Highway visibility monitoring method, device, equipment, storage medium and system

Abstract

The present application discloses a highway visibility monitoring method, device, equipment, storage medium and system, the method comprising: determining whether a first static target within the camera field of view is detected by the camera; the first static target corresponds to a first visibility; if the first static target is not detected by the camera, determining a second static target that the camera can detect within the camera field of view; the second static target corresponds to a second visibility, the second visibility is less than the first visibility, and is greater than the visibility corresponding to other static targets that the camera can detect within the camera field of view; determining a visibility range based on the second visibility and other preset visibility; within the visibility range, detecting a passing vehicle through the camera, and when the camera detects that the passing vehicle disappears, determining a measured distance between the passing vehicle and the camera through a radar; and using the measured distance as the visibility of the highway. The present application can accurately determine visual visibility.

Description

Technical Field

[0001] The present application relates to the field of visibility monitoring, and in particular to a method, device, equipment, storage medium and system for monitoring highway visibility. Background Art

[0002] The main reason for serious and major traffic accidents caused by bad weather on highways is the reduced visibility. The driving sight distance is shortened in low visibility environment, and the identification effect of variable information boards, signs, markings and other traffic safety facilities is poor. Especially when fog occurs, it is very easy to cause traffic accidents such as chain rear-end collisions.

[0003] In view of the above reasons, relevant departments have introduced visibility meters based on laser technology on highways to monitor visibility. However, the visibility meter based on laser technology actually samples and analyzes a small group of air around the instrument, and the visibility value calculated by the sampling analysis represents the visibility value of the entire large-scale area. However, relying solely on the visibility value of the air around the instrument to represent the visibility value of the entire large-scale area has low accuracy. In addition, the visibility meter is based on the principle of light scattering and calculates the extinction coefficient to obtain the optical visibility value. The optical visibility value is different from the visual visibility value of the human eye. As a result, the visibility value measured by the visibility meter cannot accurately reflect the visual visibility value of the human eye.

[0004] That is, there is a technical problem in the prior art that it is difficult to accurately determine the visual visibility value. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a highway visibility monitoring method, device, equipment, storage medium and system, which aim to solve the technical problem that it is difficult to accurately determine the visual visibility value.

[0006] The present application provides a method for monitoring road visibility, the method comprising:

[0007] Determining whether a first static target within a camera field of view is detected by the camera, wherein the first static target corresponds to a first visibility;

[0008] If the first static target is not detected by the camera, determining a second static target that can be detected by the camera within the camera field of view; wherein the second static target corresponds to a second visibility, the second visibility is smaller than the first visibility, and is larger than the visibility corresponding to other static targets that can be detected by the camera within the camera field of view;

[0009] Determining a visibility range based on the second visibility and other preset visibilities;

[0010] Within the visibility range, detecting a passing vehicle by the camera, and determining a measured distance between the passing vehicle and the camera by radar when the camera detects that the passing vehicle disappears;

[0011] The measured distance is used as the visibility of the road.

[0012] In a possible implementation manner of the present application, the method further includes:

[0013] Pre-calibrating calibration lines corresponding to various static targets within the field of view of the camera;

[0014] According to the correspondence between the static target detected by the camera and the calibration line, it is determined that the static target detected by the camera is the first static target or the second static target.

[0015] In a possible implementation manner of the present application, the detecting a passing vehicle by the camera within the visibility range includes:

[0016] Detecting by radar whether there is a vehicle passing within the visibility range;

[0017] When the radar detects that a vehicle passes within the visibility range, the camera detects the passing vehicle under preset shooting parameters corresponding to the visibility range.

[0018] In a possible implementation manner of the present application, the camera detects that the passing vehicle disappears, including:

[0019] The camera detects the rear or back contour of the passing vehicle;

[0020] When the camera detects that the rear or back outline of the vehicle disappears, it is determined that the camera detects that the passing vehicle disappears.

[0021] In a possible implementation manner of the present application, when the camera detects that the passing vehicle disappears, the step of determining the measured distance between the passing vehicle and the camera by the radar includes:

[0022] When the camera detects that the passing vehicle disappears, the radar determines the measured distances between the passing vehicle and the camera to obtain a plurality of measured distances;

[0023] Wherein, the step of using the measured distance as the visibility of the road comprises:

[0024] An average of the multiple measured distances is determined, and the average is used as the visibility of the road.

[0025] The present application also provides a highway visibility monitoring device, the device comprising:

[0026] A first determination module, used to determine whether a first static target within the camera field of view is detected by the camera; wherein the first static target corresponds to a first visibility;

[0027] a second determination module, configured to determine a second static target that can be detected by the camera within the camera field of view if the first static target is not detected by the camera; wherein the second static target corresponds to a second visibility that is smaller than the first visibility and larger than the visibility corresponding to other static targets that can be detected by the camera within the camera field of view;

[0028] A third determining module, configured to determine a visibility range based on the second visibility and other preset visibilities;

[0029] a fourth determination module, configured to detect a passing vehicle by the camera within the visibility range, and determine a measured distance between the passing vehicle and the camera by radar when the camera detects that the passing vehicle disappears;

[0030] A setting module is used to use the measured distance as the visibility of the road.

