Camera positioning method, camera positioning device, and computer storage medium

Abstract

The application discloses a camera positioning method, a camera positioning device and a computer storage medium. The camera positioning method comprises the following steps: acquiring a shooting image and a corresponding camera height, wherein a preset marker is arranged in front of a lens of the camera; acquiring a pixel number of the preset marker on the shooting image; calculating a proportion of the pixel number and a reference number, obtaining a distance between a positioning point and the camera based on the camera height and the proportion; and positioning the positioning point by using the distance. In the foregoing manner, the distance between the positioning point and the camera can be obtained based on the pixel number and the reference number of the preset marker on the shooting image, so that the positioning point can be positioned, automatic calibration of the positioning point can be realized, manual operation steps can be reduced, positioning efficiency can be improved, and calibration time can be saved.

Description

Technical Field

[0001] This application relates to the field of camera positioning, and in particular to a camera positioning method, a camera positioning device, and a computer storage medium. Background Technology

[0002] With the continuous development of computer image processing technology, image applications are becoming increasingly widespread, encompassing multiple fields such as biomedicine, military, and machine vision. Among these, image-based camera localization is an important branch. Image-based camera localization calculates the actual location information of a point in an image based on the image or video captured by the camera.

[0003] In one application scenario, early warning of forest fires has always been a top priority in forestry work. When fires occur in forests or deep mountains, the complex terrain and large area make it difficult to quickly pinpoint the fire's location after it is discovered. This prevents fire command departments from promptly deploying and organizing personnel and equipment to the fire scene, delaying the optimal time for firefighting. To improve the accuracy of positioning, camera calibration is necessary, which involves correlating camera images with images in remote sensing maps.

[0004] Existing positioning technologies typically rely on on-site technicians to visually correlate images in remote sensing maps with actual ground targets in video footage. This process is time-consuming, resulting in low camera positioning efficiency and unstable positioning accuracy, which is easily affected by human error. Summary of the Invention

[0005] The main technical problem addressed by this application is how to improve the efficiency of camera positioning. To this end, this application provides a camera positioning method, a camera positioning device, and a computer storage medium.

[0006] To solve the above-mentioned technical problems, one technical solution adopted in this application is: to provide a camera positioning method, the method comprising: acquiring a captured image and the corresponding camera height, wherein a preset marker is provided in front of the camera lens; acquiring the number of pixels occupied by the preset marker in the captured image; calculating the ratio of the number of pixels to the reference number, and obtaining the distance between the positioning point and the camera based on the camera height and the ratio; and positioning the positioning point using the distance.

[0007] The positioning point is the center point of the captured image.

[0008] The method of obtaining the distance between the positioning point and the camera based on the camera height and scale includes: multiplying the camera height by the scale to obtain the distance between the positioning point and the camera.

[0009] Before acquiring the captured image and the corresponding camera height, the process also includes: acquiring a reference image, wherein the reference image includes a reference point.

[0010] The positioning of the positioning point using distance includes: obtaining the first camera pitch angle corresponding to the reference image and the second camera pitch angle corresponding to the captured image; and calculating the position information of the positioning point based on the position information of the reference point, the first camera pitch angle, the second camera pitch angle, and the distance.

[0011] Before calculating the ratio of the number of pixels to the baseline number, the method also includes: obtaining the number of pixels occupied by the preset marker on the baseline image as the baseline number.

[0012] The reference image and the captured image have the same resolution; the reference image and the captured image are captured by the same camera, and the camera has the same magnification.

[0013] The image localization method also includes: acquiring multiple captured images and locating the localization points in each captured image.

[0014] To solve the above-mentioned technical problems, another technical solution adopted in this application is to provide a camera positioning device, which includes a processor and a memory. The memory is coupled to the processor and stores program data. The processor is used to execute the program data to implement the camera positioning method as described above.

[0015] To solve the above-mentioned technical problems, another technical solution adopted in this application is to provide a computer-readable storage medium that stores program data, which, when executed, is used to implement the above-mentioned camera positioning method.

