Optical angle measurement method, parking system, medium and intelligent vehicle

Abstract

The invention discloses an optical angle measurement method, a parking system, a medium and an intelligent vehicle, and the method comprises the steps: employing a single vehicle-mounted camera to shoot an infrared light source which emits light through a set pulse, and obtaining a corresponding two-dimensional infrared image; performing color filtering on the two-dimensional infrared image, and separating an imaging area of the infrared light source in the two-dimensional infrared image; determining a light source position point of the infrared light source in a camera coordinate system where the vehicle-mounted camera is located based on an image position of the infrared light source in an image coordinate system corresponding to the two-dimensional infrared image and internal parameters of the vehicle-mounted camera; according to the light source position point and the direction of the vehicle-mounted camera, the position angle of the infrared light source relative to the intelligent vehicle where the vehicle-mounted camera is located is calculated.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent vehicle positioning, and in particular to an optical angle measurement method, a parking system, a medium and an intelligent vehicle. Background Art

[0002] With the development of the information age, angle measurement and positioning technologies based on optics and vision have shown many unique advantages. These technologies usually measure the angle and position of target objects by capturing and analyzing image information, and have broad application prospects in the fields of intelligent navigation, autonomous driving, robotics, etc.

[0003] Taking the existing infrared positioning technology as an example, it relies on two cameras to capture visible light images and infrared images containing infrared coded information of the target object, and determines the location of the target object through the mapping relationship between the pixel position coordinates of the two images.

[0004] However, the applicant found in the research that the existing technology cannot measure the angle of the target with a single camera, which means that it requires multiple cameras for accurate positioning, and the configuration of multiple cameras may lead to problems such as increased costs, complex deployment, and reduced system flexibility and fault tolerance. In addition, it cannot directly give the position angle of the target relative to the smart vehicle, which will cause problems in applications such as autonomous driving, navigation assistance, and safety monitoring that require real-time response and precise target positioning. This limitation means that complex algorithms and additional processing steps may be required to supplement this information, which may affect the response speed and accuracy of the system, resulting in lower robustness.

[0005] It can be seen that the dual-camera infrared positioning solution described in the prior art cannot complete the position angle measurement of the target relative to the smart vehicle. Although it has certain application value, its applicability is limited in certain specific occasions. Summary of the invention

[0006] In order to solve or partially solve the technical problem that the dual-camera infrared positioning solution of the prior art cannot complete the position angle measurement of the target relative to the smart vehicle, resulting in limited applicability, the present invention provides an optical angle measurement method, a parking system, a medium and a smart vehicle, which can complete the position angle measurement of a single or multiple fixed infrared light sources relative to the smart vehicle through a single on-board camera. Compared with the prior art, the present invention can complete the position angle measurement with a single camera, and has low cost and high robustness, and can be better applied in the parking system of smart vehicles to provide orientation guidance for vehicle parking.

[0007] In order to solve the above technical problems, the first aspect of the present invention discloses an optical angle measurement method, which comprises:

[0008] A single vehicle-mounted camera is used to shoot an infrared light source that emits light with a set pulse to obtain a corresponding two-dimensional infrared image;

[0009] Performing color filtering on the two-dimensional infrared image to separate an imaging area of ​​the infrared light source in the two-dimensional infrared image;

[0010] Determine the light source position point of the infrared light source in the camera coordinate system where the vehicle-mounted camera is located based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the intrinsic parameters of the vehicle-mounted camera;

[0011] According to the direction of the light source position point and the vehicle-mounted camera, the position angle of the infrared light source relative to the smart vehicle where the vehicle-mounted camera is located is calculated.

[0012] As an optional implementation, the vehicle-mounted camera is a camera with the infrared extinction film removed.

[0013] As an optional implementation manner, after obtaining the corresponding two-dimensional infrared image, the method further includes:

[0014] The two-dimensional infrared image is optimized; wherein the image optimization includes: one or more operations of denoising, image enhancement, distortion correction, and reflective shadow removal.

[0015] As an optional implementation manner, the color filtering of the two-dimensional infrared image to separate the imaging area of ​​the infrared light source in the two-dimensional infrared image specifically includes:

[0016] according to The judgment logic processes each pixel point of the two-dimensional infrared image; wherein PX i represents the i-th pixel point, Rmin and Rmax represent the endpoint values ​​of the red channel threshold range, Gmin and Gmax represent the endpoint values ​​of the green channel threshold range, Bmin and Bmax represent the endpoint values ​​of the blue channel threshold range, r, g, and b represent the pixel point PX i The R, G, B channel values;

[0017] If the pixel point PX i If all the conditions in the judgment logic are met, the pixel point PX i Retained in the pixel point set corresponding to the imaging area; wherein the pixel point set is used to construct the imaging area.

