System for automatically adjusting an upright detector assembly

Abstract

The utility model provides a kind of system of automatically adjusting standing position detector component, comprising: data processing and control equipment and the visual acquisition equipment, interactive control terminal and chest radiographing equipment connected with data processing and control equipment, and interactive control terminal and chest radiographing equipment are connected by wired or wireless;Chest radiographing equipment includes: height adjusting device, standing position detector component and wireless receiver mounted on height adjusting device;Wireless controller is integrated on data processing and control equipment, and wireless controller sends control signal to wireless receiver.The utility model solves the technical problems, such as low work efficiency and unstable image quality, caused by manual adjustment of standing position detector component height by medical staff in the process of digital X-ray radiography examination, and the system of automatically adjusting standing position detector component provided by the utility model can automatically adjust standing position detector component following the height of patient.

Description

Technical Field

[0001] This utility model relates to the field of mechanics, and in particular to a system for automatically adjusting a standing position detector assembly. Background Technology

[0002] During digital radiography (DR) examinations, patients need to stand in front of the upright positioning detector assembly, whose height is manually adjusted by medical staff to align with the patient's anatomical target area (such as the lung field). However, this traditional adjustment method has the following problems:

[0003] Reliance on manual adjustment leads to a heavy workload: Medical staff need to manually adjust the height of the position detector component based on experience, which is highly repeatable and complex, increasing their workload.

[0004] Human error affects image quality: Different medical staff have different operating habits, and the adjustment accuracy is affected by subjective factors, which may lead to unstable image quality and affect clinical diagnosis;

[0005] Traditional measurement methods have low accuracy: height measuring rulers or visual estimation methods cannot adapt to the different standing postures of different patients, which may lead to alignment deviations and affect the shooting results. Utility Model Content

[0006] Based on the above problems, this utility model proposes a system for automatically adjusting the height of the standing detector assembly. This utility model solves the technical problems of low work efficiency and unstable image quality caused by medical staff manually adjusting the height of the standing detector assembly during digital X-ray imaging examinations. The system for automatically adjusting the standing detector assembly provided by this utility model enables the standing detector assembly to automatically adjust according to the patient's height.

[0007] This utility model proposes a system for automatically adjusting a standing position detector assembly, comprising:

[0008] The data processing and control equipment, as well as the visual acquisition equipment, interactive control terminal, and chest X-ray imaging equipment connected to the data processing and control equipment, wherein the interactive control terminal and chest X-ray imaging equipment are connected by wired or wireless means.

[0009] The chest X-ray equipment includes: a height adjustment device, a standing detector assembly mounted on the height adjustment device, and a wireless receiver;

[0010] The data processing and control equipment integrates a wireless controller, which sends control signals to the wireless receiver.

[0011] In addition, laser rangefinders or ultrasonic sensors are installed above or on the ceiling outside the visual acquisition equipment.

[0012] In addition, the height adjustment device is equipped with an encoder or pressure sensor.

[0013] In addition, the installation height of the visual acquisition device is greater than 2.3 meters and less than 2.5 meters, and the pitch angle range of the visual acquisition device is 35 degrees and 55 degrees at both ends.

[0014] In addition, the visual acquisition device includes: a mounting bracket, an angle adjustment mechanism, a housing, an RGB camera assembly, a depth camera assembly, and a data transmission interface;

[0015] One end of the angle adjustment mechanism is connected to the mounting bracket, and the other end is connected to the housing. The RGB camera assembly and the depth camera assembly are installed inside the housing, and the data transmission interface is located on the outside of the housing.

[0016] In addition, the visual acquisition device also includes heat dissipation holes and indicator lights located inside the housing.

[0017] In addition, the interactive control terminal includes: a display screen, a desktop stand, an operating console, and a speaker assembly;

[0018] A desktop stand is placed on the control panel, the display screen is placed on the desktop stand, the speaker assembly is located on the side of the display screen, and the desktop stand integrates a rotation adjustment device.

[0019] The display area of ​​the display screen body includes: the position detector component control system area and the control button area.

[0020] In addition, the position detector assembly control system area includes: a system status sub-area and a position detector assembly height control sub-area.

[0021] In addition, the control button area includes three buttons: Confirm, Cancel, and Emergency Stop.

