Vehicle visual field measurement method and device, electronic equipment and storage medium

Abstract

The invention discloses a vehicle visual field measurement method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a visual field detection image of a vehicle, wherein the visual field detection image is acquired by a target camera arranged at a driver visual angle in the vehicle; acquiring pixel coordinates of a plurality of key points and pixel coordinates of view edge points in the view detection image; acquiring a real relative distance between the vehicle and each key point; according to the pixel coordinate of each key point and the real relative distance between the vehicle and each key point, determining transformation information of the visual field detection image; and according to the transformation information of the visual field detection image, carrying out transformation processing on the pixel coordinates of the visual field edge points to obtain visual field measurement information corresponding to the visual field detection image. According to the technical scheme provided by the embodiment of the invention, the measurement of the vehicle view can be more convenient and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle testing, and in particular to a vehicle visual field measurement method, device, electronic equipment and storage medium. Background Art

[0002] With the development of vehicle testing technology, in order to ensure the safety of the vehicle during driving, it can be achieved by improving the direct field of view of the vehicle. In the process of improving the direct field of view of the vehicle, the direct field of view of the vehicle needs to be tested.

[0003] Currently, the direct field of view of the vehicle is mainly detected by laser rangefinders or aerial photography devices.

[0004] However, the above-mentioned method of realizing vehicle vision detection has the problems of high cost, difficulty in installation and maintenance, and overly complicated operation. Summary of the invention

[0005] The present invention provides a vehicle field of view measurement method, device, electronic device and storage medium. The technical solution of the embodiment of the present invention can achieve more convenient and accurate measurement of the vehicle field of view.

[0006] According to one aspect of the present invention, a vehicle vision measurement method is provided, the method comprising:

[0007] Acquire a field of view detection image of the vehicle, where the field of view detection image is acquired by a target camera placed in the vehicle from the perspective of the driver;

[0008] In the visual field detection image, the pixel coordinates of multiple key points and the pixel coordinates of the visual field edge points are obtained;

[0009] Get the real relative distance between the vehicle and each key point;

[0010] Determine the transformation information of the field of view detection image according to the pixel coordinates of each key point and the real relative distance between the vehicle and each key point;

[0011] According to the transformation information of the visual field detection image, the pixel coordinates of the visual field edge points are transformed to obtain the visual field measurement information corresponding to the visual field detection image.

[0012] According to another aspect of the present invention, there is provided a vehicle visual field measuring device, comprising:

[0013] A visual field detection image acquisition module is used to obtain a visual field detection image of the vehicle. The visual field detection image is acquired by a target camera placed in the vehicle at the driver's perspective;

[0014] A key point and edge point acquisition module is used to obtain the pixel coordinates of multiple key points and the pixel coordinates of the edge points of the visual field in the visual field detection image;

[0015] A key point real distance acquisition module is used to obtain the real relative distance between the vehicle and each key point;

[0016] An image transformation information determination module is used to determine the transformation information of the field of view detection image according to the pixel coordinates of each key point and the real relative distance between the vehicle and each key point;

[0017] The visual field edge point transformation processing module is used to transform the pixel coordinates of the visual field edge points according to the transformation information of the visual field detection image to obtain the visual field measurement information corresponding to the visual field detection image.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the vehicle field of view measurement method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle field of view measurement method according to any embodiment of the present invention when executed.

[0023] The technical solution of the embodiment of the present invention obtains the pixel coordinates of multiple key points in the field of view detection image, generates transformation information in combination with the real relative distance between the vehicle and these key points, effectively establishes a mapping relationship between the pixel coordinates of the field of view detection image and the real world coordinates, and ensures high accuracy in the subsequent transformation processing of the field of view edge points; by obtaining the real relative distance between the vehicle and each key point, and using it to determine the transformation information of the field of view detection image, it is possible to fully consider the distance relationship between the actual position of the vehicle and the calibration environment, and ensure that the geometric information in the field of view detection image can correctly reflect the actual spatial structure; by processing the pixel coordinates of the key points and the field of view edge points obtained in the field of view detection image using the transformation information, the need for manual calibration and intervention is reduced, and the transformation processing of the field of view edge points and the acquisition of the final measurement information are completed in the image analysis and calculation process, thereby improving the measurement efficiency and reducing the errors introduced by human operation.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a flow chart of a vehicle vision measurement method provided according to Embodiment 1 of the present invention;