[0018] As an optional implementation, determining the light source position point of the infrared light source in the camera coordinate system where the vehicle-mounted camera is located based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the intrinsic parameters of the vehicle-mounted camera specifically includes:

[0019] Get the intrinsic parameter matrix of the vehicle camera Among them, f x ,f y represents the focal length of the vehicle-mounted camera, (c x ,c y ) represents the optical center coordinates of the infrared light source in the image coordinate system;

[0020] According to the matrix transformation relationship Determine the position of the light source in the camera coordinate system: The coordinates of the position of the infrared light source in the two-dimensional infrared image are: (u, v, 1).

[0021] As an optional implementation manner, the calculating, according to the direction of the light source position point and the vehicle-mounted camera, the position angle of the infrared light source relative to the smart vehicle where the vehicle-mounted camera is located, specifically includes:

[0022] According to the formula Calculate the position angle θ; wherein the direction vector of the vehicle-mounted camera is V c , which is related to Z c Same direction; the position vector of the light source relative to the vehicle camera is V l , the light source position point [X c ,Y c ,Z c ]Decide.

[0023] As an optional implementation manner, after calculating the position angle of the infrared light source relative to the smart vehicle where the on-board camera is located, the method further includes:

[0024] The parking maneuver is performed with reference to the position angle.

[0025] A second aspect of the present invention discloses a parking system, comprising:

[0026] An image acquisition unit, used to use a single vehicle-mounted camera to capture an infrared light source that emits light with a set pulse, and obtain a corresponding two-dimensional infrared image;

[0027] A light source identification module, used for performing color filtering on the two-dimensional infrared image to separate an imaging area of ​​the infrared light source in the two-dimensional infrared image;

[0028] A position conversion unit, used to determine a light source position point of the infrared light source in a camera coordinate system where the vehicle-mounted camera is located based on an image position of the infrared light source in an image coordinate system corresponding to the two-dimensional infrared image and an intrinsic parameter of the vehicle-mounted camera;

[0029] The position angle calculation unit is used to calculate the position angle of the infrared light source relative to the smart vehicle where the vehicle-mounted camera is located according to the direction of the light source position point and the vehicle-mounted camera.

[0030] According to a third aspect of the present invention, a computer-readable storage medium is disclosed, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0031] According to a fourth aspect of the present invention, an intelligent vehicle is disclosed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0032] Through one or more technical solutions of the present invention, the present invention has the following beneficial effects or advantages:

[0033] The present invention provides an optical angle measurement method, a parking system, a medium and an intelligent vehicle. First, a single vehicle-mounted camera is used to shoot an infrared light source that emits light with a set pulse to obtain a corresponding two-dimensional infrared image; then the two-dimensional infrared image is color filtered to separate the imaging area of ​​the infrared light source in the two-dimensional infrared image; then, based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the internal parameters of the vehicle-mounted camera, the light source position point of the infrared light source in the camera coordinate system where the vehicle-mounted camera is located is determined; and according to the direction of the light source position point and the vehicle-mounted camera, the position angle of the infrared light source relative to the intelligent vehicle where the vehicle-mounted camera is located is calculated. In this solution, the position angle of a fixed infrared light source relative to a vehicle can be measured by a single vehicle-mounted camera, and it is low-cost and highly robust, and can be better applied in the parking system of intelligent vehicles to provide accurate orientation guidance for vehicle parking.

[0034] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0036] Figure 1 A schematic diagram showing the relative position relationship between an infrared light source and a vehicle-mounted camera in an intelligent vehicle according to an embodiment of the present invention;

[0037] Figure 2 A flow chart of an optical angle measurement method according to an embodiment of the present invention is shown;

[0038] Figure 3 A schematic diagram of a parking system according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0039] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0040] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0041] In a first aspect, an optical angle measurement method provided by an embodiment of the present invention is arranged and implemented on a vehicle-mounted end, and is mainly used for measuring the position angle of a fixed infrared light source relative to an intelligent vehicle.

