Blind area oncoming vehicle determination method, vehicle and readable storage medium

Abstract

The application provides a blind area vehicle determination method, a vehicle and a readable storage medium. The blind area vehicle determination method comprises the following steps: acquiring a front image of a vehicle collected in real time. When there is a blind area in front of the vehicle, at least part of a ground area in the front image is determined as a ground monitoring area. The current total illumination of the ground monitoring area and the current vehicle illumination are determined. According to the difference between the current total illumination and the current vehicle illumination, the area illumination increment of the ground monitoring area is determined. According to the area illumination increment, it is determined whether the blind area in front of the vehicle is coming. If the blind area in front of the vehicle is coming, the prompt device of the vehicle is controlled to send prompt information. Thus, the accuracy is higher.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method for determining vehicles approaching from blind spots, a vehicle, and a readable storage medium. Background Technology

[0002] At intersections with underground facilities such as underground parking lots, there are often architectural structures that obstruct the driver's view, creating blind spots. When a vehicle approaches an intersection with a blind spot, the driver cannot directly observe oncoming traffic, greatly increasing the risk of collisions and seriously affecting driving safety.

[0003] Some vehicles use additional hardware such as radar and ultrasonic sensors to detect vehicles approaching from blind spots. However, this detection method is easily affected by surrounding obstacles in the enclosed environment of underground facilities, resulting in lower detection accuracy. Summary of the Invention

[0004] This application provides a highly accurate method for determining oncoming vehicles in blind spots, a vehicle, and a readable storage medium.

[0005] This application provides a method for determining oncoming vehicles in blind spots, including: Acquire real-time images of the vehicle's front; When a blind spot exists in front of the vehicle, at least a portion of the ground area in the image ahead is identified as a ground monitoring area; Determine the current total illuminance and the current vehicle illuminance of the ground monitoring area; wherein, the current vehicle illuminance represents the illuminance formed in the ground monitoring area when the vehicle's headlights illuminate the ground; Based on the difference between the current total illuminance and the current illuminance of the vehicle, the regional illuminance increment of the ground monitoring area is determined; Based on the increase in illuminance in the area, determine whether there is an oncoming vehicle in the blind spot in front of the vehicle; If a vehicle approaches from the vehicle's blind spot, the vehicle's warning device will issue a warning message.

[0006] Furthermore, the method for determining vehicles approaching from the blind spot also includes: Determine the initial total illuminance and the initial illuminance of the vehicle in the ground monitoring area in the forward image; The initial ambient illuminance is determined based on the initial total illuminance and the initial illuminance of the vehicle itself. The step of determining the regional illuminance increment of the ground monitoring area based on the difference between the current total illuminance and the current illuminance of the vehicle includes: The regional illuminance increment of the ground monitoring area is determined based on the difference between the current total illuminance, the current illuminance of the vehicle, and the initial ambient illuminance.

[0007] Further, determining the current illuminance of the vehicle includes: Based on the center position of the ground monitoring area in the forward image and the camera parameters of the vehicle, determine the actual horizontal distance from the vehicle's camera to the center of the ground monitoring area; The current illuminance of the vehicle is determined based on the actual horizontal distance and the vehicle's headlight parameters.

[0008] Further, determining the actual horizontal distance from the vehicle's camera to the center of the ground monitoring area based on the center position of the ground monitoring area in the forward image and the vehicle's camera parameters includes: The actual horizontal distance from the vehicle's camera to the center of the ground monitoring area is determined by the following formula. : , in, The installation height of the camera is [height]. The vertical tilt angle corresponding to the center pixel of the ground monitoring area; The vertical tilt angle corresponding to the center pixel of the ground monitoring area is determined by the following formula. : , in, The pitch angle of the camera. The pixel row at the center of the ground monitoring area. The optical center of the camera is the pixel row in the front image. It is half the vertical angle of view of the camera. The image height is the height of the foreground image.

[0009] Further, determining the current illuminance of the vehicle based on the actual horizontal distance and the vehicle's headlight parameters includes: The current illuminance of this vehicle is determined by the following formula. : , in, The rated luminous intensity of the vehicle's headlights, The installation height of the vehicle's headlights. This refers to the actual horizontal distance.

[0010] Further, determining the current total illuminance of the ground monitoring area includes: Extract the brightness of pixels within the ground monitoring area in the forward image; The current total illuminance of the ground monitoring area is determined based on the average brightness of multiple pixels within the ground monitoring area.