[0031] In a possible implementation manner of the present application, the highway visibility monitoring device further includes: the device further includes: a calibration module, used to pre-calibrate calibration lines corresponding to each static target within the field of view of the camera; a fifth determination module, used to determine whether the static target detected by the camera is the first static target or the second static target according to the correspondence between the static target detected by the camera and the calibration lines;

[0032] And / or, the fourth determination module further includes: a first detection unit, configured to detect whether a vehicle passes within the visibility range by using a radar; a second detection unit, configured to detect the passing vehicle by using the camera under preset shooting parameters corresponding to the visibility range when the radar detects that a vehicle passes within the visibility range;

[0033] And / or, the fourth determination module further includes: the camera detecting the rear or back outline of the passing vehicle; a first determination unit, configured to determine that the camera detects that the passing vehicle disappears when the camera detects that the rear or back outline disappears;

[0034] And / or, the fourth determination module also includes: a second determination unit, used to determine the measured distance between the passing vehicle and the camera respectively by the radar when the camera detects that the passing vehicle disappears, so as to obtain multiple measured distances; wherein the setting module includes: a third determination unit, used to determine the average of the multiple measured distances, and use the average as the visibility of the highway.

[0035] The present application also provides a highway visibility monitoring device, which is a physical node device. The highway visibility monitoring device includes: a memory, a processor, and a program of the highway visibility monitoring method stored in the memory and executable on the processor. When the program of the highway visibility monitoring method is executed by the processor, the steps of the highway visibility monitoring method as described above can be implemented.

[0036] In order to achieve the above-mentioned purpose, a storage medium is further provided, on which a highway visibility monitoring program is stored. When the highway visibility monitoring program is executed by a processor, the steps of any of the above-mentioned highway visibility monitoring methods are implemented.

[0037] The present application also provides a system, which includes: a camera, a radar, and the highway visibility monitoring device described in any one of the above items.

[0038] The present application provides a highway visibility monitoring method, device, equipment, storage medium and system, which determine whether a first static target within a camera's field of view is detected by the camera, wherein the first static target corresponds to a first visibility; if the first static target is not detected by the camera, it means that the visibility at this time is lower than the first visibility, and it is necessary to accurately determine the specific visibility, then determine a second static target that the camera can detect within the camera's field of view; wherein the second static target corresponds to a second visibility, the second visibility is less than the first visibility, and is greater than the visibility corresponding to other static targets that the camera can detect within the camera's field of view; determine a visibility range based on the second visibility and other preset visibilities; and then accurately determine the specific visibility within the visibility range, specifically, within the visibility range, detect a passing vehicle by the camera, and when the camera detects that the passing vehicle disappears, determine the measured distance between the passing vehicle and the camera by radar; and use the measured distance as the visibility of the highway. Compared with the prior art in which the visibility value of a small group of air around the instrument represents the visibility value of the entire large area, the determination of visibility is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1A schematic diagram of a flow chart of a first embodiment of a method for monitoring highway visibility in the present application;

[0040] Figure 2 This is a detailed flow chart of step S30 in the first embodiment of the highway visibility monitoring method of the present application;

[0041] Figure 3 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application;

[0042] Figure 4 This is a schematic diagram of the first scenario involved in the highway visibility monitoring method of this application;

[0043] Figure 5 A schematic diagram of a second scenario involved in the highway visibility monitoring method of this application;

[0044] Figure 6 This is a schematic diagram of the entire process involved in the highway visibility monitoring method of this application;

[0045] Figure 7 This is a schematic diagram of the third scenario involved in the highway visibility monitoring method of this application. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The present application embodiment provides a highway visibility monitoring method. In one embodiment of the highway visibility monitoring method of the present application, the method is applied to a highway visibility monitoring device, referring to Figure 1 , the method comprising:

[0048] Step S10, determining whether a first static target within the field of view of a camera is detected by the camera, wherein the first static target corresponds to a first visibility;

[0049] Step S20, if the first static target is not detected by the camera, determining a second static target that the camera can detect within the camera field of view; wherein the second static target corresponds to a second visibility, the second visibility is smaller than the first visibility, and is larger than the visibility corresponding to other static targets that the camera can detect within the camera field of view;

[0050] Step S30, determining a visibility range based on the second visibility and other preset visibilities;

[0051] Step S40, within the visibility range, detecting a passing vehicle by the camera, and when the camera detects that the passing vehicle disappears, determining a measured distance between the passing vehicle and the camera by radar;

[0052] Step S50: using the measured distance as the visibility of the road.

[0053] The present embodiment aims to: improve the detection accuracy of road visibility.

[0054] Specifically, in the present application, the visibility range is determined by detecting different static targets within the field of view of the camera, and then the visibility is further determined. Compared with the prior art in which the visibility value of a small group of air around the instrument represents the visibility value of the entire large area, the visibility is determined more accurately. In addition, in the present application, it is first determined whether a first static target within the field of view of the camera is detected by the camera. If the first static target is not detected by the camera, it is determined whether the camera can detect a second static target within the field of view of the camera (the first static target corresponds to the first visibility, the second static target corresponds to the second visibility, the second visibility is less than the first visibility, and greater than the visibility that the camera can detect within the field of view of the camera). The visibility corresponding to other static targets of the highway is determined based on the second visibility and other preset visibility, and then the visibility range is determined based on the second visibility and other preset visibility; within the visibility range, the passing vehicle is detected by the camera, thereby narrowing the range for accurately obtaining the visibility. In addition, when the camera detects that the passing vehicle disappears, the measured distance between the passing vehicle and the camera is determined by radar, and the measured distance is used as the visibility of the highway. That is, in the present application, the camera visibility value is closer to the visual visibility value of the human eye, and the visibility of the highway is determined by combining video and radar perception technology (when the camera visibility value is close to the visual visibility value of the human eye, it is difficult to accurately determine the measured distance only by the camera), so as to accurately determine the visual visibility value that is closer to the human sense organ.

