Method, device, electronic equipment and medium for determining pan / tilt zero point

Abstract

The embodiments of the present application disclose a method, device, electronic device and medium for determining the zero point of a pan-tilt head. The method is executed by a pan-tilt head binocular camera, which includes a fixed-point camera and a moving-point camera. The moving-point camera is driven by the pan-tilt head to rotate in the horizontal or vertical direction. The method includes: controlling the moving-point camera to rotate to the first side in a preset direction, and collecting a first moving-point image in real time; performing image matching on a first moving-point area image in the first moving-point image collected in real time, and a first fixed-point area image in the first fixed-point image collected by the fixed-point camera; if the first moving-point area image and the first fixed-point area image are successfully matched, the current position of the pan-tilt head is used as the zero point of the pan-tilt head in the preset direction. The above scheme avoids the problem of damaging the equipment by using the moving-point camera to self-check collision to determine the zero point, and increasing the cost by using auxiliary devices to determine the zero point, thereby conveniently and efficiently determining the zero point of the pan-tilt head through image comparison.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of pan-tilt calibration technology, and in particular to a pan-tilt zero point determination method, device, electronic device, and medium. Background Art

[0002] A pan / tilt (PTZ) is a support device used to mount and secure cameras. It comes in two types: fixed and motorized. Fixed PTZs are suitable for smaller surveillance areas. After mounting the camera, the horizontal and pitch angles can be adjusted. Once the optimal working position is achieved, the adjustment mechanism is simply locked. Motorized PTZs are suitable for scanning and monitoring large areas, expanding the camera's range. High-speed positioning is achieved by two actuator motors, which receive signals from a controller for precise positioning. Controlled by these signals, the camera can automatically scan the surveillance area or track the subject under the control of a monitoring center staff member.

[0003] Existing PTZ cameras often use a power-on self-test, such as hitting a wall, or optocouplers to determine their zero position. The camera then rotates a fixed angle based on this zero position to achieve cruise control. Using a power-on self-test to determine the zero position often requires multiple wall hits, which reduces the PTZ structure and motor life. Using optocouplers to determine the zero position also increases costs. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, electronic device, and medium for determining the zero point of a gimbal, so as to conveniently and accurately determine the zero point of the gimbal.

[0005] In one embodiment, the present application provides a method for determining a pan-tilt zero point, which is performed by a pan-tilt binocular camera. The pan-tilt binocular camera includes a fixed-point camera and a moving-point camera. The moving-point camera is driven by the pan-tilt to rotate horizontally or vertically. The method includes:

[0006] In a preset direction, controlling the moving-point camera to rotate toward a first side and capturing a first moving-point image in real time;

[0007] Performing image matching on a first moving point region image in a first moving point image captured in real time and a first fixed point region image in a first fixed point image captured by a fixed point camera;

[0008] If the first moving point area image and the first fixed point area image are matched successfully, the current position point of the pan / tilt platform is used as the zero point of the pan / tilt platform in the preset direction.

[0009] In another embodiment, the present application also provides a device for determining a pan / tilt zero point, the device comprising:

[0010] A first moving-point image acquisition module, configured to control the moving-point camera to rotate toward a first side in a preset direction, and acquire a first moving-point image captured by the moving-point camera in real time;

[0011] a matching module for performing image matching between a first moving-point region image in a first moving-point image acquired in real time and a first fixed-point region image in a first fixed-point image acquired by a fixed-point camera;

[0012] The zero point determination module is used to use the current position of the pan / tilt platform as the zero point of the pan / tilt platform in a preset direction if the first moving point area image and the first fixed point area image are successfully matched.

[0013] In yet another embodiment, an embodiment of the present application further provides an electronic device, including: one or more processors;

[0014] a memory for storing one or more programs;

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the gimbal zero point determination method described in any one of the embodiments of the present application.

[0016] In one embodiment, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the gimbal zero point determination method as described in any one of the embodiments of the present application.

[0017] In an embodiment of the present application, in a preset direction, the moving point camera is controlled to rotate toward the first side and a first moving point image is captured in real time; the first moving point area image in the first moving point image captured in real time is matched with the first fixed point area image in the first fixed point image captured by the fixed point camera; if the first moving point area image and the first fixed point area image are matched successfully, the current position of the pan-tilt head is used as the zero point of the pan-tilt head in the preset direction. The above scheme avoids the pan-tilt head from hitting the wall multiple times during the zero point determination process, which affects the life of the pan-tilt head mechanism and the motor, and avoids increasing the cost during the auxiliary period, thereby determining the pan-tilt head zero point through the comparison result between the first moving point image captured in real time by the moving point camera and the first fixed point image captured by the fixed point camera, and accurately determining the pan-tilt head zero point in a convenient manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a method for determining the zero point of a pan / tilt platform provided in one embodiment of the present application;

[0019] Figure 2 A schematic diagram of a regional image provided in one embodiment of the present application;

[0020] Figure 3A flowchart of a method for determining a pan / tilt zero point provided in another embodiment of the present application;

[0021] Figure 4 A schematic diagram of angle relationships provided for another embodiment of the present application;

[0022] Figure 5 A flowchart of a method for determining a pan / tilt zero point according to another embodiment of the present application;

[0023] Figure 6 A schematic diagram of angle relationships provided in yet another embodiment of the present application;

[0024] Figure 7 A flowchart of a method for determining a pan / tilt zero point provided in yet another embodiment of the present application;

[0025] Figure 8 A flowchart of a specific implementation of a method for determining a pan / tilt zero point provided in one embodiment of the present application;

[0026] Figure 9 A flowchart of a pre-processing process provided for one embodiment of the present application;

[0027] Figure 10 A schematic diagram of the rotation direction provided by an embodiment of the present application;

[0028] Figure 11 A schematic diagram of determining the field of view angle provided in one embodiment of the present application;

[0029] Figure 12 A schematic diagram of the structure of a pan / tilt zero point determination device provided in one embodiment of the present application;

[0030] Figure 13 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0031] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the present application and are not intended to limit the present application. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions of the present application, not all of the structures. DETAILED DESCRIPTION