[0042] In order to facilitate the description and explanation of the present invention, the following Figure 1 , which is a schematic diagram of the relative position relationship between the infrared light source and the on-board camera in the smart vehicle.

[0043] In this scenario, a single or multiple infrared light sources can be arranged according to the needs. The infrared light source is sent by the positioning base station through the infrared tag. The vehicle-mounted end uses the original intelligent driving assistance camera, and the vehicle-mounted end has a central domain controller. The vehicle-mounted camera can receive infrared light source imaging and send the imaging information to the central domain controller for encoding and decoding, so as to identify the unique ID of the base station and execute the above method, implement the measurement of the position angle of the infrared light source relative to the vehicle-mounted end, complete the vehicle positioning, and assist in parking.

[0044] The emission wavelength of the infrared light source can be in the near-infrared light range of 700-1000nm, which is invisible to the human eye, but can be captured by the on-board camera. Among them, the power and intensity of the infrared light source are above 15W to ensure that the on-board camera can clearly detect the infrared light and achieve positioning at a specific distance and environment. A single infrared light source uses a set pulse to emit light, and a single infrared light source will be attached with a stabilized power supply and heat dissipation fins, which helps the infrared light source to work stably for a long time. The on-board camera is a camera with the infrared extinction film removed, with a resolution of 640x480 pixels or more, a 120° field of view, and image distortion correction rules.

[0045] See below Figure 2 The optical angle measurement method of the embodiment of the present invention at least comprises the following steps:

[0046] S201, using a single vehicle-mounted camera to photograph an infrared light source that emits light with a set pulse, to obtain a corresponding two-dimensional infrared image.

[0047] Among them, a single vehicle-mounted camera captures a single or multiple fixed infrared light sources that emit light with set pulses, thereby completing the measurement of the position angle of the single or multiple fixed infrared light sources relative to the smart vehicle where the vehicle-mounted camera is located.

[0048] Since the captured two-dimensional infrared image contains a single or multiple infrared light sources, each infrared light source will be implemented according to the scheme of S202 to S204 to measure the position angle of the single or multiple infrared light sources relative to the intelligent vehicle. In order to simplify the description, this embodiment directly introduces the processing logic of the infrared light source without limiting the number of infrared light sources.

[0049] In an optional implementation, in order to improve positioning accuracy and efficiency, it is necessary to optimize the original two-dimensional infrared image taken by the vehicle-mounted camera through image optimization operations. The image optimization includes one or more operations of denoising, image enhancement, distortion correction, and reflective shadow removal. For example, use filtering and smoothing algorithms to remove random noise points introduced during the image acquisition process; use a histogram equalization algorithm to improve image contrast and enhance the recognizability of the infrared light source in the image; perform geometric distortion correction for the field of view distortion of the wide-angle head; eliminate highlights and shadow areas caused by light reflection according to the characteristics of the infrared light source and ambient light, thereby reducing interference with the positioning of the light source.

[0050] S202, performing color filtering on the two-dimensional infrared image to separate an imaging area of ​​the infrared light source in the two-dimensional infrared image.

[0051] Since the infrared light source will have different degrees of influence on the red, green and blue channels captured by the camera, some false colors will be produced after imaging. To solve this problem, the color range is set to filter the two-dimensional infrared image, so as to separate the imaging area of ​​the infrared light source in the two-dimensional infrared image.

[0052] Specifically, according to The judgment logic processes each pixel of the two-dimensional infrared image. i Represents pixel points, Rmin and Rmax represent the endpoint values ​​of the red channel threshold range, Gmin and Gmax represent the endpoint values ​​of the green channel threshold range, Bmin and Bmax represent the endpoint values ​​of the blue channel threshold range, r, g, and b represent pixel points PX i The R, G, and B channel values ​​are obtained. The pixel points are color filtered by setting the red channel threshold range, the green channel threshold range, and the blue channel threshold range, and a pixel point set corresponding to the imaging area is set, wherein the pixel point set is used to construct the imaging area. If the pixel point PX i Satisfy all the conditions in the judgment logic, that is, pixel point PX i If the R, G, B channel values ​​r, g, b all meet the respective channel threshold ranges, then the pixel point PX i The pixels are retained in the set of pixels corresponding to the imaging area. By performing color filtering on each pixel, false colors in the imaging can be eliminated to obtain a clear infrared light source image.

[0053] S203, determining a light source position point of the infrared light source in a camera coordinate system where the vehicle-mounted camera is located based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the intrinsic parameters of the vehicle-mounted camera.