[0055] As an example, the highway visibility monitoring method may be applied to a highway visibility monitoring system, the system comprising a camera and a radar, and a highway visibility monitoring device;

[0056] As an example, the highway visibility monitoring device may be built into a camera, or built into a radar, or independent of a camera and a radar.

[0057] As an example, the highway may be an expressway, a national highway, a provincial highway, etc., without specific limitation.

[0058] As an example, the camera may be a color camera, a black and white camera, a standard definition camera, a high definition camera, etc., without limitation.

[0059] As an example, the camera is installed in a rear-facing manner, that is, the camera is installed facing the direction of the vehicle, and the rear or back contour of the vehicle can be detected when identifying the vehicle, such as Figure 4 shown.

[0060] As an example, the radar may be an over-the-horizon radar, a microwave radar, a millimeter-wave radar, a laser radar, etc.

[0061] As an example, the radar may also be a pulse radar, a continuous wave radar, a pulse compression radar, a frequency agile radar, and the like.

[0062] As an example, Figure 4 As shown, the radar and the camera can be mounted on the same vertical pole (with the same longitude and latitude), or the radar and the camera can be mounted on different vertical poles (with different longitude and latitude).

[0063] The specific steps are as follows:

[0064] Step S10, determining whether a first static target within the field of view of a camera is detected by the camera, wherein the first static target corresponds to a first visibility;

[0065] As an example, when a highway visibility monitoring instruction is detected, it is determined whether the first static target within the camera field of view is detected by the camera. The highway visibility monitoring instruction may be triggered in various scenarios, and the various scenarios may specifically be scenarios under different weather conditions, scenarios under different lighting conditions, etc. Different weather conditions may be sunny, rainy, or cloudy; different lighting conditions may be strong sunlight conditions, weak sunlight conditions, or night conditions, etc., without specific limitation.

[0066] As an example, the highway visibility monitoring instruction may be triggered at a fixed time or based on a set visibility monitoring frequency. As an example, the set visibility monitoring frequency may be 5 minutes / time. As an example, the set visibility monitoring frequency may be modified according to different scenarios.

[0067] As an example, determining whether the first static target within the camera field of view is detected by the camera, wherein the first static target corresponds to the first visibility, may be: determining whether the lane line (i.e., the first static target) at 500m within the camera field of view is detected by the camera, wherein the lane line at 500m corresponds to the visibility (500m). There are also lane lines less than 500m within the camera field of view, such as 200m, 100m, and 50m, corresponding to the visibility of 200m, 100m, and 50m, respectively.

[0068] Step S20, if the first static target is not detected by the camera, then determine the second static target that the camera can detect within the field of view of the camera; wherein the second static target corresponds to a second visibility, the second visibility is less than the first visibility, and is greater than the visibility corresponding to other static targets that the camera can detect within the field of view of the camera; continuing with the above example, step S20 may be: if the lane line at 200m within the field of view of the camera can be detected by the camera, then determine that the lane line at 200m is the second static target, and the second visibility is 200m at this time; if the lane line at 200m within the field of view of the camera cannot be detected by the camera, but the lane line at 100m can be detected by the camera, then determine that the lane line at 100m is the second static target, and the second visibility is 10m at this time; and so on.

[0069] Step S30, determining a visibility range based on the second visibility and other preset visibilities;

[0070] As an example, if the first static target is not detected by the camera, the visibility inspection mode is entered, including the above steps S20 and S30.

[0071] As an example, the visibility range is determined to be a range between the second visibility and the third visibility, wherein the third visibility is the minimum visibility among the visibilities corresponding to other static targets detectable within the field of view of the camera and greater than the second visibility.

[0072] As an example, if the second static target is a static target at 0m (such as a lane line) and the second visibility is 0m, the visibility range is 0m-50m. (50m is the minimum visibility greater than the second visibility among the preset other visibility of 50m, 100m, 200m, and 500m).

[0073] As an example, if the second static target is a static target (such as a lane line) at 50m, and the second visibility is 50m, the visibility range is 50m-100m. (100m is the minimum visibility greater than the second visibility among the preset other visibility of 100m, 200m, and 500m).

[0074] As an example, if the second static target is a static target (such as a lane line) at 100m, and the second visibility is 100m, then the visibility range is 100m-200m. (200m is the minimum visibility greater than the second visibility among the preset other visibility of 200m and 500m).

[0075] As an example, if the second static target is a static target (such as a lane line) at 200m, and the second visibility is 200m, then the visibility range is 200m-500m. (500m is the minimum visibility greater than the second visibility among the preset other visibility of 500m).

[0076] Step S30, within the visibility range, detecting a passing vehicle by the camera, and when the camera detects that the passing vehicle disappears, determining a measured distance between the passing vehicle and the camera by radar;

[0077] Within the visibility range, detecting a passing vehicle by the camera, and determining a measured distance between the passing vehicle and the camera by the radar when the camera detects that the passing vehicle disappears;

[0078] Among them, the radar generally detects the distance between the vehicle and the radar, and the positional relationship between the radar and the camera is certain. Therefore, the distance between the vehicle and the camera can be determined based on the distance between the vehicle and the radar and the positional relationship between the radar and the camera.