[0028] Figure 2 is a flow chart of a vehicle vision measurement method provided according to Embodiment 2 of the present invention;

[0029] Figure 3 is a structural schematic diagram of a calibration plate pattern provided according to Embodiment 2 of the present invention;

[0030] Figure 4 is a schematic diagram of a camera raw image to be processed provided in Embodiment 2 of the present invention;

[0031] Figure 5 This is a relative position diagram provided according to Embodiment 2 of the present invention;

[0032] Figure 6 is a schematic diagram of a camera image after correction according to the second embodiment of the present invention

[0033] Figure 7 is a schematic diagram of the actual position of a field of view boundary line in a real scene in a top view according to a second embodiment of the present invention;

[0034] Figure 8 A schematic diagram of a field of view boundary line in different scenes is provided according to the second embodiment of the present invention;

[0035] Fig. 9 A schematic structural diagram of a vehicle visual field measurement device provided according to a third embodiment of the present invention;

[0036] Fig.10 It is a schematic diagram of the structure of an electronic device for implementing the vehicle visual field measurement method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] Embodiment 1

[0040] Figure 1 A flow chart of a vehicle vision measurement method is provided for the first embodiment of the present invention. This embodiment is applicable to the case where the vehicle's vision range is measured when designing a vehicle. The method can be performed by a vehicle vision measurement device, which can be implemented in the form of hardware and / or software. The vehicle vision measurement device can be configured in a dedicated vehicle simulation test system. Figure 1 As shown, the method includes:

[0041] S101, obtaining a field of view detection image of a vehicle, where the field of view detection image is acquired by a target camera placed in the vehicle at the driver's perspective.

[0042] The field of view detection image may refer to an image used to reflect the range of the vehicle's surrounding environment that can be seen from the driver's perspective. The field of view detection image contains key information within the vehicle's field of view, such as the field of view edge points. The field of view detection image is used to provide a visual basis for subsequent analysis of the vehicle's field of view and field of view boundaries.

[0043] The target camera may refer to a camera installed in the vehicle. The target camera is installed at the driver's viewing angle to capture a field of view detection image that is consistent with the driver's line of sight. The target camera is responsible for obtaining a field of view detection image that reflects the driver's actual field of view, simulating the driver's visual perception, and capturing the scene seen from the driver's position. Exemplarily, the target camera may refer to a wide-angle camera or a smart device camera, that is, any shooting device that can simulate the visual perception of the human eye can be used as a target camera.

[0044] The target camera is placed at the driver's perspective, and the target camera is used to simulate the human eye to shoot, so as to obtain the visual detection image that can be seen from the driver's perspective in the scene.

[0045] Optionally, the optical center of the target camera is placed at the driver's eye point.

[0046] The optical center may refer to the intersection of the optical axes in the target camera, that is, the point where the light passes through the lens system and converges on the image sensor. The optical center corresponds to the geometric center of the lens. The optical center is used as the reference point for camera imaging. Positioning the optical center at the driver's eye point can further ensure that the field of view of the image is consistent with the driver's actual viewing angle, so that the image shooting range is the driver's observation range. In this way, the edge points detected in the measured image can be consistent with the edge points of the field of view of the driver's actual viewing angle, thereby improving the accuracy of the measurement.

[0047] The eye point may refer to the actual intersection point of the driver's line of sight, that is, the actual position of the driver's eyes. In vehicle visual field measurement, the eye point refers to the position of the driver's eyes in a normal driving posture. The eye point is used as a reference position for the viewing angle, so as to ensure that the visual field measurement can accurately and truly reflect the driver's actual viewing angle, thereby improving the accuracy of the visual field measurement. Exemplarily, when the driver is looking straight ahead, the eye point is located in the area where the driver's eyes are facing the front windshield.