[0011] Further, determining whether a vehicle is approaching in the blind spot ahead of the vehicle based on the increase in illuminance in the area includes: Compare the regional illuminance increment of the foreground image with the preset illuminance increment value; If the illuminance increment of the area in the forward image for a consecutive set number of frames is greater than the preset illuminance increment value, then an oncoming vehicle is determined to be in the vehicle's forward blind spot; and / or, The method for determining vehicles approaching from the blind spot also includes: The ground monitoring area in the frontal image is divided into a left area and a right area; Determine the illuminance of the left-side region and the illuminance of the right-side region; If the difference between the illuminance of the left-side region and the illuminance of the right-side region is greater than a preset illuminance diffusion value, then an oncoming vehicle is determined to be in the vehicle's blind spot.

[0012] Further, determining that at least a portion of the ground area in the forward image is a ground monitoring area includes: Determine the location of the blind spot features in the front image that form the blind spot; If the blind spot feature is located on the left side of the image ahead, then the rightmost point of the contact point between the blind spot feature and the ground is taken as the starting point, and the area extends along directions perpendicular to and parallel to the vehicle's driving road, and in directions away from the blind spot feature, to form the ground monitoring area. If the blind spot feature is located on the right side of the image ahead, then the leftmost point of the contact point between the blind spot feature and the ground is taken as the starting point, and the area extends along directions perpendicular to and parallel to the vehicle's driving road, and in directions away from the blind spot feature, to form the ground monitoring area.

[0013] This application provides a vehicle, including: a processor and a memory communicatively connected to the processor; the memory is used to store computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the blind spot vehicle determination method as described in any of the above embodiments.

[0014] This application provides a readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the blind spot vehicle determination method as described in any of the above embodiments.

[0015] The blind spot vehicle detection method provided in this application includes determining the regional illuminance increment of the ground monitoring area based on the difference between the current total illuminance and the current illuminance of the vehicle itself. Based on this regional illuminance increment, it is determined whether a vehicle is approaching in front of the vehicle's blind spot. Thus, by determining whether a vehicle is approaching in front of the vehicle through changes in the regional illuminance of the ground monitoring area, the method is less affected by surrounding obstacles, resulting in higher detection accuracy.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] Figure 1 The diagram shown is a flowchart of a blind spot vehicle detection method according to an embodiment of this application; Figure 2 As shown Figure 1 The flowchart shown is a sub-flowchart of the method for determining vehicles approaching from blind spots. Figure 3 As shown Figure 1 Another sub-flowchart of the method for determining vehicles approaching from blind spots is shown below; Figure 4 As shown Figure 1 The flowchart shown is another sub-flowchart of the method for determining vehicles approaching from blind spots; Figure 5 The diagram shown is a schematic frame diagram of a vehicle according to an embodiment of this application. Detailed Implementation

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0020] To better understand the technical solution of this application, the blind spot vehicle determination method, vehicle, and readable storage medium of this application will be described in detail below with reference to the accompanying drawings. Unless otherwise specified, the features in the following embodiments and implementations can be combined with each other.

[0021] Figure 1 The diagram shows a flowchart of a blind spot vehicle detection method according to an embodiment of this application. See also... Figure 1As shown in the figure, this application provides a method for determining oncoming vehicles in a blind spot, which includes steps S1 to S6.

[0022] In step S1, a real-time image of the vehicle's front is acquired. This can be achieved by acquiring a real-time image of the vehicle's front from a camera. The camera can be a monocular camera.

[0023] In one embodiment, when the brightness of the vehicle's surrounding environment is detected to be lower than a set brightness threshold, the vehicle's headlights are turned on, and a real-time image of the vehicle's front is acquired. The vehicle's headlights can refer to either the low beam headlights or the high beam headlights.

[0024] In one embodiment, prior to step S2, the blind spot vehicle determination method further includes: extracting structural features from the image in front of the vehicle. If the structural feature is close to a preset feature, the structural feature is determined to be a blind spot feature, and a blind spot exists in front of the vehicle. The preset features include, but are not limited to, building structures such as walls, pillars, shelves, and intersection turning signs.

[0025] In step S2, when a blind spot exists in front of the vehicle, at least a portion of the ground area in the forward image is identified as the ground monitoring area. When a blind spot exists in front of the vehicle, at least a portion of the ground area in the forward image located on the side of the blind spot feature facing away from the vehicle can be identified as the ground monitoring area. The ground monitoring area can be polygonal, circular, or other shapes; this application does not impose any limitations.