[0022] This invention solves the technical problems of low work efficiency and unstable image quality caused by medical staff manually adjusting the height of the standing detector assembly during digital X-ray examination. The system that automatically adjusts the standing detector assembly provided by this invention enables the standing detector assembly to automatically adjust to the patient's height. Attached Figure Description

[0023] Figure 1 A schematic diagram of an automatic adjustment position detector assembly system provided in one embodiment of the present invention;

[0024] Figure 2 for Figure 1 A schematic diagram of a visual acquisition device;

[0025] Figure 3 for Figure 1A schematic diagram of the interactive control terminal;

[0026] Figure 4 for Figure 1 A schematic diagram of the interactive control terminal. Detailed Implementation

[0027] The present invention will be further described in detail below with reference to specific embodiments and accompanying drawings. This description is intended only to illustrate the specific embodiments of the present invention and does not constitute any limitation on the present invention. The scope of protection of the present invention is defined by the claims.

[0028] Reference Figure 1 This utility model proposes a system for automatically adjusting a standing position detector assembly, comprising:

[0029] The data processing and control device 1, the visual acquisition device 2, the interactive control terminal 3 and the chest X-ray imaging device 4 are all connected to the data processing and control device 1, and the interactive control terminal 3 and the chest X-ray imaging device 4 are connected by wired or wireless means.

[0030] Chest X-ray imaging device 4 includes: a height adjustment device 41, a standing detector assembly 42 mounted on the height adjustment device, and a wireless receiver 43;

[0031] The data processing and control device 1 integrates a wireless controller 11, which sends control signals to the wireless receiver 43.

[0032] Currently, some patented technologies involve the automated adjustment of the position detector assembly, for example:

[0033] CN208910288U: Intelligent adjustment of the standing position detector component is achieved by combining a weight sensor with a height / shoulder height sensor;

[0034] CN215349033U: Employs a servo motor-driven auxiliary device to improve the convenience and accuracy of chest X-ray imaging for children;

[0035] CN220309130U: Automatic height following is achieved through the linkage control of the vertical position detector assembly and the X-ray tube;

[0036] CN113576513B: Employs a postural correction device to optimize patient posture and improve image quality through elbow restraint.

[0037] However, the existing automated control schemes mentioned above still have some shortcomings:

[0038] Limitations of sensor applications: Some solutions, such as pressure sensors and ultrasonic ranging, adjust the standing detector components by detecting the height of the patient's head or shoulders when standing. However, these methods are prone to inaccurate positioning when the patient's posture changes or the measurement environment changes.

[0039] Strict requirements on patient posture: Although height detection schemes based on depth vision have made some improvements, they usually require patients to stand in a fixed position, making it difficult to adapt to different examination environments and posture changes.

[0040] Lack of real-time dynamic adjustment capability: Most existing solutions can only be adjusted once after the patient enters a specific position, and cannot be adjusted in real time according to changes in the patient's posture, resulting in insufficient flexibility;

[0041] Low system integration: Existing solutions often require the addition of multiple sensing devices, which increases system complexity and potential failure points, while lacking deep integration with DR equipment.

[0042] In this embodiment, the visual acquisition device 2 acquires an image of the patient in front of the positioning detector component and transmits the image information to the data processing and control device 1. The data processing and control device 1 identifies the height of the patient's chin and obtains the height of the positioning detector component. By comparing the height of the patient's chin with the current height of the positioning detector component, the data processing and control device 1 calculates the specific value at which the positioning detector component needs to be moved up or down. Then, the data processing and control device 1 sends a control command to the chest X-ray imaging device 4. The chest X-ray imaging device 4 automatically moves up or down by the specified value according to the control command, realizing the function of automatically adjusting the height of the positioning detector component according to the patient's height. Doctors and other users can adjust the angle of the visual acquisition device 2, observe the status of each device, and control the confirmation and stopping of imaging through buttons via the interactive control terminal 3.

[0043] The wireless receiver 43 is used to receive control commands sent by the wireless controller 11 of the data processing and control equipment 1. The wireless receiver 43 controls the height adjustment device 4 to adjust the height. Optionally, a drive device is installed on the height adjustment device 4 to adjust the height of the standing position detector assembly.

[0044] Optionally, the data processing and control device 1 can acquire the height of the position detector component in various ways. It can use an image transmitted from the vision acquisition device 2 to accurately acquire the height of the position detector component by recognizing its edge contour. Alternatively, the height of the position detector component can also be acquired by installing sensors or other methods.

