CN111402610B - Method, device, equipment and storage medium for identifying lighting state of traffic light - Google Patents
Method, device, equipment and storage medium for identifying lighting state of traffic light Download PDFInfo
- Publication number
- CN111402610B CN111402610B CN202010207250.8A CN202010207250A CN111402610B CN 111402610 B CN111402610 B CN 111402610B CN 202010207250 A CN202010207250 A CN 202010207250A CN 111402610 B CN111402610 B CN 111402610B
- Authority
- CN
- China
- Prior art keywords
- traffic light
- image
- determining
- light image
- target
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
Abstract
The application discloses a method, a device, equipment and a storage medium for identifying the lighting state of a traffic light, which comprises the following steps: carrying out image recognition on a target image, and determining a traffic light image on the target image; and determining the position of the bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in the HSV space, so that the bright light state of the traffic light can be determined according to the position of the bright point area in the traffic light image. Because the positions of the red light, the yellow light and the green light on the traffic light are fixed in practical application, in the process of identifying the light-on state of the traffic light, which light is in the light-on state at present can be accurately determined according to the position of the bright point area in the traffic light image. Therefore, even if the traffic light is in an environment with weak light, the lighting state of the traffic light can be accurately identified according to the image obtained by shooting the traffic light.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for identifying a lighting status of a traffic light.
Background
In practical application scenes such as automatic driving or auxiliary driving, traffic lights on a driving road in front of a vehicle often need to be identified, so that driving control is performed on the vehicle or corresponding prompt is made for driving behaviors of a driver according to the identified light-on condition of the traffic lights.
At present, when the lighting condition of a traffic light is identified, color identification is mainly performed on an image obtained by photographing the traffic light to determine which light is in a bright state at present, and for example, when a green light image is identified in the image, the traffic light can be considered to be in a bright-green state at present. However, when the photographing device is used to photograph the traffic lights in an environment with poor light, the accuracy of the traffic light recognition result obtained by performing color recognition on the photographed image is often poor.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a storage medium for identifying the lighting state of a traffic light, so as to improve the accuracy of identifying the lighting result of the traffic light.
In a first aspect, an embodiment of the present application provides a traffic light identification method, including:
carrying out image recognition on a target image, and determining a traffic light image on the target image;
determining the position of a bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in a hue saturation value HSV space;
and determining the lighting state of the traffic light according to the position of the bright point area in the traffic light image.
In some possible embodiments, the image recognizing the target image and determining the traffic light image on the target image includes:
determining a region to be detected on a target image, wherein the region to be detected comprises a traffic light image;
and carrying out edge detection on the traffic light image in the area to be detected to obtain the traffic light image.
In some possible embodiments, the determining, according to the pixel value of each pixel point in the traffic light image in the hue saturation value HSV space, the position of the bright point area in the traffic light image includes:
determining a target pixel point in the traffic light image, wherein the pixel value of the target pixel point in a brightness V channel of the HSV space is greater than a preset threshold value;
and determining the central position of a bright spot area as the position of the bright spot area in the traffic light image, wherein pixel points in the bright spot area are the target pixel points.
In some possible embodiments, the determining a lighting state of a traffic light according to a position of the bright point area in the traffic light image includes:
when the position of the bright point area in the traffic light image is located in a first area in the traffic light image, determining that the lighting state of the traffic light is red light;
when the position of the bright spot area in the traffic light image is located in a second area in the traffic light image, determining that the lighting state of the traffic light is yellow light;
when the position of the bright point area in the traffic light image is located in a third area in the traffic light image, determining that the lighting state of the traffic light is green light;
wherein the first region, the second region, and the third region do not overlap each other.
In some possible embodiments, the method further comprises:
acquiring a light detection result of a shooting environment for the target image;
the determining the position of the bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in the hue saturation value HSV space comprises the following steps:
when the light detection result represents that light aiming at the shooting environment of the target image is weak, determining the position of a bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in a hue saturation value HSV space.