[0032] Figure 1This is a flow chart of a pan-tilt zero point determination method provided in an embodiment of the present application. The pan-tilt zero point determination method provided in the embodiment of the present application can be applied to situations where the pan-tilt zero point is determined. Typically, the embodiment of the present application is applicable to situations where the zero point of the pan-tilt that drives the moving point camera to rotate is determined for a pan-tilt binocular camera. The method can be specifically executed by a pan-tilt zero point determination device, which can be implemented in software and / or hardware, and the device can be integrated in an electronic device that can implement the pan-tilt zero point determination method. The method of the embodiment of the present application is executed by a pan-tilt binocular camera, and the pan-tilt binocular camera includes a fixed-point camera and a moving-point camera, and the moving-point camera is driven by the pan-tilt to rotate horizontally or vertically, the pan-tilt that drives the moving point camera can be an electric pan-tilt, and the pan-tilt that drives the fixed-point camera to capture images at a fixed angle can be a fixed pan-tilt. The fixed pan-tilt is suitable for situations where the monitoring range is not large. After the fixed-point camera is installed on the fixed pan-tilt, the horizontal and pitch angles of the camera can be adjusted, and the adjustment mechanism can be locked after the best working posture is achieved. See. Figure 1 , the method may include:

[0033] S110 . Control the moving-point camera to rotate toward a first side in a preset direction, and capture a first moving-point image in real time.

[0034] Among them, the preset direction can be a pre-set direction, such as the horizontal direction or the vertical direction. The pan-tilt head can control the moving point camera to rotate in the horizontal direction, and can also control the moving point camera to rotate in the vertical direction. Therefore, it is necessary to determine the zero point of the pan-tilt head in the horizontal direction, and also to determine the zero point of the moving point camera in the vertical direction. The horizontal direction can be used as the preset direction first, and the solution in the embodiment of the present application can be executed to determine the zero point in the horizontal direction. Then, the vertical direction can be used as the preset direction, and the solution in the embodiment of the present application can be executed to determine the zero point in the vertical direction. For determining the zero point in the horizontal direction and determining the zero point in the vertical direction, the zero point determination method in the embodiment of the present application is applicable.

[0035] The first side may be any side of the moving camera in the preset direction. For example, when the preset direction is horizontal, the first side may be the left side of the moving camera in a top-down perspective, or the right side of the moving camera in a top-down perspective. When the preset direction is vertical, the first side may be the upper side of the moving camera in a left-angle perspective, or the lower side of the moving camera in a left-angle perspective.

[0036] In an embodiment of the present application, when the fixed-point camera is stationary, the moving-point camera is controlled to rotate to one side in a preset direction, and the moving-point camera collects images in real time during the rotation process as the first moving-point image.

[0037] S120 : performing image matching between a first moving-point region image in a first moving-point image acquired in real time and a first fixed-point region image in a first fixed-point image acquired by a fixed-point camera.

[0038] In the embodiment of the present application, the first moving point region image may be an image of a certain region in the first moving point image selected according to actual conditions. The first fixed point region image may be an image of a certain region in the first fixed point image selected according to actual conditions. The first fixed point region may be an edge image in the first fixed point image, for example Figure 2 The region images 1 and 6 in the first fixed-point image may also be the middle region images in the first fixed-point image, such as region image 2. The first moving-point region image may be an edge image in the first moving-point image, such as region image 3 or region image 5, or an image in the middle region in the first moving-point image, such as region image 4.

[0039] In the embodiment of the present application, image matching includes but is not limited to matching of features such as brightness, content, features, structure, relationship, texture and grayscale.

[0040] S130: If the first moving-point area image and the first fixed-point area image are successfully matched, the current position of the pan / tilt platform is used as the zero point of the pan / tilt platform in a preset direction.

[0041] Exemplarily, if the first moving-point area image and the first fixed-point area image are successfully matched, it is determined that the viewing angle range of the moving-point camera is within the viewing angle range of the fixed-point camera, and the current position of the pan-tilt head is used as the zero point of the pan-tilt head in the preset direction. Since the position of the first moving-point area image and the position of the first fixed-point area image are known, it is also possible to determine the position of the current position of the pan-tilt head relative to the field of view of the fixed-point camera based on the position of the first moving-point area image and the position of the first fixed-point area image, and the current position of the pan-tilt head can be used as the zero point of the pan-tilt head. After determining the zero point of the pan-tilt head, it can be used as a reference to control the pan-tilt head to rotate a fixed angle in a specified direction to capture images of the object to be photographed.

[0042] In an embodiment of the present application, in a preset direction, the moving point camera is controlled to rotate toward the first side and a first moving point image is captured in real time; the first moving point area image in the first moving point image captured in real time is matched with the first fixed point area image in the first fixed point image captured by the fixed point camera; if the first moving point area image and the first fixed point area image are matched successfully, the current position of the pan-tilt head is used as the zero point of the pan-tilt head in the preset direction. The above scheme avoids the pan-tilt head from hitting the wall multiple times during the zero point determination process, which affects the life of the pan-tilt head mechanism and the motor, and avoids increasing the cost during the auxiliary period, thereby determining the pan-tilt head zero point through the comparison result between the first moving point image captured in real time by the moving point camera and the first fixed point image captured by the fixed point camera, and accurately determining the pan-tilt head zero point in a convenient manner.

[0043] In the embodiment of the present application, to determine the zero point of the gimbal in the horizontal direction and the zero point in the vertical direction, the preset direction can be first set to the horizontal direction, and the steps in the embodiment of the present application can be performed, and then the preset direction can be set to the vertical direction and the steps in the embodiment of the present application can be performed. Alternatively, the preset direction can be first set to the vertical direction, and the steps in the embodiment of the present application can be performed, and then the preset direction can be set to the horizontal direction and the steps in the embodiment of the present application can be performed to determine the zero point of the gimbal in the horizontal direction and the zero point in the vertical direction.

