CN113628447B - High beam light starting detection method, device, equipment and system - Google Patents

High beam light starting detection method, device, equipment and system Download PDF

Info

Publication number
CN113628447B
CN113628447B CN202010372858.6A CN202010372858A CN113628447B CN 113628447 B CN113628447 B CN 113628447B CN 202010372858 A CN202010372858 A CN 202010372858A CN 113628447 B CN113628447 B CN 113628447B
Authority
CN
China
Prior art keywords
snapshot
image
light
preset threshold
threshold value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010372858.6A
Other languages
Chinese (zh)
Other versions
CN113628447A (en
Inventor
吴召恒
徐忠杰
杜洪超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikvision Digital Technology Co Ltd
Original Assignee
Hangzhou Hikvision Digital Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Hikvision Digital Technology Co Ltd filed Critical Hangzhou Hikvision Digital Technology Co Ltd
Priority to CN202010372858.6A priority Critical patent/CN113628447B/en
Publication of CN113628447A publication Critical patent/CN113628447A/en
Application granted granted Critical
Publication of CN113628447B publication Critical patent/CN113628447B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/017Detecting movement of traffic to be counted or controlled identifying vehicles
    • G08G1/0175Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/50Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/194Segmentation; Edge detection involving foreground-background segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/64Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70Circuitry for compensating brightness variation in the scene
    • H04N23/71Circuitry for evaluating the brightness variation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70Circuitry for compensating brightness variation in the scene
    • H04N23/73Circuitry for compensating brightness variation in the scene by influencing the exposure time
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80Camera processing pipelines; Components thereof

Abstract

The application provides a method, a device, equipment and a system for detecting the opening of a high beam, which comprise the following steps: when the light intensity detection device detects that the light incoming amount of the device changes from being smaller than a preset threshold value to being larger than or equal to the preset threshold value, a snapshot signal is sent to the image acquisition device to trigger the image acquisition device to snapshot an image according to a set snapshot mode; when the light intensity detection device detects that the light entering amount of the device is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, a snapshot finishing signal is sent to the image acquisition device to trigger the image acquisition device to finish snapshot. The image acquisition equipment carries out vehicle high beam starting detection according to the snapshot duration and the snapshot image; the snapshot duration is the time difference from the first time point of receiving the snapshot signal to the second time point of receiving the snapshot finishing signal, so that automatic detection of the violation starting of the high beam is realized.

