited here, subject to what can be implemented.

[0120] In the above implementation, spot recognition processing can be performed on some images in the image sequence, thereby reducing the complexity of image recognition and improving recognition efficiency. At the same time, after the initial spot information is recognized, the spot category of the initial spot information is recognized, which can improve the accuracy of spot recognition and thus improve the accuracy of the spot recognition result.

[0121] In a possible implementation, the image recognition result determined in the above manner may include recognition attribute information, and the recognition attribute information may be understood as the above object category, object distance, object driving speed, object driving direction, object driving acceleration, light spot distance, light spot direction, light spot angle, etc. At this time, after the image recognition result is determined, new light spot information may be determined according to the image recognition result, and specifically refer to the content described in S206 below.

[0122] S206: If the image recognition result indicates an object recognition result, determining new light spot information according to the recognition attribute information included in the object recognition result; otherwise, determining new light spot information according to the light spot recognition result.

[0123] In one example, the new light spot information can be used to determine the vehicle in front of the vehicle, so as to avoid the vehicle's lights flashing on other vehicles. Therefore, the new light spot information at least includes: light spot distance and light spot angle. For example, the new light spot information can be: light spot 1: 100 meters, 1 degree; light spot 2, 100 meters, minus 1 degree. Then, the vehicle in front determined according to the new light spot information is: there is a vehicle 100 meters ahead, plus or minus 1 degree.

[0124] Based on this, if the image recognition result indicates the object recognition result, then it can be determined that there is a delay in the light spot output. At this time, it is necessary to determine the new light spot information based on the recognition attribute information included in the object recognition result; if the image recognition result indicates the light spot recognition result, then it can be determined that there is a vehicle at a long distance. At this time, the new light spot information can be determined based on the recognition attribute information included in the light spot recognition result; if it is determined that the image recognition result indicates the object recognition result and the light spot recognition result, then the normal output light spot target can be determined. At this time, the new light spot information can be determined based on the recognition attribute information included in the light spot recognition result.

[0125] In the above implementation, the output light spot can be supplemented according to the object recognition result with a faster output speed to obtain new light spot information, thereby compensating for the problem of delayed light spot output, thereby making the output of the new light spot information more stable and faster, thereby achieving the effect of avoiding the vehicle flashing external vehicles.

[0126] S207: Determine the area where the target object is located according to the new light spot information.

[0127] The target object refers to an object within the illumination range of the vehicle's lights. For example, the target object may refer to an object such as a vehicle or a pedestrian whose lights need to be avoided.

[0128] In one example, the position of the light spot can be determined based on the new light spot information, and then the area where the target object is located can be determined.

[0129] In one example, if the new light spot information corresponds to multiple target objects, the area where each target object is located can be determined.

[0130] In a possible implementation, in order to ensure the stability and regularity of the determined area where the target object is located, before determining the area where the target object is located based on the new light spot information, the new light spot information can be filtered to obtain filtered light spot information, and then the area where the target object is located can be determined based on the filtered light spot information.

[0131] Exemplarily, the new light spot information can be filtered by a morphological filtering method, or can be filtered by a combination of Gaussian filtering and median filtering. The specific implementation method of the filtering process is not limited here and is subject to meeting actual needs.

[0132] S208: Turn off the lights in the vehicle corresponding to the area where the target object is located.

[0133] At this time, one or more dark areas can be formed by adjusting the lights in the vehicle corresponding to the area where the target object is located, so as to avoid the vehicle lights flashing external vehicles, thereby improving driving safety and enhancing the user's driving experience.

[0134] In a possible implementation, before adjusting the lighting state of the vehicle lights according to the vehicle lighting control method provided in any of the above embodiments, the embodiment of the present application may first determine the initial state of the vehicle lights, and when it is determined that the initial state indicates that the vehicle lights are on, adjust the lighting state of the vehicle lights according to the new light spot information.