In some possible embodiments, the method further comprises:
and when the light detection result represents that the light aiming at the shooting environment of the target image is strong, carrying out color identification on the traffic light image, and determining the lighting state of the traffic light.
In a second aspect, an embodiment of the present application further provides a device for identifying a lighting state of a traffic light, including:
the image recognition module is used for carrying out image recognition on a target image and determining a traffic light image on the target image;
the first determining module is used for determining the position of a bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in a hue saturation value HSV space;
and the second determining module is used for determining the lighting state of the traffic light according to the position of the bright point area in the traffic light image.
In some possible embodiments, the first determining module includes:
the first determining unit is used for determining a target pixel point in the traffic light image, and the pixel value of the target pixel point in a brightness V channel of the HSV space is greater than a preset threshold value;
the second determining unit is configured to determine a central position of a bright point region as a position of the bright point region in the traffic light image, where a pixel point in the bright point region is the target pixel point.
In some possible embodiments, the image recognition module includes:
the third determining unit is used for determining a region to be detected on the target image, wherein the region to be detected comprises a traffic light image;
and the edge detection unit is used for carrying out edge detection on the traffic light image in the area to be detected to obtain the traffic light image.
In some possible embodiments, the second determining module includes:
a fourth determining unit, configured to determine that the lighting state of the traffic light is red when the position of the bright point area in the traffic light image is located in the first area in the traffic light image;
a fifth determining unit, configured to determine that a lighting state of the traffic light is yellow when a position of the bright point area in the traffic light image is located in a second area in the traffic light image;
a sixth determining unit, configured to determine that a lighting state of the traffic light is a green light when a position of the bright point area in the traffic light image is located in a third area in the traffic light image;
wherein the first region, the second region, and the third region do not overlap each other.
In some possible embodiments, the apparatus further comprises:
the acquisition module is used for acquiring a light detection result of a shooting environment aiming at the target image;
the first determining module is specifically configured to determine, when the light detection result represents that light in a shooting environment for the target image is weak, a position of a bright point area in the traffic light image according to a pixel value of each pixel point in a hue saturation value HSV space in the traffic light image.
In some possible embodiments, the apparatus further comprises:
and the color identification module is used for carrying out color identification on the traffic light image and determining the lighting state of the traffic light when the light detection result represents that the light aiming at the shooting environment of the target image is stronger.
In a third aspect, an embodiment of the present application further provides an apparatus, where the apparatus includes a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the method for identifying a lighting state of a traffic light according to any one of the first aspect described above according to instructions in the program code.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium is used to store a computer program, where the computer program is used to execute the method for identifying a lighting state of a traffic light in any one of the above first aspects.
In the implementation manner of the embodiment of the application, the target image can be subjected to image recognition, the traffic light image on the target image is determined, and then the position of the bright point area in the traffic light image is determined according to the pixel value of each pixel point in the traffic light image in the HSV space, so that the bright light state of the traffic light can be determined according to the position of the bright point area in the traffic light image. Because the positions of the red light, the yellow light and the green light on the traffic light are fixed in practical application, in the process of identifying the light-on state of the traffic light, the current light of the traffic light can be determined to be in the light-on state according to the position of the bright point area in the traffic light image. Therefore, even if the traffic light is in an environment with weak light, the lighting state of the traffic light can be accurately identified according to the image obtained by shooting the traffic light.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a schematic diagram of an exemplary application scenario in an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating a method for identifying a lighting state of a traffic light in an embodiment of the present application;
FIG. 3 is a schematic diagram of an exemplary traffic light;
FIG. 4 is a schematic view of yet another exemplary traffic light;
fig. 5 is a schematic structural diagram of an apparatus for identifying a lighting state of a traffic light in an embodiment of the present application;
fig. 6 is a schematic hardware structure diagram of an apparatus in an embodiment of the present application.