[0044] Figure 3 This is a flow chart of a method for determining the zero point of a pan / tilt platform provided in another embodiment of the present application. This embodiment of the present application is a further optimization of the above embodiment. For details not described in detail in this embodiment of the present application, please refer to the above embodiment. Figure 3 The method for determining the zero point of the pan / tilt platform provided in the embodiment of the present application may include:

[0045] S210 . Control the moving-point camera to rotate toward a first side in a preset direction, and capture a first moving-point image in real time.

[0046] S220: Perform image matching between a first moving-point region image in a first moving-point image acquired in real time and a first fixed-point region image in a first fixed-point image acquired by a fixed-point camera.

[0047] S230. If the first moving-point area image and the first fixed-point area image are successfully matched, the moving-point camera is controlled to rotate to the second side by a first preset angle and a second moving-point image is captured; wherein the first preset angle is determined according to the field of view angle of the fixed-point camera in a preset direction, and the second side is in the preset direction and opposite to the direction of the first side.

[0048] In an embodiment of the present application, if the first moving-point area image and the first fixed-point area image are successfully matched, a calibration process is required. Specifically, the moving-point camera is controlled to rotate to the second side by a first preset angle, that is, to the other side of the moving-point camera by the first preset angle, and a second moving-point image captured in real time by the moving-point camera is obtained. The first preset angle is determined based on the field of view of the fixed-point camera in a preset direction, that is, to ensure that when the moving-point camera rotates by the first preset angle, the field of view range is still within the field of view range of the fixed-point camera.

[0049] S240: Perform image matching on the second moving-point region image in the second moving-point image and the second fixed-point region image in the first fixed-point image.

[0050] Because the first preset angle is determined based on actual conditions, the image of the region in the first fixed-point image corresponding to the field of view of the moving-point camera when the moving-point camera is rotated by the first preset angle is also known. Therefore, the image of the region in the first fixed-point image corresponding to the field of view of the moving-point camera when the moving-point camera is rotated by the first preset angle is used as the second fixed-point region image. After the moving-point camera is controlled to rotate toward the second side by the first preset angle, the second moving-point region image in the second moving-point image captured by the moving-point camera is matched with the second fixed-point region image. The second moving-point region image can be an image of any region in the second moving-point image.

[0051] S250: If the second moving-point region image and the second fixed-point region image are successfully matched, it is determined that the zero point of the pan / tilt head is accurate.

[0052] For example, if the second moving point area image and the second fixed point area image match successfully, it is determined that the position of the pan-tilt head zero point is accurately determined, the actual angle of rotation of the moving point camera controlled according to the zero point is the same as the theoretical angle, and the position actually reached by the moving point camera is the position it should reach theoretically. At this time, it is determined that the zero point of the pan-tilt head determined previously is accurate, and the calibration of the pan-tilt head position is achieved.

[0053] The solution of the embodiment of the present application realizes the calibration of the pan-tilt zero point by controlling the moving point camera to rotate in the opposite direction after determining the pan-tilt zero point, further improving the accuracy of the pan-tilt zero point determination and avoiding the influence of randomness in the zero point determination process on the accuracy of the zero point.

[0054] In an embodiment of the present application, the method also includes: if the second moving point area image and the second fixed point area image are not successfully matched, then based on the current position of the moving point camera, re-execute the step of controlling the moving point camera to rotate toward the first side, and perform image matching on the first moving point area image and the first fixed point area image to determine the pan-tilt zero point.

[0055] In an embodiment of the present application, the first moving-point area image is an edge image corresponding to the first side in the first moving-point image; the first fixed-point area image is an edge image corresponding to the first side in the first fixed-point image; the second moving-point image is an edge image corresponding to the second side in the second moving-point image; and the second fixed-point area image is an edge image corresponding to the second side in the first fixed-point image.

[0056] For example, in order to facilitate the determination and calculation of the zero point, the zero point is determined to be a position close to the edge within the field of view of the fixed-point camera. Specifically, assuming that the preset direction is the horizontal direction, the first side is Figure 2 The side corresponding to the middle area image 1 is the left side of the moving point camera. The first fixed point area image is Figure 2 The first moving point area image is area image 1, the second fixed point area image is area image 6, and the third moving point area image is area image 5. The solution of the embodiment of the present application is to control the moving point camera to rotate to the first side first, until the first moving point area image matches the first fixed point area image, and the moving point camera rotates to the leftmost end of the field of view of the fixed point camera. The field of view of the moving point camera is located at the leftmost end of the field of view of the fixed point camera, as shown in FIG. Figure 4 As shown, α1 is the field of view angle of the fixed-point camera, and α2 is the field of view angle of the moving-point camera. At this time, the current position of the moving-point camera, that is, the position corresponding to the bisector of the field of view angle of the moving-point camera, serves as the zero point of the pan-tilt head in the preset direction. Then control the moving-point camera to rotate to the right by the first preset angle. In this case, the first preset angle is α1-α2, so that the moving-point camera rotates to the rightmost end of the field of view range of the fixed-point camera. At this time, the second moving-point area image is matched with the second fixed-point area image. If the match is successful, it is determined that the previously determined pan-tilt head zero point is accurate. The same is true for the case where the first side is the side corresponding to the area image 6, and the same is true for the case where the preset direction is the vertical direction.

[0057] The beneficial effect of the above scheme is that it can conveniently determine the first preset angle based on the field of view angle of the fixed-point camera and the field of view angle of the moving-point camera, and then after controlling the moving-point camera to rotate to one end of the field of view range of the fixed-point camera, reverse to the other end to achieve accurate verification of the pan-tilt zero point.

[0058] Figure 5 This is a flow chart of a method for determining the zero point of a pan / tilt platform provided in another embodiment of the present application. This embodiment of the present application is a further optimization of the above embodiment. For details not described in detail in the embodiment of the present application, please refer to the above embodiment. Figure 5 The method for determining the zero point of the pan / tilt platform provided in the embodiment of the present application may include:

[0059] S310: Control the moving-point camera to rotate toward a first side in a preset direction, and capture a first moving-point image in real time.

[0060] S320. Determine whether the first moving-point area image in the first moving-point image captured in real time matches the first fixed-point area image in the first fixed-point image captured by the fixed-point camera. If the match is successful, execute S350; if the match is not successful, execute S330.