Description

High beam light starting detection method, device, equipment and system
Technical Field
The present application relates to the field of image processing, and in particular, to a method, an apparatus, a device, and a system for detecting the opening of a high beam.
Background
Because the high beam lamp can cause great visual interference to the driver in the front vehicle, the driver is blinded instantly, and the perception to the distance and the speed is reduced, so that traffic accidents can be caused by illegally using the high beam lamp at night, and great loss is caused to life and property safety.
Therefore, how to detect the turning-on of the high beam becomes an urgent problem to be solved in the industry.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, a device and a system for detecting the turning-on of a high beam, so as to realize the automatic detection of turning-on of a high beam by a vehicle.
Specifically, the method is realized through the following technical scheme:
according to a first aspect of the present application, there is provided a high beam turn-on detection method, which is applied to a light intensity detection device, the method including:
when detecting that the light entering amount of the equipment is changed for the first time, wherein the first change is that the light entering amount of the equipment is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value, sending a snapshot signal to the image acquisition equipment to trigger the image acquisition equipment to snapshot an image according to a set snapshot mode, wherein the snapshot image is used for detecting the turning-on of a high beam of a vehicle; the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device;
when detecting that the light entering amount of the device is changed for the second time, wherein the second change means that the light entering amount of the device is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, sending a snapshot finishing signal to the image acquisition device to trigger the image acquisition device to finish the snapshot.
Optionally, the detecting that the first change occurs in the light entering amount of the apparatus includes:
detecting that the amount of incoming light entering the device at present is greater than or equal to a preset threshold value, and the configured incoming light flag is a first value, where the first value is used to indicate that the previous amount of incoming light is less than the preset threshold value, and then determining that the amount of incoming light of the device has a first change.
Optionally, when determining that the light entering amount of the apparatus changes first, the method further includes: updating the configured light entering flag from a first value to a second value, wherein the second value is used for indicating that the light entering amount is larger than or equal to a preset threshold value;
the detecting of the second change of the light entering amount of the device comprises:
detecting that the amount of light entering the equipment is smaller than a preset threshold value and the configured light entering mark is a second value, and determining that the amount of light entering the equipment is changed for the second time;
after determining that the light entering amount of the device has the second change, the method further comprises the following steps:
and updating the value of the light incoming mark from the second value to the first value.
According to a second aspect of the present application, a method for detecting turn-on of a high beam is provided, where the method is applied to an image capturing device, and the method includes:
when a snapshot signal sent by the light intensity detection equipment is received, capturing an image according to a set snapshot mode;
when a snapshot finishing signal sent by the light intensity detection equipment is received, finishing snapshot of the image;
carrying out vehicle high beam opening detection according to the snapshot duration and the snapshot image; the snapshot duration is a time difference from a first time point when the snapshot signal is received to a second time point when the snapshot finishing signal is received.
Optionally, the capturing an image according to a set capturing mode includes:
the method comprises the following steps of executing snapshot operation according to a set time interval, wherein the snapshot operation comprises the following steps: respectively capturing images by adopting the first specified exposure parameter and the second specified exposure parameter; the first designated exposure parameter at least comprises a first exposure time, the second designated exposure parameter at least comprises a second exposure time, and the first exposure time is smaller than the second exposure time.
Optionally, the detection is opened to vehicle high beam according to the length of time of taking a candid photograph and the image of taking a candid photograph, includes:
acquiring a group of images captured when each capturing operation is performed; the group of images captured when performing the capturing operation includes: capturing an image using the first specified exposure parameter and an image using the second executed exposure parameter;
and determining the car light area on each image in each group of images, when the brightness parameters of the car light area on each image in each group of images all meet the preset brightness condition, and the snapshot duration is greater than or equal to the preset duration, determining that the high beam of the vehicle is turned on, otherwise, determining that the high beam of the vehicle is not turned on.
Optionally, the determining the car light region on each image in each group of images includes:
for each group of images, inputting a first image in the group of images into a trained position determination model to obtain position information of a vehicle lamp area in the first image; the first image is a snapshot of the group of images by adopting the first specified exposure parameter;
searching a corresponding area on the first image according to the car lamp area position information, and determining the searched area as a car lamp area of the first image;
searching a region corresponding to the position information of the car light region on a second image in the group of images, and determining the searched region as the car light region of the second image; the second image is an image in the group of images that is captured using the second specified exposure parameter.
Optionally, the brightness parameter of the headlight region on each image in each group of images is determined as follows:
determining the average brightness value of the car light region on each group of images, carrying out binarization processing on the images, and calculating the pixel quantity ratio of the number of foreground pixels and the number of background pixels in the images after binarization processing; in the binary processed image, the car light area is used as a foreground, and other areas are used as backgrounds;
and determining the average brightness value and the pixel quantity ratio as the brightness parameter of the image.
Optionally, the preset brightness condition includes:
the average brightness value in the brightness parameter is greater than or equal to a preset brightness threshold value, and the pixel quantity ratio value in the brightness parameter is greater than or equal to a preset pixel quantity ratio threshold value.
Optionally, after it is determined that there is a vehicle turning on the high beam, the method further includes:
synthesizing the images of one group of captured images to obtain a synthesized image;
and identifying the vehicle information of the vehicle which turns on the high beam from the composite image.
According to a third aspect of the present application, there is provided a high beam turn-on detection system, the system comprising: the device comprises a light intensity detection device and an image acquisition device;
the light intensity detection device is used for sending a snapshot signal to the image acquisition device when detecting that the light entering amount of the device changes from being smaller than a preset threshold value to being larger than or equal to the preset threshold value; when detecting that the light entering amount of the equipment has a second change, wherein the second change is that the light entering amount of the equipment is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, sending a snapshot finishing signal to the image acquisition equipment;
the image acquisition equipment is used for snapshotting an image according to a set snapshotting mode when receiving a snapshotting signal sent by the light intensity detection equipment; when a snapshot finishing signal sent by the light intensity detection equipment is received, finishing the snapshot of the image; carrying out vehicle high beam opening detection according to the snapshot duration and the snapshot image; the snapshot duration is the time difference from a first time point when the snapshot signal is received to a second time point when the snapshot finishing signal is received;
wherein the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device.
According to a fourth aspect of the present application, there is provided a light intensity detecting apparatus comprising: a photosensor, and a control module;
the photosensitive sensor is used for sending the detected light incoming amount of the equipment to the control module;
the control module is used for sending a snapshot signal to the image acquisition equipment to trigger the image acquisition equipment to snapshot an image according to a set snapshot mode when detecting that the light incoming amount of the equipment is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value, wherein the snapshot signal is used for detecting the opening of a vehicle high beam; the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device; when detecting that the light entering amount of the device is changed for the second time, wherein the second change means that the light entering amount of the device is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, sending a snapshot finishing signal to the image acquisition device to trigger the image acquisition device to finish the snapshot.
Optionally, when detecting that the amount of light entering the device changes first, the control module is configured to detect that the amount of light entering the device is greater than or equal to a preset threshold, and the configured light entering flag is a first value, where the first value is used to indicate that the previous amount of light entering the device is less than the preset threshold, and then determine that the amount of light entering the device changes first.
Optionally, the control module is further configured to, when it is determined that the amount of light entering the apparatus changes from a first value to a second value, where the second value is used to indicate that the amount of light entering the apparatus is greater than or equal to a preset threshold;
the control module is used for detecting that the light entering amount of the current device is smaller than a preset threshold value when detecting that the light entering amount of the current device is changed for the second time, and determining that the light entering amount of the current device is changed for the second time if the configured light entering flag is a second value; after the second change of the light intake amount of the present apparatus is determined, the value of the light intake flag is also updated from the second value to the first value.
Optionally, the light intensity detecting device includes: a light inlet and a light filter; the light inlet is arranged to be inclined relative to the axial direction of the optical filter; the filter is used for filtering light except the high beam.
According to a fifth aspect of the present application, a high beam turn-on detection device is provided, the device is applied to an image acquisition apparatus, the device includes:
the snapshot unit is used for snapshotting an image according to a set snapshot mode when receiving a snapshot signal sent by the light intensity detection equipment;
the snapshot ending unit is used for ending the snapshot when receiving a snapshot ending signal sent by the light intensity detection equipment;
the detection unit is used for carrying out vehicle high beam starting detection according to the snapshot duration and the snapshot image; the snapshot duration is a time difference from a first time point when the snapshot signal is received to a second time point when the snapshot finishing signal is received.
According to a sixth aspect of the present application, there is provided an image acquisition apparatus comprising a readable storage medium and a processor;
wherein the readable storage medium is configured to store machine executable instructions;
the processor is configured to read the machine executable instructions on the readable storage medium and execute the instructions to implement the steps of the method of the second aspect.