[0048] The optical center position of the target camera is aligned with the eye point of the driver's visual field to be observed.

[0049] By placing the optical center of the target camera at the driver's eye point, the image captured by the target camera will be consistent with the perspective seen by the driver, avoiding the perspective deviation problem caused by the target camera position deviating from the driver's eye point, and ensuring accurate detection of the edge points and key points of the field of view.

[0050] Optionally, a field of view detection image of the vehicle in at least one direction is obtained; after the field of view measurement information corresponding to the field of view detection image, the method further includes: fusing the field of view measurement information corresponding to the field of view detection images in each direction to obtain the field of view boundary information of the vehicle.

[0051] Among them, the field of view measurement information may refer to data obtained by analyzing the field of view detection image of the vehicle, reflecting the field of view range and field of view edge position of the vehicle in a certain direction. The field of view measurement information is the measurement result obtained by obtaining key points and field of view edge points from the field of view detection image and transforming them. The field of view measurement information is used to accurately describe the visible field of view of the driver of the vehicle in a certain direction. The field of view measurement information provides data support for subsequent analysis of the field of view coverage of the vehicle and design of field of view optimization schemes. Accurate field of view measurement information helps to reduce blind spots, improve driver visibility, and thus improve driving safety.

[0052] Fusion can refer to an integration processing operation that integrates the field of view measurement information corresponding to the field of view detection images from different directions to generate comprehensive information about the vehicle's overall field of view. Fusion is used to obtain the field of view range and boundaries of the vehicle in multiple directions through the fusion operation, which helps to evaluate the overall field of view coverage of the vehicle during the design or testing phase and identify any potential blind spots or uncovered areas.

[0053] The visual field boundary information may refer to the boundary of the visible area of ​​the vehicle in all directions determined by fusing the visual field measurement information. The visual field boundary information indicates the end point of the visual field range and clearly defines the boundary between the visible area and the blind area. The visual field boundary information is used to help determine the visible range and invisible range of the driver's visual field. Through the visual field boundary information, vehicle designers can analyze the driver's visual field coverage.

[0054] Among them, after obtaining the field of view detection image in one direction and obtaining the field of view measurement information corresponding to this field of view detection image, the field of view detection images in other directions and the corresponding field of view measurement information are obtained, and the field of view measurement information in each direction is integrated to obtain complete vehicle field of view boundary information.

[0055] By integrating the field of view measurement information from different directions, the blind spot problem that may be caused by relying solely on data from a single direction is avoided, making the field of view boundary information more complete and comprehensive, and can more accurately reflect the overall field of view around the vehicle, which helps to comprehensively analyze and optimize blind spots or occlusion problems in vehicle design.

[0056] Optionally, the direction includes front, left, right, or back.

[0057] The direction of the visual field detection image may be selected to include the front, left, right or rear of the driver's position, and the direction is defined based on the total viewing angle that the driver can see.

[0058] That is, all directions that the driver can observe can be selected as directions, and here, the selection range of each direction is not limited.

[0059] S102 . Obtain pixel coordinates of a plurality of key points and pixel coordinates of visual field edge points in the visual field detection image.

[0060] Among them, key points can refer to positions that can be clearly identified and measured in the field of view detection image. These position points usually have high eigenvalues, which are convenient for tracking and calibration during image processing. Key points are used to determine the specific position of key points in the field of view detection image, and to determine the real distance between key points and vehicles. Exemplarily, certain specific elements in a calibration board can be used as key points. For example, if a calibration board includes a checkerboard image, key points can refer to the four vertices of the rectangle in the middle of the checkerboard image.