[0045] In this embodiment, the data processing and control device 1 processes the following: using the image and depth data acquired by the visual acquisition device, it automatically captures and accurately locates the three-dimensional coordinates of the facial jaw feature points of the examinee through a visual recognition algorithm, without requiring the examinee to adopt a specific posture during the positioning process; based on a stereo matching algorithm of three-dimensional depth vision, it accurately calculates the spatial height parameters of the standing detector component's housing component in real time, with measurement accuracy reaching the millimeter level, providing position feedback for automatic adjustment; combining wired and wireless technologies, it is responsible for establishing a data channel between the data processing and control device and the visual acquisition device, and establishing a wireless communication channel between the data processing and control unit and the driving device of the standing detector component, realizing the transmission of control commands and feedback information, ensuring the coordinated work of all parts of the system, and guaranteeing the real-time and reliable data transmission; receiving facial feature point and standing detector component position information, calculating the optimal adjustment parameters, generating control commands, and transmitting them wirelessly to the standing detector component driving device to achieve precise alignment between the standing detector component and the patient's chest position;

[0046] The interactive control terminal 3 displays system test results and operation suggestions in real time, receives confirmation or modification instructions from medical staff, supports manual intervention mode, and meets special clinical needs.

[0047] This embodiment solves the technical problems of low work efficiency and unstable image quality caused by medical staff manually adjusting the height of the standing detector component during digital X-ray imaging examinations. The system for automatically adjusting the standing detector component provided in this embodiment enables the standing detector component to automatically adjust to the patient's height.

[0048] In one embodiment, a laser rangefinder or an ultrasonic sensor is mounted on the ceiling above or outside the visual acquisition device 2.

[0049] The height of the position detector assembly can be measured by installing a laser rangefinder or ultrasonic sensor above or on the ceiling outside the visual acquisition device.

[0050] The laser rangefinder works by emitting a laser beam onto the surface of a position detector assembly. The distance between the laser rangefinder and the position detector assembly is calculated by measuring the round-trip time of the laser beam, thus obtaining the height information of the position detector assembly. This method offers high accuracy and is less affected by ambient light.

[0051] The principle of ultrasonic sensor ranging: Utilizing the reflection principle of ultrasonic waves, an ultrasonic sensor installed in a suitable location emits ultrasonic waves towards the position detector assembly, then receives the reflected waves. The height of the position detector assembly is calculated based on the propagation time of the ultrasonic waves. Its advantages include relatively low cost and insensitivity to ambient light.

[0052] In one embodiment, an encoder or pressure sensor is mounted on the height adjustment device 4.

[0053] The height change of the position detector assembly is measured by an encoder or pressure sensor mounted on the height adjustment device 4.

[0054] For example, a rotary encoder rotates along with the transmission device when the position detector assembly is raised or lowered. By recording the encoder's rotation angle and number of revolutions, and combining this with parameters such as the transmission ratio of the transmission mechanism, the height change of the position detector assembly can be accurately calculated.

[0055] Pressure sensors are installed on the support legs of the position detector assembly or on key stress-bearing parts of the height adjustment device 4. When the height of the position detector assembly changes, the pressure on the pressure sensors changes. By establishing a correlation between pressure and height, the height change and current height of the position detector assembly can be indirectly obtained.

[0056] In one embodiment, the visual acquisition device 2 is installed at a height greater than 2.3 meters and less than 2.5 meters, and the pitch angle range of the visual acquisition device 2 is 35 degrees and 55 degrees at both ends.

[0057] By installing the visual acquisition device 2 at a height greater than 2.3 meters and less than 2.5 meters, and setting its pitch angle range to 35 degrees and 55 degrees at both ends, the images captured by the visual acquisition device 2 are made clearer.

[0058] Under normal circumstances, the settings are not adjusted after being preset, which is used to ensure that the three-dimensional coordinates of facial jaw feature points are obtained in real time and the standing detector components are adjusted synchronously during actual use.

[0059] Reference Figure 2 In one embodiment, the visual acquisition device 2 includes: a mounting bracket 21, an angle adjustment mechanism 22, a housing 23, an RGB camera assembly 24, a depth camera assembly 25, and a data transmission interface 26;

[0060] One end of the angle adjustment mechanism 22 is connected to the mounting bracket 21, and the other end is connected to the housing 23. The RGB camera assembly 24 and the depth camera assembly 25 are installed inside the housing 23, and the data transmission interface 26 is located on the outside of the housing 23.