It can be known from the above description that because this application does not adopt image acquisition equipment direct detection vehicle to open the high beam, but through the light intensity check out test set that can filter non-high beam light source after tentatively confirming the suspected high beam of opening of vehicle, just inform image acquisition equipment whether open the high beam further detection to the vehicle violating regulations. The linkage design can effectively reduce the false detection condition caused by the change of the ambient light and improve the detection accuracy.
Drawings
FIG. 1 is a schematic diagram of a violation high beam detection system shown in an exemplary embodiment of the present application;
fig. 2 is a flowchart illustrating a high beam turn-on detection method according to an exemplary embodiment of the present application;
FIG. 3 is a schematic diagram of a hardware structure of a light intensity detecting device according to an exemplary embodiment of the present application;
FIG. 4 is a flow chart illustrating another method of detecting a violation of turning on a high beam in accordance with an exemplary embodiment of the present application;
fig. 5 is an interaction diagram of another high beam turn-on detection method provided in an exemplary embodiment of the present application;
FIG. 6 is a block diagram of hardware of an image capture device according to an exemplary embodiment of the present application;
fig. 7 is a block diagram of a high beam turn-on detection apparatus according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at" \8230; "or" when 8230; \8230; "or" in response to a determination ", depending on the context.
Referring to fig. 1, fig. 1 is a schematic diagram of a system for detecting a high beam violation, according to an exemplary embodiment of the present application.
The system comprises: image acquisition device 101, light intensity detection device 102.
1) Image capturing apparatus 101
The image capturing device 101 is a device having an image capturing function. For example, the image capturing device 101 may include: cameras, video cameras, etc. The image capturing apparatus is only exemplified here, and is not particularly limited.
2) Light intensity detection device 102
The light intensity detection device 102, which has a light intensity detection function, may communicate with the image capturing device to control the image capturing device to perform image capturing.
In an embodiment of the application, the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device. In other words, the monitoring area of the image pickup device includes the detection area of the light intensity pickup device.
The arrangement aims to ensure that the image of the monitoring area captured by the image acquisition equipment contains the vehicle to be subjected to the high beam violation starting detection when the image acquisition equipment detects that the light entering amount of the equipment is changed from being smaller than the preset threshold to being larger than or equal to the preset threshold.
In the embodiment of the application, when the light intensity detection device detects that the light entering amount is changed from being smaller than the preset threshold to being larger than or equal to the preset threshold, the light intensity detection device sends a snapshot signal to the image acquisition device to trigger the image acquisition device to snapshot an image. When the light intensity detection device detects that the light entering amount of the device is changed from being larger than or equal to the preset threshold value to being smaller than the preset threshold value, a snapshot ending signal is sent to the image acquisition device to trigger the image acquisition device to end snapshot. And the image acquisition equipment automatically detects that the vehicle breaks rules and opens the high beam based on the captured image and the captured duration.
The following describes in detail a method for detecting the opening of a high beam as proposed in the present application.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for detecting the activation of a high beam according to an exemplary embodiment of the present application, where the method may be applied to a light intensity detecting device and may include the following steps.
Step 201: when the light intensity detection equipment detects that the light entering amount of the equipment is changed for the first time, wherein the first change is that the light entering amount of the equipment is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value, a snapshot signal is sent to the image acquisition equipment to trigger the image acquisition equipment to snapshot an image according to a set snapshot mode, and the snapshot image is used for detecting that the high beam of the vehicle is opened illegally; the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device.
Step 202: when the light intensity detection device detects that the light entering amount of the device has a second change, wherein the second change is that the light entering amount of the device is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, a snapshot ending signal is sent to the image acquisition device to trigger the image acquisition device to end snapshot.
In the embodiment of the present application, the light intensity detection device may implement "detecting a first change in the amount of light entering the device" and "detecting a second change in the amount of light entering the device" in the following ways:
in implementation, the light intensity detection device is configured with a light entrance flag. The light entering flag indicates a relation between the amount of light entering ahead of the light intensity detection device and a preset threshold value. For example, when the light entering flag takes a first value (e.g., 0), the first value indicates that the amount of light entering before the light intensity detection device is smaller than the preset threshold. When the value of the light entering flag is a second value (for example, 1), it indicates that the amount of light entering in front of the light intensity detection device is greater than or equal to the preset threshold.
In the present application, the light intensity detection device may realize the detection of the above-described "first change in the amount of light entering", and "second change in the amount of light entering", by the amount of light entering and the light entering flag.
Specifically, the light intensity detection device may detect, in real time or periodically, whether the amount of light entering the device is greater than or equal to a preset threshold, and determine a value of the light entering flag.
When the light intensity detection device detects that the amount of light entering the device at present is greater than or equal to a preset threshold value and the value of the light entering mark is a first value, it is determined that the first change occurs in the detected amount of light (that is, it is determined that the detected amount of light is changed from being less than the preset threshold value to being greater than or equal to the preset threshold value). In addition, after determining that the amount of the light entering changes for the first time, the light intensity detection device may update the value of the light entering flag to a second value.
When the light intensity detection device detects that the amount of light entering the device is smaller than the preset threshold value and the value of the light entering flag is the second value, it is determined that the amount of light entering the device is changed for the second time (that is, it is determined that the amount of light entering the device is changed from being larger than or equal to the preset threshold value to being smaller than the preset threshold value). Further, after determining that the amount of light entering the apparatus has changed by the second amount, the value of the light entering flag is updated from the second value to the first value.
Of course, in practical applications, the light intensity detecting device may also use other manners to detect the first change and the second change of the light entering amount, which are only exemplary and not specifically limited.
In this application embodiment, when light intensity detection equipment detected the volume of intaking and take place first change, light intensity detection equipment can send the snapshot signal to image acquisition equipment to trigger image acquisition equipment and take a candid photograph the image according to setting for the snapshot mode, the image of taking a candid photograph is used for detecting that the vehicle high beam breaks rules and regulations and opens.
When the light front detection device detects that the amount of the incoming light changes for the second time, the light intensity detection device can send a snapshot ending signal to the image acquisition device to trigger the image acquisition device to end the snapshot.
When the snapshot signal or the snapshot completion signal is sent, in an optional implementation manner, the light intensity detection device may be connected to the image acquisition device through a cable, and the light intensity detection device may send the snapshot signal to the image acquisition device in a wired communication manner.
Of course, the light intensity detecting device may also send the forwarding signal to the image capturing device by way of wireless communication, and here, the sending of the snapshot signal or the snapshot ending signal is only exemplarily illustrated and is not specifically limited.
It should be noted that: the preset threshold value can be determined according to the light entering amount detected by the light intensity detection device and the preset error when the vehicle with the high beam is in the detection area of the light intensity detection device, and can also be determined by developers according to experience.
It should also be noted that: when a vehicle with a high beam lamp turned on enters the monitoring area, the light quantity of the monitoring area is increased, so that the light inlet quantity of the light intensity detection device is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value. Therefore, in the application, the light intensity detection device detects the change of the light incoming amount, and the light intensity detection device is used for preliminarily detecting whether the high beam is turned on illegally for the vehicle entering the monitoring area. And if the light intensity of the light intensity detection equipment is changed from being smaller than a preset threshold to being larger than or equal to the preset threshold, determining that vehicles suspected of starting the high beam exist in the monitored area. At this time, the light intensity detection device can send a snapshot signal to the image acquisition device to trigger the image acquisition device to snapshot an image of the monitored area, and further determine whether the vehicle suspected of opening the high beam really breaks rules and opens the high beam based on the snapshot image.
In addition, when the vehicle with the high beam light turned on leaves the monitored area, the light quantity in the monitored area is reduced, and therefore the light incoming quantity of the light intensity detection device is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value. Therefore, in the present application, when the light intensity detection device detects that the amount of light entering the device changes from being greater than or equal to the preset threshold to being smaller than the preset threshold, it can be determined that the vehicle suspected of turning on the high beam has driven away from the monitoring area. At this time, the light intensity detection device may send a snapshot ending signal to the image acquisition device to trigger the image acquisition device to end the snapshot.
The linkage mechanism of the light intensity detection device and the image acquisition device has the advantages that: the light intensity detection equipment firstly carries out preliminary detection of breaking rules and regulations to open the high beam on the vehicle in the monitoring area through the change of the light entering amount, and after the vehicle is determined to be suspected to open the high beam, the image acquisition equipment can be controlled to acquire the image of the vehicle suspected to open the high beam, and whether the vehicle really opens the high beam is further determined through the image. The detection accuracy can be greatly improved by combining the light input quantity with the image processing technology and detecting twice to determine whether the vehicle turns on the remote turn-off lamp illegally.