[0061] Pixel coordinates may refer to the position coordinates of pixel points in the field of view detection image, which are represented by horizontal and vertical coordinates (X, Y). The field of view detection image includes several pixels, and each pixel corresponds to a pixel coordinate. Pixel coordinates are used to determine the specific positions of key points and field of view edge points in the image during vehicle field of view measurement. Through these coordinates, image transformation processing can be performed to calculate the real position of the field of view edge in real space. For example, in the field of view detection image, the pixel coordinates of a key point correspond to (100, 200), and the pixel coordinates of a field of view edge point correspond to (10, 20).

[0062] The visual field edge point may refer to the boundary point formed in the visual field detection image due to the occlusion of the vehicle structure. The visual field edge point is not the end point of the driver's visual field, but identifies the occlusion area of ​​the vehicle body structure in the driver's visual field. The visual field edge point is used for general analysis of the visual field edge point and calculates the mapping position of the visual field edge point in the real space.

[0063] In this step, it is necessary to obtain the pixel coordinates of a preset number of key points in the corresponding field of view detection image, and to obtain the pixel coordinates of the field of view edge points in the corresponding field of view detection image.

[0064] Optionally, in the field of view detection image, at least one key point on a calibration plate is detected to obtain pixel coordinates of each key point on the calibration plate; the calibration plate is placed within the direct field of view of the vehicle.

[0065] The calibration plate may refer to a tool used for calibration of a photographing device, and the calibration plate generally includes patterns of known size and regular arrangement, such as a checkerboard, a dot array, etc. The calibrating plate is used to provide multiple key points with detectable and known relative positions. By detecting these key points on the calibration plate, the image captured by the photographing device can be matched with the distance information in the real space, and transformation information can be generated, thereby realizing the conversion of pixel coordinates in the image into physical coordinates in the real space.

[0066] The direct field of view may refer to the unobstructed and directly visible area around the vehicle from the driver's perspective. The direct field of view includes the part that the driver sees through the front windshield, side windows, and rear windows, as well as the area that is not blocked by the internal or external structure of the vehicle. The direct field of view is used to help place the calibration plate in the appropriate position to ensure that the key points on the calibration plate can be accurately captured by the target camera, thereby obtaining the necessary information for the transformation process.

[0067] By placing a calibration plate within the direct field of view and detecting its key points, accurate calibration point coordinates can be obtained, which helps determine the relative position and angle of the vehicle camera and provides accurate image space to actual space conversion information, ensuring that the calibration plate is clearly detected within the field of view of the target camera, which is beneficial to improving calibration accuracy, thereby improving the accuracy and reliability of subsequent steps in field of view measurement.

[0068] Optionally, distortion correction is performed on the field of view detection image of the vehicle according to key points of a calibration plate in the field of view detection image of the vehicle.

[0069] Distortion correction refers to an image processing algorithm that corrects the geometric deformation of the image caused by the camera lens, such as barrel distortion or pincushion distortion. Due to the optical characteristics of the camera lens, the captured image may be distorted to a certain extent, especially in wide-angle lenses, where the distortion phenomenon is more obvious. Distortion correction is used in the process of measuring the vehicle's field of view. If the target camera is distorted, distortion correction must be performed first to ensure that the pixel coordinates in the image accurately correspond to the geometric relationship in the real space, avoid coordinate deviations caused by distortion, and ensure the accuracy of subsequent field of view edge point transformation processing.

[0070] By utilizing the distortion correction method, the geometric distortion caused by lens characteristics in the field of view detection image is directly reduced, ensuring that in subsequent measurement and analysis, the image of the vehicle's field of view more accurately reflects the actual spatial geometric relationship, which can improve the accuracy of field of view measurement and ensure the reliability of data.

[0071] Optionally, the calibration plate includes a checkerboard image, and the vertices of the middle rectangle of the checkerboard image are key points.

[0072] S103: Obtain the real relative distance between the vehicle and each key point.