[0061] Mounting bracket 21 is used to mount the entire visual acquisition device 2 on a fixed object such as the ceiling. Angle adjustment mechanism 22 is used to adjust the shooting angle of the visual acquisition device 2. The RGB camera assembly 24 and depth camera assembly 25 are used together to ensure that the details of the photographed object are clear. Data transmission interface 26 is used to transmit the captured image to data processing and control device 1. This embodiment can obtain images with clear details.

[0062] In one embodiment, the visual acquisition device 2 further includes: heat dissipation holes 27 and indicator lights 28 disposed inside the housing 23. The indicator lights 28 indicate whether the device is working properly, and the heat dissipation holes 27 allow the device to dissipate heat overall. A metal base 29 is also included.

[0063] Reference Figure 3 In one embodiment, the interactive control terminal 3 includes: a display screen body 31, a desktop stand 32, an operating console 33, and a speaker assembly 34;

[0064] A desktop stand 32 is placed on the control panel 33, the display screen body 31 is placed on the desktop stand 32, the speaker assembly 34 is located on the side of the display screen body 31, and the desktop stand 32 integrates a rotation adjustment device.

[0065] The display area of ​​the display screen body 31 includes: the position detector component control system area and the control button area.

[0066] The interactive control terminal 3 provides a clear and intuitive display of the equipment status for chest X-ray imaging.

[0067] The interactive control terminal 3 also includes: a connection interface area 35, a control button area 36, ​​an angle adjustment device 37 (optionally, the adjustment range is between 30 and 80 degrees) and an emergency stop button 38.

[0068] Figure 4 A more detailed illustration is shown below.

[0069] In one embodiment, the position detector assembly control system area includes a system status sub-area and a position detector assembly height control sub-area. Through the specifically configured system status sub-area and position detector assembly height control sub-area, the user can clearly view the equipment status.

[0070] In one embodiment, the control button area includes three buttons: Confirm, Cancel, and Emergency Stop. By providing this control button area, users can control the chest X-ray process, ensuring operational safety. A manual intervention mode allows doctors to adjust or pause the automatic adjustment process as needed.

[0071] Optionally, the wireless communication in the above embodiments uses the 2.4GHz frequency band, which has anti-interference capability and can realize the transmission of wireless data between the wireless receiver 43 and the wireless controller 11 of the receiving data processing and control device 1.

[0072] Optionally, the data processing and control device 1, as the core hardware of the system, is composed of a high-performance processor and a dedicated computing chip, responsible for receiving the data stream from the visual acquisition device 2 and processing it in real time. This hardware unit is equipped with a high-speed cache and data processing circuitry to provide the computing resources required for algorithm execution, while also incorporating self-diagnostic and monitoring circuitry to ensure stable system operation.

[0073] Optionally, the data processing and control equipment is fixed to the wall of the DR examination room via a wall-mounted bracket. Specifically, the data processing and control equipment 1 identifies the height of the patient's mandible by recognizing the image information as follows:

[0074] In step 1, a face image is acquired and the face bounding box is extracted. The two-dimensional coordinates of the jaw feature points are then extracted from the face bounding box.

[0075] The process of acquiring a face image and extracting the face bounding box is as follows:

[0076] There are multiple methods for image edge detection. For example, the Canny operator can be used to extract facial contours and then generate bounding boxes. Typically, a set of values ​​is used to represent the position and extent of the face in the image.

[0077] For example, the coordinate representation of the top left corner + bottom right corner is (xmin, ymin, xmax, ymax). Example: (100, 150, 300, 400) means that the left boundary is in column 100, the top boundary is in row 150, the right boundary is in column 300, and the bottom boundary is in row 400.

[0078] The representation of center point + width and height (x_center, y_center, width, height) is as follows:

[0079] The rectangle is represented by its center coordinates (x_center, y_center) plus its width and height. Example: (200, 275, 200, 250) means the center point is at (200, 275), the width is 200 pixels, and the height is 250 pixels.

[0080] Normalization can be performed subsequently.

[0081] The two-dimensional coordinates of the jaw feature points extracted from the face bounding box are as follows:

[0082] Extracting key points of the mandible involves selecting points related to the mandible (such as the mandibular apex and mandibular line points) from a list of key points. For example, in a 68-point model, the key points of the mandibular region are points 17-26 (a total of 10 points, arranged from left to right / clockwise along the mandibular line). Among them: point 17: the starting point of the left mandible (the leftmost end of the mandibular line), point 26: the starting point of the right mandible (the rightmost end of the mandibular line), and point 24: the mandibular apex (the lowest point of the mandibular line, the point with the largest y-coordinate). The coordinate format is: each point is a pixel coordinate (x, y), for example, the coordinates of point 24 are (x24, y24).

