Visual acquisition system and method

Abstract

The invention provides a visual acquisition system and method. The system comprises a motor, a camera component and a spring, the camera assembly comprises a first camera and a second camera, the first camera and the second camera are symmetrical relative to the symmetrical face, the first camera rotates around a first rotating shaft, the second camera rotates around a second rotating shaft, and the first rotating shaft and the second rotating shaft are parallel and symmetrical relative to the symmetrical face. The intersection point of the first camera light path and the second camera light path is located on the symmetry plane; an output shaft of the motor is in transmission connection with a worm, the worm is in transmission connection with a first worm gear and a second worm gear, a rotating shaft of the first worm gear coincides with the first rotating shaft, a rotating shaft of the second worm gear coincides with the second rotating shaft, and the motor drives the first camera and the second camera to rotate in opposite directions; the spring is arranged between the first camera and the second camera and is used for eliminating the back clearance of the worm and the worm gear, avoiding the rotation error caused by the gear back clearance, improving the angle adjustment accuracy and improving the imaging stability.

Description

[0001] This application claims priority to Chinese Patent Application No. 202510097441.6, filed on January 21, 2025, entitled "Visual Acquisition Method, System, Apparatus and Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of stereomicroscopy technology, and more particularly to a visual acquisition system and method. Background Technology

[0003] A stereomicroscope, also known as a anatomical microscope, is a visual instrument that provides an orthographic, three-dimensional image. It utilizes a dual-channel optical path, where the two beams in the binocular tubes are not parallel but rather angled (stereoscopic angle, typically 12°-15°), thus providing a three-dimensional image for both eyes.

[0004] Currently, in some designs, the angle between the tubes of a stereomicroscope is fixed and cannot be adjusted, resulting in poor stereoscopic imaging for objects viewed at different distances. In other designs, the angle between the tubes is adjustable, with the angle primarily adjusted by the rotation of a worm gear.

[0005] However, due to the backlash between the worm gear and the worm, the angle adjustment may be inaccurate, affecting the imaging effect. Summary of the Invention

[0006] This application provides a visual acquisition system and method to solve the problem of poor imaging effect caused by back gap when adjusting the angle of existing stereomicroscopes.

[0007] In a first aspect, this application provides a visual acquisition system, comprising: a motor, a camera assembly, and a spring; the camera assembly includes a first camera and a second camera, the first camera and the second camera being symmetrically arranged relative to a symmetrical plane, the first camera being rotatable about a first axis, the second camera being rotatable about a second axis, the first axis and the second axis being parallel and symmetrically arranged relative to the symmetrical plane, the intersection of the optical paths of the first camera and the second camera being located on the symmetrical plane; the output shaft of the motor is drivenly connected to a worm gear, the two sides of the worm gear being drivenly connected to a first worm wheel and a second worm wheel respectively, the axis of rotation of the first worm wheel coinciding with the first axis, the axis of rotation of the second worm wheel coinciding with the second axis, the motor being capable of driving the first camera and the second camera to rotate in opposite directions; the spring is connected to the first camera and the second camera respectively along its elastically extending ends, the spring being used to eliminate the backlash between the worm gear and the first worm wheel when the first camera is at a preset angle, and to eliminate the backlash between the worm gear and the second worm wheel when the second camera is at a preset angle.

[0008] Secondly, this application provides a visual acquisition method applied to the visual acquisition system described above; the method includes:

[0009] The object distance from the camera component to the object carrier is obtained, and the object carrier is used to place the object to be detected;

[0010] The target angle is determined based on the object distance and the distance between the first rotating axis and the second rotating axis;

[0011] Adjust the first camera and the second camera to a preset angle;

[0012] The motor controls the first camera and the second camera to rotate from the preset angle so that the angle between the light path of the first camera and the plane of symmetry and the angle between the light path of the second camera and the plane of symmetry are both equal to the target angle.

[0013] A first image of the observed object is acquired through the first camera, and a second image of the observed object is acquired through the second camera. A stereoscopic image is then output based on the first image and the second image.

[0014] Optionally, the method includes:

[0015] Determine the new object distance after the first camera and the second camera are rotated;

[0016] A new target angle is determined based on the new object distance and the distance between the first rotating axis and the second rotating axis;

[0017] Control the first camera and the second camera to adjust to the preset angle;

[0018] The motor controls the first camera and the second camera to rotate from a preset angle so that the angle between the light path of the first camera and the plane of symmetry, and the angle between the light path of the second camera and the plane of symmetry, are both equal to the new target angle.

[0019] Optionally, before controlling the first camera and the second camera to adjust to the preset angle, the method further includes:

[0020] Determine the difference between the new target angle and the original target angle;

[0021] Determine whether the difference is greater than the preset difference threshold;

[0022] If the difference is less than the preset difference threshold, then there is no need to adjust the angles of the first camera and the second camera.

[0023] Optionally, the method further includes:

[0024] Obtain the magnification of the first camera and the second camera;

[0025] The preset difference threshold is determined based on the magnification factor.

[0026] Optionally, the method further includes:

[0027] Determine whether the included angle of the target is within the preset volume view threshold range;

[0028] If the target angle is not within the body view threshold range, then control the movement of the loading device;

[0029] The target angle is recalculated based on the object distance after the movement until the target angle is within the body view threshold range.

[0030] Optionally, controlling the movement of the loading device includes:

[0031] If the included angle of the target is greater than the upper limit of the body view threshold range, then control the loading device to move downward by a first preset distance;

[0032] If the target angle is less than the lower limit of the body view threshold range, then control the loading device to move upward by a second preset distance.

[0033] Optionally, the method further includes:

[0034] The first preset distance or the second preset distance is determined based on the magnification of the first camera and the second camera.

[0035] This application provides a visual acquisition system and method. The system includes a motor, a camera assembly, and a spring. The camera assembly includes a first camera and a second camera, which are symmetrically arranged with respect to a symmetrical plane. The first camera can rotate around a first axis, and the second camera can rotate around a second axis. The first and second axes are parallel and symmetrically arranged with respect to a symmetrical plane. The intersection of the optical paths of the first and second cameras is located on the symmetrical plane. A worm gear is driven through the output shaft of the motor. A first worm wheel and a second worm wheel are driven through the two sides of the worm gear, respectively. The axis of rotation of the first worm wheel coincides with the first axis, and the axis of rotation of the second worm wheel coincides with the second axis. The motor can drive the first and second cameras to rotate in opposite directions. The spring is connected to the first and second cameras at its elastically extended ends. The spring is used to eliminate the backlash between the worm gear and the first worm wheel when the first camera is at a preset angle, and also to eliminate the backlash between the worm gear and the second worm wheel when the second camera is at a preset angle. This avoids rotational errors caused by gear backlash, improves the accuracy of angle adjustment, and enhances stability during imaging. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0037] Figure 1 A schematic diagram of the backlash between the worm gear and the worm provided in this application;

[0038] Figure 2 This is a schematic diagram illustrating an application scenario of a visual acquisition system according to some embodiments of this specification;

[0039] Figure 3 These are schematic diagrams of a vision acquisition system according to some embodiments of this application specification;

[0040] Figure 4 This is a schematic diagram of the initial state of a vision acquisition system according to some embodiments of this specification;

[0041] Figure 5 This is another initial state schematic diagram of the visual acquisition system according to some embodiments of this specification;

[0042] Figure 6 These are schematic diagrams illustrating the state of the vision acquisition system during imaging, as shown in some embodiments of this specification.