Detailed Description
In practical application scenarios such as automatic driving or assisted driving, the lighting condition of a traffic light on a vehicle driving path is usually recognized, so as to control the vehicle driving state or give a corresponding prompt to a driver. However, in the current traffic light identification scheme, after an image including a traffic light is obtained by shooting, a halo formed on the image by a bright light of the traffic light is generally identified to determine a bright light state of the traffic light, for example, when the halo appears green, it indicates that the traffic light is currently bright green, and when the halo appears red, it indicates that the traffic light is currently bright red.
However, the inventor of the present invention has found that, when a traffic light is photographed, if the traffic light is in an environment with weak light, a halo formed in the photographed image by a bright light in the image is not obvious, and it is difficult to accurately identify which light is currently in a bright state according to the color of the halo. In practical application, it is important to accurately identify the lighting state of the traffic light, and the driving safety of the vehicle (especially an automatic driving scene) is seriously affected by the wrong identification of the lighting state of the traffic light.
Based on this, the embodiment of the application provides a method for identifying the lighting state of a traffic light, aiming at improving the accuracy rate of identifying the lighting result of the traffic light, thereby improving the driving safety of a vehicle. Specifically, the image recognition can be performed on the target image, the traffic light image on the target image is determined, and then the position of the bright point area in the traffic light image is determined according to the pixel value of each pixel point in the traffic light image in an HSV (hue, saturation and brightness) space, so that the bright light state of the traffic light can be determined according to the position of the bright point area in the traffic light image. Because the red light, the yellow light and the green light are fixed in position on the traffic light in practical application, in the process of identifying the bright light state of the traffic light, according to the position of the bright point area in the traffic light image, it can be determined which light is currently in the bright light state of the traffic light, for example, when the bright point area is in the middle position in the traffic light image, it is generally characterized that the traffic light is currently bright as the yellow light (in practical application, the yellow light is located in the middle of the traffic light). Therefore, even if the traffic light is in an environment with weak light, the lighting state of the traffic light can be accurately identified according to the image obtained by shooting the traffic light.
As an example, the embodiment of the present application may be applied to an exemplary application scenario as shown in fig. 1. In this scenario, a camera 101 may be disposed on the vehicle 100, and the camera 101 may capture traffic lights on a road in front of the vehicle 100 to obtain an image (hereinafter referred to as a target image) including a traffic light image; then, the controller 102 on the vehicle 100 may acquire the target image from the camera 101, perform image recognition on the target image, and determine the traffic light image on the target image, so as to determine the position of the bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in the HSV space, and further determine the lighting state of the traffic light according to the position of the bright point area in the traffic light image, so as to control the form state of the vehicle 100 according to the determined lighting state, and if the traffic light is determined to be a bright red light, the vehicle 100 may be controlled to decelerate to 0.
It is to be understood that the above scenario is only one example of a scenario provided in the embodiment of the present application, and the embodiment of the present application is not limited to this scenario. For example, the identification process of the lighting state of the traffic light may also be completed by the server, that is, the vehicle 100 may send the target image to the server, and the server processes the target image to obtain a corresponding identification result and feeds the identification result back to the vehicle 100; or the identification process of the lighting state of the traffic light is completed by the cooperation of the vehicle 100 and the server, and the like. In summary, the embodiments of the present application may be applied in any applicable scenario and are not limited to the scenario examples described above.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, various non-limiting embodiments accompanying the present application examples are described below with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a method for identifying a lighting state of a traffic light in an embodiment of the present application. The method may be applied to the vehicle 100 shown in fig. 1, may be applied to a server, or may be cooperatively implemented by the vehicle 100 and the server. The method specifically comprises the following steps:
s201: and carrying out image recognition on the target image, and determining the traffic light image on the target image.
In this embodiment, the lighting state of the traffic light may be determined according to an image including the traffic light. In practical applications, a shooting device (such as a camera disposed on a vehicle) may be used to shoot a traffic light, so as to obtain an image (hereinafter referred to as a target image) including a traffic light image; then, the traffic light image on the target image can be determined by carrying out image recognition on the target image.