[0026] Figure 2 As shown Figure 1 The flowchart shown illustrates the method for determining oncoming vehicles in the blind spot. See also... Figure 2 As shown, in one embodiment, determining at least a portion of the ground area in the foreground image as the ground monitoring area includes steps S21 to S23.

[0027] In step S21, the location of the blind spot feature forming the blind spot in the front image is determined.

[0028] In one embodiment, determining at least a portion of the ground area in the foreground image as the ground monitoring area further includes step S24.

[0029] In step S24, the driving road in the ground area of ​​the forward image is extracted. This can be done using an image segmentation algorithm. This eliminates lighting interference from building obstructions and non-road areas such as pedestrians.

[0030] In step S22, if the blind spot feature is located on the left side of the front image, the rightmost point of the contact point between the blind spot feature and the ground is taken as the starting point, and the area is extended along the direction perpendicular to and parallel to the vehicle's driving road, and in the direction away from the blind spot feature, to form a ground monitoring area.

[0031] In step S23, if the blind spot feature is located on the right side of the image ahead, the leftmost point of the contact point between the blind spot feature and the ground is taken as the starting point, and the area is extended along directions perpendicular to and parallel to the vehicle's driving path, and in directions away from the blind spot feature, to form a ground monitoring area. This forms a rectangular ground monitoring area, thus clearly defining the pixel range of the ground monitoring area. The method of forming the ground monitoring area is simple and highly operable.

[0032] In step S3, the current total illuminance of the ground monitoring area is determined. and the current illuminance of this vehicle The current vehicle illuminance refers to the illuminance generated within the ground monitoring area when the vehicle's headlights illuminate the ground.

[0033] In one embodiment, the current total illuminance of the ground monitoring area is determined. This includes extracting the brightness of pixels within a ground monitoring area in the foreground image. Specifically, it can extract the brightness of multiple pixels within the ground monitoring area of ​​the foreground image. These multiple pixels can include all pixels.

[0034] The current total illuminance of the ground monitoring area is determined based on the average brightness of multiple pixels within the ground monitoring area. The current total illuminance can be determined based on the average brightness of all pixels extracted from the ground monitoring area. Alternatively, the current total illuminance can be determined based on the average brightness of a subset of pixels extracted from the ground monitoring area. Thus, the current total illuminance is determined. The method is simple and more efficient.

[0035] Figure 3 As shown Figure 1 Another sub-flowchart of the blind spot vehicle detection method is shown. See also... Figure 3 As shown, in one embodiment, the current illuminance of the vehicle is determined. This includes steps S31 to S32.

[0036] In step S31, the actual horizontal distance from the vehicle's camera to the center of the ground monitoring area is determined based on the center position of the ground monitoring area in the forward image and the vehicle's camera parameters. The camera parameters include intrinsic and extrinsic parameters. The intrinsic parameters include the camera's optical center coordinates and vertical viewing angle. The extrinsic parameters include the camera's pitch angle and installation height.

[0037] In one embodiment, step S31 includes: determining the actual horizontal distance from the vehicle's camera to the center of the ground monitoring area using the following formula. : , in, For the installation height of the camera, The vertical tilt angle corresponding to the pixel at the center of the ground monitoring area.

[0038] In one embodiment, the vertical tilt angle corresponding to the pixel at the center of the ground monitoring area is determined by the following formula. : , in, The camera's tilt angle. The pixel row at the center of the ground monitoring area. The row of pixels in the front image where the optical center of the camera is located. It is half the vertical angle of the camera. The image height is the height of the image ahead. Thus, the above method for determining the actual horizontal distance is highly robust. The actual horizontal distance calculated in this way can be used to quickly determine whether there is a collision risk at intersections of underground facilities such as underground parking lots.

[0039] In step S32, the current illuminance of the vehicle is determined based on the actual horizontal distance and the vehicle's headlight parameters. The parameters for vehicle lights include the rated luminous intensity and the installation height of the lights.

[0040] In one embodiment, step S32 includes: determining the current illuminance of the vehicle using the following formula. : , in, Rated luminous intensity for vehicle headlights, The installation height of vehicle headlights, This refers to the actual horizontal distance. The installation height of the vehicle's camera. Can be installed at the same height as the vehicle's headlights Equal. Thus, the current illuminance of this vehicle is determined. More accurate.