[0043] Figure 7This is a schematic diagram of the main view structure of a vision acquisition system according to some embodiments of this specification;

[0044] Figure 8 This is a schematic diagram of the structure of a spring in a vision acquisition system according to some embodiments of this specification;

[0045] Figure 9 This is a bottom-view structural diagram of a vision acquisition system according to some embodiments of this specification;

[0046] Figure 10 This is a side view structural schematic diagram of a vision acquisition system according to some embodiments of this specification;

[0047] Figure 11 This is a rear view structural diagram of a vision acquisition system according to some embodiments of this specification;

[0048] Figure 12 This is a three-dimensional structural diagram of a vision acquisition system according to some embodiments of this specification. Figure 1 ;

[0049] Figure 13 This is a three-dimensional structural diagram of a vision acquisition system according to some embodiments of this specification. Figure 2 ;

[0050] Figure 14 A flowchart illustrating an embodiment of a visual acquisition method provided in this application;

[0051] Figure 15 A flowchart illustrating a second embodiment of a visual acquisition method provided in this application;

[0052] Figure 16 A flowchart illustrating a third embodiment of a visual acquisition method provided in this application;

[0053] Figure 17 A flowchart illustrating a fourth embodiment of a visual acquisition method provided in this application;

[0054] Figure 18 This is a schematic diagram of the structure of a visual acquisition device according to one embodiment of the present application.

[0055] Figure label:

[0056] 100 - Application scenarios; 120 - Signal transmission equipment; 130 - Storage devices; 150 - Terminal equipment;

[0057] 1400 - Visual acquisition device; 1401 - Acquisition module; 1402 - Determination module; 1403 - First control module; 1404 - Second control module; 1405 - Output module;

[0058] 200-Vision Acquisition System;

[0059] 210 - Camera assembly; 220 - Processor; 230 - Spring; 231 - Mounting bracket; 232 - First adjusting nut; 233 - Second adjusting nut;

[0060] 211-First camera; 212-Second camera; 213-Motor; 214-Worm gear; 215-First worm wheel; 216-Second worm wheel; 217-First shaft; 218-Second shaft;

[0061] 221 - First camera bracket; 222 - Second camera bracket;

[0062] 2211 - First connecting end; 2212 - First fixed position; 2221 - Second connecting end; 2222 - Second fixed position.

[0063] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0064] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0065] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0066] A stereomicroscope, also known as a anatomical microscope, is a visual instrument that produces an orthogonal, three-dimensional image. It utilizes a dual-channel optical path; the two beams in the binocular tubes are not parallel but rather at an angle (stereoscopic angle, typically 12°-15°), thus providing a stereoscopic image for both eyes. When observing an object with a stereomicroscope to output a stereoscopic image, to enhance the effect, the center points of the fields of view observed by the two tubes should not be too far apart. To accommodate objects at different observation distances, the field of view of at least one tube needs to be adjusted to bring the center points of the two fields of view closer together, thereby improving the stereoscopic effect of the image.

[0067] In some designs, the angle between the tubes of a stereomicroscope is fixed and cannot be adjusted, resulting in poor stereoscopic imaging for objects viewed at different distances. In other designs, the angle between the tubes is adjustable, with the angle primarily adjusted by the rotation of a worm gear.

[0068] Figure 1 This diagram illustrates the backlash between the worm gear and worm shaft provided in this application. The backlash between the worm gear and worm shaft causes errors when adjusting the microscope tube angle. For example, if the current position is 6° and the desired adjustment is to 6.5°, the backlash will result in an ineffective rotation of 0.1°, with only a 0.4° adjustment actually made. Furthermore, after adjusting to a certain angle, the backlash can cause slight wobbling of the microscope tube. For stereomicroscopes, accurate rotation angles are crucial for obtaining clear images. Therefore, this phenomenon affects image clarity.

[0069] In view of the above problems, the inventors, in the course of their research in this field, discovered that... Figure 1 The gear on the left side of the worm gear is larger than the gear on the right side, resulting in less backlash at the initial position. Using this initial position as the starting point for angle adjustment prevents angular deviation caused by backlash. In this design, the inventors also installed a spring between the two lens barrels. This prevents the lens barrels from wobbling due to backlash after reaching a certain angle.

[0070] Therefore, this application proposes a visual acquisition system, which includes a camera assembly and a processor. The camera assembly includes a motor, a spring, a first camera, and a second camera.

[0071] The first camera and the second camera are symmetrically arranged with respect to a symmetrical plane. The first camera can rotate around a first axis, and the second camera can rotate around a second axis. The first axis and the second axis are parallel and symmetrically arranged with respect to a symmetrical plane. The intersection of the optical paths of the first camera and the second camera is located on the symmetrical plane.

[0072] The target angle is determined by the object distance and the distance between the first and second rotating axes. By controlling the rotation of the first and second cameras, they are first rotated to a specified angle and then to the target angle, so that the angle between the light path of the first camera and the plane of symmetry and the angle between the light path of the second camera and the plane of symmetry are both equal to the target angle. Both cameras rotate, which conforms to the observation habits of the human eye, making the user experience of observing with the visual acquisition system better and more comfortable. After rotation, the springs can make the two lens barrels more stable and prevent shaking due to backlash.

[0073] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0074] refer to Figure 2 and Figure 3 In some embodiments, the application scenario of the visual acquisition system may include processor 220, signal transmission device 120, storage device 130, visual acquisition system 200 and terminal device 150.

[0075] The processor 220 can be connected to the storage device 130, the vision acquisition system 200, and / or the terminal device 150 via the signal transmission device 120 to access and / or receive data and information. For example, the processor 220 can receive relevant information from the vision acquisition system 200 (e.g., stereoscopic images of the observed object, initial images of the observed object, etc.) via the signal transmission device 120.

[0076] The visual acquisition system 200 can be used to perform stereoscopic imaging of the observed object to output a stereoscopic image of the object.

[0077] The visual acquisition system 200 mainly includes a camera component 210 and a processor 220. The camera component 210 is mainly used to observe and image external objects, while the processor 220 is mainly used to control the camera component 210 and process and output the images output by the camera component 210.

[0078] The camera assembly 210 includes a first camera 211 and a second camera 212, which can observe the object and form a first image and a second image respectively. After the processor 220 processes the first image and the second image, the visual acquisition system 200 can output a stereoscopic image of the object.

[0079] In some embodiments, the visual acquisition system 200 may further include a loading device, such as a stage (not shown). The stage can be used to support the object being observed. The loading device can be communicatively connected to the processor of the visual acquisition system, or it can be a device not connected to devices such as cameras or processors, such as an external table or bed.

[0080] refer to Figures 4-6 The first camera 211 and the second camera 212 are symmetrically arranged with respect to the symmetry plane S1. The first camera 211 can rotate around the first axis, and the second camera 212 can rotate around the second axis. The first axis and the second axis are fixed and perpendicular to the plane of the paper. The first axis and the second axis are parallel and symmetrically arranged with respect to the symmetry plane S1, so that the field of view of the first camera 211 and the second camera 212 is adjustable, thereby improving the observation and imaging effect of the camera assembly 210 on objects at different observation distances.