As a specific implementation example of image recognition, a region to be detected on a target image may be determined, and of course, the region to be detected includes a traffic light image. The method includes determining a region to be detected, that is, determining an approximate position of a traffic light image on a target image, where the region to be detected may include images of other contents, such as an image including a part of sky, in addition to the traffic light image. Further, in practical application, the determined region to be detected can be marked on the target image by using a two-dimensional frame. Then, edge detection can be performed on the traffic light image in the determined region to be detected, so that the traffic light image is obtained. The contour of the traffic light image can be determined by utilizing an edge detection technology, so that a plurality of pixel points in the contour can form the traffic light image.
For example, when the area to be detected on the target image is determined, the high-precision map may be used to complete the positioning of the traffic light image, and specifically, the high-precision map may be used to obtain the position information of the traffic light image, so that the image position corresponding to the position information may be determined from the target image, and thus, the traffic light image may be determined on the target image based on the image position. In other possible embodiments, the region to be detected on the target image may also be detected by image similarity comparison and the like. It should be noted that, the area to be detected including the traffic light image is identified and determined on the target image, and there are other possible embodiments in the prior art, which is not limited in this embodiment.
S202: and determining the position of a bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in the HSV space.
In an actual application scene, only one traffic light is usually on at the same time, an image of a shell of the traffic light on a traffic light image is usually black, an image of a light in an off state on the traffic light image is also black or nearly black, and an image of only the light in the current bright state on the traffic light image is a region with a white edge as a color halo at the center, namely a bright spot region. Therefore, in the embodiment, the position of the bright point area in the traffic light image can be located first, so as to further identify which light of the traffic light is currently on based on the position.
In the concrete implementation, the position of the bright point area in the traffic light image can be determined according to the pixel value of each pixel point in the traffic light image in the HSV space. The HSV (Hue, Saturation, and brightness) space is a color space created according to the intuitive characteristics of colors, and includes three parameters, namely Hue (Hue, abbreviated as H), Saturation (Saturation, abbreviated as S), and brightness (Value, abbreviated as V). According to the pixel value of the pixel point in the HSV space, the bright point area can be distinguished from the black image area on the traffic light image.
In a further embodiment, the position of the bright point region in the traffic light image may be determined according to the pixel value of the V channel in the HSV space. Specifically, the pixel value of each pixel point in the traffic light image in the V channel of the HSV space may be determined, and the pixel point with the pixel value of the V channel being greater than the preset threshold may be determined as the target pixel point, and the determined target pixel point constitutes the bright point region. It can be understood that the brightness can represent the brightness degree of the color, and the larger the brightness value is, the larger the brightness of the representative illuminant is, so that the pixel points with the brightness value larger than the preset threshold value can be regarded as the pixel points forming the image of the bright light on the traffic light image, that is, the pixel points in the bright point region.
Then, the central position of the bright point region can be calculated, specifically, the pixel point located at the central position in the target pixel points can be determined according to the pixel coordinates of each target pixel point on the traffic light image, so that the position (pixel coordinate) of the pixel point can be determined as the central position of the bright point region. In this embodiment, the calculated center position of the bright point area can be used as the position of the bright point area in the traffic light image.
It should be noted that, in the present embodiment, the embodiment that the central position of the bright point area is taken as the position of the bright point area in the traffic light image is merely an example, and is not used to limit the specific embodiment for determining the position of the bright point area.
S203: and determining the lighting state of the traffic light according to the position of the bright spot area in the traffic light image.
In practical applications, the positions of the respective lights (such as the red light, the yellow light and the green light) in the traffic light are fixed, as shown in fig. 3, the light located at the left side of the traffic light is usually the red light, the light located at the middle of the traffic light is usually the yellow light, and the light located at the right side of the traffic light is usually the green light; as also shown in fig. 4, the lights located above the traffic lights are typically red lights, the lights located in the middle of the traffic lights are typically yellow lights, and the lights located below the traffic lights are typically green lights. Therefore, in the embodiment, which position the light is in the bright state can be determined according to the position of the bright point in the traffic light image, so that the bright state of the traffic light can be determined.