[0079] In the visibility inspection mode, within the visibility range (e.g., within 200m-500m), the camera detects passing vehicles, and when the camera detects that the passing vehicle disappears, the radar determines the measured distance between the passing vehicle and the camera.

[0080] In this embodiment, the camera is used as a tool for measuring distance, which itself has inaccuracies.

[0081] Specifically, since the camera uses different camera parameters under different visibility ranges, that is, the camera changes the camera parameters, frequent changes in the camera parameters make it difficult to accurately determine the relationship between the current camera parameters and the measurement distance. Furthermore, it is difficult to accurately determine the measurement distance based on the camera (the camera needs to clearly determine the measurement distance). At this time, it is necessary to combine with the radar to determine the measurement distance between the vehicle and the camera.

[0082] Furthermore, in this embodiment, compared to measuring visibility with only a camera, that is, compared to detecting visibility with pure video, the radar is combined with the camera, that is, the radar and video are combined to determine the precise distance between the corresponding vehicle and the camera through radar data when the vehicle disappears, which is more reliable than the distance output by a single video.

[0083] Furthermore, using only cameras to monitor visibility, that is, pure video for visibility monitoring must adopt target detection technology for accurate detection of vehicles. However, in scenes with insufficient light at night, pure video cannot accurately detect the precise distance between the vehicle and the camera (this is because the current camera settings can detect whether the vehicle disappears or not, but cannot achieve the accuracy of detecting the distance). Radar can avoid such problems.

[0084] like Figure 2 As shown, within the visibility range, detecting a passing vehicle by the camera includes:

[0085] Step S31, detecting by radar whether there is a vehicle passing within the visibility range;

[0086] Step S32, when the radar detects that a vehicle passes within the visibility range, the camera detects the passing vehicle under preset shooting parameters corresponding to the visibility range.

[0087] In this embodiment, the research and development background is:

[0088] Existing video cameras have different camera parameters, some of which are very different from the visual visibility values ​​of human sense organs. Therefore, it is necessary to adjust the camera parameters to accurately determine the visual visibility values ​​that are closer to human sense organs. Specifically, it is necessary to adjust the camera parameters accordingly according to the visibility range of the camera to accurately determine the visual visibility values ​​that are closer to human sense organs.

[0089] In this embodiment, the radar is used to detect whether a vehicle passes within the visibility range. When the radar detects that a vehicle passes within the visibility range, the camera is used to detect the passing vehicle under preset shooting parameters corresponding to the visibility range. For example, the preset shooting parameters are preset optimal shooting parameters (shooting parameters that are closest to human senses).

[0090] As an example, the visibility range is 200m-500m, and the shooting parameters of the camera are adjusted to the first preset shooting parameters (first optimal shooting parameters) within the range of 200m-500m.

[0091] As an example, the visibility range is 100m-200m, and the shooting parameters of the camera are adjusted to the second preset shooting parameters (second optimal shooting parameters) within the range of 100m-200m.

[0092] As an example, the visibility range is 50m-100m, and the shooting parameters of the camera are adjusted to the third preset shooting parameters (third optimal shooting parameters) within the range of 50m-100m.

[0093] Under the preset shooting parameters, when the camera detects that the passing vehicle disappears, the measured distance between the passing vehicle and the camera is determined by the radar.

[0094] In this embodiment, when the camera detects that the passing vehicle disappears under the preset shooting parameters, the radar is used to determine the measured distance between the passing vehicle and the camera. Therefore, within various visibility ranges, a visual visibility value that is closer to human senses can be accurately determined.

[0095] Wherein, when the camera detects that the passing vehicle disappears, the step of determining the measured distance between the passing vehicle and the camera by radar comprises:

[0096] Step A1, under preset shooting parameters, when the camera detects that a vehicle passing on the road disappears, associating the disappeared vehicle detected by the camera with the vehicle detected by the radar;

[0097] Step A2, after association, determining the measured distance between the passing vehicle and the camera by the radar;

[0098] When the camera detects a vehicle within the visibility range, if the minimum pixel of the detected vehicle meets a preset detection requirement, it is determined that the vehicle has disappeared.

[0099] In this embodiment, the camera is set with a minimum pixel requirement for detecting vehicles within the visibility range;

[0100] As an example, the minimum pixel requirement for a vehicle detected by a camera within the visibility range is 200*200.

[0101] As an example, if the minimum pixel requirement of a vehicle detected by the camera in different visibility ranges is lower than 200*200, the camera determines that the vehicle disappears in the visibility range.

[0102] When the camera detects that the passing vehicle disappears, a measured distance between the passing vehicle and the camera is determined by the radar.

[0103] In this embodiment, a mapping relationship is established between radar coordinates and camera coordinates. Therefore, when the camera detects a vehicle on the road, it can be found by the radar based on the mapping relationship. Specifically, the camera detects a vehicle passing on the road through the rear profile of the vehicle. Based on the mapping relationship, the same vehicle can be found by the radar at the same time. Based on this, the distance detected by the radar can be determined as visibility.

[0104] Step S40: Using the measured distance as the visibility of the road.

[0105] In this embodiment, the measured distance between the vehicle and the camera measured by the radar is used as the visibility of the road.

[0106] Wherein, when the camera detects that the passing vehicle disappears, the step of determining the measured distance between the passing vehicle and the camera by the radar comprises:

[0107] When the camera detects that the passing vehicle disappears, the radar determines the measured distances between the passing vehicle and the camera to obtain a plurality of measured distances;

[0108] Wherein, the step of using the measured distance as the visibility of the road comprises:

[0109] An average of the multiple measured distances is determined, and the average is used as the visibility of the road.