[0041] In one embodiment, the blind spot vehicle detection method further includes: Determine the initial total illuminance of the ground monitoring area in the forward image. and the initial illuminance of the vehicle This involves determining the initial total illuminance of the ground monitoring area in the first preset frame image after a blind spot exists in front of the vehicle, and the initial illuminance of the vehicle itself at the corresponding moment in the first preset frame image. In this embodiment, the first preset frame image is the first frame image. Initial total illuminance The method for determining the current total illuminance is the same as described above. The method for determining the initial illuminance of the vehicle. The method for determining the current illuminance of this vehicle is the same as described above. The method of determination.

[0042] The initial ambient illuminance is determined based on the initial total illuminance and the initial illuminance of the vehicle itself. Specifically, the initial total illuminance can be used as a basis for determining the initial ambient illuminance. and initial vehicle illumination The difference is used to determine the initial ambient illuminance. In this embodiment, .

[0043] In step S4, based on the current total illuminance And the current illuminance of this vehicle The difference is used to determine the regional illuminance increment in the ground monitoring area. In one embodiment, .

[0044] In one embodiment, step S4 includes: determining the regional illuminance increment of the ground monitoring area based on the difference between the current total illuminance, the current vehicle illuminance, and the initial ambient illuminance. In this embodiment, Thus, the increase in illuminance within the determined ground monitoring area is... More accurate, as it eliminates the influence of ambient light levels.

[0045] In step S5, the presence of oncoming vehicles in the blind spot ahead of the vehicle is determined based on the area illuminance increment.

[0046] Figure 4 As shown Figure 1 The flowchart shown is another sub-flowchart of the blind spot vehicle determination method. In one embodiment, step S5 includes steps S51 to S52.

[0047] In step S51, the regional illuminance increment of the foreground image is compared with a preset illuminance increment value. The preset illuminance increment value can be 20% to 30% of the initial ambient light illuminance.

[0048] In step S52, if the illuminance increment of the area in the forward image for a consecutive set number of frames is greater than a preset illuminance increment value, then an oncoming vehicle is determined to be in the vehicle's forward blind spot. In this embodiment, the set number of frames is three frames. If the illuminance increment of the area in the forward image for three consecutive frames is greater than the preset illuminance increment value, then an oncoming vehicle is determined to be in the vehicle's forward blind spot.

[0049] In one embodiment, if the regional illuminance increment of the forward image for a continuously set number of frames increases continuously, then an oncoming vehicle in the vehicle's forward blind spot is determined.

[0050] In one embodiment, the blind spot vehicle detection method further includes: The ground monitoring area is divided into multiple windows. Each window includes at least one pixel.

[0051] Determine the illuminance increment of the windows within the ground monitoring area.

[0052] Based on the illuminance increment of the windows within the ground monitoring area, determine the concentrated area of ​​illuminance increment within the ground monitoring area.

[0053] Step S5 includes: if the position of the concentrated area of ​​illuminance increment in the forward image of a time-adjacent frame changes, then an oncoming vehicle in the vehicle's forward blind spot is determined. Specifically, if the concentrated area of ​​illuminance increment in the forward image of a time-adjacent frame moves towards the center of the ground monitoring area, then an oncoming vehicle in the vehicle's forward blind spot is determined.

[0054] In one embodiment, if the difference between the rate of change of the position of the concentrated area of ​​illumination increment in the forward image of consecutive frames and the vehicle's speed is greater than a preset speed difference value, then an oncoming vehicle is determined to be in the vehicle's forward blind spot.

[0055] In one embodiment, the blind spot vehicle detection method further includes: dividing the ground monitoring area in the forward image into a left area and a right area.

[0056] Determine the illuminance of the left and right regions.

[0057] If the difference in illuminance between the left and right sides of the vehicle exceeds a preset illuminance diffusion value, an oncoming vehicle is identified in the vehicle's blind spot. This eliminates interference from the vehicle's own headlights and ambient light, resulting in higher accuracy. Specifically, an oncoming vehicle in the vehicle's blind spot can be identified when at least one of the above conditions is met.