In an exemplary embodiment, when it is determined that the position of the bright point area in the traffic light image is located in the first area (e.g., the left position shown in fig. 3 or the upper position shown in fig. 4) in the traffic light image, it may be determined that the bright light state of the traffic light is the bright red light; when the position of the bright point area in the traffic light image is determined to be located in a second area (such as the middle position shown in fig. 3 or fig. 4) in the traffic light image, the lighting state of the traffic light can be determined to be the yellow light; when the position of the bright point area in the traffic light image is determined to be located in a third area (such as the right position shown in fig. 3 or the lower position shown in fig. 4) in the traffic light image, it may be determined that the lighting state of the traffic light is the green light. Of course, the first region, the second region, and the third region do not overlap with each other. Because which lamp of the traffic lights is in the bright state is determined according to the position of the bright spot area, even if the traffic lights are in an environment with weak light, the bright state of the traffic lights can be accurately identified, so that the identification precision of the bright state of the traffic lights can be improved, and the driving safety in an automatic driving or auxiliary driving scene can be further improved.
It can be understood that, in the above embodiments, the identification of the lighting state of the traffic light is mainly performed in a scene where the traffic light is in a weak light, and therefore, before the step S202 and the step S203 are adopted to identify the lighting state of the traffic light, whether the traffic light is in an environment with weak light or not may be detected, and in the specific implementation, the light detection result of the shooting environment of the target image can be obtained by means of light detection through the light sensor, and when the light detection result represents that the light of the shooting environment for the target image is weak, after the traffic light image is determined, step S202 and step S203 may be executed to identify the lighting state of the traffic light, and when the light detection result represents that the light aiming at the shooting environment of the target image is strong, the color halo imaging of the bright lamp on the traffic light image is obvious, so that the bright lamp state of the traffic light can be directly identified based on the halo. Of course, in practical applications, even if it is detected that the light of the shooting environment is strong, the lighting state of the traffic light may be identified by performing the processes of step S202 and step S203.
In this embodiment, image recognition may be performed on a target image, a traffic light image on the target image is determined, and then, according to a pixel value of each pixel point in the traffic light image in the HSV space, a position of a bright point area in the traffic light image is determined, so that a bright light state of a traffic light may be determined according to the position of the bright point area in the traffic light image. Because the positions of the red light, the yellow light and the green light on the traffic light are fixed in practical application, in the process of identifying the light-on state of the traffic light, the current light of the traffic light can be determined to be in the light-on state according to the position of the bright point area in the traffic light image. Therefore, even if the traffic light is in an environment with weak light, the lighting state of the traffic light can be accurately identified according to the image obtained by shooting the traffic light.
In addition, the embodiment of the application also provides a traffic light information identification device. Referring to fig. 5, fig. 5 shows a schematic structural diagram of a traffic light information identification apparatus in an embodiment of the present application, where the apparatus 500 may specifically include:
the image recognition module 501 is configured to perform image recognition on a target image and determine a traffic light image on the target image;
a first determining module 502, configured to determine, according to a pixel value of each pixel point in the traffic light image in a hue saturation value HSV space, a position of a bright point area in the traffic light image;
the second determining module 503 is configured to determine a lighting state of the traffic light according to a position of the bright point area in the traffic light image.
In some possible embodiments, the first determining module 502 includes:
the first determining unit is used for determining a target pixel point in the traffic light image, and the pixel value of the target pixel point in a brightness V channel of the HSV space is greater than a preset threshold value;
the second determining unit is configured to determine a central position of a bright point region as a position of the bright point region in the traffic light image, where a pixel point in the bright point region is the target pixel point.
In some possible embodiments, the image recognition module 501 includes:
the third determining unit is used for determining a region to be detected on the target image, wherein the region to be detected comprises a traffic light image;
and the edge detection unit is used for carrying out edge detection on the traffic light image in the area to be detected to obtain the traffic light image.