[0081] In some embodiments, when observing and imaging an object, the first optical path L1 of the first camera 211 intersects the second optical path L2 of the second camera 212, and the intersection point D of the two is located on the plane of symmetry S1 (e.g., Figure 6 As shown in the figure, this enhances the stereoscopic effect of the output object image and improves the user's viewing experience.

[0082] In some embodiments, in the vertical direction, a first rotating shaft is disposed at the end of the first camera 211 near the object, and a second rotating shaft is disposed at the end of the second camera 212 near the object, so that the first camera 211 and the second camera 212 will not collide or interfere with each other when rotating, thereby improving the rotation adjustment range of the first camera 211 and the second camera 212.

[0083] exist Figures 4-6 In the vertical plane shown, this vertical plane is the symmetrical plane of the camera assembly 210. The first rotation axis and the second rotation axis are line segments perpendicular to the vertical plane. The first rotation axis intersects the vertical plane at the first rotation axis point B1, and the second rotation axis intersects the vertical plane at the second rotation axis point B2. The first rotation axis can intersect the first optical path L1 at the first rotation axis point B1, and the second rotation axis can intersect the second optical path L2 at the second rotation axis point B2. With this setting, when the camera rotates around the rotation axis points, the rotation of the optical path is synchronized with the rotation of the camera, thereby improving the control accuracy of the first optical path L1 and the second optical path L2 when the first camera 211 and the second camera 212 rotate, and reducing the control difficulty.

[0084] In some embodiments, in order to adapt to the interpupillary distance of the human eye and improve user comfort, the distance between the first rotating axis and the second rotating axis can be 40mm-80mm.

[0085] In some embodiments, the intersection point A1 of the first optical path L1 and the observation plane S2 is the center point of the field of view of the first camera 211 on the observation plane S2, and the intersection point A2 of the second optical path L2 and the observation plane S2 is the center point of the field of view of the second camera 212 on the observation plane S2. Figures 4-6 In the vertical plane shown, the symmetry plane S1 intersects the observation plane S2 at point E. In some embodiments, when the field-of-view center point A1 of the first camera 211 coincides with or nearly coincides with the field-of-view center point A2 of the second camera 212, the intersection point D of the first optical path L1 and the second optical path L2 coincides with or nearly coincides with the two field-of-view centers A1 and A2. Since the intersection point D of the first optical path L1 and the second optical path L2 is located on the symmetry plane S1 (e.g., ...), Figure 6 As shown), therefore, the center points A1 and A2 of the two fields of view are also located or approximately located on the plane of symmetry S1 (as shown). Figure 6 As shown in the figure, this makes the image of the object output by the visual acquisition system 200 better and more in line with human eye usage habits.

[0086] In some embodiments, to ensure that the first camera 211 and the second camera 212 produce similar imaging effects of the object observed, thereby improving the final output stereoscopic image, the first camera 211 and the second camera 212 may be the same. Of course, in other embodiments, the first camera 211 and the second camera 212 may be different, as long as the imaging effect of the output object is good.

[0087] In some embodiments, both the first camera 211 and the second camera 212 include a charge-coupled device (CCD). CCDs offer high image clarity and a high signal-to-noise ratio. Furthermore, CCDs have advantages such as small size, resistance to strong light, vibration, and magnetic fields, low distortion, long lifespan, and ease of operation. CCDs are highly applicable in the medical field.

[0088] In some embodiments, the camera assembly 210 may include a first motor and a second motor (not shown in the figure). The first motor is driven by a first rotating shaft of the first camera 211, and the second motor is driven by a second rotating shaft of the second camera 212. The first motor and the second motor independently control the rotation of the first camera 211 and the second camera 212, respectively. In this case, the rotation of the first camera 211 and the second camera 212 is independent of each other, and their rotation angles may be the same or different. The angles between their optical paths and the plane of symmetry S1 may be the same or different.

[0089] like Figures 7-13In some embodiments, the camera assembly 210 may include a motor 213, which simultaneously controls the rotation of the first camera 211 and the second camera 212. In this case, the first camera 211 and the second camera 212 rotate in opposite directions, and their rotation angles may be the same, and the angles between their optical paths and the plane of symmetry S1 may be the same.

[0090] The output shaft of motor 213 can be connected to worm gear 214 for transmission. The two sides of worm gear 214 can be connected to the first worm wheel 215 and the second worm wheel 216 respectively. The first rotating shaft 217 coincides with the rotating shaft of the first worm wheel 215, and the second rotating shaft 218 coincides with the rotating shaft of the second worm wheel 216. Therefore, motor 213 can simultaneously drive the first camera 211 and the second camera 212 to rotate. Since the first worm wheel 215 and the second worm wheel 216 rotate in opposite directions, the first camera 211 and the second camera 212 can synchronously move closer to or further away from the plane of symmetry S1.

[0091] In some embodiments, the first worm gear 215 and the second worm gear 216 both have 60 teeth, the worm 214 has 1 thread, and the speed ratio between the worm 214 and the first worm gear 215 and the second worm gear 216 is 60.

[0092] In some embodiments, the first camera 211 and the second camera 212 can be connected to the main body of the vision acquisition system 200 (not shown in the figure) using an FPC (flexible printed circuit board). The FPC is fixed to the main body of the vision acquisition system 200 and is used to connect relevant cables (e.g., video output cables, control cables, power cables, etc.). The FPC serves as a flexible connection, reducing the resistance of the relevant cables when the first camera 211 and the second camera 212 rotate, thereby reducing the impact on the rotation angle accuracy of the first camera 211 and the second camera 212, and also reducing the loss of the worm gear connection.

[0093] like Figures 7-13 In some embodiments, the visual acquisition system also includes a mounting bracket 231.

[0094] Both the motor 213 and the camera assembly 210 are mounted on a mounting bracket, which can be a metal bracket. The mounting bracket is positioned in the first horizontal direction (…). Figure 9 (As shown in the y-direction) it is located between the motor 213 and the camera assembly 210.

[0095] By placing the motor 213 and the camera assembly 210 on both sides of the mounting bracket 231, the vertical distance between the camera bracket and the bearing is shortened, which facilitates the verticality calibration and control of the camera optical axis and transmission components, thereby improving the overall accuracy and stability of the system.

[0096] In some embodiments, the visual acquisition system further includes: a first camera bracket 221, a second camera bracket 222, a first image sensor, and a second image sensor.

[0097] The first camera 211 and the first image sensor are both mounted on the first camera bracket 221. The first image sensor is optically connected to the first camera 211. The first image sensor is used to receive and convert the optical image signals acquired by the first camera 211 and generate the corresponding first image electrical signals. The second camera 212 and the second image sensor are both mounted on the second camera bracket 222. The second image sensor is optically connected to the second camera 212. The second image sensor is used to receive and convert the optical image signals acquired by the second camera 212 and generate the corresponding second image electrical signals.