In addition, because the light that the high beam was sent has the characteristic that the light vertical offset is great (in other words, the high beam is shone the angle and is great), so in order to ensure that light intensity detection equipment is based on the change of light inlet volume, whether open the preliminary detection of high beam to the vehicle that gets into the monitoring area more accuracy, this application has related to the light intensity detection equipment who is applicable to the high beam illumination according to this specific of high beam.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a light intensity detecting apparatus according to an exemplary embodiment of the present application;
as shown in fig. 3, the light intensity detecting apparatus includes: a photosensitive sensor 301, a control module 303, a filter 304, a housing 302 and a light inlet 305.
1) Optical filter 304
The filter 304 is used to filter light other than the light emitted from the high beam. For example, the optical filter can filter out road surface reflected light and other ambient light caused by dipped headlights in the monitored area.
The light filter can filter out other light except the light emitted by the high beam as much as possible, so the light filter reduces the influence of other light on the light inlet quantity, and the light inlet quantity can accurately represent the illumination condition of the high beam.
2) Light inlet 305
The port on one side of the housing 302 is an optical inlet 305. In the present application, the light inlet is disposed to be inclined with respect to the axial direction of the filter 304, forming an inclined opening as shown in fig. 3.
The light entrance is provided in this manner to reduce the influence of ambient light in the monitoring area or the detection area on the amount of light entering. For example, the influence of light emitted from a street lamp in a monitoring area or a detection area, light emitted from a vehicle at a distance, or the like on the amount of light entering is reduced.
When installed, it can be installed in the manner presented in fig. 3, so that the light inlet of the light intensity detecting device can face the detection area.
It should be noted that, this application sets up the light filter and sets up the light inlet of this kind of form, all is in order to reduce the influence to the light inlet quantity of other lights except that the high beam for the light inlet quantity can comparatively accurately characterize the illumination condition of high beam, and then makes the change based on the light inlet quantity whether open the preliminary survey of high beam more accurate to the vehicle that gets into the control area.
3) Photosensitive sensor 301
And a photosensor 301 for detecting the amount of incoming light and sending the amount of incoming light to the control module 203.
4) Control module 303
The control module 303 may perform detection of a change in the amount of incident light, and send a snapshot signal or a snapshot completion signal to the image capturing apparatus based on the detected change in the amount of incident light.
In the embodiment of the present application, the photosensor 301 of the light intensity detection device can detect the amount of incoming light. The amount of light entering is then sent to the control module 303.
The control module 303 may implement steps 201 through 202 described above.
Specifically, the control module 303 may determine whether the amount of light entering the apparatus has changed in the above manner. If the amount of light entering the device changes first, the control module 303 may send a snapshot signal to the image capturing device. If the light entering amount of the device changes second, the control module 303 may send a snapshot ending signal to the image capturing device.
As can be seen from the above description, on the one hand, because this application has designed the light intensity detection equipment that matches with the light that the high beam sent to the light has disposed the light filter in light intensity detection equipment, and has set up the light inlet of light intensity detection equipment for the form of the axial slope of this light filter, so can reduce the influence of other lights except for the high beam to the amount of light that advances, make light intensity detection equipment whether open the preliminary detection of high beam to the vehicle that gets into the monitoring area more accurate based on the change of the amount of light that advances.
On the other hand, after the light intensity detection device preliminarily detects whether the high beam is turned on by the vehicle entering the monitoring area based on the change of the light incoming amount, if the vehicle is determined to be suspected to be turned on, the image acquisition device can be controlled to acquire the image of the vehicle, and whether the high beam is turned on by the vehicle violating the regulations is further determined. The mode of linkage of two devices and secondary detection is adopted, so that the detection of opening the high beam violating the regulations is more accurate.
Referring to fig. 4, fig. 4 is a flowchart illustrating another detection method for turning on a high beam violating regulations according to an exemplary embodiment of the present application, where the method may be applied to an image capturing device and may include the following steps.
Step 401: when the image acquisition equipment receives the snapshot signal sent by the light intensity detection equipment, the image is snapshot according to the set snapshot mode.
When the device is realized, the light intensity detection device sends a snapshot signal to the image acquisition device when detecting that the light entering amount of the device is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value.
After receiving the snapshot signal, the image acquisition device can snapshot an image according to a set snapshot mode.
In the snapshot, the image capturing apparatus may perform the snapshot operation at set time intervals. Wherein, the snapshot operation includes: and respectively capturing images by adopting the first specified exposure parameter and the second specified exposure parameter.
In other words, the image capturing apparatus may perform the snapshot operation at set time intervals. When each snapshot operation is executed, the image acquisition equipment can adopt the first exposure parameter to snapshot the image and adopt the second exposure parameter to snapshot the image, and generate the image group corresponding to the snapshot operation. The image group includes: the image is captured using the first exposure parameters and the image is captured using the second exposure parameters.
The first specified exposure parameter at least comprises a first exposure time, and the second specified exposure parameter at least comprises a second exposure time. The first exposure time is less than the second exposure time.
Of course, in practical applications, the first and second designated exposure parameters include other contents, which are only exemplary and not specifically limited herein.
It should be noted that, since the first exposure time is shorter than the second exposure time, the mode of capturing an image by using the first exposure parameter may be referred to as a short-exposure image capturing mode, and the mode of capturing an image by using the second exposure parameter may be referred to as a long-exposure image capturing mode, which is not described in detail below.
Step 402: and when the image acquisition equipment receives the snapshot finishing signal sent by the light intensity detection equipment, finishing the snapshot of the image.
When the device is realized, when the light intensity detection device detects that the light entering amount of the device is changed from being larger than or equal to the preset threshold value to being smaller than the preset threshold value, the light intensity detection device can send a snapshot finishing signal to the image acquisition device.
The image acquisition equipment can finish capturing the image after receiving the capturing end signal.
Step 403: the image acquisition equipment carries out vehicle high beam starting detection according to the snapshot duration and the snapshot image; the snapshot duration is a time difference from a first time point when the snapshot signal is received to a second time point when the snapshot ending signal is received.
Step 403 is explained in detail below by means of step 4031 through step 4032.
Step 4031: the image acquisition equipment acquires a group of images which are captured when the capturing operation is executed each time; the group of images captured when performing the capturing operation includes: the image taken with the first specified exposure parameter and the image taken with the second exposure parameter.
Step 4032: the image capture device determines the area of the vehicle headlight on each image in each set of images.
Step 4033: and when the brightness parameters of the car lamp area on each image in each group of images meet the preset brightness condition and the snapshot time length is greater than or equal to the preset time length, determining that the high beam of the vehicle is illegally started, otherwise, determining that the vehicle is not illegally started.
For convenience of description, an image captured with the first specified exposure parameter will be referred to as a first image, and an image captured with the second specified exposure parameter will be referred to as a second image. And will not be described in detail below.
Next, steps 4031 to 4033 are described, respectively.
Step 4031: the image acquisition equipment acquires a group of images captured when the capturing operation is executed each time; the group of images that are snapped while performing the snapping operation includes: a short exposure image taken with a first specified exposure parameter and a long exposure image taken with a second executed exposure parameter.
In implementation, after acquiring the image group corresponding to each snapshot operation, the image acquisition device may record the image group.
Then, when the vehicle high beam violation starting detection is carried out, the image acquisition device can acquire a group of recorded images (also called an image group) captured at the time of the capturing operation. The image group comprises a first image captured by adopting a first appointed exposure parameter and a second image captured by adopting a second appointed exposure parameter.
For example, assuming that the image capturing apparatus performs 5 times of capturing operations, the image capturing apparatus captures 5 image groups. Each image group includes: a first image captured using a first specified exposure parameter and a second image captured using a second specified exposure parameter.
When the vehicle high beam violation starting detection is carried out, the image acquisition equipment can acquire 5 captured image groups.
Step 4032: the image capture device determines the area of the vehicle headlight on each image in each set of images.
In implementation, for each group of images, the image acquisition device may obtain the position information of the lamp region in the first image from the trained position determination model of the first image input value in the group of images.
For example, the location determination model may be the YOLOv3 model.
After the image acquisition equipment inputs the first image into the YOLOv3 model and the image feature extraction is carried out, the YOLOv3 model can generate a plurality of anchor frames on the first feature image and predict the confidence coefficient and the offset of each anchor frame. And the confidence coefficient of the anchor frame represents the reliability degree of the vehicle lamp area of the anchor frame. The offset of the position of the anchor frame represents the offset of the anchor frame relative to the position of the vehicle lamp area.
Then, for each anchor frame, the YOLOv3 model may obtain the position coordinates of the candidate frame according to the position coordinates and the offset of the anchor frame. Then, the YOLOv3 model may select a candidate box with a confidence higher than a preset threshold value among the candidate boxes.
Then, the YOLOv3 model may process the selected candidate frame based on a Non Maximum Suppression (NMS) algorithm, thereby determining the car light region.
For example, when implemented, the YOLOv3 model may order the selected candidate boxes in order of the confidence level. Then, the YOLOv3 model may select the candidate box with the highest confidence from the ranking as the retained box. Then, the YOLOv3 model may delete candidate frames having an overlapping area with the reserved frame larger than a preset threshold. Then, the YOLOv3 model may obtain the candidate box with the second highest confidence from the ranking as the retained box. Then, the YOLOv3 model may delete the candidate frames having the overlap area greater than the predetermined threshold. And repeating the steps until the candidate boxes in the sequence are traversed. Then, YOLOv3 will determine the position information of the headlight region based on the remaining candidate frames.
It should be noted that the position determination model may be a YOLOv3 model, or may be another model, and here, the position determination model is only exemplarily described and is not specifically limited.