[0135] In one example, the initial state of the vehicle's lights can be determined by determining the activation state of the vehicle's ADB function. For example, if it is determined that the ADB function is activated, the initial state of the vehicle's lights can be determined to be on; if it is determined that the ADB function is not activated, the initial state of the vehicle's lights can be determined to be off.

[0136] This implementation can adjust the lighting state of the vehicle lights according to new light spot information when it is determined that the vehicle lights need to be adjusted, that is, when the vehicle lights are on, thereby avoiding invalid operations and saving resources.

[0137] See also Figure 6 , Figure 6 The following is a schematic diagram of the implementation process of a vehicle lighting control method provided in an embodiment of the present application. Figure 6As shown, the FLC of the vehicle can obtain an image sequence, and perform recognition processing on the images in the image sequence to obtain an image recognition result, that is, an object recognition result, and / or a light spot recognition result. Afterwards, the image recognition result can be sent to the main control unit, which can determine new light spot information based on the image recognition result, and after filtering the new light spot information, determine the area where the target object is located based on the filtered light spot information. Afterwards, it can communicate with the electronic control unit of the light to adjust the lighting state of the vehicle's light according to the electronic control unit.

[0138] Figure 7 A schematic diagram of the structure of a vehicle lighting control device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the vehicle lighting control device 700 provided in this embodiment includes:

[0139] The acquisition unit 701 is used to acquire an image sequence captured by a camera of the vehicle.

[0140] The recognition unit 702 is used to perform recognition processing on the images in the image sequence to obtain an image recognition result corresponding to the image sequence; wherein the image recognition result indicates an object recognition result and / or a light spot recognition result.

[0141] The determination unit 703 is used to determine new light spot information according to the object recognition result indicated by the image recognition result and / or the light spot recognition result.

[0142] The adjustment unit 704 is used to adjust the lighting state of the vehicle light according to the new light spot information.

[0143] Figure 8 A schematic diagram of the structure of another vehicle lighting control device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the vehicle lighting control device 800 provided in this embodiment includes:

[0144] The acquisition unit 801 is used to acquire an image sequence captured by a camera of the vehicle.

[0145] The recognition unit 802 is used to perform recognition processing on the images in the image sequence to obtain an image recognition result corresponding to the image sequence; wherein the image recognition result indicates an object recognition result and / or a light spot recognition result.

[0146] The determination unit 803 is used to determine new light spot information according to the object recognition result indicated by the image recognition result and / or the light spot recognition result.

[0147] The adjustment unit 804 is used to adjust the lighting state of the vehicle light according to the new light spot information.

[0148] In a possible implementation, the identification unit 802 is configured to:

[0149] Performing object recognition processing on some images in the image sequence to obtain initial objects included in the image sequence;

[0150] According to the object category corresponding to each initial object, each initial object is identified and processed to obtain an object recognition result.

[0151] In a possible implementation, the identification unit 802 is configured to:

[0152] Performing spot recognition processing on part of the images in the image sequence to obtain initial spot information included in the image sequence;

[0153] According to the light spot category corresponding to each piece of initial light spot information, each piece of initial light spot information is identified and processed to obtain a light spot identification result.

[0154] In a possible implementation, the image recognition result includes recognition attribute information; in this case, the determination unit 803 is used to:

[0155] If the image recognition result indicates an object recognition result, new light spot information is determined according to the recognition attribute information included in the object recognition result; otherwise, new light spot information is determined according to the light spot recognition result.

[0156] In a possible implementation, the adjusting unit 804 is configured to:

[0157] Determine the area where the target object is located according to the new light spot information; wherein the target object refers to an object located within the illumination range of the vehicle's light;

[0158] Adjust the lights in the vehicle to turn off corresponding to the area where the target object is located.

[0159] In a possible implementation, the device further includes a filtering unit 805, which is used to:

[0160] Before determining the area where the target object is located according to the new light spot information, the new light spot information is filtered to obtain filtered light spot information; wherein the filtered light spot information is used to determine the area where the target object is located.