[0098] The first camera bracket 221 has a first connecting end 2211, which is connected to the first rotating shaft 217 so that the first camera bracket 221 drives the first camera 211 to rotate around the first rotating shaft 217; the second camera bracket 222 has a second connecting end 2221, which is connected to the second rotating shaft 218 so that the second camera bracket 222 drives the second camera 212 to rotate around the second rotating shaft 218.

[0099] By mounting the camera bracket with the rotating shaft, camera, and image sensor, the camera components are integrated, ensuring the fixity and consistency of the relative positions between the lens optical axis, the image sensor imaging plane, and the rotating shaft. This optimizes the camera's optical alignment, effectively improves the perpendicularity between the camera's optical axis and the system's rotating shaft, thereby reducing image geometric distortion and resolution loss caused by optical axis tilt and improving image quality.

[0100] like Figure 7 and Figure 8 In some embodiments, the camera assembly 210 may also include a spring 230, which is disposed between the first camera 211 and the second camera 212. When the spring 230 is in its natural state, the angle between the first camera 211 and the second camera 212 is at a preset initial position.

[0101] The first camera bracket 221 is provided with a first fixing position 2212, the second camera bracket 222 is provided with a second fixing position 2222, and the two ends of the spring 230 along its elastic extension direction are respectively fixedly connected to the first fixing position 2212 and the second fixing position 2222.

[0102] Spring 230 is used to eliminate the backlash between worm 214 and first worm wheel 215 when the first camera 211 is at a preset angle, and to eliminate the backlash between worm 214 and second worm wheel 216 when the second camera 212 is at a preset angle, thereby avoiding rotational errors caused by gear backlash, improving the accuracy of the adjusted angle, and improving stability during imaging.

[0103] like Figure 9 In some embodiments, the first rotating shaft 217 includes a first external threaded section and a second external threaded section spaced apart in its axial direction. A first adjusting nut 232 and a second adjusting nut 233 are rotatably connected to the first external threaded section and the second external threaded section, respectively. The first connecting end 2211 of the first camera bracket 221 is connected to the first rotating shaft 217 through a limiting structure, so that the first camera bracket 221 can slide along the axial direction of the first rotating shaft 217 and cannot rotate around the axial direction of the first rotating shaft 217. The first connecting end 2211 of the first camera bracket 221 is located between the first adjusting nut 232 and the second adjusting nut 233. The rotational movement of the first adjusting nut 232 and the second adjusting nut 233 can be converted into axial displacement along the first rotating shaft 217 and push the first camera bracket 221 to produce a first micro displacement along the axial direction of the first rotating shaft 217.

[0104] The rotational motion of the first adjusting nut 232 can be converted into an axial displacement along the first rotating shaft 217, and push the first camera bracket 221 to produce a first micro displacement along the y-axis; the rotational motion of the second adjusting nut 233 can be converted into an axial displacement along the first rotating shaft 217, and push the first camera bracket 221 to produce a first micro displacement along the y-axis.

[0105] refer to Figure 12 The first connecting end 2211 of the first camera bracket 221 is connected to the first rotating shaft 217 through a limiting structure, so that the first camera bracket 221 can slide along the axial direction of the first rotating shaft 217, but cannot rotate around the axial direction of the first rotating shaft 217. The first connecting end 2211 is clamped on the first rotating shaft 217, and the limiting structure can be a fastening screw connected to the first connecting end 2211. When the fastening screw is loosened, the first camera bracket 221 can slide along the axial direction of the first rotating shaft 217, but cannot rotate around the axial direction of the first rotating shaft 217. When the fastening screw is tightened, the first camera bracket 221 cannot slide along the axial direction of the first rotating shaft 217, but can rotate around the axial direction of the first rotating shaft 217.

[0106] Alternatively, the limiting structure can be an axial limiting groove provided on the first rotating shaft 217 and an axial limiting key provided on the first connecting end 2211. The axial limiting key is fitted into the axial limiting groove and can move in the axial limiting groove, so that the first camera bracket 221 can slide along the axial direction of the first rotating shaft 217, but cannot rotate around the axial direction of the first rotating shaft 217.

[0107] By connecting the camera bracket and adjusting nut in series with a single rotating shaft, the structure is compact and has high rigidity. Furthermore, by utilizing the threaded pair between the nut and the rotating shaft, the rotational motion is converted into high-precision axial micro-displacement, enabling fine adjustment of the relative height of the camera's imaging plane.

[0108] This adjustment method offers high resolution, depends on the thread pitch, is easy to operate, and after adjustment, the self-locking characteristic of the nut and the constraints of the overall structure ensure that the adjusted state remains stable for a long time, effectively improving the calibration accuracy and operational reliability of the binocular vision system.

[0109] It should be noted that the second rotating shaft 218 also includes a first adjusting nut 232 and a second adjusting nut 233 spaced apart in its axial direction, the same as the first rotating shaft 217, and will not be described again here.

[0110] In some embodiments, the first worm gear 215 and the second worm gear 216 are partially circular structures, and the maximum rotation angle of the partially circular structure is 15°.

[0111] A partially circular structure can be a partially circular sector structure, in which the teeth only retain the sector segment required to meet the maximum rotational stroke. Compared with the traditional full-circle worm gear, it significantly reduces the radial and axial structural dimensions of the worm gear itself, achieving the ultimate compactness and lightweight of the structure.

[0112] In some embodiments, the visual acquisition system further includes a ranging mechanism, which is horizontally mounted on the mounting bracket 231. The ranging mechanism is used to measure the distance between the light path exit point of the first camera 211 and / or the second camera 212 and the corresponding center point of the field of view. The measuring optical axis of the ranging mechanism is configured in a horizontal direction (the x-direction or y-direction shown in the figure). An optical path deflection element is provided on the ranging mechanism. The optical path deflection element is fixedly mounted at a preset angle relative to the horizontal direction. The optical path deflection element is used to change the direction of the measuring optical axis so that the direction of the measuring optical axis is vertically downward.

[0113] The optical path deflection element can be a reflector, which is fixedly installed at a 45° angle relative to the horizontal direction.

[0114] By horizontally mounting the ranging mechanism and setting a 45° reflector to deflect the optical path, the measuring beam is made to point vertically downwards, thus reducing the overall height of the visual acquisition system.

[0115] In some embodiments, the ranging mechanism may include, but is not limited to, a laser rangefinder, an ultrasonic rangefinder, an infrared rangefinder, etc.

[0116] This application also proposes a visual acquisition method, which is applied to the aforementioned visual acquisition system, with the processor as the execution entity, and the visual acquisition method is described in detail.

[0117] refer to Figure 14 The method includes:

[0118] S101. Obtain the object distance from the camera component to the carrying device.

[0119] In this step, the object to be detected is placed on the object carrier. The object refers to the object observed by the vision acquisition system 200, which may include, but is not limited to, physical objects and biological tissues, and its form may include liquids, gases, solids, or combinations or mixtures thereof.

[0120] The camera assembly 210 has a ranging device that can measure the distance between the light path exit point of the first camera 211 and / or the second camera 212 and the observation surface S2 of the object. The observation surface S2 of the object refers to the surface of the object that can be observed by the first camera 211 and / or the second camera 212. In some embodiments, the first light path L1 of the first camera 211 and the second light path L2 of the second camera 212 are emitted along their respective central axes. The light path exit point of the first camera 211 and / or the second camera 212 is the intersection point of the central axis of the first camera 211 and / or the second camera 212 with the end face of the first camera 211 and / or the second camera 212 closest to the object. In some embodiments, the exit point of the first light path L1 of the first camera 211 can be the intersection point of the first light path L1 and the first rotation axis, designated as the first rotation axis point B1, and the exit point of the second light path L2 of the second camera 212 can be the intersection point of the second light path L2 and the second rotation axis, designated as the second rotation axis point B2.