In some possible embodiments, the second determining module 503 includes:
a fourth determining unit, configured to determine that the lighting state of the traffic light is red when the position of the bright point area in the traffic light image is located in the first area in the traffic light image;
a fifth determining unit, configured to determine that a lighting state of the traffic light is yellow when a position of the bright point area in the traffic light image is located in a second area in the traffic light image;
a sixth determining unit, configured to determine that a lighting state of the traffic light is a green light when a position of the bright point area in the traffic light image is located in a third area in the traffic light image;
wherein the first region, the second region, and the third region do not overlap each other.
In some possible embodiments, the apparatus 500 further comprises:
the acquisition module is used for acquiring a light detection result of a shooting environment aiming at the target image;
the first determining module is specifically configured to determine, when the light detection result represents that light in a shooting environment for the target image is weak, a position of a bright point area in the traffic light image according to a pixel value of each pixel point in a hue saturation value HSV space in the traffic light image.
In some possible embodiments, the apparatus 500 further comprises:
and the color identification module is used for carrying out color identification on the traffic light image and determining the lighting state of the traffic light when the light detection result represents that the light aiming at the shooting environment of the target image is stronger.
It should be noted that, for the contents of information interaction, execution process, and the like between the modules and units of the apparatus, since the same concept is based on the method embodiment in the embodiment of the present application, the technical effect brought by the contents is the same as that of the method embodiment in the embodiment of the present application, and specific contents may refer to the description in the foregoing method embodiment in the embodiment of the present application, and are not described herein again.
In this embodiment, because the red light, the yellow light, and the green light are fixed in position on the traffic light in practical application, in the process of identifying the light-on state of the traffic light, which light is currently in the light-on state of the traffic light can be determined according to the position of the bright point area in the traffic light image. Therefore, even if the traffic light is in an environment with weak light, the lighting state of the traffic light can be accurately identified according to the image obtained by shooting the traffic light.
In addition, the embodiment of the application also provides equipment. Referring to fig. 6, fig. 6 shows a hardware structure diagram of an apparatus in an embodiment of the present application, and the apparatus 600 may include a processor 601 and a memory 602.
Wherein the memory 602 is used for storing computer programs;
the processor 601 is configured to execute the method for identifying the lighting state of the traffic light according to the computer program in the above method embodiments.
In addition, a computer-readable storage medium is provided in an embodiment of the present application, and is configured to store a computer program, where the computer program is configured to execute the method for identifying a lighting state of a traffic light in the above method embodiment.
In the names of the "first determination module", "first determination unit", and the like, the "first" mentioned in the embodiments of the present application is used only for name identification, and does not represent the first in sequence. The same applies to "second", "third", "fourth", etc.
As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by software plus a general hardware platform. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a read-only memory (ROM)/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network communication device such as a router, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the method embodiment for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, may be located in one position, or may be distributed on a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only an exemplary embodiment of the present application, and is not intended to limit the scope of the present application.
Claims (8)
1. A method of identifying a lighting status of a traffic light, the method comprising:
performing image recognition on a target image, and determining a traffic light image on the target image, wherein the target image is an image obtained by shooting under the condition that the traffic light is weak; the image recognition of the target image and the determination of the traffic light image on the target image comprise: acquiring position information of the traffic light image by using a high-precision map, determining an image position corresponding to the position information from the target image, and determining the traffic light image on the target image based on the image position;
determining the position of a bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in a hue saturation value HSV space;
the determining the position of the bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in the hue saturation value HSV space comprises the following steps: determining a target pixel point in the traffic light image, wherein the pixel value of the target pixel point in a brightness V channel of the HSV space is larger than a preset threshold value; determining the central position of a bright spot area as the position of the bright spot area in the traffic light image, wherein a pixel point in the bright spot area is the target pixel point;
and determining the lighting state of the traffic light according to the position of the bright point area in the traffic light image.
2. The method of claim 1, wherein the image recognizing the target image and determining the traffic light image on the target image comprises:
determining a region to be detected on a target image, wherein the region to be detected comprises a traffic light image;
and carrying out edge detection on the traffic light image in the area to be detected to obtain the traffic light image.