[0073] Among them, the real relative distance may refer to the actual physical distance between the vehicle and the key point in the field of view detection image. The position of the key point obtains its pixel coordinates through the above steps, and the real relative distance refers to the precise distance between the vehicle and the key point in the real space. The real relative distance is used to combine the pixel information in the two-dimensional image with the physical distance in the actual three-dimensional space, and is used to calculate the transformation information of the image. By combining the pixel coordinates and these actual distances, the driver's field of view and boundary information can be accurately determined. For example, it is assumed that in the field of view detection image of the vehicle, the pixel coordinates of a key point on the calibration plate have been identified, and the real relative distance between the vehicle and the key point is 3 meters.

[0074] Among them, the real relative distance between the vehicle and each key point in the actual real space is obtained to ensure that the distance between the vehicle and the key point can be accurately measured.

[0075] S104: Determine transformation information of the field of view detection image according to the pixel coordinates of each key point and the real relative distance between the vehicle and each key point.

[0076] Transformation information may refer to a mapping relationship that establishes a mapping relationship between image pixel coordinates and real space coordinates by combining the pixel coordinates of key points and field of view edge points in the field of view detection image with the real relative distance in the real space. Transformation information is used to realize the conversion between pixel coordinates in the field of view detection image and position coordinates in the real space. Through the correspondence between the pixel position of the key point and the real space distance, the spatial transformation relationship of the entire image can be derived. Exemplarily, assuming that a calibration plate is set in front of the vehicle, and the key points on the calibration plate are identified in the field of view detection image, by measuring the actual distance between the vehicle and each key point on the calibration plate, combined with the pixel position of the key point in the image, the transformation information can be derived, and the field of view edge points in the field of view detection image are transformed using the transformation information, and the position of the field of view edge points in the real space is calculated, thereby accurately measuring the driver's visual range and blind spot position.

[0077] Among them, by obtaining the pixel positions of key points and field of view edge points in the vehicle field of view detection image, using the pixel coordinates of the key points and the real relative distance between the vehicle and each key point, the mapping relationship between the image and the real world is obtained, and the mapping relationship is the transformation relationship.

[0078] S105 . Perform transformation processing on the pixel coordinates of the visual field edge points according to the transformation information of the visual field detection image to obtain the visual field measurement information corresponding to the visual field detection image.

[0079] Transformation processing may refer to a conversion process that converts pixel coordinates in a field of view detection image into position coordinates in real space. By combining the pixel position of key points with the real relative distance between the vehicle and the key points, the pixel points in the image (such as field of view edge points) are subjected to corresponding geometric transformation to obtain the accurate positions of these points in physical space.

[0080] The pixel coordinates of the visual field edge points in the visual field detection image are converted into position coordinates in the real space through the transformation information obtained through the above process, and the visual field measurement information corresponding to the visual field image is obtained.

[0081] By obtaining the pixel coordinates of multiple key points in the field of view detection image and generating transformation information in combination with the real relative distance between the vehicle and these key points, an effective mapping relationship between the pixel coordinates of the field of view detection image and the real-world coordinates is established, ensuring high accuracy in the subsequent transformation processing of the field of view edge points; by obtaining the real relative distance between the vehicle and each key point and using it to determine the transformation information of the field of view detection image, the distance relationship between the actual position of the vehicle and the calibration environment can be fully considered, ensuring that the geometric information in the field of view detection image can correctly reflect the actual spatial structure; by processing the pixel coordinates of the key points and field of view edge points obtained in the field of view detection image using the transformation information, the need for manual calibration and intervention is reduced, and the transformation processing of the field of view edge points and the acquisition of the final measurement information are completed in the image analysis and calculation process, which improves the measurement efficiency and reduces the errors introduced by human operation.

[0082] Embodiment 2

[0083] Figure 2 1 is a flow chart of a vehicle vision measurement method provided according to Embodiment 2 of the present invention. This embodiment is a specific implementation method implemented based on the above embodiment.

[0084] The specific implementation steps of this method are as follows:

[0085] S201. The vehicle to be tested is placed stationary on a flat and sufficiently wide test site.