[0058] Because the headlights of the vehicle and oncoming vehicles overlap in the ground monitoring area, it is difficult to determine the oncoming vehicle's direction of travel by separating the area, direction of movement, and gradient distribution of the oncoming vehicle's light spot characteristics. The vehicle control method of this application indirectly determines whether there is an oncoming vehicle in the vehicle's blind spot by using the area illuminance increment, thus achieving more accurate differentiation between the vehicle's headlights and oncoming vehicle headlights.

[0059] In step S6, if a vehicle approaches from the vehicle's blind spot, the vehicle's warning device is activated to issue a warning message. This warning message may include, but is not limited to, at least one of visual, auditory, and tactile cues. When the warning message is visual, the warning device may include, but is not limited to, the instrument panel or the central control screen. When the warning message is auditory, the warning device may include, but is not limited to, an alarm. When the warning message is tactile, the warning device may include, but is not limited to, a seat vibration device or a steering wheel vibration device.

[0060] In one embodiment, the method for determining oncoming vehicles in the blind spot includes: The rate of change of the regional illuminance increment is determined based on the regional illuminance increment of the ground monitoring area in two adjacent frames of the foreground image and the interval acquisition time of the vehicle's camera.

[0061] Step S6 includes: if the rate of change of the area illuminance increment is less than a first preset value, then the vehicle's warning device issues a first warning message. In one embodiment, the first warning message may indicate that the oncoming vehicle is far away.

[0062] If the rate of change of the area's illuminance increment is not less than a second preset value, the vehicle's warning device issues a second warning message. In one embodiment, the second warning message may indicate that an approaching vehicle is close. The second preset value may be greater than or equal to a first preset value. This allows for tiered warnings, enabling the determination of the approaching vehicle's distance and improving safety.

[0063] The blind spot vehicle detection method provided in this application includes determining the regional illuminance increment of the ground monitoring area based on the difference between the current total illuminance and the current illuminance of the vehicle itself. Based on this regional illuminance increment, it is determined whether a vehicle is approaching in front of the vehicle's blind spot. Thus, by determining whether a vehicle is approaching in front of the vehicle through changes in the regional illuminance of the ground monitoring area, the method is less affected by surrounding obstacles, resulting in higher detection accuracy.

[0064] Figure 5 The diagram shown is a frame schematic of a vehicle according to one embodiment of this application. See also... Figure 5 As shown, this application embodiment also provides a vehicle 100, which includes a processor 101 and a memory 102 communicatively connected to the processor 101. The memory 102 is used to store computer-executable instructions. The processor 101 executes the computer-executable instructions stored in the memory 102 to implement the blind spot vehicle determination method described in any of the above embodiments.

[0065] This application also provides a readable storage medium storing computer-executable instructions, which, when executed by processor 101, are used to implement the blind spot vehicle determination method as described in any of the above embodiments.

[0066] This application also provides a computer program product, including a computer program / instruction, which, when executed by processor 101, implements the blind spot vehicle determination method as described in any of the above embodiments.

[0067] This application also provides a computer program stored in a readable storage medium, and when the processor 101 executes the computer program, it causes the processor 101 to perform the blind spot vehicle determination method as described in any of the above embodiments.

[0068] This application may take the form of a computer program product implemented on one or more readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of readable storage media include, but are not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0069] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for determining oncoming vehicles in a blind spot, characterized in that, include: Acquire real-time images of the vehicle's front; When a blind spot exists in front of the vehicle, at least a portion of the ground area in the image ahead is identified as a ground monitoring area; Determine the current total illuminance and the current vehicle illuminance of the ground monitoring area; wherein, the current vehicle illuminance represents the illuminance formed in the ground monitoring area when the vehicle's headlights illuminate the ground; Based on the difference between the current total illuminance and the current illuminance of the vehicle, the regional illuminance increment of the ground monitoring area is determined; The ground monitoring area is divided into multiple windows; each window includes at least one pixel; based on the illuminance increment of the windows within the ground monitoring area, the concentrated area of ​​illuminance increment within the ground monitoring area is determined. Based on the increase in illuminance in the area, determine whether there is an oncoming vehicle in the blind spot in front of the vehicle; The step of determining whether a vehicle is approaching in the blind spot ahead of the vehicle based on the regional illuminance increment includes: if the position of the concentrated area of ​​illuminance increment in the front image of adjacent time frames changes, and the difference between the position change rate of the concentrated area of ​​illuminance increment in the front image of consecutive frames and the vehicle's driving speed is greater than a preset speed difference value, then it is determined that a vehicle is approaching in the blind spot ahead of the vehicle. If a vehicle approaches from the vehicle's blind spot, the vehicle's warning device will issue a warning message.