3. The method of claim 1, wherein the determining the lighting status of the traffic light according to the position of the bright point area in the traffic light image comprises:
when the position of the bright point area in the traffic light image is located in a first area in the traffic light image, determining that the lighting state of the traffic light is red light;
when the position of the bright spot area in the traffic light image is located in a second area in the traffic light image, determining that the lighting state of the traffic light is yellow light;
when the position of the bright spot area in the traffic light image is located in a third area in the traffic light image, determining that the lighting state of the traffic light is green light;
wherein the first region, the second region, and the third region do not overlap each other.
4. The method according to any one of claims 1 to 3, further comprising:
acquiring a light detection result of a shooting environment for the target image;
the determining the position of the bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in the hue saturation value HSV space comprises the following steps:
when the light detection result represents that light aiming at the shooting environment of the target image is weak, determining the position of a bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in a hue saturation value HSV space.
5. The method of claim 4, further comprising:
and when the light detection result represents that the light aiming at the shooting environment of the target image is strong, carrying out color identification on the traffic light image, and determining the lighting state of the traffic light.
6. A traffic light identification device, the device comprising:
the image identification module is used for carrying out image identification on a target image and determining a traffic light image on the target image, wherein the target image is an image obtained by shooting under the condition that the traffic light is weak;
the first determining module is used for determining the position of a bright point area in the traffic light image according to the pixel value of each pixel point in the traffic light image in a hue saturation value HSV space;
the first determining module includes:
the first determining unit is used for determining a target pixel point in the traffic light image, and the pixel value of the target pixel point in a brightness V channel of the HSV space is greater than a preset threshold value;
a second determining unit, configured to determine a central position of a bright point region as a position of the bright point region in the traffic light image, where a pixel point in the bright point region is the target pixel point;
the second determining module is used for determining the lighting state of the traffic light according to the position of the bright point area in the traffic light image;
the image identification module is specifically configured to acquire position information of the traffic light image by using a high-precision map, determine an image position corresponding to the position information from the target image, and determine the traffic light image on the target image based on the image position.
7. An apparatus, comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the method for identifying the lighting state of the traffic light according to any one of claims 1 to 5 according to instructions in the program code.
8. A computer-readable storage medium for storing a computer program for executing the method for identifying a lighting status of a traffic light according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010207250.8A CN111402610B (en) | 2020-03-23 | 2020-03-23 | Method, device, equipment and storage medium for identifying lighting state of traffic light |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010207250.8A CN111402610B (en) | 2020-03-23 | 2020-03-23 | Method, device, equipment and storage medium for identifying lighting state of traffic light |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111402610A CN111402610A (en) | 2020-07-10 |
| CN111402610B true CN111402610B (en) | 2022-05-10 |
Family
ID=71429090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010207250.8A Active CN111402610B (en) | 2020-03-23 | 2020-03-23 | Method, device, equipment and storage medium for identifying lighting state of traffic light |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111402610B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113642521B (en) * | 2021-09-01 | 2024-02-09 | 东软睿驰汽车技术（沈阳）有限公司 | Traffic light identification quality evaluation method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129779A (en) * | 2010-01-13 | 2011-07-20 | 中国科学院自动化研究所 | Monitoring system of safety and efficiency of traffic signal of intersection |