[0121] It should be noted that the object distance from the camera component 210 to the carrier device refers to the object distance from the camera component 210 to the object being detected on the carrier device. When the carrier device is at the same height, the object distance obtained will be different if the objects being detected are placed at different heights.

[0122] In some embodiments, Figures 4-6 In the vertical plane shown, the line connecting the first pivot point B1 and the second pivot point B2 intersects the plane of symmetry S1 at point C. Then the first object distance is the length of the line segment CE.

[0123] In some embodiments, the first object distance can be indirectly calculated using the distance between the exit point of the optical path of the first camera 211 and / or the second camera 212 and the corresponding center point of the field of view (e.g., the lengths of line segments A1B1 and A2B2). Specifically, in the vertical plane, the distance between the exit point B1 of the first optical path L1 of the first camera 211 and the corresponding center point A1 of the field of view is the length of line segment A1B1, the distance between the exit point B2 of the second optical path L2 of the second camera 212 and the corresponding center point A2 of the field of view is the length of line segment A2B2, and the first object distance is the length of line segment CE.

[0124] like Figure 4 As shown, when the initial state of the visual acquisition system 200 is that the first camera 211 and the second camera 212 are set vertically parallel, the first object distance d1' can be equal to the distance d1 between the light path exit point of the first camera 211 and / or the second camera 212 and the corresponding field of view center point.

[0125] like Figure 5 As shown, when the initial state of the visual acquisition system 200 is that the optical paths of the first camera 211 and the second camera 212 each have an initial angle with the plane of symmetry S1, the first object distance d1' can be determined based on the distance between the light path exit point and the corresponding center point of the field of view (e.g., the length d1 of line segment A1B1) and the corresponding initial angle (e.g., the initial angle α0). Taking the first camera 211 as an example, draw a perpendicular line A1F from the center point A1 of the field of view of the first camera 211 to line segment B1B2. The length of line segment A1F is the first object distance. In the right triangle A1FB1, the first object distance d1' = d1 × cosα0.

[0126] Of course, in some embodiments, the first camera 211 and the second camera 212 can be adjusted to such a position first. Figure 4 The initial state is shown, and then subsequent steps are executed.

[0127] In some embodiments, the object distances corresponding to the first camera 211 and the second camera 212 may be different. In some embodiments, the smaller object distance can be used as the first object distance to ensure that the camera assembly 210 can preferentially focus on the area on the observation surface S2 that is relatively close to the camera assembly 210. In some embodiments, the average of the two object distances can also be used as the first object distance.

[0128] In some embodiments, the first camera 211 and the second camera 212 can be autofocus cameras. An autofocus camera can automatically focus its lens on the observation surface S2 of the object. In this case, the focal length of the autofocus camera is the distance d1 between the light path exit point of the corresponding camera and the center point of the corresponding field of view. Therefore, the processor 220 can determine the first object distance d1' based on the autofocus focal length d1.

[0129] In some embodiments, the visual acquisition system 200 may further include a ranging mechanism (not shown in the figure), which can directly measure the distance d1 between the light path exit point and the corresponding field of view center point. The processor 220 can calculate the first object distance d1' based on the measured d1. In some embodiments, the ranging mechanism may include, but is not limited to, a laser rangefinder, an ultrasonic rangefinder, an infrared rangefinder, etc.

[0130] S102. Determine the target angle based on the object distance and the distance between the first and second rotating axes.

[0131] The first included angle α1 refers to the angle between the optical paths of the first camera 211 and / or the second camera 212 and the target on the symmetry plane S1 when the intersection point D of the first optical path L1 and the second optical path L2 falls on the observation plane S2. That is, the angle between the optical paths of the first camera 211 and / or the second camera 212 and the target on the symmetry plane S1 when points D, E, A1, and A2 coincide or approximately coincide. In some embodiments, the first included angle α1 can be determined based on the first object distance d1' and the distance l between the first pivot point B1 and the second pivot point B2. Since the first pivot point B1 and the second pivot point B2 are symmetrical with respect to the symmetry plane S1, the length of line segment B1C is equal to the length of line segment B2C, both being l / 2. Please refer to... Figure 4 and Figure 5 In right triangle B1CE, the first included angle α1 is the angle of ∠B1EC. Therefore, the first included angle α1 = arctan l / (2d1').

[0132] S103. Adjust the first camera and the second camera to the preset angle.

[0133] The preset angle can be the initial 0°, i.e., as shown below. Figure 4 As shown, the two camera devices are positioned vertically downwards.

[0134] In some other embodiments, the preset angle can also be set to other angles, such as 0°, 5°, 7°, etc. The preset angle setting needs to be related to the gear setting of the worm wheel and worm. At the preset angle, the gears of the worm wheel and worm are in close contact with each other to reduce backlash.

[0135] By setting a preset angle, the rotation is performed at that angle each time, which can reduce errors. This is because the backlash may be different at different angles. Not using a starting point as a standard will lead to the accumulation of errors, making the errors larger and larger.

[0136] S104. The first and second cameras are controlled by a motor to rotate from a preset angle so that the angle between the light path of the first camera and the plane of symmetry and the angle between the light path of the second camera and the plane of symmetry are both equal to the target angle.

[0137] In this step, the motors can control two cameras simultaneously, or two motors can control two cameras separately. The motors control the first camera 211 and the second camera 212 to rotate from a preset angle, so that the angle between the first optical path L1 of the first camera 211 and the symmetry plane S1, and the angle between the second optical path L2 of the second camera 212 and the symmetry plane S1, are both equal to the target angle (i.e., the first angle α1). Figure 6As shown. It should be noted that in some embodiments, in the initial state, the initial angle between the first optical path L1 of the first camera 211 and the symmetry plane S1, and the initial angle between the second optical path L2 of the second camera 212 and the symmetry plane S1, may be the same or different. Therefore, in order to ensure that the angles between the first optical path L1 of the first camera 211 and the symmetry plane S1, and the angles between the second optical path L2 of the second camera 212 and the symmetry plane S1, after rotation, are both equal to the target angle (i.e., the first angle α1), the rotation angles of the first camera 211 and the second camera 212 may be the same or different. Furthermore, due to factors such as mechanical fit errors and operational errors, the fact that the angles between the first optical path L1 of the first camera 211 and the symmetry plane S1, and the angles between the second optical path L2 of the second camera 212 and the symmetry plane S1, are both equal to the target angle does not mean they are absolutely equal; approximate equality is sufficient.

[0138] After rotating to the preset angle, the spring will cause a force to be applied between the worm gear and the worm shaft, preventing any shaking.

[0139] Because of the spring, at a certain angle, the force will cause one side of the gear joint to have no backlash, while the backlash on the other side will increase. If subsequent rotations are not performed by rotating to the preset angle and instead proceed directly in the direction of greater backlash, the error will increase. Therefore, it is necessary to rotate to the preset angle before proceeding with subsequent rotations.