[0086] S202: placing the camera at the driver's eye point, and placing the calibration plate on the ground within the direct field of view around the vehicle.

[0087] Exemplarily, the camera is placed at the driver's eye point. A tripod may be used and placed above the driver's seat. The height and position of the tripod are adjusted until the optical center of the camera is located at the driver's eye point.

[0088] S203, previewing the camera shooting scene through a monitor, adjusting the camera posture and the calibration plate position until the shooting scene includes both the field of view boundary and the complete calibration plate pattern.

[0089] For example, Figure 3 is a structural schematic diagram of a calibration plate pattern provided according to Embodiment 2 of the present invention, Figure 3 It is a schematic diagram of a shooting scene that meets the conditions provided according to the second embodiment of the present invention.

[0090] S204: Use a camera to shoot the above shooting scene to obtain a camera original image to be processed.

[0091] For example, Figure 4 401 is a schematic diagram of a camera original image to be processed according to the second embodiment of the present invention, wherein 401 refers to the direct field of view boundary line of the vehicle, 402 refers to the direct field of view of the front windshield, and 403 refers to the indicator plate.

[0092] S205: Obtain the relative position between the feature points on the calibration plate and the vehicle to be tested.

[0093] For example, with the center of the front edge of the vehicle as the origin, the X-axis points from the left side of the vehicle to the right side of the vehicle, and the Y-axis points from the rear side of the vehicle to the front side of the vehicle, the position coordinates of the characteristic points of the calibration plate are recorded as A(X1, Y1), B(X2, Y2), C(X3, Y3), and D(X4, Y4). Figure 5 This is a relative position diagram provided according to Embodiment 2 of the present invention.

[0094] S206: Perform distortion correction on the original camera image to be processed to obtain a corrected camera image.

[0095] For example, Figure 6 is a schematic diagram of a calibrated camera image provided according to the second embodiment of the present invention.

[0096] S207 , obtaining pixel coordinates of feature points on the calibration plate in the corrected camera image and pixel coordinates of the edge of the direct field of view.

[0097] For example, with the upper left corner of the image as the origin, the x-axis points from the left side of the image to the right side, and the y-axis points from the top of the image to the bottom, the pixel coordinates of the feature points of the calibration plate in the image are recorded as a(x1, y1), b(x2, y2), c(x3, y3), d(x4, y4), and the recorded pixel coordinate positions are as follows: Figure 6 shown.

[0098] S208: Calculate the transformation coefficient from the captured scene to the actual position using the pixel coordinates of the feature points on the calibration plate and the physical relative position between the feature points on the calibration plate and the vehicle to be measured.

[0099] Exemplarily, the transformation matrix T may be as shown in the following formula:

[0100]

[0101] Where T is the transformation matrix, t 11 ,t 12 ,t 13 ,t 21 ,t 22 ,t 23 ,t 31 and t 32 There are eight conversion parameters.

[0102] For example, taking a feature point as an example, assuming that the pixel coordinates of the feature point are (x1, y1), and the actual position coordinates of the feature point are (X1, Y1), the relationship equation between the pixel coordinates of the feature point and the actual position coordinates of the feature point is constructed according to the above conversion parameters as shown in the following formula:

[0103]

[0104] For each feature point, two relationship equations similar to the above can be established. The calibration plate has four feature points in total, so eight relationship equations can be established.

[0105] Using these eight relationship equations to establish a system of equations, we can solve the unique t 11 -t 32 And other 8 parameters, so as to solve the transformation matrix T.

[0106] S209: Using the pixel coordinates of the edge of the direct field of view obtained on the calibrated camera image and the transformation coefficient of the actual position, calculate the physical position of the pixel coordinates of the edge of the direct field of view at the actual position.