In the embodiment of the application, after the position information of the car light region is obtained, the image acquisition device can search the corresponding region on the first image according to the position information of the car light region, and determine the searched region as the car light region of the first image.
In addition, the image acquisition device can also search a region corresponding to the vehicle lamp region position information on a second image in the group of images, and determine the searched region as the vehicle lamp region of the second image.
It should be noted that: the advantage of identifying the position information of the headlight region in the first image by using machine learning and determining the headlight region in the first image and the second image based on the identified position information is as follows:
since the first image is obtained by a short-exposure image capturing mode (i.e., shortening the exposure time and reducing the light input amount), the short-exposure image capturing mode can suppress the brightness of an over-bright area and reduce the influence of reflected light and other weak light sources, so that the quality of scene information in the first image obtained by the short-exposure image capturing mode is higher.
Since the scene information in the first image is higher in quality, machine learning is adopted to identify the position information of the car light region in the first image, and the obtained position information is more accurate.
Step 4033: when the brightness parameters of the car light area on each image in each group of images all meet the preset brightness condition, and the snapshot duration is greater than or equal to the preset duration, determining that the high beam of the vehicle is illegally opened, otherwise, determining that the vehicle is not illegally opened
Step 4033 is described below with reference to steps a to D.
Step A: for each set of images, the image capture device obtains a brightness parameter for a vehicle light region on each image in the set of images.
During implementation, aiming at each image in each group of images, the image acquisition equipment can determine the average brightness value of the car light region on the image, carry out binarization processing on the image and calculate the pixel quantity ratio of the number of foreground pixels and the number of background pixels in the image after binarization processing; in the binary processed image, the car light area is used as the foreground, and other areas are used as the background.
Specifically, for each set of images. The image acquisition device may acquire a first image of the set of images. The image capture device may then determine an average brightness value for the headlight region on the first image. In addition, the image acquisition device can also carry out binarization processing on the first image by taking the car light area as a foreground and other areas as backgrounds. Then, the image capturing device may calculate a pixel quantity ratio of the number of foreground pixels and the number of background pixels in the binarized first image. The image acquisition device can use the determined average brightness value and the determined pixel quantity ratio as the brightness parameter of the first image.
Similarly, the image capture device may acquire a second image of the set of images. The image capture device may then determine an average brightness value for the headlight region on the second image. In addition, the image acquisition device can also carry out binarization processing on the second image by taking the car light area as a foreground and other areas as backgrounds. Then, the image capturing apparatus may calculate a pixel amount ratio of the number of foreground pixels and the number of background pixels in the binarized second image. The image acquisition device can use the determined average brightness value and the determined pixel quantity ratio as the brightness parameter of the second image.
Thus, for each set of images, the image acquisition device may obtain an average luminance value and a pixel amount ratio of a first image in the set of images and obtain an average luminance value and a pixel amount ratio of a second image in the set of images.
Here, the content included in the luminance parameter is only exemplarily described, and the content included in the luminance parameter is not specifically limited.
And B, the image acquisition equipment can detect whether the brightness parameter of the car lamp area on each image in each group of images meets a preset brightness condition and whether the snapshot time length is greater than or equal to the preset time length.
Wherein the brightness condition may include: the average brightness value in the brightness parameter is greater than or equal to a preset brightness threshold value, and the pixel quantity ratio value in the brightness parameter is greater than or equal to a preset pixel quantity ratio threshold value. Here, the luminance condition is only exemplified and is not particularly limited.
In implementation, for each image (i.e., the first image or the second image) of each set of images, the image capture device may detect whether an average brightness value of the image is greater than or equal to a preset brightness threshold and whether a pixel quantity ratio of the image is greater than or equal to a preset pixel quantity ratio threshold.
And if the average brightness value of the image is greater than or equal to a preset brightness threshold value and the pixel quantity ratio of the image is greater than or equal to a preset pixel quantity ratio threshold value, determining that the brightness parameter of the image meets the brightness condition.
And if the average brightness value of the image is smaller than a preset brightness threshold value and/or the pixel quantity ratio of the image is smaller than a preset pixel quantity ratio threshold value, determining that the brightness parameter of the image does not meet the brightness condition.
And C: and if the brightness parameters of the lamp area on each image in each group of images all meet the preset brightness condition and the snapshot duration is greater than or equal to the preset duration, determining that the high beam of the vehicle is illegally turned on.
And D, if the brightness parameters of the car light areas on each image in each group of images do not meet the preset brightness condition and/or the snapshot duration is less than the preset duration, determining that the vehicle does not illegally start the high beam.
In addition, in the embodiment of the application, after it is determined that the high beam of the vehicle is illegally turned on, the image acquisition device further needs to identify the vehicle information of the vehicle which illegally turns on the high beam.
Because the long exposure image snapshot mode is to acquire images by increasing the exposure time and increasing the exposure, the brightness of a darker area in a monitored area can be improved by taking the snapshot images in the long exposure snapshot mode, and therefore, more scene information can be displayed on the second images which are snapshot in the long exposure snapshot mode. As can be seen from the above description, the first image captured by the short exposure mode may display higher quality scene information. Therefore, in order to improve the accuracy of vehicle information identification, the image acquisition device can comprehensively utilize the respective advantages of the first image and the second image to identify the vehicle information.
In implementation, the image capturing device may combine the first image and the second image in the captured group of images to obtain a combined image. The composite image may combine the advantages of the first image and the second image. For example, the composite image may display more scene information and also higher quality scene information.
The image capture device may then identify vehicle information for the vehicle violating the opening of the high beam from the composite image.
Wherein the vehicle information may include: the license plate number of the vehicle, the color of the vehicle, the brand of the vehicle, etc. Here, the vehicle information is merely exemplary and is not particularly limited.
As apparent from the above description, in a first aspect, the present application designs a light intensity detecting apparatus adapted to detect a high beam. In the embodiment of the application, the light intensity detection device is provided with the optical filter, and the light inlet of the light intensity detection device is arranged to be inclined relative to the axial direction of the optical filter, so that the design can effectively prevent the non-high beam lamp light source from influencing the light inlet quantity of the light intensity detection device. In addition, the light intensity detection device is also internally provided with a photosensitive sensor and a signal control module. The signal control module can preliminarily detect that the vehicle starts the high beam and then sends a signal to the image acquisition equipment according to the change of the light inlet quantity so that the image acquisition equipment can further detect whether the vehicle starts the high beam or not.
Because this application does not adopt image acquisition equipment direct detection vehicle to open the high beam, but through the light intensity check out test set that can filter non-high beam light source preliminary definite vehicle is suspected to open the high beam after, just inform image acquisition equipment whether open the high beam to the vehicle violating regulations and go on further detecting. The linkage design can effectively reduce the false detection condition caused by the change of the ambient light and improve the detection accuracy.
In the second aspect, when the image acquisition equipment carries out snapshot operation each time, the first image is snapshot through a short-exposure image snapshot mode, the second image is snapshot through a long-exposure image snapshot mode, whether the vehicle breaks rules and regulations and opens the high beam in the monitored area or not is determined based on the image group generated by each snapshot operation and the snapshot duration, and therefore automatic detection that the vehicle breaks rules and regulations and opens the high beam is achieved.
In the third aspect, the quality of the scene information in the first image captured by the short-exposure image capturing mode is higher, and the scene information in the second image captured by the long-exposure image capturing mode is more, so that the image acquisition equipment detects the violation of opening the high beam based on the brightness parameters of the lamp area of the first image and the second image, and the advantages of the first image and the second image can be comprehensively utilized, so that the detection result of whether the vehicle breaks the violation of opening the high beam or not obtained by the image acquisition equipment is more accurate.
In a fourth aspect, in determining a vehicular lighting region for each image in each set of images, an image capturing device machine learning model identifies positional information of the vehicular lighting region in a first image, and determines the vehicular lighting region in the first image and a second image based on the identified positional information.
The scene information quality in the first image obtained by the short-exposure image capturing mode is higher, so that the position information obtained by identifying the position of the car light region in the first image with higher scene information quality through machine learning is more accurate, and the car light region determined in the first image and the second image according to the position information is more accurate.
Referring to fig. 5, fig. 5 is an interactive diagram of another violation opening detection method by high beam and the like according to an exemplary embodiment of the present application.
Step 501: when the light intensity detection device detects that the light incoming amount of the device changes from being smaller than a preset threshold value to being larger than or equal to the preset threshold value, a snapshot signal is sent to the image acquisition device.
For specific implementation, refer to step 201 to step 202, which are not described herein again.
Step 502: when receiving a snapshot signal, the image acquisition equipment executes snapshot operation according to a set time interval, wherein the snapshot operation comprises the following steps: and respectively capturing images by adopting the first specified exposure parameter and the second specified exposure parameter.
Specifically, refer to step 401 above, which is not described herein again.
Step 503: and when the light intensity detection device detects that the light entering amount of the device is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, sending a snapshot ending signal to the image acquisition device.
For specific implementation, refer to step 201 to step 202, which are not described herein again.