[0016] The beneficial effects of this application are as follows: Unlike existing technologies, the camera positioning method provided in this application is applied to a camera positioning device. The camera positioning device acquires a captured image and the corresponding camera height, wherein a preset marker is placed in front of the camera lens; the number of pixels occupied by the preset marker in the captured image is acquired; the ratio of the number of pixels to the reference number is calculated, and the distance between the positioning point and the camera is obtained based on the camera height and the ratio; the positioning point is then located using this distance. Compared with conventional camera positioning methods, this application uses a preset marker on the camera lens in the camera positioning device, calculates the distance between the positioning point and the camera by acquiring the number of pixels occupied by the marker in the captured image, and then locates the positioning point using the obtained distance. The camera positioning device provided in this application can automatically calibrate the positioning point by acquiring the number of pixels of the preset marker in the captured image, without manual intervention. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] in:

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the camera positioning method provided in this application;

[0020] Figure 2 This is an analytical schematic diagram illustrating the principle of the arc length formula in the camera positioning method provided in this application;

[0021] Figure 3 This is a flowchart illustrating the application of the camera positioning method in the camera positioning device provided in this application.

[0022] Figure 4 This is a schematic diagram of an image captured by the camera lens in the camera positioning method provided in this application;

[0023] Figure 5 This is a schematic diagram of the camera acquiring a reference image and capturing an image in the camera positioning method provided in this application;

[0024] Figure 6 This is a flowchart illustrating the second embodiment of the camera positioning method provided in this application;

[0025] Figure 7 This is a schematic diagram of the structure of the first embodiment of the camera positioning device provided in this application;

[0026] Figure 8 This is a schematic diagram of the structure of the second embodiment of the camera positioning device provided in this application;

[0027] Figure 9 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0029] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this document means two or more. Moreover, the term "at least one" in this document means any combination of at least two of any one or more of a plurality of objects. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0030] The camera positioning method provided in this application is mainly applied to a camera positioning device, wherein the camera positioning device can be a server or a system in which the server and terminal devices cooperate with each other. Accordingly, the various parts of the camera positioning device, such as various units, sub-units, modules, and sub-modules, can all be set in the server, or they can be set in the server and the terminal device respectively.

[0031] Furthermore, the aforementioned server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules, such as software or software modules used to provide distributed servers, or as a single software program or software module; no specific limitation is made here. In some possible implementations, the camera positioning method of this application embodiment can be implemented by a processor calling computer-readable instructions stored in memory.

[0032] The camera positioning method provided in this application is mainly used to locate positioning points in videos or images based on videos or images, thereby associating the positioning points with remote sensing images in remote sensing maps, and then mapping the horizontal or pitch angle of the camera that acquires the video or image with the latitude and longitude of the geographical location in the real scene. Thus, once the camera positioning device detects the point that needs to be located, it can obtain the latitude and longitude of the current positioning point through the current horizontal or pitch angle of the camera.

[0033] Current camera positioning methods primarily rely on technicians manually comparing remote sensing images on remote sensing maps with actual ground targets in video footage using the naked eye, and then associating them. However, due to the complex terrain and dense forests in forests or deep mountains where positioning points are located, on-site technicians spend a significant amount of time calibrating the points. Furthermore, the untimely updating of remote sensing maps can lead to the inability to find the corresponding actual target for a given location, thus affecting the accuracy of the positioning. Therefore, this application provides a camera positioning method, and the technical solution adopted in this application will be described in detail below.

[0034] See Figures 1 to 3 , Figure 1 This is a flowchart illustrating the first embodiment of the camera positioning method provided in this application; Figure 2 This is an analytical schematic diagram illustrating the principle of the arc length formula in the camera positioning method provided in this application; Figure 3 This is a schematic diagram of the process of applying the camera positioning method in the camera positioning device provided in this application.

[0035] Step 11: Obtain the captured image and the corresponding camera height. There is a preset marker in front of the camera lens.

[0036] Specifically, when the object or positioning point to be positioned in the camera positioning device is located at the exact center of the camera lens's image, the camera in the camera positioning device takes a picture of the current image in the lens as the captured image.

[0037] Specifically, the captured image can be a video frame extracted from a video clip captured by a camera device that meets certain quality requirements, or any video frame extracted from a video clip, or a single image frame captured by the camera device, etc. Meeting certain quality requirements can refer to requirements for elements such as brightness and sharpness of the image; specific requirements for image quality are not specified here.

[0038] The images are captured by a camera device in a relatively fixed position. This relatively fixed camera device can be a camera, video camera, scanner, or other device with video and / or photographic capabilities installed in a fixed location; no specific limitation is made here.

[0039] Specifically, before acquiring the captured image, the camera positioning device will also pre-obtain the height H of the fixed position where the camera equipment is installed, in order to facilitate subsequent calculations.