[0054] Among them, the intrinsic parameter matrix of the vehicle-mounted camera is obtained Among them, f x ,f y represents the focal length of the vehicle-mounted camera, (c x ,c y ) represents the coordinates of the optical center of the infrared light source in the image coordinate system, which is obtained by anchoring the separated infrared light source through the feature matching algorithm. Then, combined with the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image, the two-dimensional image coordinate system is converted into a three-dimensional camera coordinate system to obtain the light source position point. Specifically, according to the matrix transformation relationship Determine the light source position in the camera coordinate system: The coordinates of the position of the infrared light source in the two-dimensional infrared image are: (u, v, 1).

[0055] In the specific implementation process, with the support of the camera manufacturer, the depth information Z corresponding to the infrared light source can be estimated through the intrinsic parameter matrix of the vehicle camera. c You can also use short-range communication technology and ToF ranging to get the ranging result, and estimate the depth information Z corresponding to the infrared light source based on the ranging result. c After that, other coordinate parameters of the light source position point are obtained according to the matrix transformation, and the light source position point can be determined.

[0056] S204, calculating the position angle of the infrared light source relative to the smart vehicle where the onboard camera is located according to the direction of the light source position point and the onboard camera.

[0057] Specifically, according to the formula Calculate the position angle θ; wherein the direction vector of the vehicle-mounted camera is V c , which is related to Z c Same direction, representing the direction in which the vehicle-mounted camera is pointed at the light source; the position vector of the light source relative to the vehicle-mounted camera is V l , the light source position point [X c ,Y c ,Z c ] is determined, when the light source position point is obtained, the position vector V of the light source position point relative to the vehicle-mounted camera can be obtained l .

[0058] The above is a method for calculating the position angle of the infrared light source relative to the smart vehicle where the on-board camera is located. After the position angle is obtained, the parking operation is performed with reference to the position angle, thereby achieving the purpose of assisted parking.

[0059] It is worth noting that when there are multiple infrared light sources, the position angles of the multiple infrared light sources relative to the smart vehicle can be calculated, and parking operations can be performed with reference to the position angles of the multiple infrared light sources relative to the smart vehicle, thereby achieving the purpose of assisted parking more accurately.

[0060] In a second aspect, based on the same inventive concept as the optical angle measurement method provided in the embodiment of the first aspect, the embodiment of the present invention further provides a parking system, see Figure 3 ,include:

[0061] An image acquisition unit 301 is used to use a single vehicle-mounted camera to capture an infrared light source that emits light with a set pulse to obtain a corresponding two-dimensional infrared image;

[0062] A light source identification module 302 is used to perform color filtering on the two-dimensional infrared image to separate an imaging area of ​​the infrared light source in the two-dimensional infrared image;

[0063] A position conversion unit 303 is used to determine a light source position point of the infrared light source in a camera coordinate system where the vehicle-mounted camera is located based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the intrinsic parameters of the vehicle-mounted camera;

[0064] The position angle calculation unit 304 is used to calculate the position angle of the infrared light source relative to the smart vehicle where the vehicle-mounted camera is located according to the direction of the light source position point and the vehicle-mounted camera.

[0065] It should be noted that, in the parking system provided in the embodiment of the present invention, the specific manner in which each module performs operations has been described in detail in the method embodiment provided in the first aspect above. The specific implementation process can refer to the method embodiment provided in the first aspect above, and will not be elaborated here.

[0066] In the third aspect, based on the same inventive concept as the optical angle measurement method provided in the embodiment of the first aspect mentioned above, the embodiment of the present invention further discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0067] In the fourth aspect, based on the same inventive concept as the optical angle measurement method provided in the embodiment of the first aspect mentioned above, the embodiment of the present invention also discloses an intelligent vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the methods described above when executing the program.

[0068] The present invention provides an optical angle measurement method, a parking system, a medium and an intelligent vehicle. First, a single vehicle-mounted camera is used to shoot an infrared light source that emits light with a set pulse to obtain a corresponding two-dimensional infrared image; then the two-dimensional infrared image is color filtered to separate the imaging area of ​​the infrared light source in the two-dimensional infrared image; then, based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the internal parameters of the vehicle-mounted camera, the light source position point of the infrared light source in the camera coordinate system where the vehicle-mounted camera is located is determined; and according to the direction of the light source position point and the vehicle-mounted camera, the position angle of the infrared light source relative to the intelligent vehicle where the vehicle-mounted camera is located is calculated. In this solution, the position angle of a fixed infrared light source relative to a vehicle can be measured by a single vehicle-mounted camera, and it is low-cost and highly robust, and can be better applied in the parking system of intelligent vehicles to provide accurate orientation guidance for vehicle parking.