[0061] S330: Determine whether the angle of rotation of the moving-point camera toward the first side reaches a second preset angle; if so, execute S340; if not, execute S310.

[0062] S340: Control the moving-point camera to rotate toward the second side by a third preset angle, and execute S310-S320.

[0063] Among them, the second preset angle is determined according to the angle between the limit line when the pan-tilt head rotates to the second side and the edge of the field of view angle of the fixed camera on the first side; the third preset angle is determined according to the angle between the limit line when the pan-tilt head rotates to the first side and the edge of the field of view angle of the fixed camera on the first side.

[0064] For example, Figure 6 As shown, assuming that the moving point camera is located at Figure 6 The center of the circle in the image, the direction of the first side is counterclockwise, limit line 1 is the maximum range that the field of view of the moving point camera can reach when it rotates counterclockwise, and limit line 2 is the maximum range that the field of view of the moving point camera can reach when it rotates clockwise. If the field of view of the current moving point camera is within the range of α4 and is not within the field of view of the fixed-point camera, then when the moving point camera is controlled to rotate to the first side, no matter how many degrees it is rotated, an image that matches the first fixed-point image cannot be captured. The first moving point area image and the first fixed-point area image in the first fixed-point image captured in real time by the moving point camera do not match. At this time, the shooting angle of the moving point camera needs to be adjusted so that its field of view is within the field of view of the fixed-point camera. Since the field of view of the moving point camera is within the range of α4, the moving point camera can be adjusted according to Figure 6The clockwise rotation is greater than or equal to α4, and the third preset angle is an angle greater than or equal to α4, so that the field of view of the moving point camera is within the field of view of the fixed point camera, and then S310-S320 are re-executed. For example, if the maximum field of view of the moving point camera reaches the position of the limit line 2 within the range of α5, then the angle required to rotate the moving point camera to the first side so that the field of view of the moving point camera is located at the leftmost side of the fixed point field of view is the largest, and the maximum angle is set to the second preset angle. If the angle of the moving point camera to be rotated to the first side reaches the second preset angle, and there is no match between the first moving point area image and the first fixed point area image, then it is determined that the field of view of the moving point camera is within the range of α4. The second preset angle can be determined based on the angle between the limit line when the pan / tilt head rotates to the second side and the edge of the field of view angle of the fixed point camera on the first side, that is, Figure 6 α1+α5 in. In an embodiment of the present application, in a preset direction, while controlling the moving-point camera to rotate toward the first side, a first moving-point image is captured in real time, and it is determined whether the first moving-point region image in the first moving-point image matches the first fixed-point region image in the first fixed-point image. If they do not match, it is determined whether the angle of rotation of the moving-point camera toward the first side has reached a second preset angle, that is, whether it has reached the limit line. If the angle of rotation of the moving-point camera toward the first side has not reached the second preset angle, the moving-point camera is continued to be controlled to rotate toward the first side, and it is determined whether the first moving-point region image in the first moving-point image captured in real time matches the first fixed-point region image in the first fixed-point image. In addition, if they do not match, it is determined whether the angle of rotation of the moving-point camera toward the first side has reached the second preset angle. Similarly, the case where the first side is clockwise can be deduced in the opposite direction of the above process.

[0065] S350: If the first moving-point area image and the first fixed-point area image are successfully matched, the current position of the pan / tilt platform is used as the zero point of the pan / tilt platform in a preset direction.

[0066] In the technical solution of the embodiment of the present application, if the angle of the moving-point camera controlled to rotate to the first side reaches a second preset angle, the moving-point camera is controlled to rotate to the second side by a third preset angle, thereby avoiding the situation where the field of view of the moving-point camera is outside the field of view of the fixed-point camera, and when it cannot enter the field of view of the fixed-point camera when rotating to the first side, it is difficult to match the first fixed-point area image with the first moving-point area image to determine the pan-tilt zero point, so that the moving-point camera is controlled to rotate in the opposite direction so that the field of view of the moving-point camera is within the field of view of the fixed-point camera, and then the zero point determination step is re-executed to determine the pan-tilt zero point.

[0067] Figure 7This is a flow chart of a method for determining the zero point of a pan / tilt platform provided in another embodiment of the present application. This embodiment of the present application is a further optimization of the above embodiment. For details not described in detail in the embodiment of the present application, please refer to the above embodiment. Figure 7 The method for determining the zero point of the pan / tilt platform provided in the embodiment of the present application may include:

[0068] S410: Acquire a second fixed-point image captured by a fixed-point camera and a third moving-point image captured by a moving-point camera.

[0069] In the event of a sudden power outage or restart of the device, the relative position of the moving-point camera and the fixed-point camera is unpredictable, and the field of view of the moving-point camera is not necessarily within the field of view of the fixed-point camera. At this time, if the moving-point camera is directly controlled to rotate, it may cause the moving-point camera to hit the wall multiple times and be unable to rotate into the field of view of the fixed-point camera, thus falling into an infinite loop. In an embodiment of the present application, after the device is powered on, it is first determined whether a preprocessing process needs to be performed on the moving-point camera based on the image matching results. When the moving-point camera does not rotate, a third moving-point image captured by the moving-point camera and a second fixed-point image captured by the fixed-point camera are obtained.

[0070] S420: If there is a matching image area between the third moving-point image and the second fixed-point image, then the current position of the moving-point camera is not adjusted.

[0071] If there is a matching image area between the third moving-point image and the second fixed-point image, it is determined that the moving-point camera is within the field of view of the fixed-point camera, and the current position of the moving-point camera is not adjusted, and the moving-point camera is not preprocessed.

[0072] S430: If there is no matching image area between the third moving-point image and the second fixed-point image, adjust the current position of the moving-point camera so that the field of view of the moving-point camera is within the field of view of the fixed-point camera.

[0073] For example, if there is no matching image area between the third moving-point image and the second fixed-point image, it is determined that the field of view of the moving-point camera is no longer within the field of view of the fixed-point camera. Therefore, the position of the moving-point camera needs to be adjusted so that the field of view of the moving-point camera is within the field of view of the fixed-point camera, so as to facilitate the subsequent control of the moving-point camera to rotate and determine the pan-tilt zero point.