[0040] Please continue reading. Figure 2The camera positioning method used in this application is mainly calculated based on the principle of the arc length formula shown in the figure. The figure contains a large circle and a small circle. Assuming the radius of the large circle is twice that of the small circle, the arc length of the large circle corresponding to the same angle α is equal to twice the arc length of the small circle, i.e., cc' = 2 × aa'. Assuming α is the field of view of a camera, and the camera captures two images—a close-up and a distant view—with the field of view and magnification remaining constant, then aa' is the total number of horizontally effective pixels occupied by the entire image when the camera captures the close-up view, and cc' is the total number of horizontally effective pixels occupied by the entire image when the camera captures the distant view.

[0041] Since the close-up and distant images were taken by the same camera, and since the camera's resolution is fixed, the total number of effective pixels in the entire horizontal plane is also fixed, meaning that the number of pixels occupied by aa' is equal to the number of pixels occupied by cc'.

[0042] If both images contain a ruler A of fixed length, and the horizontal area occupied by ruler A in the close-up image is bb', and the horizontal area occupied by ruler A in the distant image is tt', then since the arc length cc' = 2 × aa' in both images, the number of pixels in bb' occupied by ruler A in the close-up image is twice the number of pixels in tt' occupied by ruler A in the distant image.

[0043] Among them, the field of view is the angle formed by the two edges of the maximum range through which the image of the target object can pass through the lens, with the lens as the vertex. Magnification refers to the ratio of the size of the image of the object on the focal plane through the lens to the actual size of the object.

[0044] Specifically, a preset marker is placed in front of the lens when capturing the image, serving as a pixel reference between different images of the positioning point and the reference point. This preset marker can be located anywhere on the lens's viewing window; for ease of viewing, it can be positioned directly below the center point of the lens. The number of preset markers can be one or more, and is not limited here. For simplicity, this article will use one preset marker as an example.

[0045] In one embodiment of this application, see reference Figure 4 , Figure 4 This is a schematic diagram of an image captured by the camera lens in the camera positioning method provided in this application. For example... Figure 4 As shown, the preset marker can be a screen-printed ruler on a viewing window. This ruler has a fixed length and scale and is located directly below the camera lens. The object to be positioned needs to be located in the exact center of the captured image.

[0046] Specifically, before acquiring the captured image and its corresponding camera height, the camera positioning device also acquires a reference image, which includes a reference point. The reference point can be any point with a known distance from the camera and a known pitch angle. When the reference point is perpendicular to the camera, the distance between the reference point and the camera is the camera height. The camera height is used to represent the distance between the capturing device taking the current image and the reference point.

[0047] Optionally, the reference point can be the center point of the captured image when the camera's pitch angle is 0°. For example... Figure 5 As shown, Figure 5 This is a schematic diagram of the camera when acquiring a reference image and taking a picture in the camera positioning method provided in this application.

[0048] In one embodiment of this application, the camera in the camera positioning device is mounted on a pan-tilt platform at a fixed height H, and the preset marker is a silkscreen ruler. When the camera's pitch angle T = 0°, the image captured by the camera when the reference point is located at the center point of the camera lens is used as the reference image, and the number of pixels occupied by the silkscreen ruler on the reference image is used as the reference number N1. The calculation of the number of pixels can be achieved by the camera positioning device calling an interface with the function of calculating the number of pixels, or by pre-setting a piece of code in the camera positioning device to calculate the number of pixels in a certain area of ​​the image; no limitation is made here.

[0049] Step 12: Obtain the number of pixels occupied by the preset marker in the captured image.

[0050] Specifically, after obtaining the number of pixels occupied by the preset marker in the reference image, the camera positioning device will also use the same method to obtain the number of pixels occupied by the preset marker in the captured image. Please continue reading. Figure 5 ,by Figure 5 For example, the camera in the camera positioning device remains stationary on a fixed-height iron tower (H). When positioning point A1 is at the center of the camera lens, the camera acquires the current image as the captured image. This captured image includes the same preset marker, i.e., a silkscreened scale, as in the reference image. The camera positioning device obtains the camera's pitch angle T = X° at this moment and calculates the number of pixels occupied by the silkscreened scale on the captured image as the pixel count N2. The method for calculating the pixel count is as described above and will not be repeated here.

[0051] Step 13: Calculate the ratio of the number of pixels to the number of reference pixels, and obtain the distance between the positioning point and the camera based on the camera height and ratio.

[0052] Specifically, after the camera positioning device obtains the number of pixels occupied by the preset marker in the captured image where the positioning point is located and the number of pixels occupied by the preset marker in the reference image where the reference point is located (i.e., the reference number), the camera positioning device calculates the ratio P between the number of pixels and the reference number, based on... Figure 2 Taking the arc length formula as an example, the distance D between the positioning point and the camera is obtained.

[0053] Since the magnification and field of view of the camera in the camera positioning device remain unchanged, the number of horizontal pixels occupied by the captured image and the reference image are the same, and the actual physical length of the preset marker is the same. Therefore, the ratio of the number of pixels to the number of reference pixels can be the ratio between the distance from the camera to the reference point and the distance from the camera to the positioning point.

[0054] Therefore, the camera positioning device can obtain D = P × H.

[0055] Step 14: Use distance to locate the positioning point.

[0056] Specifically, after the camera positioning device obtains the distance between the positioning point and the camera, it can also obtain the latitude and longitude of the positioning point based on the latitude and longitude of the camera, thereby associating it with the GIS map to achieve the calibration of the positioning point.

[0057] Geographic Information System (GIS) is a system designed to visualize and analyze georeferenced information, used to describe and represent the Earth and other geographical phenomena. It places simple latitude and longitude coordinates within specific geographic information, representing a location, landmark, or orientation that can be recognized and understood by users. After obtaining location information through relevant technologies, users also need to understand their surrounding geographic environment, query and analyze environmental information, thereby providing information support and services for their activities.

[0058] For specific methods on obtaining the latitude and longitude of the positioning point from the camera's location, please refer to [link / reference needed]. Figure 6 , Figure 6 This is a flowchart illustrating the second embodiment of the camera positioning method provided in this application.

[0059] Step 61: Obtain the first camera pitch angle corresponding to the reference image and the second camera pitch angle corresponding to the captured image.

[0060] Specifically, taking the first camera pitch angle corresponding to the reference image, i.e., the pitch angle of the reference point, as 0° and the second camera pitch angle corresponding to the captured image, i.e., the pitch angle of the positioning point, as 30° as an example, the camera positioning device obtains the angle between the two points as 30°-0°=30°.

[0061] Step 62: Based on the location information of the reference point, the pitch angle of the first camera, the pitch angle of the second camera, and the distance, calculate the location information of the positioning point.

[0062] Optionally, the camera positioning device can first calculate the longitude of the positioning point. Based on the angle between the two points and the distance between the camera and the reference point, the camera positioning device calculates the horizontal translation distance of the positioning point relative to the reference point, and then obtains the longitude of the positioning point based on the longitude of the reference point. This calculation can be performed using the following formula.

[0063] long2=long1+d*sinb / [ARC*cos(lat1)*2π / 360]

[0064] Where long2 is the longitude of the positioning point, long1 is the longitude of the reference point, ARC is the equatorial radius of the Earth, which is the distance from the Earth's center to the equator, approximately 6371.393 km, lat1 is the latitude of the reference point, and b is the angle between the reference point and the positioning point.

[0065] Alternatively, the camera positioning device can calculate the latitude of the positioning point according to the following formula:

[0066] lat2=lat1+d*cosb / (ARC*2π / 360)

[0067] Where lat2 is the latitude of the positioning point and lat1 is the latitude of the reference point.

[0068] Specifically, the order in which the camera positioning device calculates the latitude and longitude of the positioning point can be set by the user and is not limited here.

[0069] Specifically, after obtaining the latitude and longitude of the positioning point, the camera positioning device associates the latitude and longitude with the pt value of the gimbal, i.e., the device that fixes the camera, thereby calibrating the positioning point. The pt value includes the horizontal and vertical angles of the gimbal.

[0070] Specifically, the camera positioning device can capture multiple images, each with a different pitch angle. Positioning points A2, A3, etc., in each captured image are then located and associated with their corresponding gimbal pt values, thereby automatically calibrating all positioning points. The positioning method is similar to the steps described above and will not be repeated here.

[0071] The camera positioning method provided in this application can automatically calibrate each positioning point using a camera positioning device without manual intervention, thus saving a significant amount of calibration time. Furthermore, the camera positioning device can automatically acquire the distance between the positioning point and the camera. Even if the camera positioning device operates for an extended period or is tilted due to severe weather conditions such as typhoons or heavy rain, it can still automatically calibrate the positioning point without requiring manual recalibration.

[0072] Unlike existing technologies, the camera positioning method provided in this application is applied to a camera positioning device. The camera positioning device acquires a captured image and the corresponding camera height, wherein a preset marker is placed in front of the camera lens. The method acquires the number of pixels occupied by the preset marker in the captured image; calculates the ratio of the number of pixels to a reference number; and obtains the distance between the positioning point and the camera based on the camera height and the ratio. The positioning point is then located using this distance. Compared to conventional camera positioning methods, this application uses a preset marker on the camera lens in the camera positioning device. By acquiring the number of pixels occupied by the marker in the captured image, the distance between the positioning point and the camera is calculated, and then the positioning point is located using the obtained distance. The camera positioning device provided in this application can automatically calibrate the positioning point by acquiring the number of pixels of the preset marker in the captured image, without manual intervention.

[0073] The method described in the above embodiments can be implemented using a camera positioning device, as described below. Figure 7 Describe it. Figure 7 This is a schematic diagram of the structure of the first embodiment of the camera positioning device provided in this application.

[0074] like Figure 7 As shown, the camera positioning device 70 in this embodiment includes an image acquisition module 71, a quantity acquisition module 72, a distance calculation module 73, and a positioning module 74.

[0075] The image acquisition module 71 is used to acquire the captured image and the corresponding camera height, wherein there is a preset marker in front of the camera lens.

[0076] The quantity acquisition module 72 is used to acquire the number of pixels occupied by the preset marker in the captured image.

[0077] The distance calculation module 73 is used to calculate the ratio of the number of pixels to the number of reference pixels, and obtain the distance between the positioning point and the camera based on the camera height and ratio.

[0078] The positioning module 74 is used to locate the positioning point using distance.

[0079] The method described in the above embodiments can be implemented using a camera positioning device, as described below. Figure 8 , Figure 8 This is a schematic diagram of the structure of the second embodiment of the camera positioning device provided in this application. The camera positioning device 80 includes a memory 81 and a processor 82. The memory 81 is used to store program data, and the processor 82 is used to execute the program data to implement the following method:

[0080] Acquire the captured image and its corresponding camera height, where a preset marker is located in front of the camera lens; obtain the number of pixels occupied by the preset marker in the captured image; calculate the ratio of the number of pixels to the reference number, and obtain the distance between the positioning point and the camera based on the camera height and the ratio; use the distance to locate the positioning point.

[0081] See Figure 9 , Figure 9 This is a schematic diagram of an embodiment of the computer-readable storage medium 90 provided in this application. The computer-readable storage medium 90 stores program data 91, which, when executed by a processor, is used to implement the following method:

[0082] Acquire the captured image and its corresponding camera height, where a preset marker is located in front of the camera lens; obtain the number of pixels occupied by the preset marker in the captured image; calculate the ratio of the number of pixels to the reference number, and obtain the distance between the positioning point and the camera based on the camera height and the ratio; use the distance to locate the positioning point.

[0083] When the embodiments of this application are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0084] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An image localization method, characterized in that, The image localization method includes: Acquire the captured image and its corresponding camera height, where there are preset markers in front of the camera lens; Obtain the number of pixels occupied by the preset marker in the captured image; Calculate the ratio of the number of pixels to the reference number, and obtain the distance between the positioning point and the camera based on the camera height and the ratio. The reference number is the number of pixels occupied by the preset marker in the reference image. The pitch angle of the reference image is known, the field of view of the reference image and the captured image are the same, and the horizontal number of pixels of the reference image and the captured image are the same. The location point is located using the distance.

2. The image localization method according to claim 1, characterized in that, The positioning point is the center point of the captured image.

3. The image localization method according to claim 1, characterized in that, The step of determining the distance between the positioning point and the camera based on the camera height and the ratio includes: Multiply the camera height by the ratio to obtain the distance between the positioning point and the camera.

4. The image localization method according to claim 1, characterized in that, Before acquiring the captured image and the corresponding camera height, the process also includes: A reference image is acquired, wherein the reference image includes a reference point.

5. The image localization method according to claim 4, characterized in that, The step of locating the positioning point using the distance includes: Obtain the first camera pitch angle corresponding to the reference image and the second camera pitch angle corresponding to the captured image; Based on the location information of the reference point, the pitch angle of the first camera, the pitch angle of the second camera, and the distance, the location information of the positioning point is calculated.

6. The image localization method according to claim 4, characterized in that, Before calculating the ratio of the number of pixels to the reference number, the method further includes: The number of pixels occupied by the preset marker on the reference image is obtained as the reference number.

7. The image localization method according to claim 4, characterized in that, The reference image has the same resolution as the captured image; The reference image and the captured image were captured by the same camera, and the camera has the same magnification.

8. The image localization method according to claim 1, characterized in that, The image localization method further includes: Multiple captured images are obtained, and the positioning points in the captured images are located respectively.

9. An image positioning device, characterized in that, The image positioning device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the image positioning method as described in any one of claims 1 to 8.

10. A computer storage medium, characterized in that, The computer storage medium is used to store program data, which, when executed by the computer, is used to implement the image positioning method as described in any one of claims 1 to 8.

Images