[0107] Exemplarily, assuming that the pixel coordinates of the preset boundary point are (x, y), the pixel coordinates of the preset boundary point are transformed using a transformation matrix to obtain the transformed pixel coordinates (X, Y), as shown below:

[0108]

[0109] Figure 7 701 is a schematic diagram of the actual position of a field of view boundary line in a real scene in a top view according to a second embodiment of the present invention, wherein 701 refers to the position of the field of view boundary line in the top view.

[0110] S210: photograph other scenes to obtain the physical positions of the direct visual field edge pixel coordinates in the actual positions in the other scenes.

[0111] S211, integrating the physical positions of the direct vision edge pixel coordinates in the real scene of the top view under different scenes, obtaining a direct vision boundary map, and completing the direct vision measurement.

[0112] For example, Figure 8 is a schematic diagram of a field of view boundary line in different scenes provided by the second embodiment of the present invention, wherein: Figure 8 The front windshield field of view boundary, the left window field of view boundary and the right window field of view boundary are indicated.

[0113] Embodiment 3

[0114] Fig. 9 This is a schematic diagram of the structure of a vehicle visual field measurement device provided by Embodiment 3 of the present invention. Fig. 9 As shown, the device comprises:

[0115] The visual field detection image acquisition module 901 is used to obtain the visual field detection image of the vehicle, and the visual field detection image is acquired by a target camera placed in the vehicle at the driver's perspective;

[0116] The key point and edge point acquisition module 902 is used to acquire the pixel coordinates of multiple key points and the pixel coordinates of the edge points of the visual field in the visual field detection image;

[0117] The key point real distance acquisition module 903 is used to obtain the real relative distance between the vehicle and each key point;

[0118] An image transformation information determination module 904 is used to determine the transformation information of the field of view detection image according to the pixel coordinates of each key point and the real relative distance between the vehicle and each key point;

[0119] The visual field edge point transformation processing module 905 is used to transform the pixel coordinates of the visual field edge points according to the transformation information of the visual field detection image to obtain the visual field measurement information corresponding to the visual field detection image.

[0120] By obtaining the pixel coordinates of multiple key points in the field of view detection image and generating transformation information in combination with the real relative distance between the vehicle and these key points, an effective mapping relationship between the pixel coordinates of the field of view detection image and the real-world coordinates is established, ensuring high accuracy in the subsequent transformation processing of the field of view edge points; by obtaining the real relative distance between the vehicle and each key point and using it to determine the transformation information of the field of view detection image, the distance relationship between the actual position of the vehicle and the calibration environment can be fully considered, ensuring that the geometric information in the field of view detection image can correctly reflect the actual spatial structure; by processing the pixel coordinates of the key points and field of view edge points obtained in the field of view detection image using the transformation information, the need for manual calibration and intervention is reduced, and the transformation processing of the field of view edge points and the acquisition of the final measurement information are completed in the image analysis and calculation process, which improves the measurement efficiency and reduces the errors introduced by human operation.

[0121] Optionally, the visual field detection image acquisition module 901 is specifically used for:

[0122] According to the key points of the calibration plate in the field of vision detection image of the vehicle, the field of vision detection image of the vehicle is rectified for distortion.

[0123] Optionally, the visual field detection image acquisition module 901 is specifically used for:

[0124] The optical center of the target camera is placed at the driver's eye point.

[0125] Optionally, the visual field detection image acquisition module 901 is specifically used for:

[0126] Acquire a field of view detection image of the vehicle in at least one direction;

[0127] After the visual field measurement information corresponding to the visual field detection image, it also includes:

[0128] The field of view measurement information corresponding to the field of view detection images in each direction is fused to obtain the field of view boundary information of the vehicle.

[0129] Optionally, the direction includes front, left, right, or back.

[0130] Optionally, the key point and edge point acquisition module 902 is specifically used for:

[0131] In the field of vision detection image, at least one key point on a calibration plate is detected to obtain pixel coordinates of each key point on the calibration plate; the calibration plate is placed within the direct field of vision of the vehicle.

[0132] Optionally, the visual field detection image acquisition module 901 and the key point and edge point acquisition module 902 are specifically used for:

[0133] The calibration plate includes a checkerboard image, and the vertices of the middle rectangle of the checkerboard image are key points.