[0069] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0070] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An optical angle measurement method, characterized in that: The method comprises: A single vehicle-mounted camera is used to shoot an infrared light source that emits light with a set pulse to obtain a corresponding two-dimensional infrared image; Performing color filtering on the two-dimensional infrared image to separate an imaging area of ​​the infrared light source in the two-dimensional infrared image; Determine the light source position point of the infrared light source in the camera coordinate system where the vehicle-mounted camera is located based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the intrinsic parameters of the vehicle-mounted camera; According to the direction of the light source position point and the vehicle-mounted camera, the position angle of the infrared light source relative to the intelligent vehicle where the vehicle-mounted camera is located is calculated.

2. The method according to claim 1, characterized in that The vehicle-mounted camera is a camera with the infrared extinction film removed.

3. The method according to claim 1, characterized in that After obtaining the corresponding two-dimensional infrared image, the method further includes: The two-dimensional infrared image is optimized; wherein the image optimization includes: one or more operations of denoising, image enhancement, distortion correction, and reflective shadow removal.

4. The method according to claim 1, characterized in that The color filtering of the two-dimensional infrared image to separate the imaging area of ​​the infrared light source in the two-dimensional infrared image specifically includes: according to The judgment logic processes each pixel point of the two-dimensional infrared image; wherein PX i represents the i-th pixel point, Rmin and Rmax represent the endpoint values ​​of the red channel threshold range, Gmin and Gmax represent the endpoint values ​​of the green channel threshold range, Bmin and Bmax represent the endpoint values ​​of the blue channel threshold range, r, g, and b represent the pixel point PX respectively. i The R, G, B channel values; If the pixel point PX i If all the conditions in the judgment logic are met, the pixel point PX i Retained in the pixel point set corresponding to the imaging area; wherein the pixel point set is used to construct the imaging area.

5. The method according to claim 1, characterized in that The step of determining the light source position point of the infrared light source in the camera coordinate system where the vehicle-mounted camera is located based on the image position of the infrared light source in the image coordinate system corresponding to the two-dimensional infrared image and the intrinsic parameters of the vehicle-mounted camera specifically includes: Get the intrinsic parameter matrix of the vehicle camera Among them, f x ,f y represents the focal length of the vehicle-mounted camera, (c x ,c y ) represents the optical center coordinates of the infrared light source in the image coordinate system; According to the matrix transformation relationship Determine the position of the light source in the camera coordinate system: The coordinates of the position of the infrared light source in the two-dimensional infrared image are: (u, v, 1).

6. The method according to claim 1, characterized in that The calculating, according to the direction of the light source position point and the vehicle-mounted camera, the position angle of the infrared light source relative to the smart vehicle where the vehicle-mounted camera is located specifically includes: According to the formula Calculate the position angle θ; wherein the direction vector of the vehicle-mounted camera is V c , which is related to Z c Same direction; the position vector of the light source relative to the vehicle camera is V l , the light source position point [X c ,Y c ,Z c ]Decide.

7. The method according to claim 1, characterized in that After calculating the position angle of the infrared light source relative to the smart vehicle where the on-board camera is located, the method further includes: The parking maneuver is performed with reference to the position angle.

8. A parking system, characterized in that: include: An image acquisition unit, used to use a single vehicle-mounted camera to capture an infrared light source that emits light with a set pulse, and obtain a corresponding two-dimensional infrared image; A light source identification module, used for performing color filtering on the two-dimensional infrared image to separate an imaging area of ​​the infrared light source in the two-dimensional infrared image; A position conversion unit, used to determine a light source position point of the infrared light source in a camera coordinate system where the vehicle-mounted camera is located based on an image position of the infrared light source in an image coordinate system corresponding to the two-dimensional infrared image and an intrinsic parameter of the vehicle-mounted camera; The position angle calculation unit is used to calculate the position angle of the infrared light source relative to the smart vehicle where the vehicle-mounted camera is located according to the direction of the light source position point and the vehicle-mounted camera.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An intelligent vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images