[0110] In this embodiment, the average of multiple measured distances is determined and used as the visibility of the road, that is, the average value of the distances when multiple vehicles disappear is taken as the visibility value to avoid errors caused by accidental factors.

[0111] The present application provides a method, device, equipment, storage medium and system for monitoring visibility of a highway. Compared with the current visibility meter based on laser technology that monitors visibility, which makes it difficult to accurately determine the visual visibility value, in the present application, it is determined whether a first static target within the field of view of a camera is detected by the camera, wherein the first static target corresponds to a first visibility; if the first static target is not detected by the camera, a second static target that can be detected by the camera within the field of view of the camera is determined; wherein the second static target corresponds to a second visibility, the second visibility is less than the first visibility, and is greater than the visibility corresponding to other static targets that can be detected by the camera within the field of view of the camera; based on the second visibility and other preset visibility, a visibility range is determined; within the visibility range, a passing vehicle is detected by the camera, and when the camera detects that the passing vehicle disappears, a measured distance between the passing vehicle and the camera is determined by a radar; and the measured distance is used as the visibility of the highway. In the present application, the visibility range is determined by detecting different static targets within the field of view of the camera, and then the visibility is further determined. Compared with the prior art in which the visibility value of a small group of air around the instrument represents the visibility value of the entire large area, the visibility is determined more accurately. In addition, in the present application, it is first determined whether a first static target within the field of view of the camera is detected by the camera. If the first static target is not detected by the camera, a second static target that can be detected by the camera within the field of view of the camera is determined (the first static target corresponds to the first visibility, the second static target corresponds to the second visibility, the second visibility is smaller than the first visibility, and larger than the other static targets that can be detected by the camera within the field of view of the camera). The method further comprises the following steps: first, determining a visibility range based on the second visibility and other preset visibilities; second, determining a passing vehicle by the camera within the visibility range, thereby narrowing the range for accurately obtaining visibility; and third, determining a measured distance between the passing vehicle and the camera by radar when the camera detects that the passing vehicle has disappeared, and using the measured distance as the visibility of the highway. That is, in the present application, the camera visibility value is closer to the visual visibility value of the human eye, and the video and radar perception technologies are combined (when the camera visibility value is close to the visual visibility value of the human eye, it is difficult to accurately determine the measured distance by the camera alone) to determine the visibility of the highway, so as to accurately determine a visual visibility value that is closer to the human sense organ.

[0112] Further, based on the first embodiment of the present application, another embodiment of the present application is provided. In this embodiment, the method further includes:

[0113] Step S60, pre-calibrating calibration lines corresponding to each static target within the field of view of the camera;

[0114] As an example, a 0m calibration line corresponding to the lane line at 0m is pre-calibrated within the field of view of the camera; (continuing the above example, a 50m calibration line corresponding to the lane line at 50m, a 100m calibration line corresponding to the lane line at 100m, a 200m calibration line corresponding to the lane line at 200m, and a 500m calibration line corresponding to the lane line at 500m can also be pre-calibrated).

[0115] As an example, Figure 7 As shown, the lengths of lane line A and lane line B are determined and known (unified standards for national highways). Therefore, based on lane line A, lane line B, and the pixel coordinate system inside the camera, the lane line at 50m, the lane line at 100m, the lane line at 200m, the lane line at 500m, etc. can be determined. Furthermore, the camera calibrates the distance lines at the lane lines at 50m, 100m, 200m, 500m, etc. to obtain the calibration lines.

[0116] Step S70: determining whether the static target detected by the camera is the first static target or the second static target according to the correspondence between the static target detected by the camera and the calibration line.

[0117] According to the correspondence between the static targets detected by the camera and the calibration lines (the correspondence between the lane line at 0m and the 0m calibration line, the correspondence between the lane line at 50m and the 50m calibration line, the correspondence between the lane line at 100m and the 100m calibration line, the correspondence between the lane line at 200m and the 200m calibration line, and the correspondence between the lane line at 500m and the 500m calibration line), it is determined that the static target detected by the camera is the first static target or the second static target.

[0118] like Figure 7 As shown, as an example, the static target detected by the camera at the 500m calibration line is the first static target;

[0119] As an example, the static target detected by the camera 200m calibration line is the second static target.

[0120] In this embodiment, calibration lines corresponding to various static targets are pre-calibrated within the field of view of the camera; and according to the correspondence between the static targets detected by the camera and the calibration lines, it is determined that the static target detected by the camera is the first static target or the second static target. In this embodiment, accurately determining the first static target or the second static target lays the foundation for accurately determining visibility.

[0121] Further, based on the first embodiment of the present application, another embodiment of the present application is provided. In this embodiment, the camera detects that the passing vehicle disappears, including:

[0122] Step B1, the camera detects the rear or back outline of the passing vehicle; when the camera detects that the rear or back outline of the vehicle disappears, it is determined that the camera detects that the passing vehicle disappears.

[0123] In this embodiment, the application scenario may be:

[0124] Bad weather on highways can easily cause serious or major traffic accidents, and at night, due to the added darkness, drivers' ability to distinguish is even worse, which can easily lead to traffic accidents such as chain rear-end collisions. Therefore, how to accurately determine visibility at night is a technical problem that needs to be solved urgently.