Step 504: and after receiving the snapshot signal, the image acquisition equipment finishes snapshot.
Refer specifically to step 402, which is not described herein.
Step 505: and the image acquisition equipment carries out vehicle high beam violation starting detection according to the snapshot duration and the snapshot image.
For details, refer to step 403, which is not described herein again.
Referring to fig. 6, fig. 6 is a hardware structure diagram of an image capturing device according to an exemplary embodiment of the present application;
the image pickup apparatus includes: a communication interface 601, a processor 602, a machine-readable storage medium 603, and a bus 604; wherein the communication interface 601, the processor 602, and the machine-readable storage medium 603 communicate with each other via a bus 604. The processor 602 may perform the above described violation of turning on high beam method by reading and executing machine executable instructions in the machine readable storage medium 603 corresponding to the violation of turning on high beam control logic.
The machine-readable storage medium 603 referred to herein may be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and the like. For example, the machine-readable storage medium may be: volatile memory, non-volatile memory, or similar storage media. In particular, the machine-readable storage medium 603 may be a RAM (random Access Memory), a flash Memory, a storage drive (e.g., a hard drive), a solid state drive, any type of storage disk (e.g., a compact disk, a DVD, etc.), or similar storage medium, or a combination thereof.
Referring to fig. 7, fig. 7 is a block diagram of a high beam turn-on detection apparatus according to an exemplary embodiment of the present application. The device is applied to image acquisition equipment, the device includes:
the snapshot unit 701 is used for snapshotting an image according to a set snapshot mode when receiving a snapshot signal sent by the light intensity detection device;
the snapshot ending unit 702 is configured to end the snapshot when receiving a snapshot ending signal sent by the light intensity detection device;
the detection unit 703 is configured to perform vehicle high beam turn-on detection according to the snapshot duration and the snapshot image; the snapshot duration is a time difference from a first time point when the snapshot signal is received to a second time point when the snapshot ending signal is received.
Optionally, the capturing unit 701 is specifically configured to execute capturing operations according to a set time interval when capturing an image according to a set capturing mode, where the capturing operations include: respectively capturing images by adopting a first specified exposure parameter and a second specified exposure parameter; the first specified exposure parameters at least comprise first exposure time, the second specified exposure parameters at least comprise second exposure time, and the first exposure time is smaller than the second exposure time.
Optionally, the detection unit 703 is specifically configured to acquire a group of images captured during each capturing operation when the vehicle high beam is turned on and detected according to the capturing duration and the captured images; the group of images captured when performing the capturing operation includes: capturing an image using the first specified exposure parameter and an image using the second executed exposure parameter; and determining the car light area on each image in each group of images, when the brightness parameters of the car light area on each image in each group of images all meet the preset brightness condition, and the snapshot duration is greater than or equal to the preset duration, determining that the high beam of the vehicle is illegally started, otherwise, determining that the vehicle is not illegally started.
Optionally, when determining the car light region on each image in each group of images, the detecting unit 703 is specifically configured to, for each group of images, input a first image in the group of images into the trained position determination model to obtain the position information of the car light region in the first image; the first image is a snapshot of the group of images by adopting the first specified exposure parameter; searching a corresponding area on the first image according to the car lamp area position information, and determining the searched area as a car lamp area of the first image; searching a region corresponding to the car light region position information on a second image in the group of images, and determining the searched region as a car light region of the second image; the second image is an image in the group of images that is captured using the second specified exposure parameter.
Optionally, the brightness parameter of the headlight region on each image in each group of images is determined as follows:
determining the average brightness value of the car light area on each image in each group of images, carrying out binarization processing on the images, and calculating the pixel quantity ratio of the foreground pixel quantity and the background pixel quantity in the images after binarization processing; in the image after the binary processing, the car light area is used as a foreground, and other areas are used as backgrounds;
and determining the average brightness value and the pixel quantity ratio as the brightness parameter of the image.
Optionally, the preset brightness condition includes:
the average brightness value in the brightness parameter is greater than or equal to a preset brightness threshold value, and the pixel quantity ratio value in the brightness parameter is greater than or equal to a preset pixel quantity ratio threshold value.
Optionally, the apparatus further comprises:
the identification unit 704 is used for synthesizing all the images of the group of captured images to obtain a synthesized image after the fact that the vehicle breaks rules and turns on the high beam is determined; and identifying the vehicle information of the vehicle which breaks rules and opens the high beam from the composite image.
In addition, this application still provides a detection system is opened to high beam, the system includes: the device comprises a light intensity detection device and an image acquisition device;
the light intensity detection device is used for sending a snapshot signal to the image acquisition device when detecting that the light incoming amount of the device is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value; when detecting that the light entering amount of the equipment has a second change, wherein the second change is that the light entering amount of the equipment is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, sending a snapshot finishing signal to the image acquisition equipment;
the image acquisition equipment is used for capturing images according to a set capturing mode when receiving capturing signals sent by the light intensity detection equipment; when a snapshot finishing signal sent by the light intensity detection equipment is received, finishing snapshot of the image; carrying out vehicle high beam opening detection according to the snapshot duration and the snapshot image; the snapshot duration is a time difference from a first time point when the snapshot signal is received to a second time point when the snapshot finishing signal is received;
wherein the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device.
Optionally, when detecting that the amount of light entering the device changes first, the light intensity detection device is specifically configured to detect that the amount of light entering the device is greater than or equal to a preset threshold, and the configured light entering flag is a first value, where the first value is used to indicate that the previous amount of light entering the device is less than the preset threshold, and it is determined that the amount of light entering the device changes first.
Optionally, when determining that the light entering amount of the device changes from a first value to a second value, the light intensity detecting device is further configured to update the configured light entering flag from the first value to the second value, where the second value is used to indicate that the light entering amount is greater than or equal to a preset threshold;
when detecting that the light entering amount of the device changes for the second time, specifically, the method is used for detecting that the light entering amount of the current device is smaller than a preset threshold value, and the configured light entering flag is a second value, and then determining that the light entering amount of the current device changes for the second time;
and after the light entering amount of the equipment is determined to be changed for the second time, the light entering device is also used for updating the value of the light entering mark from the second value to the first value.
Optionally, the light intensity detecting device includes: a light inlet and a light filter; the light inlet is arranged to be inclined relative to the axial direction of the optical filter; the filter is used for filtering light except the high beam.
Optionally, the image capturing device is configured to, when capturing an image according to a set capturing mode, execute capturing operations according to a set time interval, where the capturing operations include: respectively capturing images by adopting a first specified exposure parameter and a second specified exposure parameter; the first specified exposure parameters at least comprise first exposure time, the second specified exposure parameters at least comprise second exposure time, and the first exposure time is smaller than the second exposure time.
Optionally, the image acquisition device is specifically configured to acquire a group of images captured during each capturing operation when vehicle high beam starting detection is performed according to the capturing duration and the captured images; the group of images captured when performing the capturing operation includes: the image is captured by adopting the first appointed exposure parameter and the image is captured by adopting the second execution exposure parameter; and determining the car light area on each image in each group of images, when the brightness parameters of the car light area on each image in each group of images all meet the preset brightness condition, and the snapshot duration is greater than or equal to the preset duration, determining that the high beam of the vehicle is illegally started, otherwise, determining that the vehicle is not illegally started.
Optionally, when determining the car light region on each image in each group of images, the image acquisition device is specifically configured to, for each group of images, input a first image in the group of images into the trained position determination model to obtain the position information of the car light region in the first image; the first image is a snapshot of the group of images by adopting the first specified exposure parameter; searching a corresponding area on the first image according to the car lamp area position information, and determining the searched area as a car lamp area of the first image; searching a region corresponding to the car light region position information on a second image in the group of images, and determining the searched region as a car light region of the second image; the second image is an image in the group of images that is captured by using the second specified exposure parameter.
Optionally, the brightness parameter of the headlight region on each image in each group of images is determined as follows:
determining the average brightness value of the car light region on each group of images, carrying out binarization processing on the images, and calculating the pixel quantity ratio of the number of foreground pixels and the number of background pixels in the images after binarization processing; in the binary processed image, the car light area is used as a foreground, and other areas are used as backgrounds;
and determining the average brightness value and the pixel quantity ratio as the brightness parameter of the image.
Optionally, the preset brightness condition includes:
the average brightness value in the brightness parameter is greater than or equal to a preset brightness threshold value, and the pixel quantity ratio value in the brightness parameter is greater than or equal to a preset pixel quantity ratio threshold value.
Optionally, the image acquisition device is further configured to synthesize each image of the group of captured images to obtain a synthesized image after determining that the high beam is turned on due to violation of the vehicle; and identifying the vehicle information of the vehicle which breaks rules and opens the high beam from the composite image.
The specific details of the implementation process of the functions and actions of each unit in the above device are the implementation processes of the corresponding steps in the above method, and are not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims (17)