[0074] In an embodiment of the present application, the current position of the moving-point camera is adjusted so that the field of view of the moving-point camera is within the field of view of the fixed-point camera, including: controlling the moving-point camera to rotate to the first side by a fourth preset angle, determining whether a fourth moving-point image captured by the moving-point camera at the current position and the second fixed-point image have a matching image area; if so, determining that the field of view of the moving-point camera is within the field of view of the fixed-point camera; if not, controlling the moving-point camera to rotate to the second side by a fourth preset angle.

[0075] The fourth preset angle is determined based on the angle between the limit line when the moving point camera rotates to the first side and the edge of the field of view of the fixed point camera on the first side, or based on the angle between the limit line when the moving point camera rotates to the second side and the edge of the field of view of the fixed point camera on the second side. Figure 6 As shown, if you turn to the first side Figure 6 If the moving-point camera rotates counterclockwise, the fourth preset angle is a value greater than or equal to α4, or a value greater than or equal to α5. If α4 and α5 are inconsistent, the larger value is selected as the fourth preset angle. For example, if the field of view of the moving-point camera is not within the field of view of the fixed-point camera, it means that the field of view of the moving-point camera should be within the range of α4 or α5. Therefore, the moving-point camera is controlled to rotate by a fourth preset angle greater than or equal to α4, or greater than or equal to α5, so that the field of view of the moving-point camera is rotated within the field of view of the fixed-point camera. Furthermore, since the specific position of the moving-point camera is uncertain, it is impossible to know which direction the moving-point camera should be controlled to rotate so that the field of view of the moving-point camera is rotated within the field of view of the fixed-point camera. Therefore, the moving-point camera is first tentatively controlled to rotate the fourth preset angle to the first side. If the fourth moving-point image captured by the moving-point camera at the current position has an image area matching the second fixed-point image, it is determined that the field of view of the moving-point camera has rotated within the field of view of the fixed-point camera. If the fourth moving point image captured by the moving point camera at the current position does not have a matching image area with the second fixed point image, the moving point camera is controlled to rotate to the second side by a fourth preset angle. Figure 6 As shown, assuming that the rotation to the first side is Figure 6Rotate counterclockwise along the middle, if the field of view of the moving-point camera is within the range of α5, then after controlling the moving-point camera to rotate to the first side by the fourth preset angle, since the fourth preset angle is an angle greater than or equal to the larger value of α4 and α5, it should be possible to rotate the field of view of the moving-point camera to within the field of view of the fixed-point camera. Therefore, if the fourth moving-point image captured by the moving-point camera at the current position has a matching image area with the second fixed-point image, then it is determined that the field of view of the initial moving-point camera is within the range of α5, and after controlling the moving-point camera to rotate to the first side by the fourth preset angle, the field of view of the moving-point camera is rotated to within the field of view of the fixed-point camera. If the fourth moving-point image captured by the moving-point camera at the current position does not have a matching image area with the second fixed-point image, it is determined that the field of view of the moving-point camera is within the range of α4. In this case, controlling the moving-point camera to rotate toward the first side will inevitably fail to rotate the field of view of the moving-point camera to within the field of view of the fixed-point camera. At this time, the moving-point camera is controlled to rotate toward the second side by a fourth preset angle, that is, to rotate the fourth preset angle in the opposite direction, so that the field of view of the moving-point camera is rotated to within the field of view of the fixed-point camera.

[0076] In the embodiment of the present application, if the fourth preset angle is greater than the field of view of the fixed-point camera, the rotation angle may be too large, and the field of view of the moving-point camera may still not be able to rotate within the field of view of the fixed-point camera. Therefore, the rotation angle can be adjusted gradually. If the fourth preset angle is greater than the field of view of the fixed-point camera, the moving-point camera is first controlled to rotate to the field of view of the fixed-point camera, and then a determination is made as to whether a matching image area exists between the fourth moving-point image captured by the moving-point camera at the current position and the second fixed-point image. If not, the moving-point camera is continuously controlled to rotate to the same side until it reaches the fourth preset angle.

[0077] S440: Control the moving-point camera to rotate toward a first side in a preset direction, and capture a first moving-point image in real time.

[0078] S450: Perform image matching on a first moving-point region image in a first moving-point image acquired in real time and a first fixed-point region image in a first fixed-point image acquired by a fixed-point camera.

[0079] S460: If the first moving-point area image and the first fixed-point area image are successfully matched, the current position of the pan / tilt platform is used as the zero point of the pan / tilt platform in a preset direction.

[0080] The technical solution of the embodiment of the present application does not control the moving point camera to rotate to the first side to determine the zero point after the device is powered on. Instead, it determines whether the moving point image needs to be pre-processed based on the current image matching results. If pre-processing is required, the moving point camera is then tentatively rotated. After determining that the field of view of the moving point camera is within the field of view of the fixed point camera based on the image matching results after rotation, the zero point determination step is then performed. This avoids the situation where the field of view of the moving point camera is not within the field of view of the fixed point camera, where the control of the moving point camera rotation cannot quickly and accurately determine the pan / tilt zero point, or where the camera repeatedly hits the wall and falls into an infinite loop.

[0081] The embodiment of the present application is a specific implementation of the above embodiment. Figure 8 This is a flowchart of a specific implementation of the method for determining the zero point of a pan / tilt platform provided in one embodiment of the present application, as shown in FIG. Figure 8 As shown, the details are as follows:

[0082] When the device suddenly loses power, the relative position of the field of view of the device's moving point camera and fixed point camera cannot be guaranteed. To solve this problem, a preprocessing action is required before starting the zero point determination logic. The preprocessing process is as follows: Figure 9 As shown. After the device is powered on and the fixed-point camera and the moving-point camera capture images normally, the main control chip first determines whether the captured moving-point image has a matching area with the fixed-point image. If so, no preprocessing is required, which also means that the field of view of the moving-point camera is within the field of view of the fixed-point camera. If not, the moving-point camera is controlled to move to the same area as the fixed-point camera. Figure 6 Rotate the camera counterclockwise by an angle of α4 and then compare the images. If there are matching areas between the moving-point image and the fixed-point image, it indicates that the moving-point camera's field of view has been rotated to within the fixed-point camera's field of view before rotation. If there are no matching areas, it indicates that the moving-point camera's field of view was within the range of α4 before rotation, and the device needs to be rotated clockwise by an angle of α4 to complete preprocessing. Preprocessing in the vertical direction can be performed in the same way.