[0125] In this embodiment, the camera detects the rear or back outline of the passing vehicle; when the camera detects that the rear or back outline disappears, it is determined that the camera has detected that the passing vehicle has disappeared; when the camera detects that the passing vehicle has disappeared, the measured distance between the passing vehicle and the camera is determined by radar, thereby accurately detecting nighttime visibility (nighttime visibility refers to the maximum horizontal distance at which a preset medium-intensity light source can be identified).

[0126] That is, in this embodiment, it should be emphasized that when the camera detects that the rear or back outline of the vehicle disappears, it is determined that the camera detects that the passing vehicle disappears, and then, the measured distance (night visibility) between the passing vehicle and the camera is determined. That is, in this embodiment, the camera uses the light emitted by the taillights of the vehicle at night to detect visibility at night.

[0127] This is because: at night, due to the dark background, many vehicles need to turn on the high beam or headlights to drive, and turning on the high beam or headlights can easily cause the camera to be overexposed. In order to avoid the camera being overexposed, it is difficult to accurately determine the moment when the vehicle disappears, and thus, it is difficult to accurately determine visibility.

[0128] In this embodiment, it is important to emphasize that because the camera needs to accurately determine the moment when the vehicle disappears at night, it will accordingly consider the vehicle determined by the vehicle rear end detection method or the vehicle back outline detection method, and associate it with the vehicle detected by the radar (when the camera detects that the vehicle rear end or back outline disappears, it is determined that the camera detects that the passing vehicle disappears; when the camera detects that the passing vehicle disappears, the measured distance between the passing vehicle and the camera is determined by the radar).

[0129] In this embodiment, the camera is set with a minimum pixel requirement for detecting vehicles within the visibility range at night;

[0130] As an example, if a vehicle is detected by a camera within the visibility range at night, the minimum pixel requirement is 200*200.

[0131] As an example, if the minimum pixel requirement of a vehicle detected by the camera within the visibility range at night is less than 200*200, the camera determines that the vehicle disappears within the visibility range. Therefore, the measured distance between the vehicle and the camera can be determined based on the radar, thereby accurately determining the visibility.

[0132] In this embodiment, the camera detects the rear or back outline of the passing vehicle; when the camera detects that the rear or back outline of the vehicle disappears, it is determined that the camera detects that the passing vehicle disappears, thereby accurately determining nighttime visibility.

[0133] Further, based on the first embodiment and the second embodiment of the present application, another embodiment of the present application is provided. In this embodiment, after the step of detecting a passing vehicle by the camera within the visibility range, the method includes:

[0134] Step C1, if the camera does not detect a passing vehicle, return to the step of determining a second static target that the camera can detect within the camera field of view until the camera detects a passing vehicle.

[0135] In this embodiment, the research and development background is:

[0136] In bad weather, such as fog, visibility may fluctuate.

[0137] As an example, in foggy weather, the visibility on the road drops to 100m, then rises to 400m, then rises to 500m, and then drops to 300m. Therefore, after determining the visibility range (200m-500m), within the determined visibility range (due to visibility oscillation, the actual visibility range may be 100m-300m, which is different from the determined visibility range), it is possible that the camera has difficulty detecting passing vehicles within the determined visibility range (the pixels of a detected vehicle are lower than the minimum pixel requirement).

[0138] Therefore, in this embodiment, if the camera does not detect a passing vehicle, the process returns to the step of determining a second static target that the camera can detect within the camera field of view until the camera detects a passing vehicle.

[0139] In this embodiment, after reporting the visibility, the next detection cycle is waited for and the visibility detection is performed again.

[0140] In this embodiment, if the camera does not detect a passing vehicle, the process returns to the step of determining a second static target that the camera can detect within the camera field of view until the camera detects a passing vehicle. In this embodiment, the visibility of the highway is accurately monitored in a visibility oscillation scenario.

[0141] It should be noted that the highway visibility monitoring method in this embodiment can be applied to a highway visibility monitoring system, such as Figure 6 As shown in the figure, the whole process of visibility monitoring by the highway visibility monitoring system includes:

[0142] Step 1. The highway visibility monitoring system configures calibration lines for the camera (determines several calibration lines on the camera screen). Specifically, through static targets such as lane lines, roadside reflective signs, and additional luminous signs, determine several calibration lines on the camera screen (such as: calibration lines at 50m, 100m, 200m, 500m, etc.).

[0143] Step 2: The highway visibility monitoring system configures the optimal focal length and magnification (preset shooting parameters) for the range composed of continuous calibration lines (continuing the above example, such as 50m-100m, 100m-200m, 200m-500m), and sets the monitoring frequency (such as 5mins / time);

[0144] Step 3: The highway visibility monitoring system detects a static target (which may be the first static target) at the farthest calibration line (continuing the above example, 500 m).

[0145] Step 4. The highway visibility monitoring system detects whether the static target (which can be the first static target) at the farthest calibration line is identified. If not identified, it indicates that the visibility is less than 500m at this time, and it is necessary to accurately monitor the specific visibility value, then execute step 5. If it is identified, it indicates that the visibility is not less than 500m at this time, which meets the application scenario requirements, outputs the maximum visibility (the position of the farthest calibration line, such as the position of the farthest calibration line is 500m), and waits for the next detection cycle to perform another detection.

[0146] Step 5: When the radar determines that a vehicle is passing, the camera (video) detects the passing vehicle at the farthest calibration line (continuing the above example, 500m).

[0147] Step 6: The highway visibility monitoring system determines whether the camera detects a vehicle at the farthest calibration line. If not, execute step 7. If yes, output the farthest calibration line position (500m).