1. A high beam light starting detection method is characterized in that the method is applied to a light intensity detection device, and the method comprises the following steps:
when detecting that the light entering the photosensitive sensor in the equipment has a first change, wherein the first change is that the light entering amount of the equipment is changed from being smaller than a preset threshold to being larger than or equal to the preset threshold, sending a snapshot signal to the image acquisition equipment to trigger the image acquisition equipment to snapshot an image according to a set snapshot mode, wherein the snapshot image is used for detecting whether a vehicle high beam is turned on or not; the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device;
when detecting that the quantity of the incoming light entering the photosensitive sensor in the device changes for the second time, wherein the second change means that the quantity of the incoming light of the device changes from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, determining that the detected vehicle has driven away from the monitoring area, and sending a snapshot finishing signal to the image acquisition device to trigger the image acquisition device to finish the snapshot.
2. The method of claim 1, wherein the detecting a first change in the amount of incoming light to the device comprises:
detecting that the amount of incoming light entering the device at present is greater than or equal to a preset threshold value, and the configured incoming light flag is a first value, where the first value is used to indicate that the previous amount of incoming light is less than the preset threshold value, and then determining that the amount of incoming light of the device has a first change.
3. The method according to claim 2, wherein determining that the amount of light entering the apparatus has the first change, further comprises: updating the configured light entering flag from a first value to a second value, wherein the second value is used for indicating that the light entering amount is larger than or equal to a preset threshold value;
the detecting of the second change of the light entering amount of the device comprises:
detecting that the light entering the equipment at present is smaller than a preset threshold value and the configured light entering flag is a second value, and determining that the light entering amount of the equipment is changed for the second time;
after determining that the second change occurs in the light entering amount of the present device, the method further includes:
and updating the value of the light incoming mark from the second value to the first value.
4. A method for detecting the opening of a high beam is characterized in that the method is applied to an image acquisition device, and comprises the following steps:
when light intensity detection equipment detects that the quantity of incoming light entering a photosensitive sensor in the equipment has a first change, wherein the first change is that when a snapshot signal sent by the light intensity detection equipment is received under the condition that the quantity of incoming light of the equipment is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value, an image is snapshot according to a set snapshot mode, and the snapshot image is used for detecting whether a high beam of a vehicle is turned on or not; the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device;
when the light intensity detection device detects that the quantity of light entering a photosensitive sensor in the device has a second change, wherein the second change is that the quantity of light entering the device is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value and the vehicle is determined to be driven away from the monitoring area, the snapshot image is finished when a snapshot finishing signal sent by the light intensity detection device is received;
carrying out vehicle high beam opening detection according to the snapshot duration and the snapshot image; the snapshot duration is a time difference from a first time point when the snapshot signal is received to a second time point when the snapshot ending signal is received.
5. The method of claim 4, wherein said capturing an image in a set capture mode comprises:
the method comprises the following steps of executing snapshot operation according to a set time interval, wherein the snapshot operation comprises the following steps: respectively capturing images by adopting a first specified exposure parameter and a second specified exposure parameter; the first designated exposure parameter at least comprises a first exposure time, the second designated exposure parameter at least comprises a second exposure time, and the first exposure time is smaller than the second exposure time.
6. The method according to claim 5, wherein the detecting of the turning on of the high beam of the vehicle according to the snapshot duration and the snapshot image comprises:
acquiring a group of images captured when each capturing operation is performed; the group of images captured when performing the capturing operation includes: the method comprises the steps of capturing an image by adopting a first specified exposure parameter and capturing an image by adopting a second specified exposure parameter;
and determining the car light area on each image in each group of images, when the brightness parameters of the car light area on each image in each group of images all meet the preset brightness condition, and the snapshot duration is greater than or equal to the preset duration, determining that the high beam is turned on by the vehicle, otherwise, determining that the high beam is not turned on by the vehicle.
7. The method of claim 6, wherein determining the headlight region on each image in each set of images comprises:
for each group of images, inputting a first image in the group of images into a trained position determination model to obtain position information of a vehicle lamp area in the first image; the first image is a snapshot of the group of images by adopting the first specified exposure parameter;
searching a corresponding area on the first image according to the car lamp area position information, and determining the searched area as a car lamp area of the first image;
searching a region corresponding to the car light region position information on a second image in the group of images, and determining the searched region as a car light region of the second image; the second image is an image in the group of images that is captured by using the second specified exposure parameter.
8. The method of claim 6, wherein the brightness parameter of the headlight region on each image in each set of images is determined by:
determining the average brightness value of the car light region on each group of images, carrying out binarization processing on the images, and calculating the pixel quantity ratio of the number of foreground pixels and the number of background pixels in the images after binarization processing; in the binary processed image, the car light area is used as a foreground, and other areas are used as backgrounds;
and determining the average brightness value and the pixel quantity ratio as the brightness parameter of the image.
9. The method of claim 8, wherein the preset brightness condition comprises:
the average brightness value in the brightness parameter is greater than or equal to a preset brightness threshold value, and the pixel quantity ratio value in the brightness parameter is greater than or equal to a preset pixel quantity ratio threshold value.
10. The method of claim 5, wherein after determining that the vehicle has the high beam turned on, the method further comprises:
synthesizing all the images of one group of the captured images to obtain a synthesized image;
and identifying the vehicle information of the vehicle which turns on the high beam from the composite image.
11. A high beam turn-on detection system, the system comprising: the device comprises a light intensity detection device and an image acquisition device;
the light intensity detection device is used for sending a snapshot signal to the image acquisition device when detecting that the quantity of light entering the photosensitive sensor in the device changes from being smaller than a preset threshold value to being larger than or equal to the preset threshold value; when detecting that the quantity of incoming light entering a photosensitive sensor in the equipment has a second change, wherein the second change is that the quantity of incoming light of the equipment is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, determining that the detected vehicle has driven away from a monitoring area of the image acquisition equipment, and sending a snapshot finishing signal to the image acquisition equipment;
the image acquisition equipment is used for snapshotting an image according to a set snapshotting mode when receiving a snapshotting signal sent by the light intensity detection equipment; when a snapshot finishing signal sent by the light intensity detection equipment is received, finishing snapshot of the image; carrying out vehicle high beam opening detection according to the snapshot duration and the snapshot image; the snapshot duration is the time difference from a first time point when the snapshot signal is received to a second time point when the snapshot finishing signal is received;
wherein the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device.
12. A light intensity detecting apparatus characterized by comprising: a photosensor, and a control module;
the photosensitive sensor is used for sending the light entering the photosensitive sensor in the device to the control module;
the control module is used for sending a snapshot signal to the image acquisition equipment to trigger the image acquisition equipment to snapshot an image according to a set snapshot mode when detecting that the light entering the photosensitive sensor in the equipment has a first change, wherein the first change is that the light entering amount of the equipment is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value, and the snapshot image is used for detecting the opening of a high beam of a vehicle; the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device; when detecting that the quantity of the incoming light entering the photosensitive sensor in the device changes for the second time, wherein the second change means that the quantity of the incoming light of the device changes from being larger than or equal to a preset threshold value to being smaller than the preset threshold value, determining that the detected vehicle has driven away from the monitoring area, and sending a snapshot finishing signal to the image acquisition device to trigger the image acquisition device to finish the snapshot.
13. The apparatus according to claim 12, wherein the control module, when detecting that the amount of incoming light of the apparatus changes first, is configured to detect that the amount of incoming light currently entering the apparatus is greater than or equal to a preset threshold, and the configured incoming light flag is a first value, and the first value is used to indicate that the previous amount of incoming light is less than the preset threshold, and then determine that the amount of incoming light of the apparatus changes first.
14. The apparatus according to claim 13, wherein the control module, upon determining that the amount of light entering the apparatus has changed for the first time, is further configured to update the configured light entering flag from a first value to a second value, the second value indicating that the amount of light entering is greater than or equal to a preset threshold;
the control module is used for detecting that the current light inlet amount entering the equipment is smaller than a preset threshold value and the configured light inlet flag is a second value when detecting that the second change occurs in the light inlet amount of the equipment, and then determining that the second change occurs in the light inlet amount of the equipment; and after the light entering amount of the equipment is determined to be changed for the second time, the light entering device is also used for updating the value of the light entering mark from the second value to the first value.
15. The apparatus according to any one of claims 12 to 14, wherein the light intensity detecting apparatus comprises: a light inlet and a light filter; the light inlet is arranged to be inclined relative to the axial direction of the optical filter; the optical filter is used for filtering light except for the high beam.
16. The utility model provides a detection device is opened to high beam, its characterized in that, the device is applied to image acquisition equipment, the device includes:
the snapshot unit is used for snapshotting an image according to a set snapshot mode when receiving a snapshot signal sent by the light intensity detection device under the condition that the light intensity detection device detects that the light entering amount of the photosensitive sensor in the device is changed from being smaller than a preset threshold value to being larger than or equal to the preset threshold value; the snapshot image is used for detecting whether a high beam of the vehicle is turned on or not; the detection area of the light intensity detection device is a subset of the monitoring area of the image acquisition device;
the snapshot finishing unit is used for finishing snapshot images when receiving a snapshot finishing signal sent by the light intensity detection equipment under the condition that the light intensity detection equipment detects that the quantity of light entering the photosensitive sensor in the equipment is changed from being larger than or equal to a preset threshold value to being smaller than the preset threshold value and the detected vehicle is determined to drive away from the monitored area;
the detection unit is used for carrying out vehicle high beam opening detection according to the snapshot duration and the snapshot image; the snapshot duration is a time difference from a first time point when the snapshot signal is received to a second time point when the snapshot finishing signal is received.
17. An image acquisition device, characterized in that the device comprises a readable storage medium and a processor;
wherein the readable storage medium is configured to store machine executable instructions;
the processor configured to read the machine executable instructions on the readable storage medium and execute the instructions to implement the steps of the method of any one of claims 4 to 10.
CN202010372858.6A 2020-05-06 2020-05-06 High beam light starting detection method, device, equipment and system Active CN113628447B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010372858.6A CN113628447B (en) 2020-05-06 2020-05-06 High beam light starting detection method, device, equipment and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010372858.6A CN113628447B (en) 2020-05-06 2020-05-06 High beam light starting detection method, device, equipment and system