[0161] In a possible implementation, the device is also used for:

[0162] Determine the initial state of the vehicle's lights;

[0163] When it is determined that the initial state indicates that the vehicle's lights are on, the lighting state of the vehicle's lights is adjusted according to the new light spot information.

[0164] The vehicle light control device provided in this embodiment can execute the vehicle light control method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0165] Fig. 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig. 9 As shown, the electronic device 900 provided in this embodiment includes: at least one processor 901 and a memory 902. Optionally, the electronic device 900 further includes a communication component 903. The processor 901, the memory 902 and the communication component 903 are connected via a bus 904.

[0166] In a specific implementation process, at least one processor 901 executes the computer execution instructions stored in the memory 902, so that at least one processor 901 executes the above method.

[0167] The specific implementation process of the processor 901 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0168] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0169] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0170] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0171] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0172] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0173] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0174] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0175] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0176] 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.

[0177] In addition, each functional unit in each embodiment of the present invention 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.

[0178] If the function 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 technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0179] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0180] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A vehicle lighting control method, characterized in that: include: Obtain an image sequence captured by a camera of a vehicle; Performing recognition processing on the images in the image sequence to obtain an image recognition result corresponding to the image sequence; wherein the image recognition result indicates an object recognition result and / or a light spot recognition result; Determine new light spot information according to the object recognition result indicated by the image recognition result and / or the light spot recognition result; According to the new light spot information, the lighting state of the vehicle light is adjusted.

2. The method according to claim 1, characterized in that Performing recognition processing on the images in the image sequence to obtain object recognition results corresponding to the image sequence includes: Performing object recognition processing on some images in the image sequence to obtain initial objects included in the image sequence; According to the object category corresponding to each of the initial objects, identification processing is performed on each of the initial objects to obtain the object identification result.

3. The method according to claim 1, characterized in that Performing recognition processing on the images in the image sequence to obtain the light spot recognition result corresponding to the image sequence includes: Performing spot recognition processing on some images in the image sequence to obtain initial spot information included in the image sequence; According to the light spot category corresponding to each piece of the initial light spot information, identification processing is performed on each piece of the initial light spot information to obtain the light spot identification result.

4. The method according to any one of claims 1 to 3, characterized in that The image recognition result includes recognition attribute information; Determining new light spot information according to the object recognition result indicated by the image recognition result and / or the light spot recognition result includes: If the image recognition result indicates an object recognition result, determining the new light spot information according to the recognition attribute information included in the object recognition result; Otherwise, the new light spot information is determined according to the light spot recognition result.

5. The method according to claim 1, characterized in that According to the new light spot information, adjusting the light emitting state of the vehicle light includes: Determine the area where the target object is located according to the new light spot information; wherein the target object indicates an object located within the illumination range of the vehicle's light; The lights in the vehicle corresponding to the area where the target object is located are adjusted to turn off.

6. The method according to claim 5, characterized in that Before determining the area where the target object is located according to the new light spot information, the method further includes: The new light spot information is filtered to obtain filtered light spot information; wherein the filtered light spot information is used to determine the area where the target object is located.

7. The method according to any one of claims 1 to 3, characterized in that The method further comprises: determining an initial state of lights of the vehicle; When it is determined that the initial state indicates that the light of the vehicle is on, the lighting state of the light of the vehicle is adjusted according to the new light spot information.

8. A vehicle lighting control device, characterized in that: include: An acquisition unit, used to acquire an image sequence captured by a camera of the vehicle; An identification unit, configured to perform identification processing on the images in the image sequence to obtain an image identification result corresponding to the image sequence; wherein the image identification result indicates an object identification result and / or a light spot identification result; a determination unit, configured to determine new light spot information according to an object recognition result indicated by the image recognition result and / or a light spot recognition result; An adjustment unit is used to adjust the lighting state of the vehicle light according to the new light spot information.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A vehicle, characterized in that: The vehicle includes the electronic device according to claim 9.

Images