[0148] Step 7, enter the visibility inspection mode; determine the farthest visibility range through the farthest calibration line where the vehicle can be detected (for example, if the vehicle can be detected at 200m, the farthest visibility range is 200m-500m), and adjust the video image to the farthest visibility range according to the preset focal length and magnification, so that the minimum pixel of the vehicle within the camera's observation range meets the video target detection requirements.

[0149] Step 8: Wait for the radar to detect a vehicle. If the radar detects a vehicle, proceed to step 9.

[0150] Step 9: Can the camera (video) detect the vehicle? If so, associate it with the vehicle detected by the radar and execute step 10. If not, return to step 8.

[0151] Step 10: Determine the distance of the vehicle detected by the radar when the vehicle disappears, and take the average of multiple vehicle distances as the visibility value for reporting.

[0152] Reference Figure 3 , Figure 3 It is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application.

[0153] like Figure 3 As shown, the highway visibility monitoring device may include: a processor 1001 , a memory 1005 , and a communication bus 1002 . The communication bus 1002 is used to realize the connection and communication between the processor 1001 and the memory 1005 .

[0154] Optionally, the highway visibility monitoring device may further include a user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, a WiFi module, etc. The user interface may include a display screen (Display), an input submodule such as a keyboard (Keyboard), and the optional user interface may also include a standard wired interface and a wireless interface. The network interface may include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0155] Those skilled in the art will understand that Figure 3 The highway visibility monitoring device structure shown in the figure does not constitute a limitation on the highway visibility monitoring device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0156] like Figure 3 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module and a highway visibility monitoring program. The operating system is a program that manages and controls the hardware and software resources of the highway visibility monitoring device, and supports the operation of the highway visibility monitoring program and other software and / or programs. The network communication module is used to realize the communication between the components inside the memory 1005, and the communication with other hardware and software in the highway visibility monitoring system.

[0157] exist Figure 3 In the highway visibility monitoring device shown, the processor 1001 is used to execute the highway visibility monitoring program stored in the memory 1005 to implement the steps of any of the above-mentioned highway visibility monitoring methods.

[0158] The specific implementation of the highway visibility monitoring device of the present application is basically the same as the above-mentioned embodiments of the highway visibility monitoring method, and will not be repeated here.

[0159] The present application also provides a highway visibility monitoring device, the device comprising:

[0160] A first determination module, used to determine whether a first static target within the camera field of view is detected by the camera; wherein the first static target corresponds to a first visibility;

[0161] a second determination module, configured to determine a second static target that can be detected by the camera within the camera field of view if the first static target is not detected by the camera; wherein the second static target corresponds to a second visibility that is smaller than the first visibility and larger than the visibility corresponding to other static targets that can be detected by the camera within the camera field of view;

[0162] A third determining module, configured to determine a visibility range based on the second visibility and other preset visibilities;

[0163] a fourth determination module, configured to detect a passing vehicle by the camera within the visibility range, and determine a measured distance between the passing vehicle and the camera by radar when the camera detects that the passing vehicle disappears;

[0164] A setting module is used to use the measured distance as the visibility of the road.

[0165] In a possible implementation manner of the present application, the device further includes: a calibration module, configured to pre-calibrate calibration lines corresponding to each static target within the field of view of the camera; a fifth determination module, configured to determine, based on the correspondence between the static target detected by the camera and the calibration lines, whether the static target detected by the camera is the first static target or the second static target;

[0166] And / or, the fourth determination module further includes: a first detection unit, configured to detect whether a vehicle passes within the visibility range by using a radar; a second detection unit, configured to detect the passing vehicle by using the camera under preset shooting parameters corresponding to the visibility range when the radar detects that a vehicle passes within the visibility range;

[0167] And / or, the fourth determination module further includes: the camera detecting the rear or back outline of the passing vehicle; a first determination unit, configured to determine that the camera detects that the passing vehicle disappears when the camera detects that the rear or back outline disappears;

[0168] And / or, the fourth determination module also includes: a second determination unit, used to determine the measured distance between the passing vehicle and the camera respectively by the radar when the camera detects that the passing vehicle disappears, so as to obtain multiple measured distances; wherein the setting module includes: a third determination unit, used to determine the average of the multiple measured distances, and use the average as the visibility of the highway.

[0169] The specific implementation of the highway visibility monitoring device of the present application is basically the same as the various embodiments of the above-mentioned highway visibility monitoring method, and will not be repeated here.

[0170] An embodiment of the present application provides a storage medium, and the storage medium stores one or more programs, and the one or more programs can also be executed by one or more processors to implement the steps of any of the above-mentioned highway visibility monitoring methods.

[0171] The specific implementation method of the storage medium of the present application is basically the same as the above-mentioned embodiments of the highway visibility monitoring method, and will not be repeated here.

[0172] An embodiment of the present application provides a highway visibility monitoring system, the system comprising: a camera, a radar, and the highway visibility monitoring device according to any one of the above claims.

[0173] The specific implementation of the highway visibility monitoring system of the present application is basically the same as the various embodiments of the above-mentioned highway visibility monitoring method, and will not be repeated here.

[0174] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned highway visibility monitoring method when executed by a processor.

[0175] The specific implementation of the computer program product of the present application is basically the same as the various embodiments of the above-mentioned highway visibility monitoring method, and will not be repeated here.