[0083] Entering the logic of zero point determination, when the device is powered on and the fixed-point camera and the moving-point camera pick up images normally, the main control chip records the features of the image edge area 1 and the image edge area 2 of the fixed-point image captured at this time, such as Figure 10As shown, the moving point camera is controlled to rotate in direction 1. After the rotation action is started, the main control chip begins to determine whether the edge area features of the moving point image can match the features of the edge area 1 of the fixed point image. If so, the reference point 1 is recorded and rotated in the opposite direction, that is, direction 2, by a fixed angle γ (γ is determined according to the field of view of the fixed point camera, for example, it can be α1-α2, where α1 is the field of view of the fixed point camera and α2 is the field of view of the moving point camera). At this time, the moving point camera collects the moving point image and determines whether the edge area features of the moving point image collected at this time can successfully match the edge area 2 of the fixed point image. Angle verification is performed as a standard. If the verification is successful, it means that the reference point 1 is the accurate zero point. If the match is unsuccessful, the zero point determination logic is restarted.

[0084] If the device is powered on and the fixed-point camera and the moving-point camera capture images normally, the main control chip records the features of the image edge area 1 and image edge area 2 of the fixed-point image captured at this time and controls the moving-point camera to rotate in direction 1. After starting this rotation, the main control chip determines that the edge area features of the moving-point image and the features of edge area 1 of the fixed-point image still do not match, and the angle of rotation of the moving-point camera has reached α5 + α1, then the main control chip needs to drive the moving-point camera to rotate in the opposite direction, that is, direction 2, by β degrees (β is a value greater than or equal to α4 and greater than or equal to α5), so that the field of view of the moving-point camera rotates within the field of view of the fixed-point camera, and restart the zero point detection logic. The method for obtaining the vertical zero point can be obtained in the same way.

[0085] In the embodiment of the present application, the process of determining the field of view angle of the moving point camera or the fixed point camera in the preset direction can be as follows: Figure 11 As shown, the horizontal or vertical field of view angle of the moving or fixed-point camera is determined by taking a section formed by extending the three-dimensional model of the field of view range of the moving or fixed-point camera and the edge line of the sensor target surface.

[0086] In the embodiment of the present application, after determining the zero point of the pan / tilt, it is also necessary to determine the angle between the zero point and the limit line, so as to determine how much the moving point camera needs to rotate from the zero point to reach the limit line for quantitative control. Figure 6 As shown in the figure, the angle covered by the counterclockwise rotation from the PTZ zero point to the moving point camera at limit line 1 is 180 + (α2 - α1 - α3) / 2, and the angle covered by the clockwise rotation from the PTZ zero point to the moving point camera at limit line 2 is 180 + (α1 - α2 - α3) / 2. Therefore, the angle covered by the moving point camera can be controlled to not exceed 180 + (α2 - α1 - α3) / 2 when the PTZ zero point rotates counterclockwise to the moving point camera at limit line 1, and not exceed 180 + (α1 - α2 - α3) / 2 when the PTZ zero point rotates clockwise to the moving point camera at limit line 2, to avoid collision with the wall.

[0087] The solution provided in the embodiment of the present application has the same beneficial effects as the above embodiment.

[0088] Figure 12 This is a schematic diagram of the structure of a device for determining the zero point of a pan-tilt platform provided by an embodiment of the present application. The device can be applied to situations where the zero point of a pan-tilt platform is determined. Typically, the embodiment of the present application is applicable to situations where the zero point of a pan-tilt platform that drives a moving point camera to rotate is determined for a pan-tilt platform binocular camera. The device can be implemented by software and / or hardware, and the device can be integrated into an electronic device. Figure 12 , the device specifically includes:

[0089] A first moving-point image acquisition module 510 is configured to control the moving-point camera to rotate toward a first side in a preset direction and acquire a first moving-point image captured by the moving-point camera in real time;

[0090] a matching module 520 for performing image matching between a first moving-point region image in a first moving-point image acquired in real time and a first fixed-point region image in a first fixed-point image acquired by a fixed-point camera;

[0091] The zero point determination module 530 is configured to use the current position of the pan / tilt platform as the zero point of the pan / tilt platform in a preset direction if the first moving point area image and the first fixed point area image are successfully matched.

[0092] In the embodiment of the present application, the zero point determination module 530 includes:

[0093] The second moving-point image acquisition unit is used to control the moving-point camera to rotate to the second side by a first preset angle if the first moving-point area image and the first fixed-point area image are successfully matched, and to capture the second moving-point image in real time; wherein the first preset angle is determined according to the field of view angle of the fixed-point camera in a preset direction, and the second side is in the preset direction and opposite to the direction of the first side.

[0094] An image matching unit is used to perform image matching on a second moving-point region image in the second moving-point image and a second fixed-point region image in the first fixed-point image.

[0095] The zero point correction unit is used to determine whether the zero point of the pan / tilt head is accurate if the second moving point area image and the second fixed point area image are matched successfully.

[0096] In an embodiment of the present application, the first moving-point area image is an edge image corresponding to the first side in the first moving-point image; the first fixed-point area image is an edge image corresponding to the first side in the first fixed-point image; the second moving-point image is an edge image corresponding to the second side in the second moving-point image; and the second fixed-point area image is an edge image corresponding to the second side in the first fixed-point image.

[0097] In an embodiment of the present application, the device further includes:

[0098] The restart module is used to re-execute the step of controlling the moving point camera to rotate toward the first side and performing image matching on the first moving point area image and the first fixed point area image to determine the pan-tilt zero point if the second moving point area image and the second fixed point area image are not matched successfully based on the current position of the moving point camera.