[0140] S105. Acquire a first image of the observed object using a first camera and a second image of the observed object using a second camera, and output a stereoscopic image based on the first and second images.

[0141] A first image of the object is acquired by the first camera 211, and a second image of the object is acquired by the second camera 212. A stereoscopic image of the object is then output based on the first and second images.

[0142] In some embodiments, the first camera 211 can directly output a first image, and the second camera 212 can directly output a second image. In some embodiments, the first image and the second image can be output to different terminal devices 150 respectively (without forming a stereoscopic image), or they can be output to the same terminal device 150 (directly forming a stereoscopic image, such as VR glasses). In some embodiments, the number of terminal devices 150 to which the first camera 211 and the second camera 212 directly output can be one or more.

[0143] In some embodiments, the first image captured by the first camera 211 and the second image captured by the second camera 212 can be processed by the processor 220 to form a stereoscopic image before being output. In some embodiments, the number of terminal devices 150 for which the processor 220 outputs stereoscopic images can be one or more.

[0144] This embodiment provides a visual acquisition method that obtains the object distance from the camera component to the carrying device; determines the target angle based on the object distance and the distance between the first and second rotating axes; adjusts the first and second cameras to a preset angle; controls the first and second cameras to rotate from the preset angle using a motor, so that the angle between the optical path of the first camera and the plane of symmetry, and the angle between the optical path of the second camera and the plane of symmetry, are both equal to the target angle; acquires a first image of the object using the first camera and a second image of the object using the second camera, and outputs a stereoscopic image based on the first and second images. This method avoids rotational errors caused by gear backlash, improves the accuracy of the adjusted angle, and enhances stability during imaging.

[0145] After rotating to the target angle, the positions of the center points of the fields of view of the first camera 211 and the second camera 212 change, and their observation areas change. Since the object may be three-dimensional, the observation surface S2 may not be flat and may have undulations. Therefore, the height of the observation surface S2 corresponding to the observation areas of the first camera 211 and the second camera 212 may be different before and after the rotation. Consequently, the second object distance between the first camera 211 and the object after the rotation may be different from the first object distance before the rotation. Therefore, it is necessary to reconfirm the second object distance to further determine whether the first camera 211 and the second camera 212 are in a suitable observation and imaging position.

[0146] refer to Figure 15 The method includes:

[0147] S201. Determine the new object distance after the camera assembly rotates.

[0148] S202. Determine the new target angle based on the new object distance and the distance between the first and second rotating axes.

[0149] S203, Control the first camera and the second camera to adjust to the preset angle.

[0150] S204. The first and second cameras are rotated from a preset angle by controlling the motor so that the angle between the light path of the first camera and the plane of symmetry and the angle between the light path of the second camera and the plane of symmetry are both equal to the new target angle.

[0151] The method steps in this second embodiment are the same as those in the first embodiment, and will not be repeated here.

[0152] Based on the rotated position, a new object distance and a new target angle are determined, which can further determine whether the object is in a suitable observation and imaging position, thus improving the accuracy of imaging.

[0153] refer to Figure 16 Based on the above-described embodiment two, if the field of view difference is large after rotation, and the new target angle differs significantly from the previous target angle, then rotation is required again. If the difference is not significant, then rotation is not necessary. Therefore, before step S203, the following steps are also included:

[0154] S301. Determine the difference between the new target angle and the target angle.

[0155] In this step, after rotating to the target angle for the first time, a new target angle is determined based on the new object distance. The difference between the new target angle and the previous target angle is then obtained.

[0156] S302. Determine whether the difference is greater than the preset difference threshold.

[0157] In one implementation, a difference threshold is preset. If the difference is greater than the threshold, it indicates that the angle difference is too large and the rotation needs to be repeated. If the difference is less than the threshold, it indicates that the rotation does not need to be repeated.

[0158] In another implementation, because the field of view differs at different magnifications, and the higher the magnification, the more sensitive it is to changes in angle, it is necessary to set corresponding angle difference thresholds for different magnifications. The magnification can be directly obtained from the camera component, and the difference threshold is determined based on the magnification, thereby determining whether the difference exceeds the preset difference threshold.

[0159] In another implementation, the newly determined object distance is used as the independent variable x, and the magnification is used as the independent variable y. The preset difference threshold f(x,y) = ax^2 + bxy + cy^2 + d. Here, a, b, c, and d are constants that can be obtained through testing. Specifically, based on a determined second object distance x0 and magnification y0, the size of the field of view of the first camera 211 and / or the second camera 212 on the observation plane S2 can be determined, for example, the length of the field of view along the line connecting the first rotation axis point B1 and the second rotation axis point B2. Using 1% of the field of view length as the length difference threshold, and combining the length difference threshold with the second object distance x0, the preset difference threshold f(x0,y0) for the corresponding included angle can be calculated. By using multiple second object distances x1, x2...xn and their corresponding magnifications y1, y2...yn, multiple corresponding preset difference thresholds f(x1,y1), f(x2,y2)...f(xn,yn) are calculated. Substituting the corresponding data into the formula f(x,y)=ax^2+bxy+cy^2+d, the values ​​of constants a, b, c, and d can be calculated.

[0160] In some embodiments, the visual acquisition system 200 has a minimum working distance, at which point the magnification of the visual acquisition system 200 is at its maximum, and the corresponding preset difference threshold can be 0.1°.

[0161] In some embodiments, the preset difference threshold may also be determined by a machine learning model based on the adjusted object distance (i.e., the second object distance) and magnification. The initial machine learning model may be stored in the processor 220 or other memory (e.g., storage device 130). The processor 220 may obtain multiple training samples to train the initial machine learning model.

[0162] In some embodiments, the machine learning model may be a supervised learning model. Multiple training samples may include exemplary inputs to the machine learning model and labels representing the desired outputs corresponding to the exemplary inputs. The process for training a supervised learning model enables the machine learning model to learn general rules that map inputs to corresponding outputs. Exemplary algorithms that may be used to train a supervised machine learning model may include gradient boosting decision tree (GBDT) algorithms, decision tree algorithms, random forest algorithms, logistic regression algorithms, support vector machine (SVM) algorithms, Naive Bayes algorithms, adaptive boosting algorithms, K-nearest neighbor (KNN) algorithms, Markov chain algorithms, etc., or any combination thereof.

[0163] In some embodiments, historically adjusted object distance and magnification can be used as training samples. The identifier of the training samples can be a preset difference threshold corresponding to the historically adjusted object distance and magnification. The labeled training samples are input into the initial machine learning model, and the parameters of the initial machine learning model are updated through training. When the trained machine learning model meets the preset conditions, the training ends, and the trained machine learning model is obtained.

[0164] S303. If the difference is less than the preset difference threshold, then there is no need to adjust the angles of the first camera and the second camera.

[0165] If the difference is greater than or equal to the preset difference threshold, then steps S203 and S204 are executed.

[0166] This method dynamically determines whether further adjustments are needed after rotating to the target angle, based on a preset difference threshold. After determining the new target angle, the method can also iterate until the difference is less than the preset difference threshold.

[0167] refer to Figure 17 Based on the above method embodiment one, the stereomicroscope's stereo angle is generally 12°-15°, and the imaging effect is better when observed at this angle. Therefore, before step S103, the following steps are also included:

[0168] S401. Determine whether the target angle is within the preset volume view threshold range.

[0169] The body view threshold range can be set to 12°-15° or other angle ranges, and steps S103 and S104 are executed.

[0170] If the target angle is within the volume view threshold range, then the angle is appropriate.

[0171] If the target angle is not within the volume view threshold range, it means that the angle will affect the imaging effect, and step S402 is executed.

[0172] S402, Control the movement of the cargo carrier.

[0173] In this step, if the target angle is not within the volume view threshold range, it means that the position of the loading device is not suitable and the loading device needs to be moved. The direction of the loading device's movement needs to be determined based on the target angle.

[0174] If the included angle of the target is greater than the upper limit of the body view threshold range, it means that the observed object needs to be moved downwards, so control the carrying device to move downwards by a first preset distance.

[0175] If the included angle of the target is less than the lower limit of the body view threshold range, it means that the observed object needs to be moved upward, so control the carrying device to move upward by a second preset distance.

[0176] The first preset distance or the second preset distance is determined based on the magnification of the camera component.

[0177] S403. Recalculate the target angle based on the object distance after the movement until the target angle is within the body view threshold range.

[0178] After moving the object carrier, the target angle needs to be recalculated. If the newly calculated target angle is also not within the volume view threshold range, the movement needs to continue until the target angle is within the volume view threshold range.

[0179] The method provided in this embodiment controls the object-carrying device to keep the target angle within the volume view threshold range, and then performs subsequent operations such as re-determining the target angle, rotation, and imaging.

[0180] refer to Figure 18 The visual acquisition device 1400 includes:

[0181] Acquisition module 1401 is used to acquire the object distance from the camera component to the object carrier;

[0182] The determining module 1402 is used to determine the target angle based on the object distance and the distance between the first rotating axis and the second rotating axis;

[0183] The first control module 1403 is used to adjust the first camera and the second camera to a preset angle;

[0184] The second control module 1404 is used to control the first camera and the second camera to rotate from a preset angle by a motor, so that the angle between the light path of the first camera and the plane of symmetry and the angle between the light path of the second camera and the plane of symmetry are both equal to the target angle.

[0185] The output module 1405 is used to acquire a first image of the observed object through a first camera and a second image of the observed object through a second camera, and output a stereoscopic image based on the first and second images.

[0186] Optionally, the determining module 1402 is also used for:

[0187] Determine the new object distance after the camera assembly rotates;

[0188] Determine the new target angle based on the new object distance and the distance between the first and second rotating axes;

[0189] The first control module 1403 is also used to control the first camera and the second camera to adjust to a preset angle;

[0190] The second control module 1404 is also used to control the first camera and the second camera to rotate from a preset angle by a motor, so that the angle between the light path of the first camera and the plane of symmetry and the angle between the light path of the second camera and the plane of symmetry are both equal to the new target angle.

[0191] Optionally, the determining module 1402 is also used for:

[0192] Determine the difference between the new target angle and the original target angle;

[0193] Determine whether the difference is greater than a preset difference threshold;

[0194] If the difference is less than the preset difference threshold, then there is no need to adjust the angles of the first and second cameras.

[0195] Optionally, the determining module 1402 is also used for:

[0196] Obtain the magnification of the camera component;

[0197] The preset difference threshold is determined based on the magnification factor.

[0198] Optionally, the device further includes a judgment module, which is used for:

[0199] Determine whether the target angle is within the preset volume view threshold range;

[0200] If the target angle is not within the body view threshold range, control the movement of the carrying device;

[0201] The target angle is recalculated based on the object distance after the movement until the target angle is within the body view threshold range.

[0202] Optionally, the first control module 1403 is also used for:

[0203] If the included angle of the target is greater than the upper limit of the body view threshold range, the loading device is controlled to move downward by a first preset distance;

[0204] If the target angle is less than the lower limit of the body view threshold range, the loading device is controlled to move upward by a second preset distance.

[0205] Optionally, the determining module 1402 is also used for:

[0206] The first preset distance or the second preset distance is determined based on the magnification of the camera component.

[0207] The visual acquisition device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0208] The components of the visual acquisition system are described below.

[0209] Processor 220 can be used to process data and / or information from at least one component of application scenario 100 or an external data source (e.g., a cloud data center). Processor 220 can be connected to storage device 130, vision acquisition system 200, and / or terminal device 150 via signal transmission device 120 to access and / or receive data and information. For example, processor 220 can receive relevant information output by vision acquisition system 200 (e.g., object distance between the camera component of vision acquisition system 200 and the object, initial image obtained from the observed object, etc.) via signal transmission device 120. In other embodiments, processor 220 can send parameters related to adjusting vision acquisition system 200 (e.g., the distance between the first axis of the first camera and the second axis of the second camera of vision acquisition system 200, the angle between the optical path of the first camera and the plane of symmetry of the two cameras, and the angle between the optical path of the second camera and the plane of symmetry of the two cameras, etc.) to terminal device 150 via signal transmission device 120.

[0210] In some embodiments, processor 220 may include one or more processing engines (e.g., a single-chip processing engine or a multi-chip processing engine). By way of example only, processor 220 may include a central processing unit (CPU). Processor 220 may process data, information and / or processing results obtained from other devices or system components, and execute program instructions based on such data, information and / or processing results to perform one or more functions described in this specification.

[0211] Signal transmission device 120 can connect various components of application scenario 100 (e.g., storage device 130, vision acquisition system 200, terminal device 150, etc.) and / or connect application scenario 100 to external resources. Signal transmission device 120 enables communication between the components and with other parts outside application scenario 100, facilitating the exchange of data and / or information. In some embodiments, storage device 130 can be connected to signal transmission device 120 to communicate with one or more components of application scenario 100 (e.g., processor 220, vision acquisition system 200, terminal device 150). In some embodiments, signal transmission device 120 may also include a network. In some embodiments, the network may include a local area network (LAN), a wide area network (WAN), a wired network, a wireless network, etc. Figure 1 The signal transmission device 120, which includes a network, is illustrated by way of example only and does not constitute a limitation on the embodiments described herein. It will be understood that the signal transmission device 120 may transmit signals through other media. For example, the signal transmission device 120 may include a data transmission cable.

[0212] Storage device 130 can be used to store data and / or instructions. In some embodiments, storage device 130 can store data and / or instructions that processor 220 uses to execute or use in order to perform the exemplary methods described herein. For example, storage device 130 can store image information (e.g., an initial image of an object, etc.) output by vision acquisition system 200.

[0213] In some embodiments, storage device 130 may be part of processor 220. In some embodiments, storage device 130 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), etc. In some embodiments, storage device 130 may be implemented on a cloud platform. In some embodiments, storage device 130 may be connected to signal transmission device 120 to communicate with one or more components of application scenario 100 (e.g., processor 220, vision acquisition system 200, terminal device 150).

[0214] In some embodiments, the visual acquisition system 200 can be used to perform stereoscopic imaging of an observed object to output a stereoscopic image of the object. In some embodiments, the visual acquisition system 200 may include a camera assembly, which may include a first camera and a second camera. The first camera and the second camera respectively observe and image the object, forming a first image and a second image of the object, respectively, wherein the first image and the second image are the initial images of the object. In some embodiments, the processor 220 may be part of the visual acquisition system 200. After the processor 220 processes the first image and the second image, the visual acquisition system 200 can output a stereoscopic image of the object.

[0215] Terminal device 150 may include one or more terminal devices or software. In some embodiments, terminal device 150 may include a mobile phone, tablet computer, laptop computer, VR glasses, 2D display, 3D display, etc. In some embodiments, a user can view information and / or input data and / or instructions through terminal device 150. In some embodiments, terminal device 150 may include a signal transmitter and a signal receiver, configured to communicate with visual acquisition system 200 to obtain relevant information about the observed object and image it.

[0216] In some embodiments, the terminal device 150 may be fixed and / or mobile. For example, the terminal device 150 may be directly mounted on the processor 220 and / or the vision acquisition system 200, becoming part of the processor 220 and / or the vision acquisition system 200. Alternatively, the terminal device 150 may be a mobile device, allowing an operator to carry it to a location relatively far from the processor 220 and the vision acquisition system 200. The terminal device 150 may connect to and / or communicate with the processor 220 and the vision acquisition system 200 via the signal transmission device 120.

[0217] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A visual acquisition system, characterized in that, include: Motor, camera assembly, and springs; The camera assembly includes a first camera and a second camera, which are symmetrically arranged with respect to a symmetrical plane. The first camera is capable of rotating around a first axis, and the second camera is capable of rotating around a second axis. The first axis and the second axis are parallel and symmetrically arranged with respect to the symmetrical plane. The intersection of the optical paths of the first camera and the second camera is located on the symmetrical plane. The output shaft of the motor is driven by a worm gear, and a first worm wheel and a second worm wheel are driven by the two sides of the worm gear respectively. The shaft of the first worm wheel coincides with the first shaft, and the shaft of the second worm wheel coincides with the second shaft. The motor can drive the first camera and the second camera to rotate in opposite directions. The spring is connected to the first camera and the second camera respectively at its two ends along its elastic extension and contraction. The spring is used to eliminate the backlash between the worm and the first worm wheel when the first camera is at a preset angle, and to eliminate the backlash between the worm and the second worm wheel when the second camera is at a preset angle.

2. The visual acquisition system according to claim 1, characterized in that, The visual acquisition system also includes a mounting bracket; The motor and the camera assembly are mounted on the mounting bracket, and the mounting bracket is located between the motor and the camera assembly in a first horizontal direction.

3. The visual acquisition system according to claim 1, characterized in that, The visual acquisition system further includes: a first camera bracket, a second camera bracket, a first image sensor, and a second image sensor; The first camera and the first image sensor are both mounted on the first camera bracket. The first image sensor is optically connected to the first camera. The first image sensor is used to receive and convert the optical image signal acquired by the first camera and generate the corresponding first image electrical signal. The first camera bracket is connected to the first rotating shaft so that the first camera bracket drives the first camera to rotate around the first rotating shaft; The second camera and the second image sensor are both mounted on the first camera bracket. The second image sensor is optically connected to the second camera. The second image sensor is used to receive and convert the optical image signals acquired by the second camera and generate corresponding second image electrical signals. The second camera bracket is connected to the second pivot, so that the second camera bracket drives the second camera to rotate around the second pivot.

4. The visual acquisition system according to claim 3, characterized in that, The first rotating shaft includes a first external threaded section and a second external threaded section spaced apart in its axial direction, and a first adjusting nut and a second adjusting nut are respectively rotatably connected to the first external threaded section and the second external threaded section. The first connecting end of the first camera bracket is connected to the first rotating shaft through a limiting structure, so that the first camera bracket can slide along the axial direction of the first rotating shaft, but cannot rotate around the axial direction of the first rotating shaft. The first connecting end of the first camera bracket is located between the first adjusting nut and the second adjusting nut. The rotational movement of the first adjusting nut and the second adjusting nut can be converted into axial displacement along the first rotating shaft, and push the first camera bracket to produce a first micro displacement along the axial direction of the first rotating shaft.

5. The visual acquisition system according to claim 1, characterized in that, The first worm gear and the second worm gear are partially circular structures, and the maximum rotation angle of the partially circular structure is 15°.

6. The visual acquisition system according to claim 2, characterized in that, The visual acquisition system also includes a ranging mechanism; The ranging mechanism is horizontally mounted on the mounting bracket, and the ranging mechanism is used to measure the distance between the optical path exit point of the first camera and / or the second camera and the corresponding field of view center point; The measuring optical axis of the ranging mechanism is configured in a horizontal direction. An optical path deflection element is provided on the ranging mechanism. The optical path deflection element is fixedly installed at a preset angle relative to the horizontal direction. The optical path deflection element is used to change the direction of the measuring optical axis so that the direction of the measuring optical axis is vertically downward.

7. A visual acquisition method, characterized in that, Applied to the visual acquisition system according to any one of claims 1-6; the method includes: The object distances from the first camera and the second camera to the object carrier are obtained, and the object carrier is used to place the object to be detected; The target angle is determined based on the object distance and the distance between the first rotating axis and the second rotating axis; Adjust the first camera and the second camera to a preset angle; The motor controls the first camera and the second camera to rotate from the preset angle so that the angle between the light path of the first camera and the plane of symmetry and the angle between the light path of the second camera and the plane of symmetry are both equal to the target angle. A first image of the observed object is acquired through the first camera, and a second image of the observed object is acquired through the second camera. A stereoscopic image is then output based on the first image and the second image.

8. The method according to claim 7, characterized in that, The method further includes: Determine the new object distance after the first camera and the second camera are rotated; A new target angle is determined based on the new object distance and the distance between the first rotating axis and the second rotating axis; Control the first camera and the second camera to adjust to the preset angle; The motor controls the first camera and the second camera to rotate from a preset angle so that the angle between the light path of the first camera and the plane of symmetry, and the angle between the light path of the second camera and the plane of symmetry, are both equal to the new target angle.

9. The method according to claim 8, characterized in that, Before controlling the first camera and the second camera to adjust to the preset angle, the method further includes: Determine the difference between the new target angle and the original target angle; Determine whether the difference is greater than a preset difference threshold; If the difference is less than the preset difference threshold, then there is no need to adjust the angles of the first camera and the second camera.

10. The method according to claim 9, characterized in that, The method further includes: Obtain the magnification of the camera component; The preset difference threshold is determined based on the magnification factor.

11. The method according to claim 7, characterized in that, The method further includes: Determine whether the included angle of the target is within the preset volume view threshold range; If the target angle is not within the body view threshold range, then control the movement of the loading device; The target angle is recalculated based on the object distance after the movement until the target angle is within the body view threshold range.

12. The method according to claim 11, characterized in that, The control of the movement of the loading device includes: If the included angle of the target is greater than the upper limit of the body view threshold range, then control the loading device to move downward by a first preset distance; If the target angle is less than the lower limit of the body view threshold range, then control the loading device to move upward by a second preset distance.

13. The method according to claim 12, characterized in that, The method further includes: The first preset distance or the second preset distance is determined based on the magnification of the first camera and the second camera.

Images