[0134] The vehicle vision measuring device provided in the embodiment of the present invention can execute the vehicle vision measuring method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0135] Embodiment 4

[0136] Fig.10 1 is a schematic diagram of the structure of an electronic device for implementing the vehicle vision measurement method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0137] like Fig.10 As shown, the electronic device 1000 includes at least one processor 1001, and a memory connected to the at least one processor 1001 in communication, such as a read-only memory (ROM) 1002, a random access memory (RAM) 1003, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 1001 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 1002 or the computer program loaded from the storage unit 1008 to the random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the electronic device 1000 can also be stored. The processor 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0138] Multiple components in the electronic device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the electronic device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0139] The processor 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 1001 executes the various methods and processes described above, such as a vehicle vision measurement method.

[0140] In some embodiments, the vehicle vision measurement method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the processor 1001, one or more steps of the vehicle vision measurement method described above may be performed. Alternatively, in other embodiments, the processor 1001 may be configured to perform the vehicle vision measurement method in any other appropriate manner (e.g., by means of firmware).

[0141] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0143] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0145] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0146] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0147] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0148] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle visual field measurement method, characterized in that: The method comprises: Acquire a field of view detection image of the vehicle, wherein the field of view detection image is acquired by a target camera placed in the vehicle from a driver's perspective; In the visual field detection image, obtaining pixel coordinates of a plurality of key points and pixel coordinates of visual field edge points; Acquire the real relative distance between the vehicle and each of the key points; Determining transformation information of the visual field detection image according to the pixel coordinates of each of the key points and the real relative distance between the vehicle and each of the key points; According to the transformation information of the visual field detection image, the pixel coordinates of the visual field edge points are transformed to obtain the visual field measurement information corresponding to the visual field detection image.

2. The method according to claim 1, characterized in that The step of obtaining pixel coordinates of a plurality of key points includes: In the field of vision detection image, at least one key point on a calibration plate is detected to obtain pixel coordinates of each key point on the calibration plate; the calibration plate is placed within the direct field of vision of the vehicle.

3. The method according to claim 2, characterized in that The obtaining of the field of view detection image of the vehicle comprises: According to the key points of the calibration plate in the field of vision detection image of the vehicle, distortion correction is performed on the field of vision detection image of the vehicle.

4. The method according to claim 2 or 3, characterized in that: The calibration plate includes a checkerboard image, and the vertices of the middle rectangle of the checkerboard image are key points.

5. The method according to claim 1, characterized in that The optical center of the target camera is placed at the eye point of the driver.

6. The method according to claim 1, characterized in that The obtaining of the field of view detection image of the vehicle comprises: Acquire a field of view detection image of the vehicle in at least one direction; After the visual field measurement information corresponding to the visual field detection image, it also includes: The visual field measurement information corresponding to the visual field detection images in each of the directions is fused to obtain the visual field boundary information of the vehicle.

7. The method according to claim 6, characterized in that The directions include front, left, right, or back.

8. A vehicle visual field measuring device, characterized in that: include: A visual field detection image acquisition module, used to acquire a visual field detection image of a vehicle, wherein the visual field detection image is acquired by a target camera placed in the vehicle at a driver's viewing angle; A key point and edge point acquisition module, used to acquire pixel coordinates of a plurality of key points and pixel coordinates of visual field edge points in the visual field detection image; A key point real distance acquisition module, used to acquire the real relative distance between the vehicle and each key point; An image transformation information determination module, used to determine the transformation information of the field of view detection image according to the pixel coordinates of each of the key points and the real relative distance between the vehicle and each of the key points; The visual field edge point transformation processing module is used to transform the pixel coordinates of the visual field edge points according to the transformation information of the visual field detection image to obtain the visual field measurement information corresponding to the visual field detection image.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle vision measurement method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle field of view measurement method according to any one of claims 1 to 7 when executed.

Images