[0099] In an embodiment of the present application, the device further includes:

[0100] The rotation test module is used to determine whether the angle of rotation of the moving-point camera to the first side reaches a second preset angle if the first moving-point area image and the first fixed-point area image are not successfully matched.

[0101] The rotation control module is configured to control the moving point camera to rotate toward the second side by a third preset angle if yes.

[0102] The re-execution module is used to re-execute the steps of controlling the moving point camera to rotate toward the first side and performing image matching on the first moving point area image and the first fixed point area image to determine the pan / tilt zero point.

[0103] The continue rotation control module is used to continue to control the camera to rotate toward the first side, and to collect the first moving point image in real time, and to determine whether the angle of rotation of the moving point camera toward the first side reaches the second preset angle if the first moving point area image and the first fixed point area image are not successfully matched.

[0104] Among them, the second preset angle is determined according to the angle between the limit line when the pan-tilt head rotates to the second side and the edge of the field of view angle of the fixed camera on the first side; the third preset angle is determined according to the angle between the limit line when the pan-tilt head rotates to the first side and the edge of the field of view angle of the fixed camera on the first side.

[0105] In an embodiment of the present application, the device further includes:

[0106] The image acquisition module is used to acquire a second fixed-point image captured by a fixed-point camera and a third moving-point image captured by a moving-point camera.

[0107] The position maintaining control module is configured to not adjust the current position of the moving-point camera if there is a matching image area between the third moving-point image and the second fixed-point image.

[0108] A position adjustment module is used to adjust the current position of the moving-point camera if there is no matching image area between the third moving-point image and the second fixed-point image, so that the field of view of the moving-point camera is within the field of view of the fixed-point camera.

[0109] In an embodiment of the present application, the position adjustment module includes:

[0110] The area matching unit is used to control the moving point camera to rotate to the first side by a fourth preset angle to determine whether there is a matching image area between the fourth moving point image captured by the moving point camera at the current position and the second fixed point image.

[0111] The field of view range determining unit is configured to determine that, if yes, the field of view range of the moving-point camera is within the field of view range of the fixed-point camera.

[0112] The rotation control unit is used to control the moving point camera to rotate to the second side by a fourth preset angle if the answer is no.

[0113] The pan-tilt zero point determination device provided in the embodiments of the present application can execute the pan-tilt zero point determination method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0114] Figure 13 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. Figure 13 A block diagram of an exemplary electronic device 612 suitable for implementing embodiments of the present application is shown. Figure 13 The electronic device 612 shown is merely an example and should not limit the functionality and scope of use of the embodiments of the present application.

[0115] like Figure 13 As shown, the electronic device 612 may include: one or more processors 616; a memory 628 for storing one or more programs. When the one or more programs are executed by the one or more processors 616, the one or more processors 616 implement the pan-tilt zero point determination method provided in the embodiment of the present application, including:

[0116] In a preset direction, controlling the moving-point camera to rotate toward a first side and capturing a first moving-point image in real time;

[0117] Performing image matching on a first moving point region image in a first moving point image captured in real time and a first fixed point region image in a first fixed point image captured by a fixed point camera;

[0118] If the first moving point area image and the first fixed point area image are matched successfully, the current position point of the pan / tilt platform is used as the zero point of the pan / tilt platform in the preset direction.

[0119] The electronic device 612 may be a pan-tilt binocular camera. In this case, the electronic device 612 includes Figure 13 In addition to the structure shown in FIG, the basic structure of the pan-tilt binocular camera for image acquisition, such as the image sensor, lens, and other accessories, is also included, which will not be described in detail here. The electronic device 612 can also be other devices that communicate with the pan-tilt binocular camera, obtain image information through the pan-tilt binocular camera, execute the method in the above embodiment, and then send the obtained zero point detection result to the pan-tilt binocular camera or control the pan-tilt binocular camera based on the zero point detection result.

[0120] Components of the electronic device 612 may include, but are not limited to, one or more processors 616 , a memory 628 , and a bus 618 that connects the various device components, including the memory 628 and the processor 616 .

[0121] Bus 618 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, a processed ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0122] The electronic device 612 typically includes a variety of computer-readable storage media, which can be any available storage media that can be accessed by the electronic device 612, including volatile and non-volatile storage media, removable and non-removable storage media.

[0123] The memory 628 may include computer-readable storage media in the form of volatile memory, such as random access memory (RAM) 630 and / or cache memory 632. The electronic device 612 may further include other removable / non-removable, volatile / non-volatile computer storage media. By way of example only, the storage system 634 may be configured to read and write non-removable, non-volatile magnetic storage media ( Figure 13 Not shown, often called a "hard drive"). Although Figure 13Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical storage medium) may be provided. In these cases, each drive may be connected to bus 618 via one or more data storage medium interfaces. Memory 628 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present application.

[0124] A program / utility 640 having a set (at least one) of program modules 642 may be stored, for example, in memory 628. Such program modules 642 include, but are not limited to, operating devices, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 642 generally implement the functions and / or methods of the embodiments described herein.

[0125] The electronic device 612 may also communicate with one or more external devices 614 and / or a display 624, and may also communicate with one or more devices that enable a user to interact with the electronic device 612, and / or any device that enables the electronic device 612 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 622. Furthermore, the electronic device 612 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 620. Figure 13 As shown, the network adapter 620 communicates with other modules of the electronic device 612 via the bus 618. Figure 13 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 612, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID devices, tape drives, and data backup storage devices.

[0126] The one or more processors 616 execute various functional applications and data processing by running at least one of the other programs among the multiple programs stored in the memory 628, such as implementing a pan-tilt zero point determination method provided in an embodiment of the present application.

[0127] One embodiment of the present application provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to perform a pan-tilt zero point determination method, including:

[0128] In a preset direction, controlling the moving-point camera to rotate toward a first side and capturing a first moving-point image in real time;

[0129] Performing image matching on a first moving point region image in a first moving point image captured in real time and a first fixed point region image in a first fixed point image captured by a fixed point camera;

[0130] If the first moving point area image and the first fixed point area image are matched successfully, the current position point of the pan / tilt platform is used as the zero point of the pan / tilt platform in the preset direction.