2. The method for determining oncoming vehicles in blind spots according to claim 1, characterized in that, The method for determining vehicles approaching from the blind spot also includes: Determine the initial total illuminance and the initial illuminance of the vehicle in the ground monitoring area in the forward image; The initial ambient illuminance is determined based on the initial total illuminance and the initial illuminance of the vehicle itself. The step of determining the regional illuminance increment of the ground monitoring area based on the difference between the current total illuminance and the current illuminance of the vehicle includes: The regional illuminance increment of the ground monitoring area is determined based on the difference between the current total illuminance, the current illuminance of the vehicle, and the initial ambient illuminance.

3. The method for determining oncoming vehicles in blind spots according to claim 1, characterized in that, Determining the current illuminance of the vehicle includes: Based on the center position of the ground monitoring area in the forward image and the camera parameters of the vehicle, determine the actual horizontal distance from the vehicle's camera to the center of the ground monitoring area; The current illuminance of the vehicle is determined based on the actual horizontal distance and the vehicle's headlight parameters.

4. The method for determining oncoming vehicles in blind spots according to claim 3, characterized in that, The step of determining the actual horizontal distance from the vehicle's camera to the center of the ground monitoring area based on the center position of the ground monitoring area in the forward image and the vehicle's camera parameters includes: The actual horizontal distance from the vehicle's camera to the center of the ground monitoring area is determined by the following formula. : ， in, The installation height of the camera is [height]. The vertical tilt angle corresponding to the center pixel of the ground monitoring area; The vertical tilt angle corresponding to the center pixel of the ground monitoring area is determined by the following formula. : ， in, The pitch angle of the camera. The pixel row at the center of the ground monitoring area. The optical center of the camera is the pixel row in the front image. It is half the vertical angle of view of the camera. The image height is the height of the foreground image.

5. The method for determining oncoming vehicles in blind spots according to claim 3, characterized in that, Determining the current illuminance of the vehicle based on the actual horizontal distance and the vehicle's headlight parameters includes: The current illuminance of this vehicle is determined by the following formula. : ， in, The rated luminous intensity of the vehicle's headlights, The installation height of the vehicle's headlights. This refers to the actual horizontal distance.

6. The method for determining oncoming vehicles in blind spots according to claim 1, characterized in that, Determining the current total illuminance of the ground monitoring area includes: Extract the brightness of pixels within the ground monitoring area in the forward image; The current total illuminance of the ground monitoring area is determined based on the average brightness of multiple pixels within the ground monitoring area.

7. The method for determining oncoming vehicles in blind spots according to claim 1, characterized in that, Determining whether a vehicle is approaching in the blind spot ahead of the vehicle based on the regional illuminance increment includes: Compare the regional illuminance increment of the foreground image with the preset illuminance increment value; If the illuminance increment of the area in the forward image for a consecutive set number of frames is greater than the preset illuminance increment value, then an oncoming vehicle is determined to be in the vehicle's forward blind spot; and / or, The method for determining vehicles approaching from the blind spot also includes: The ground monitoring area in the frontal image is divided into a left area and a right area; Determine the illuminance of the left-side region and the illuminance of the right-side region; If the difference between the illuminance of the left-side region and the illuminance of the right-side region is greater than a preset illuminance diffusion value, then an oncoming vehicle is determined to be in the vehicle's blind spot.

8. The method for determining oncoming vehicles in blind spots according to claim 1, characterized in that, Determining that at least a portion of the ground area in the forward image is a ground monitoring area includes: Determine the location of the blind spot features in the front image that form the blind spot; If the blind spot feature is located on the left side of the image ahead, then the rightmost point of the contact point between the blind spot feature and the ground is taken as the starting point, and the area extends along directions perpendicular to and parallel to the vehicle's driving road, and in directions away from the blind spot feature, to form the ground monitoring area. If the blind spot feature is located on the right side of the image ahead, then the leftmost point of the contact point between the blind spot feature and the ground is taken as the starting point, and the area extends along directions perpendicular to and parallel to the vehicle's driving road, and in directions away from the blind spot feature, to form the ground monitoring area.

9. A vehicle, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory is used to store computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the blind spot vehicle determination method as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that, The readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the blind spot vehicle determination method as described in any one of claims 1 to 8.

Images