[0176] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0177] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0178] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus hardware platform, or by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0179] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for monitoring highway visibility, characterized in that: Applied to a highway visibility monitoring system, the highway visibility monitoring system includes a camera and a radar, the camera is installed facing the direction of vehicle travel, and the method includes: Determining whether a first static target within a camera field of view is detected by the camera, wherein the first static target corresponds to a first visibility; If the first static target is not detected by the camera, determining a second static target that can be detected by the camera within the camera field of view; wherein the second static target corresponds to a second visibility, the second visibility is smaller than the first visibility, and is larger than the visibility corresponding to other static targets that can be detected by the camera within the camera field of view; Determine a visibility range based on the second visibility and the third visibility; wherein the third visibility is the minimum visibility among the visibilities corresponding to other static targets detectable within the field of view of the camera and greater than the second visibility; Determining, according to the visibility range, shooting parameters corresponding to the visibility range; Within the visibility range, detecting a passing vehicle by the camera under shooting parameters corresponding to the visibility range, and determining a measured distance between the passing vehicle and the camera by radar when the camera detects that the passing vehicle disappears; The measured distance is used as the visibility of the road.

2. The method for monitoring highway visibility according to claim 1, characterized in that: The method further comprises: Pre-calibrating calibration lines corresponding to various static targets within the field of view of the camera; According to the correspondence between the static target detected by the camera and the calibration line, it is determined that the static target detected by the camera is the first static target or the second static target.

3. The highway visibility monitoring method according to claim 1, characterized in that: The method of detecting a passing vehicle within the visibility range by using the camera under shooting parameters corresponding to the visibility range includes: Detecting by radar whether there is a vehicle passing within the visibility range; When the radar detects that a vehicle passes within the visibility range, the camera detects the passing vehicle under shooting parameters corresponding to the visibility range.

4. The highway visibility monitoring method according to claim 1, characterized in that: The camera detects that the passing vehicle disappears, including: The camera detects the rear or back contour of the passing vehicle; When the camera detects that the rear or back outline of the vehicle disappears, it is determined that the camera detects that the passing vehicle disappears.

5. The highway visibility monitoring method according to any one of claims 1 to 4, characterized in that: The step of determining the measured distance between the passing vehicle and the camera by the radar when the camera detects that the passing vehicle disappears comprises: When the camera detects that the passing vehicle disappears, the radar determines the measured distances between the passing vehicle and the camera to obtain a plurality of measured distances; Wherein, the step of using the measured distance as the visibility of the road comprises: An average of the multiple measured distances is determined, and the average is used as the visibility of the road.

6. A highway visibility monitoring device, characterized in that: Applied to a highway visibility monitoring system, the highway visibility monitoring system includes a camera and a radar, the camera is installed facing the direction of vehicle travel, and the device includes: A first determination module, used to determine whether a first static target within the camera field of view is detected by the camera; wherein the first static target corresponds to a first visibility; a second determination module, configured to determine a second static target that can be detected by the camera within the camera field of view if the first static target is not detected by the camera; wherein the second static target corresponds to a second visibility that is smaller than the first visibility and larger than the visibility corresponding to other static targets that can be detected by the camera within the camera field of view; a third determination module, configured to determine a visibility range based on the second visibility and a third visibility; wherein the third visibility is a minimum visibility among the visibilities corresponding to other static targets detectable within the field of view of the camera and greater than the second visibility; and determine a shooting parameter corresponding to the visibility range according to the visibility range; a fourth determination module, configured to detect a passing vehicle within the visibility range by the camera under shooting parameters corresponding to the visibility range, and determine a measured distance between the passing vehicle and the camera by radar when the camera detects that the passing vehicle disappears; A setting module is used to use the measured distance as the visibility of the road.

7. The highway visibility monitoring device according to claim 6, characterized in that: The device further includes: a calibration module, configured to pre-calibrate calibration lines corresponding to each static target within the field of view of the camera; a fifth determination module, configured to determine whether the static target detected by the camera is the first static target or the second static target based on the correspondence between the static target detected by the camera and the calibration lines; And / or, the fourth determination module further includes: a first detection unit, configured to detect whether a vehicle passes within the visibility range by using a radar; a second detection unit, configured to detect the passing vehicle by using the camera under shooting parameters corresponding to the visibility range when the radar detects that a vehicle passes within the visibility range; And / or, the fourth determination module further includes: the camera detecting the rear or back outline of the passing vehicle; a first determination unit, configured to determine that the camera detects that the passing vehicle disappears when the camera detects that the rear or back outline disappears; And / or, the fourth determination module also includes: a second determination unit, used to determine the measured distance between the passing vehicle and the camera respectively by the radar when the camera detects that the passing vehicle disappears, so as to obtain multiple measured distances; wherein the setting module includes: a third determination unit, used to determine the average of the multiple measured distances, and use the average as the visibility of the highway.

8. A highway visibility monitoring device, characterized in that: The invention comprises a memory, a processor and a highway visibility monitoring program stored in the memory and executable on the processor, wherein the processor implements the steps of the highway visibility monitoring method described in any one of claims 1 to 5 when executing the highway visibility monitoring program.

9. A storage medium, characterized in that: The storage medium stores a highway visibility monitoring program, and when the highway visibility monitoring program is executed by the processor, the steps of the highway visibility monitoring method according to any one of claims 1 to 5 are implemented.

10. A highway visibility monitoring system, characterized in that: The system comprises: a camera, a radar and the highway visibility monitoring device according to any one of claims 6 to 8.

Images