| CN102496282A (en) * | 2011-12-16 | 2012-06-13 | 湖南工业大学 | Traffic intersection signal light state identification method based on RGB color transformation |
| CN103295411A (en) * | 2012-12-27 | 2013-09-11 | 天津森宇科技发展有限公司 | Signal lamp monitoring and prompting device in process of driving |
| CN107273838A (en) * | 2017-06-08 | 2017-10-20 | 浙江大华技术股份有限公司 | Traffic lights capture the processing method and processing device of picture |
| CN107341806A (en) * | 2017-06-02 | 2017-11-10 | 青岛克路德机器人有限公司 | Based on the detection of the indoor indicator lamp of color and shape facility and condition discrimination method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102568242B (en) * | 2012-01-17 | 2015-04-08 | 杭州海康威视系统技术有限公司 | Signal lamp state detection method and system based on video processing |
| CN105023452B (en) * | 2014-04-24 | 2017-09-29 | 深圳市赛格导航科技股份有限公司 | A kind of method and device of multichannel traffic lights signal acquisition |
| JP6477876B2 (en) * | 2015-06-18 | 2019-03-06 | 日産自動車株式会社 | Signal detection device and signal detection method |
| US20190206248A1 (en) * | 2017-12-29 | 2019-07-04 | Joseph Carroll | Roadway safety system |
| CN110532903B (en) * | 2019-08-12 | 2022-02-22 | 浙江大华技术股份有限公司 | Traffic light image processing method and equipment |
| CN110705485A (en) * | 2019-10-08 | 2020-01-17 | 东软睿驰汽车技术（沈阳）有限公司 | Traffic signal lamp identification method and device |
-
2020
- 2020-03-23 CN CN202010207250.8A patent/CN111402610B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129779A (en) * | 2010-01-13 | 2011-07-20 | 中国科学院自动化研究所 | Monitoring system of safety and efficiency of traffic signal of intersection |
| CN102496282A (en) * | 2011-12-16 | 2012-06-13 | 湖南工业大学 | Traffic intersection signal light state identification method based on RGB color transformation |
| CN103295411A (en) * | 2012-12-27 | 2013-09-11 | 天津森宇科技发展有限公司 | Signal lamp monitoring and prompting device in process of driving |
| CN107341806A (en) * | 2017-06-02 | 2017-11-10 | 青岛克路德机器人有限公司 | Based on the detection of the indoor indicator lamp of color and shape facility and condition discrimination method |
| CN107273838A (en) * | 2017-06-08 | 2017-10-20 | 浙江大华技术股份有限公司 | Traffic lights capture the processing method and processing device of picture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111402610A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110660254B (en) | Traffic signal lamp detection and intelligent driving method and device, vehicle and electronic equipment | |
| WO2021082662A1 (en) | Method and apparatus for assisting user in shooting vehicle video | |
| CN101558415B (en) | Pedestrian detection device and pedestrian detection method | |
| CN107480676B (en) | Vehicle color identification method and device and electronic equipment | |
| CN112598922B (en) | Parking space detection method, device, equipment and storage medium | |
| US20210103746A1 (en) | Method and apparatus for identifying travelling state of intelligent driving device, and device | |
| CN111123912A (en) | Calibration method and device for travelling crane positioning coordinates | |
| CN111444810A (en) | Traffic light information identification method, device, equipment and storage medium | |
| US20150379334A1 (en) | Object recognition apparatus | |
| CN111402610B (en) | Method, device, equipment and storage medium for identifying lighting state of traffic light | |
| CN209991983U (en) | Obstacle detection equipment and unmanned aerial vehicle | |
| CN109635639B (en) | Method, device, equipment and storage medium for detecting position of traffic sign | |
| CN111565283A (en) | Traffic light color identification method, correction method and device | |
| CN113343872A (en) | Traffic light identification method, device, equipment, medium and product | |
| CN113343873A (en) | Signal lamp identification method, device, equipment, medium and product | |
| US10417518B2 (en) | Vehicle camera system | |
| US20110164144A1 (en) | Electronic camera | |
| CN112580489A (en) | Traffic light detection method and device, electronic equipment and storage medium | |
| CN109960990B (en) | Method for evaluating reliability of obstacle detection | |
| KR20140147211A (en) | Method for Detecting Fog for Vehicle and Apparatus therefor | |
| CN107992789B (en) | Method and device for identifying traffic light and vehicle | |
| CN111260538A (en) | Positioning and vehicle-mounted terminal based on long-baseline binocular fisheye camera | |
| CN114268737A (en) | Automatic trigger method for shooting, certificate identification method, equipment and storage medium | |
| CN114428257A (en) | Object detection device | |
| CN111462244B (en) | On-line calibration method, system and device for vehicle-mounted looking-around system |
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 |