Publications (2)

Publication Number Publication Date
CN113628447A CN113628447A (en) 2021-11-09
CN113628447B true CN113628447B (en) 2022-12-23

Family

ID=78376533

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010372858.6A Active CN113628447B (en) 2020-05-06 2020-05-06 High beam light starting detection method, device, equipment and system

Country Status (1)

Country Link
CN (1) CN113628447B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116698377B (en) * 2023-07-31 2023-10-03 常州星宇车灯股份有限公司 ADB function test method and system for automobile LED matrix headlight

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102014006598A1 (en) * 2014-05-06 2015-11-12 Audi Ag Method for operating a driver assistance system of a motor vehicle, driver assistance system and motor vehicle
CN108417043A (en) * 2018-02-09 2018-08-17 浙江安谐智能科技有限公司 A kind of detection method that high beam persistently opens
CN110823533A (en) * 2019-09-10 2020-02-21 李东华 Non-standard light detection system and detection method thereof

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104008650A (en) * 2014-05-20 2014-08-27 宁辉 Motor vehicle high beam monitoring device and identification method thereof
CN104065930B (en) * 2014-06-30 2017-07-07 青岛歌尔声学科技有限公司 The vision householder method and device of integrated camera module and optical sensor
CN104574956B (en) * 2014-12-05 2017-01-18 大连民族学院 Monitoring device for abuse of high beam during meeting of vehicles at night
CN204440645U (en) * 2015-02-16 2015-07-01 北京精英智通科技股份有限公司 A kind of driving at night illegal use high beam behavior automatic evidence-collecting equipment
CN205388828U (en) * 2016-01-20 2016-07-20 王威立 Motor vehicle far -reaching headlamp is violating regulations to be detected and snapshot system
WO2017128012A1 (en) * 2016-01-25 2017-08-03 黄冠明 Method for collecting data about technology for prompting of switching to low beam headlamps, and prompting system
CN107563265B (en) * 2016-06-30 2021-08-17 杭州海康威视数字技术股份有限公司 High beam detection method and device
CN206164739U (en) * 2016-11-30 2017-05-10 中山大学 Automation video recording that vehicle far -reaching headlamp used is in violation of rules and regulations collected evidence and enforcement system
CN108875458B (en) * 2017-05-15 2020-11-06 杭州海康威视数字技术股份有限公司 Method and device for detecting turning-on of high beam of vehicle, electronic equipment and camera
CN207650994U (en) * 2017-11-29 2018-07-24 武汉万集信息技术有限公司 A kind of night meeting high beam violation detection device based on RFID
CN108986476B (en) * 2018-08-07 2019-12-06 安徽金赛弗信息技术有限公司 method, system and storage medium for recognizing non-use of high beam by motor vehicle according to regulations
CN110246337A (en) * 2018-08-10 2019-09-17 浙江大华技术股份有限公司 A kind of method, apparatus and computer storage medium detecting Misuse car light
CN210112100U (en) * 2018-08-31 2020-02-21 百度在线网络技术(北京)有限公司 Intelligent road side unit

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102014006598A1 (en) * 2014-05-06 2015-11-12 Audi Ag Method for operating a driver assistance system of a motor vehicle, driver assistance system and motor vehicle
CN108417043A (en) * 2018-02-09 2018-08-17 浙江安谐智能科技有限公司 A kind of detection method that high beam persistently opens
CN110823533A (en) * 2019-09-10 2020-02-21 李东华 Non-standard light detection system and detection method thereof

Also Published As

Publication number Publication date
CN113628447A (en) 2021-11-09

Similar Documents

Publication Publication Date Title
CN107967806B (en) Vehicle fake-license detection method, device, readable storage medium storing program for executing and electronic equipment
CN101833859B (en) Self-triggering license plate identification method based on virtual coil
CN109515304B (en) Vehicle lamp control method, device and system
US8233662B2 (en) Method and system for detecting signal color from a moving video platform
CN103886759B (en) System and method for snapshotting behavior of running red light
KR101971878B1 (en) Video surveillance system and method using deep-learning based car number recognition technology in multi-lane environment
CN109716400B (en) Image recording apparatus, image recording method, and storage medium
CN102556021B (en) Control device for preventing cars from running red light
US9077907B2 (en) Image processing apparatus
CN105046966A (en) System and method for automatically detecting illegal parking behaviors in drop-off areas
US20220375341A1 (en) Peccancy monitoring system and peccancy monitoring method
CN113246846A (en) Vehicle light control method and device and vehicle
CN113628447B (en) High beam light starting detection method, device, equipment and system
CN204856897U (en) It is detection device violating regulations in abscission zone territory that motor vehicle stops promptly
US8229170B2 (en) Method and system for detecting a signal structure from a moving video platform
CN114708533A (en) Target tracking method, device, equipment and storage medium
US20130335601A1 (en) Imaging apparatus which suppresses fixed pattern noise generated by an image sensor of the apparatus
CN111046741A (en) Method and device for identifying lane line
CN115690441A (en) Traffic signal lamp area detection method, device and equipment
CN111523368B (en) Information processing device, server, and traffic management system
CN111768630A (en) Violation waste image detection method and device and electronic equipment
CN112232441B (en) Illegal parking judgment method, system, computer equipment and storage medium
CN113581059A (en) Light adjusting method and related device
JPH11219493A (en) Method for processing traffic information
KR101686244B1 (en) Accident record apparatus for the use of a vehicle to recognize day and night and accident record method of the same

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant