Pole camera, image processing method, device and storage medium

Abstract

The present application provides a pole camera, an image processing method, a device and a storage medium. The method is applied to a pole camera, wherein the pole of the pole camera is fixed on the ground, a beacon is arranged on the ground, the lens of the pole camera includes at least two periscope structures; the at least two periscope structures are used to enable the pole camera to shoot the beacon from different angles, and the pole camera is configured to: collect a target scene image, the target scene image includes: a picture of the target scene, and the beacon photographed by each periscope structure; according to the position of the beacon photographed by each periscope structure in the target scene image, obtain the displacement data of the pole camera in at least one direction; according to the displacement data of the camera in at least one direction, correct the target scene image to obtain the corrected target scene image.

Description

Technical Field

[0001] The present application relates to camera technology, and in particular to a pole camera, an image processing method, a device and a storage medium. Background Art

[0002] In outdoor scenes such as along high-speed rail lines, highlands, and oceans, pole cameras are usually installed to capture the surrounding environment. However, in outdoor scenes, due to the influence of irregular factors such as wind speed, wind direction, and turbulent disturbances, the camera will shake irregularly, resulting in low clarity of the image captured by the pole camera.

[0003] At present, the pole camera mainly improves the clarity of the image by performing reverse motion offset calculation on the image taken by the pole camera based on the movement signal of the pole camera collected by the sensor installed on the lens.

[0004] However, shooting with a pole camera is an operation at the light signal level, and the sensor collecting the movement signal of the pole camera has a high latency. Therefore, the clarity of the image obtained by the above method is still low. Summary of the invention

[0005] The present application provides a pole camera, an image processing method, a device and a storage medium to improve the image clarity of the pole camera.

[0006] In a first aspect, the present application provides a pole camera, wherein the pole of the pole camera is fixed on the ground, a beacon is arranged on the ground, and the lens of the pole camera includes at least two periscope structures; the at least two periscope structures are used to enable the pole camera to photograph the beacon from different angles, and the pole camera is configured as follows:

[0007] Collecting a target scene image, the target scene image comprising: a picture of the target scene, and the beacon photographed by each of the periscope structures;

[0008] Acquire displacement data of the camera of the pole camera in at least one direction according to the position of the beacon in the target scene image photographed by each periscope structure;

[0009] The target scene image is deflected according to the displacement data of the camera in at least one direction to obtain a deflected target scene image.

[0010] Optionally, the lens of the pole camera includes: a first periscope structure, a second periscope structure, a third periscope structure, and a fourth periscope structure, the first periscope structure and the second periscope structure constitute a first binocular field of view, and the third periscope structure and the fourth periscope structure constitute a second binocular field of view;

[0011] The straight line where the first optical center of the camera and the second optical center of the camera in the first binocular field of view are located is parallel to the ground and perpendicular to the optical axis of the pole camera; the straight line where the third optical center of the camera and the fourth optical center of the camera in the second binocular field of view are located is parallel to the optical axis of the pole camera; the first optical center of the camera is formed by the pole camera through the first periscope structure, the second optical center of the camera is formed by the pole camera through the second periscope structure, the third optical center of the camera is formed by the pole camera through the third periscope structure, and the fourth optical center of the camera is formed by the pole camera through the fourth periscope structure;

[0012] The pole camera is configured as follows:

[0013] Acquire the displacement data of the pole camera in the left-right direction according to the position of the beacon in the target scene image captured through the first binocular field of view;

[0014] According to the position of the beacon in the target scene image captured through the second binocular field of view, the displacement data of the camera of the pole camera in the front-to-back direction is obtained.

[0015] Optionally, the pole camera is configured as:

[0016] Acquire the depth of the beacon relative to the camera in the first binocular field of view according to the position of the beacon in the target scene image captured through the first binocular field of view;

[0017] According to the depth of the beacon relative to the camera in the first binocular field of view, the displacement data of the camera of the pole camera in the left and right directions is obtained.

[0018] Optionally, the pole camera is configured as:

[0019] When the displacement data of the camera in the front-to-back direction is not equal to zero, the target scene image is cropped according to the displacement data of the camera in the front-to-back direction to obtain the target scene image after initial correction;

[0020] When the displacement data of the camera in the left-right direction is not equal to zero, the jitter in the left-right direction of the target scene image after the initial deflection correction is eliminated according to the displacement of the camera in the left-right direction to obtain the target scene image after deflection correction.

[0021] Optionally, the beacons photographed by each of the periscope structures are located in a target area of ​​the target scene image, and the pole camera is configured as follows:

[0022] Before the target scene image is cropped according to the displacement data of the camera in the front-rear direction to obtain the target scene image after initial correction, the target area of ​​the target scene image is cut to obtain the target scene image without the target area.

[0023] Optionally, the beacons photographed by each of the periscope structures are located in a target area of ​​the target scene image; and the pole camera is configured as follows:

[0024] Before obtaining the displacement data of the pole camera in at least one direction according to the position of the beacon in the target scene image photographed by each periscope structure, beacon recognition is performed on the target area of ​​the target scene image to obtain the position of the beacon in the target scene image photographed by each periscope structure.

[0025] Optionally, the pole camera is configured as:

[0026] After correcting the target scene image according to the displacement data of the camera in at least one direction to obtain the corrected target scene image, compressing and encoding the corrected target scene image to obtain a video including the target scene;

[0027] The video including the target scene is output.

[0028] In a second aspect, the present application provides an image processing method, the method being applied to the pole camera as described in any one of the first aspects, the method comprising:

[0029] Capturing a target scene image, the target scene image comprising: a picture of the target scene, and a beacon photographed by each periscope structure of the lens of the pole camera; the beacon is set on the ground to which the pole camera is fixed;

[0030] Acquire displacement data of the camera of the pole camera in at least one direction according to the position of the beacon in the target scene image;

[0031] The target scene image is deflected according to the displacement data of the camera in at least one direction to obtain a deflected target scene image.

[0032] In a third aspect, the present application provides an image processing device, the device being applied to the pole camera as described in any one of the first aspects, the device comprising:

[0033] A collection module, used for collecting a target scene image, wherein the target scene image includes: a picture of the target scene, and a beacon photographed by each periscope structure of the lens of the pole camera; the beacon is set on the ground where the pole camera is fixed;

[0034] A processing module is used to obtain the displacement data of the camera of the pole camera in at least one direction according to the position of the beacon in the target scene image; and to correct the target scene image according to the displacement data of the camera in at least one direction to obtain the corrected target scene image.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the second aspect.

[0036] The pole camera, image processing method, device and storage medium of the present application, through the periscope structure of the pole camera, enable the pole camera to capture the beacon on the ground, thereby realizing the simultaneous acquisition of the beacon on the ground and the picture of the target scene as the target scene image. The displacement data of the camera in at least one direction can be obtained by the position of the beacon in the target scene image. Because the beacon on the ground is fixed, the change in the position of the beacon in the target scene image can be used to represent the displacement data of the camera. That is, it is realized that the displacement data of the camera and the target scene captured by the camera are collected simultaneously. The target scene is corrected by the displacement data of the camera in at least one direction, so that the displacement data used to correct the target scene is collected at the same time as the target scene, thereby improving the accuracy of correcting the target scene, and then improving the clarity of the target scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1It is a structural schematic diagram of a pole camera;

[0039] Figure 2 A schematic diagram of the structure of a pole camera provided in this application;

[0040] Figure 3 A schematic diagram of a periscope structure provided for this application;

[0041] Figure 4 A flowchart of an image processing method provided in this application;

[0042] Figure 5 A schematic diagram of a target scene image provided for this application;

[0043] Figure 6 It is a schematic diagram of a binocular field of view algorithm;

[0044] Figure 7 A schematic diagram of a reverse calculation method for binocular displacement data;

[0045] Figure 8 A schematic diagram of the structure of an image processing device provided by the present application;

[0046] Fig. 9 A schematic diagram of the structure of an electronic device provided in this application.

[0047] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In outdoor scenes in vast areas such as along high-speed rail lines, highlands, and oceans, pole cameras are usually installed to capture the surrounding environment. Figure 1 Figure 1 is a schematic diagram of the structure of a pole camera. Figure 1 As shown, the camera can be mounted on a pole.

[0050] However, in outdoor scenes, the pole to which the camera is attached will shake greatly due to irregular factors such as wind speed, wind direction, and turbulence disturbance of high-speed trains. When the pole shakes, the camera will also shake, which will lead to poor image clarity in the pole camera. How to simply and effectively solve the problem of poor image clarity caused by camera shaking is a long-term goal explored by technicians.

[0051] At present, the existing pole cameras mainly solve the problem of poor image clarity caused by camera shaking by installing an optical anti-shake device (also called a servo device) on the camera lens or the camera housing. The optical anti-shake device can be provided with a sensor for collecting displacement data of the camera. Then, the camera can perform reverse motion offset calculation on the image collected by the camera based on the displacement data of the camera to offset the influence of the camera shaking trend on the image.

[0052] However, the image acquisition of the camera is an operation at the light signal level, and the process of the sensor collecting the displacement data of the pole camera usually has a high delay. If the image jitter is eliminated based on the displacement data, the displacement data may not be the displacement data at the moment when the image jitter exists. Therefore, the accuracy of the method of performing reverse motion compensation calculation based on the displacement data is poor. Under extreme conditions, it may even aggravate the deterioration of the camera image acquisition effect. Therefore, the existing pole camera still has the problem of low image clarity.

[0053] Considering that the above-mentioned problem of the existing pole camera is caused by the time difference between the displacement acquisition of the pole camera sensor and the image acquisition of the camera, the present application proposes a method that can simultaneously acquire the scene image and the camera displacement data. Through this method, the time difference between the scene image acquisition and the displacement data acquisition of the camera is reduced, so that the displacement data of the camera is the displacement data that causes the scene image to shake, thereby improving the clarity of the scene image obtained by image processing based on the displacement data.

[0054] first, Figure 2 This is a schematic diagram of the structure of a pole camera provided in this application. Figure 2 As shown, the pole of the pole camera can be fixed on the ground. A beacon can be set on the ground. The lens of the pole camera can include at least two periscope structures. The at least two periscope structures can be used to enable the pole camera to shoot the beacon from different angles.

[0055] It should be understood that the present application does not limit the shape of the beacon. For example, the beacon can be circular, rectangular, or diamond-shaped. In addition, the present application does not limit the location of the beacon on the ground.

[0056] It should be understood that Figure 2 The structure of the pole camera is described by taking the pole camera including four periscope structures as an example. In this example, the first periscope structure and the second periscope structure of the four periscope structures can constitute a first binocular field of view. The third periscope structure and the fourth periscope structure can constitute a second binocular field of view. For example, Figure 2 As shown, the first periscope structure and the second periscope structure can be located on the left and right of the camera respectively. The third periscope structure and the fourth periscope structure can be located in front and behind the camera respectively.

[0057] In some embodiments, the pole camera may include two periscope structures, for example, only the first periscope structure and the second periscope structure. Alternatively, in some embodiments, the pole camera may include more than four periscope structures. For example, if the pole camera includes six periscope structures, the fifth periscope structure and the sixth periscope structure may constitute a third binocular field of view.

[0058] It should be understood that the present application does not limit the specific implementation of the periscope structure, and optionally, any existing periscope lens can be referred to. Figure 3 A schematic diagram of a periscope structure provided in this application. Figure 3 As shown, through each optical lens (such as Figure 3 The reflection of the optical lens 1, the optical lens 2 and the optical lens 3 shown in the figure can project the beacon on the ground onto the lens of the pole camera, so that the pole camera can capture the beacon.

[0059] The following uses the pole camera as an example of the execution subject of the image processing method provided by the present application to explain the technical solution of the present application in detail in combination with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0060] Figure 4 This is a flow chart of an image processing method provided in this application. Figure 4 As shown, the method comprises the following steps:

[0061] S101, collecting a target scene image, wherein the target scene image may include: a picture of the target scene, and the beacon photographed by each periscope structure.

[0062] The target scene may be an area that the pole camera needs to monitor, such as along a high-speed rail line, an ocean, an urban road, etc. The present application does not limit the target scene. It should be understood that the present application does not limit the image of the target scene in the target scene image and the position distribution of the beacons captured by each periscope structure.

[0063] Optionally, the beacons captured by each periscope structure may all be located in the target area of ​​the target scene image. The target area may not overlap with the position of the target scene image in the target scene image. For example, taking the target area as being located below the target scene image and the target scene image including four beacons, Figure 5 A schematic diagram of a target scene image provided in this application. Figure 5 As shown, the four beacons may be located in a target area of ​​the target scene image.

[0064] S102: Acquire displacement data of the pole camera in at least one direction according to the position of the beacon in the target scene image photographed by each periscope structure.

[0065] The at least one direction may include, for example, at least one of the following: left-right direction (or horizontal direction), front-back direction, up-down direction (or vertical direction), etc. It should be understood that the displacement data of the camera in any direction may refer to the displacement of the current position of the camera relative to the position of the pole camera when it is in a stationary state.

[0066] It should be understood that the present application does not limit how the pole camera obtains the position of the beacon in the target scene image. Exemplarily, taking the example that the beacons photographed by each periscope structure are located in the target area of ​​the target scene image, the pole camera can perform beacon recognition on the target area of ​​the target scene image through a preset beacon recognition algorithm to obtain the position of the beacon photographed by each periscope structure in the target scene image. In this implementation, by performing beacon recognition on the target area of ​​the target scene image, the range that the pole camera needs to recognize is reduced, the amount of calculation for beacon recognition is reduced, and the efficiency of determining the position of each beacon in the target scene image is improved.

[0067] In some embodiments, the pole camera may also perform beacon recognition on the target scene image through a preset beacon recognition algorithm to obtain the position of each beacon in the target scene image.

[0068] Optionally, the above-mentioned preset beacon recognition algorithm can refer to any existing target detection algorithm, for example, and this application will not go into details here.

[0069] Optionally, for any two beacons in the target scene image, the pole camera may use, for example, a binocular field of view algorithm to obtain displacement data of the pole camera in one direction according to the positions of the two beacons in the target scene image.

[0070] S103: Correct the target scene image according to the displacement data of the camera in at least one direction to obtain a corrected target scene image.

[0071] For example, taking the displacement data of the camera in the left and right directions as an example, the pole camera can eliminate the jitter of the target scene in the left and right directions according to the displacement data of the camera in the left and right directions through a preset image jitter elimination algorithm to obtain a scene image after correction. Optionally, the preset image jitter elimination algorithm can refer to any existing implementation method of image correction based on the displacement data of the camera, which will not be described in detail in this application.

[0072] In this embodiment, the periscope structure of the pole camera allows the pole camera to capture the beacon on the ground, thereby realizing the simultaneous acquisition of the beacon on the ground and the picture of the target scene as the target scene image. The displacement data of the camera in at least one direction can be obtained through the position of the beacon in the target scene image. Because the beacon on the ground is fixed, the change in the position of the beacon in the target scene image can be used to represent the displacement data of the camera. That is, the displacement data of the camera and the target scene captured by the camera are simultaneously acquired. The target scene is corrected through the displacement data of the camera in at least one direction, so that the displacement data used to correct the target scene is acquired simultaneously with the target scene, thereby improving the accuracy of correcting the target scene and further improving the clarity of the target scene.

[0073] As a possible implementation method, the pole camera corrects the target scene image according to the displacement data of the camera in at least one direction, and after obtaining the corrected target scene image, it can also compress and encode the corrected target scene image to obtain a video including the target scene. Optionally, the specific implementation method of compressing and encoding the corrected target scene image to obtain the video including the target scene can refer to any existing implementation method of converting an image into a video, which will not be repeated here. After obtaining the video including the target scene, the pole camera can output the video including the target scene. Exemplarily, the pole camera can, for example, output the video including the target scene to a server, so that the server can perform video processing based on the video including the target scene.

[0074] In this implementation, by using the corrected target scene image, a video including the target scene is obtained, which improves the clarity of each frame image in the video, thereby improving the clarity of the video including the target scene.

[0075] As another possible implementation, after obtaining the above-mentioned corrected target scene image, the pole camera may, for example, perform early warning processing based on the corrected target scene image.

[0076] The following is an example in which a pole camera includes a first periscope structure, a second periscope structure, a third periscope structure, and a fourth periscope structure, and the first periscope structure and the second periscope structure constitute a first binocular field of view, and the third periscope structure and the fourth periscope structure constitute a second binocular field of view. How the pole camera obtains displacement data of the pole camera in at least one direction according to the positions of at least two beacons in the target scene image is described in detail:

[0077] For the first binocular field of view, the straight line where the first optical center of the camera and the second optical center of the camera in the first binocular field of view are located is parallel to the ground and perpendicular to the optical axis of the pole camera. The first optical center of the camera is formed by the pole camera through the first periscope structure. The second optical center of the camera is formed by the pole camera through the second periscope structure.

[0078] In this implementation, the pole camera can, for example, obtain the displacement data of the pole camera in the left-right direction according to the position of the beacon in the target scene image captured by the first binocular field of view. The left-right direction mentioned here can be a direction parallel to the ground and perpendicular to the optical axis of the pole camera.

[0079] For the second binocular field of view, the straight line where the third optical center of the camera and the fourth optical center of the camera in the second binocular field of view are located is parallel to the optical axis of the pole camera. The third optical center of the camera is formed by the pole camera through the third periscope structure. The fourth optical center of the camera is formed by the pole camera through the fourth periscope structure.

[0080] In this implementation, the pole camera can, for example, obtain the displacement data of the pole camera in the front-to-back direction according to the position of the beacon in the target scene image captured through the first binocular field of view. The front-to-back direction mentioned here can be a direction parallel to the optical axis of the pole camera.

[0081] It should be understood that the present application does not limit the order of the pole camera executing "obtaining displacement data of the pole camera in the left-right direction based on the position of the beacon in the target scene image captured by the first binocular field of view" and "obtaining displacement data of the pole camera in the front-back direction based on the position of the beacon in the target scene image captured by the first binocular field of view".

[0082] Still Figure 5 For example, the beacons photographed through the first binocular field of view may be beacon 1 and beacon 4. The beacons photographed through the second binocular field of view may be beacon 2 and beacon 3, for example.

[0083] Taking the first binocular field of view as an example, the following describes in detail how the pole camera obtains the displacement data of the pole camera in the left and right directions by capturing the position of the beacon in the target scene image through the first binocular field of view:

[0084] The pole camera can first obtain the depth of the beacon relative to the camera in the first binocular field of view by using the position of the beacon in the target scene image captured by the first binocular field of view. Then, the pole camera can obtain the displacement data of the pole camera in the left and right direction according to the depth of the beacon relative to the camera in the first binocular field of view.

[0085] For example, Figure 6 Schematic diagram of a binocular field of view algorithm. Figure 7 Figure 1 is a schematic diagram of a reverse calculation method for binocular displacement data. Figure 6 and Figure 7 As shown, Or may represent the first optical center of the camera in the first binocular field of view. Ot may represent the second optical center of the camera in the first binocular field of view. The distance between Or and Ot is B. P represents a beacon. When the camera shoots the beacon P through the first periscope structure, the imaging point on the photoreceptor of the camera may be P. When the camera shoots the beacon P through the second periscope structure, the imaging point on the photoreceptor of the camera may be P'. Because the observation positions of the first periscope structure and the second periscope structure are different, X R and X T When the first binocular field of view is disturbed by external force and generates displacement data, X R and X T will change. R and X T The change of can obtain the depth Z of the beacon relative to the camera in the first binocular field of view. Where Z=f B / (X R -X T). Wherein f is the focal length of the lens. Optionally, f is a parameter of the lens, which may be pre-stored in the pole camera. R and X T The calculation method of can refer to the existing binocular system ranging method, which will not be repeated here.

[0086] After obtaining the depth Z of the beacon relative to the camera in the first binocular field of view, Figure 7 As shown, assuming that the displacement data of the camera in the left and right direction is PPn, according to the triangle similarity principle, it can be known that: P'Pn' / PPn=f / Z. Among them, P'Pn' is the position of the beacon in the target scene image under the first binocular field of view, and the pole camera can obtain PPn, that is, the displacement data of the camera in the left and right direction, based on P'Pn'.

[0087] Optionally, the specific implementation method of the pole camera obtaining the displacement data of the pole camera in the front-to-back direction according to the position of the beacon in the target scene image captured through the first binocular field of view is similar to the method described in the above embodiment and will not be repeated here.

[0088] The following is a detailed description of how the pole camera corrects the target scene image according to the displacement data of the camera in at least one direction to obtain the corrected target scene image:

[0089] In some embodiments, when the displacement data of the camera in the front-to-back direction is not equal to zero, the pole camera can crop the target scene image according to the displacement data of the camera in the front-to-back direction to obtain the target scene image after initial correction.

[0090] For example, assuming that the pole camera determines that the camera backward displacement data is s (s is greater than zero), it means that the camera is far away from the target scene, that is, too many scene images are collected. Therefore, the pole camera can intercept and crop the target scene in the target scene image to obtain the target scene image after initial correction. Furthermore, the pole camera can also crop the target area of ​​the target scene image to remove the beacon in the target scene image to obtain the target scene image after initial correction. Assuming that the pole camera determines that the camera forward displacement data is s, it means that the camera is close to the target scene, that is, too few scene images are collected. Optionally, the pole camera can only crop the target area of ​​the target scene image to remove the beacon in the target scene image to obtain the target scene image after initial correction.

[0091] If the pole camera determines that the displacement data of the camera in the front-to-back direction is equal to zero, it means that the camera does not shake forward and backward. Therefore, optionally, the pole camera can directly use the target scene image as the target scene image after initial correction.

[0092] Then, when the displacement data of the camera in the left and right directions is not equal to zero, the pole camera can eliminate the jitter in the left and right directions of the target scene image after initial correction according to the displacement data of the camera in the left and right directions to obtain the corrected target scene image.

[0093] Exemplarily, the pole camera can output the displacement data of the camera in the left-right direction and the target scene image after initial correction to a preset image jitter elimination algorithm to eliminate the jitter of the target scene image in the left-right direction after initial correction. The image jitter elimination algorithm can refer to any existing implementation method, which will not be described in detail here.

[0094] If the pole camera determines that the displacement data of the camera in the left and right directions is equal to zero, it means that the camera does not shake left and right. Therefore, optionally, the pole camera can directly use the initial deflected target scene image as the deflected target scene image.

[0095] In some embodiments, taking the example that the beacons photographed by each periscope structure are located in the target area of ​​the target scene image, the pole camera can also crop the target scene image according to the displacement data of the camera in the front-to-back direction to obtain the target scene image after initial correction, and then cut the target area of ​​the target scene image to obtain the target scene image without the target area. Then, the pole camera can correct the target scene image without the target area to obtain the corrected target scene image.

[0096] In this implementation, the corrected target scene image includes the corrected image of the target scene, but does not include the beacon. Through this method, the pole camera can capture clear images that do not include objects other than the target scene, thereby improving the flexibility of the pole camera and the user experience.

[0097] In some embodiments, the pole camera can first eliminate the jitter of the target scene image in the left and right directions according to the displacement data of the camera in the left and right directions, and obtain the target scene image after left and right deviation correction. Then, the pole camera can crop the target scene image after left and right deviation correction according to the displacement data of the camera in the front and back directions, and obtain the target scene image after deviation correction.

[0098] Figure 8 This is a schematic diagram of the structure of an image processing device provided in this application. The device can be applied to the pole camera described in any of the above embodiments. Figure 8 As shown, the device includes: a collection module 21 and a processing module 22. Among them,

[0099] The acquisition module 21 is used to acquire a target scene image, wherein the target scene image includes: a picture of the target scene, and the beacon photographed by each periscope structure.

[0100] The processing module 22 is used to obtain the displacement data of the camera of the pole camera in at least one direction according to the position of the beacon in the target scene image photographed by each periscope structure; and to correct the target scene image according to the displacement data of the camera in at least one direction to obtain the corrected target scene image.

[0101] Optionally, taking the example that the lens of the pole camera includes: a first periscope structure, a second periscope structure, a third periscope structure, and a fourth periscope structure, the first periscope structure and the second periscope structure constitute a first binocular field of view, and the third periscope structure and the fourth periscope structure constitute a second binocular field of view, optionally, the processing module 22 is specifically used to obtain the displacement data of the pole camera in the left and right direction according to the position of the beacon in the target scene image photographed through the first binocular field of view; and obtain the displacement data of the pole camera in the front and back direction according to the position of the beacon in the target scene image photographed through the second binocular field of view.

[0102] Among them, the straight line where the first optical center of the camera and the second optical center of the camera in the first binocular field of view are located is parallel to the ground and perpendicular to the optical axis of the pole camera; the straight line where the third optical center of the camera and the fourth optical center of the camera in the second binocular field of view are located is parallel to the optical axis of the pole camera; the first optical center of the camera is formed by the pole camera through the first periscope structure, the second optical center of the camera is formed by the pole camera through the second periscope structure, the third optical center of the camera is formed by the pole camera through the third periscope structure, and the fourth optical center of the camera is formed by the pole camera through the fourth periscope structure;

[0103] Optionally, the processing module 22 is specifically used to obtain the depth of the beacon relative to the camera in the first binocular field of view according to the position of the beacon in the target scene image captured through the first binocular field of view; and obtain the displacement data of the pole camera in the left and right directions according to the depth of the beacon relative to the camera in the first binocular field of view.

[0104] Optionally, the processing module 22 is specifically used to crop the target scene image according to the displacement data of the camera in the front-to-back direction when the displacement data of the camera in the front-to-back direction is not equal to zero, so as to obtain the target scene image after initial correction; when the displacement data of the camera in the left-to-right direction is not equal to zero, eliminate the jitter in the left-to-right direction of the target scene image after initial correction according to the displacement data of the camera in the left-to-right direction, so as to obtain the target scene image after correction.

[0105] Optionally, the beacons photographed by each of the periscope structures are located in the target area of ​​the target scene image. Optionally, the processing module 22 is further used to perform beacon recognition on the target area of ​​the target scene image before acquiring the displacement data of the camera of the pole camera in at least one direction according to the position of the beacon photographed by each of the periscope structures in the target scene image, so as to obtain the position of the beacon photographed by each of the periscope structures in the target scene image.

[0106] Optionally, the processing module 22 is further configured to, after correcting the target scene image according to the displacement data of the camera in at least one direction to obtain the corrected target scene image, compress and encode the corrected target scene image to obtain a video including the target scene. Optionally, the device may also include an output module 23, configured to output the video including the target scene.

[0107] The image processing device provided in the present application is used to execute the aforementioned image processing method embodiment, and its implementation principle and technical effect are similar, which will not be described in detail.

[0108] Fig. 9 This is a schematic diagram of the structure of an electronic device provided in this application. The electronic device can be as described above. Fig. 9 As shown, the electronic device 300 may include: at least one processor 301 , a memory 302 , and a camera 304 .

[0109] The camera 304 is coupled to the processor 301 , and the processor 301 controls the camera 304 to capture images.

[0110] The memory 302 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.

[0111] The memory 302 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0112] The processor 301 is used to execute the computer-executable instructions stored in the memory 302 to implement the image processing method described in the above method embodiment. The processor 301 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0113] Optionally, the electronic device 300 may further include a communication interface 303. In a specific implementation, if the communication interface 303, the memory 302 and the processor 301 are implemented independently, the communication interface 303, the memory 302 and the processor 301 may be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0114] Optionally, in a specific implementation, if the communication interface 303, the memory 302 and the processor 301 are integrated on a chip, the communication interface 303, the memory 302 and the processor 301 can complete communication through an internal interface.

[0115] The present application also provides a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes. Specifically, the computer-readable storage medium stores program instructions, and the program instructions are used for the methods in the above embodiments.

[0116] The present application also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of the electronic device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the electronic device implements the image processing method provided by the various embodiments described above.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A pole-mounted camera, characterized in that, the pole of the pole-mounted camera is fixed on the ground, a beacon is provided on the ground, and the lens of the pole-mounted camera includes at least two periscope structures; the at least two periscope structures are used for the pole-mounted camera to capture the beacon from different angles, and the pole-mounted camera is configured to: acquire a target scene image, the target scene image including: a picture of the target scene, and the beacon captured by each of the periscope structures; obtain displacement data of the camera of the pole-mounted camera in at least one direction according to the position of the beacon captured by each of the periscope structures in the target scene image; correct the target scene image according to the displacement data of the camera in at least one direction to obtain a corrected target scene image; the lens of the pole-mounted camera includes: a first periscope structure, a second periscope structure, a third periscope structure, and a fourth periscope structure, the first periscope structure and the second periscope structure form a first binocular field of view, and the third periscope structure and the fourth periscope structure form a second binocular field of view; the straight line where the first optical center and the second optical center of the camera in the first binocular field of view are parallel to the ground and perpendicular to the optical axis of the pole-mounted camera; the straight line where the third optical center and the fourth optical center of the camera in the second binocular field of view are parallel to the optical axis of the pole-mounted camera; the first optical center of the camera is formed by the pole-mounted camera through the first periscope structure, the second optical center of the camera is formed by the pole-mounted camera through the second periscope structure, the third optical center of the camera is formed by the pole-mounted camera through the third periscope structure, and the fourth optical center of the camera is formed by the pole-mounted camera through the fourth periscope structure; the pole-mounted camera is configured to: obtain displacement data of the camera of the pole-mounted camera in the left-right direction according to the position of the beacon captured by the first binocular field of view in the target scene image; obtain displacement data of the camera of the pole-mounted camera in the front-back direction according to the position of the beacon captured by the second binocular field of view in the target scene image.

2. The pole-mounted camera according to claim 1, characterized in that, the pole-mounted camera is configured to: obtain the depth of the beacon relative to the camera in the first binocular field of view according to the position of the beacon captured by the first binocular field of view in the target scene image; obtain displacement data of the camera of the pole-mounted camera in the left-right direction according to the depth of the beacon relative to the camera in the first binocular field of view.

3. The pole-mounted camera according to claim 1, characterized in that, the pole-mounted camera is configured to: when the displacement data of the camera in the front-back direction is not equal to zero, crop the target scene image according to the displacement data of the camera in the front-back direction to obtain an initially corrected target scene image; When the displacement data of the camera in the left-right direction is not equal to zero, the jitter of the target scene image after the initial deflection correction in the left-right direction is eliminated according to the displacement data of the camera in the left-right direction to obtain the target scene image after deflection correction.

4. The pole camera according to claim 3, It is characterized in that The beacons photographed by each of the periscope structures are located in the target area of ​​the target scene image, and the pole camera is configured as follows: Before the target scene image is cropped according to the displacement data of the camera in the front-rear direction to obtain the target scene image after initial correction, the target area of ​​the target scene image is cut to obtain the target scene image without the target area.

5. The pole camera according to any one of claims 1 to 3, It is characterized in that The beacons photographed by each of the periscope structures are located in the target area of ​​the target scene image; the pole camera is configured as follows: Before obtaining the displacement data of the pole camera in at least one direction according to the position of the beacon in the target scene image photographed by each periscope structure, beacon recognition is performed on the target area of ​​the target scene image to obtain the position of the beacon in the target scene image photographed by each periscope structure.

6. The pole camera according to any one of claims 1 to 3, It is characterized in that The pole camera is configured as follows: After correcting the target scene image according to the displacement data of the camera in at least one direction to obtain the corrected target scene image, compressing and encoding the corrected target scene image to obtain a video including the target scene; The video including the target scene is output.

7. An image processing method, It is characterized in that The method is applied to the pole camera according to any one of claims 1 to 6, and the method comprises: Capturing a target scene image, the target scene image comprising: a picture of the target scene, and a beacon photographed by each periscope structure of the lens of the pole camera; the beacon is set on the ground to which the pole camera is fixed; Acquire displacement data of the camera of the pole camera in at least one direction according to the position of the beacon in the target scene image; The target scene image is deflected according to the displacement data of the camera in at least one direction to obtain a deflected target scene image.

8. An image processing device, It is characterized in that The device is applied to the pole camera according to any one of claims 1 to 6, and the device comprises: A collection module, used for collecting a target scene image, wherein the target scene image includes: a picture of the target scene, and a beacon photographed by each periscope structure of the lens of the pole camera; the beacon is set on the ground where the pole camera is fixed; A processing module is used to obtain the displacement data of the camera of the pole camera in at least one direction according to the position of the beacon in the target scene image; and to correct the target scene image according to the displacement data of the camera in at least one direction to obtain the corrected target scene image.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to claim 7 when executed by a processor.

Images