[0131] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable storage media. The computer-readable storage medium can be a computer-readable signal storage medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 thereof. In an embodiment of the present application, a computer-readable storage medium can be any tangible storage medium containing or storing a program, which can be used by an instruction execution device, device or device or used in combination with it.

[0132] A computer-readable signal storage medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal storage medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution device, apparatus, or component.

[0133] The program code embodied on the computer-readable storage medium may be transmitted using any appropriate storage medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0134] The computer program code for performing the operations of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or device. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] Note that the above are only preferred embodiments of the present application and the technical principles employed. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present application. The scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for determining the zero point of a pan / tilt platform, characterized in that: The method is performed by a pan-tilt binocular camera, the pan-tilt binocular camera includes a fixed-point camera and a moving-point camera, and the moving-point camera is driven by the pan-tilt to rotate horizontally or vertically. The method includes: In a preset direction, controlling the moving-point camera to rotate toward a first side and capturing a first moving-point image in real time; Performing image matching on a first moving point region image in a first moving point image captured in real time and a first fixed point region image in a first fixed point image captured by a fixed point camera; If the first moving point area image and the first fixed point area image match successfully, it is determined that the viewing angle range of the moving point camera is within the viewing angle range of the fixed point camera. According to the position of the first moving point area image and the position of the first fixed point area image, the current position of the pan-tilt head relative to the field of view of the fixed point camera is determined, and the current position of the pan-tilt head is used as the zero point of the pan-tilt head in the preset direction.

2. The method according to claim 1, characterized in that If the first moving point area image and the first fixed point area image are successfully matched, the current position of the gimbal is used as the zero point of the gimbal in the preset direction, including: If the first moving-point area image and the first fixed-point area image are successfully matched, controlling the moving-point camera to rotate to a second side by a first preset angle and capturing a second moving-point image; wherein the first preset angle is determined based on the field of view of the fixed-point camera in a preset direction, and the second side is in the preset direction and opposite to the direction of the first side; performing image matching on a second moving-point region image in the second moving-point image and a second fixed-point region image in the first fixed-point image; If the second moving point area image and the second fixed point area image are matched successfully, it is determined that the zero point of the pan / tilt head is accurate.

3. The method according to claim 2, characterized in that The first moving-point area image is the edge image corresponding to the first side in the first moving-point image; the first fixed-point area image is the edge image corresponding to the first side in the first fixed-point image; the second moving-point image is the edge image corresponding to the second side in the second moving-point image; and the second fixed-point area image is the edge image corresponding to the second side in the first fixed-point image.

4. The method according to claim 2, characterized in that The method further comprises: If the second moving point area image and the second fixed point area image are not matched successfully, based on the current position of the moving point camera, the step of controlling the moving point camera to rotate toward the first side and performing image matching on the first moving point area image and the first fixed point area image to determine the pan / tilt zero point is re-executed.

5. The method according to claim 1, wherein After controlling the moving-point camera to rotate toward the first side in a preset direction and capturing a first moving-point image in real time, the method further includes: If the first moving-point area image and the first fixed-point area image are not successfully matched, determining whether the angle of rotation of the moving-point camera toward the first side reaches a second preset angle; If so, controlling the moving point camera to rotate to the second side by a third preset angle; Re-execute the step of controlling the moving-point camera to rotate toward the first side, and performing image matching between the first moving-point area image and the first fixed-point area image to determine the pan / tilt zero point; If not, continue to control the camera to rotate toward the first side and capture the first moving point image in real time, and if the first moving point area image and the first fixed point area image do not match successfully, determine whether the angle of rotation of the moving point camera toward the first side reaches a second preset angle; Among them, the second preset angle is determined according to the angle between the limit line when the pan-tilt head rotates to the second side and the edge of the field of view angle of the fixed camera on the first side; the third preset angle is determined according to the angle between the limit line when the pan-tilt head rotates to the first side and the edge of the field of view angle of the fixed camera on the first side.

6. The method according to claim 1, characterized in that Before controlling the moving-point camera to rotate toward the first side in a preset direction and capturing the first moving-point image in real time, the method further includes: Acquire a second fixed-point image captured by the fixed-point camera and a third moving-point image captured by the moving-point camera; If there is a matching image area between the third moving-point image and the second fixed-point image, then the current position of the moving-point camera is not adjusted; If there is no matching image area between the third moving-point image and the second fixed-point image, the current position of the moving-point camera is adjusted so that the field of view of the moving-point camera is within the field of view of the fixed-point camera.

7. The method according to claim 6, characterized in that Adjusting the current position of the moving-point camera so that the field of view of the moving-point camera is within the field of view of the fixed-point camera includes: controlling the moving-point camera to rotate toward the first side by a fourth preset angle, and determining whether a fourth moving-point image captured by the moving-point camera at the current position has a matching image area with the second fixed-point image; If yes, determining that the field of view of the moving-point camera is within the field of view of the fixed-point camera; If not, the moving point camera is controlled to rotate toward the second side by a fourth preset angle.

8. A device for determining the zero point of a pan / tilt platform, characterized in that: A binocular camera is configured on a pan-tilt platform, wherein the binocular camera includes a fixed-point camera and a moving-point camera. The moving-point camera is driven by the pan-tilt platform to rotate horizontally or vertically. The device includes: A first moving-point image acquisition module, configured to control the moving-point camera to rotate toward a first side in a preset direction, and acquire a first moving-point image captured by the moving-point camera in real time; a matching module for performing image matching between a first moving-point region image in a first moving-point image acquired in real time and a first fixed-point region image in a first fixed-point image acquired by a fixed-point camera; A zero point determination module is used to determine that the viewing angle range of the moving point camera is within the viewing angle range of the fixed point camera if the first moving point area image and the first fixed point area image are successfully matched, and to determine the current position of the pan-tilt head relative to the field of view of the fixed point camera based on the position of the first moving point area image and the position of the first fixed point area image, and then use the current position of the pan-tilt head as the zero point of the pan-tilt head in the preset direction.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the gimbal zero point determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining the zero point of a pan / tilt platform as described in any one of claims 1 to 7 is implemented.

Images