[0083] Alternatively, you can choose a lightweight model to output 5 points, 10 points, or only the mandibular tip (or mandibular midpoint), for example, the 5th point is the midpoint of the mandibular base (x_center, y_bottom).

[0084] The process of extracting key points of the mandible can be quickly implemented by directly calling mature image processing libraries (such as Dlib and OpenCV) without the need for manual coordinate calculation.

[0085] Facial images can be acquired using an RGB camera.

[0086] In step 2, a subset of the face region point cloud is obtained from the face point cloud image;

[0087] Face point cloud images can be acquired using a depth point cloud camera. A 3D search space is constructed based on the center of the face bounding box, and points that meet the selection criteria constitute a subset of the face region point cloud.

[0088] The specific steps are as follows: traverse each point (x, y, z) in the original point cloud (face bounding box), retaining points that meet preset conditions to form a subset of the face region point cloud. The process of transforming the original data into a point cloud subset is essentially a process of filtering out useful points, keeping only the necessary ones. Therefore, the input data is the original image data, and the output data is the filtered image data.

[0089] In step 3, a spatial ray equation is constructed based on the two-dimensional coordinates of the mandibular feature points and the intrinsic parameters of the camera device that captures the face image;

[0090] Input the two-dimensional coordinates of the mandibular feature points, and normalize the two-dimensional coordinates using the intrinsic parameters of the camera device;

[0091] Determine the ray direction vector;

[0092] The spatial ray equation is constructed based on the normalized two-dimensional coordinates and the ray direction vector, where the ray direction vector is:

[0093]

[0094] Where K is the intrinsic parameter of the camera device, xc y c Two-dimensional coordinate points;

[0095] The equation of space ray is

[0096]

[0097] Where t represents the distance the ray extends along the direction of the ray direction vector after being triggered by the optical center.

[0098] The spatial ray equation represents a three-dimensional ray that originates from the optical center of the camera and passes through a point on the image plane. The ray direction vector points from the optical center to the unit vector of the target point on the image plane.

[0099] The two-dimensional coordinate points are converted into normalized coordinates in the camera coordinate system using the camera intrinsic parameter matrix K.

[0100] In the camera coordinate system, the ray originates from the optical center (0,0,0) and passes through the normalized coordinate point (x,y,1), therefore the direction vector is:

[0101]

[0102] Substituting the starting point (0,0,0) and the direction vector, we obtain the equation of the space ray as follows:

[0103]

[0104] In step 4, the point closest to the ray represented by the spatial ray equation is found from the face region point cloud subset and used as the three-dimensional coordinate point of the mandibular feature point;

[0105] The calculation formula is:

[0106]

[0107] Where o is the origin of the camera coordinate system, Let P be the three-dimensional coordinate point of the mandibular feature point, and P be the nearest point.

[0108] In step 5, the three-dimensional coordinates of at least three mandibular feature points are fitted to the ground plane equation;

[0109] The least squares method was used to fit the ground plane equation Ax + By + Cz + D = 0;

[0110] Where A, B, C, and D are the plane parameters to be determined;

[0111] Input the three-dimensional coordinates of the mandibular feature points into the ground plane equation and solve for the optimal plane parameters.

[0112] When solving for the optimal plane parameters, singular value decomposition (SVD) and normal equation formulas can be used.

[0113] For example, the process of solving using the normal equation formula is as follows:

[0114]

[0115] Solution:

[0116] At this point, C is the negative of the coefficient of Z.

[0117] M is the design matrix, Z is the observation vector, and M... T It is the transpose of M, (M T M) - 1 is matrix M T The inverse of M.

[0118] The SVD solution method involves decomposing the original matrix M and utilizing its pseudoinverse M. + We can directly calculate the solution. Both methods are mature algorithms and will not be elaborated upon here.

[0119] In step 6, the three-dimensional coordinates of the mandibular feature points are transformed from the camera coordinate system to the world coordinate system with reference to the ground plane equation, and the distance from the mandible to the ground is calculated using the three-dimensional coordinates of the mandibular feature points in the world coordinate system.

[0120] The formula for transforming the three-dimensional coordinates of the mandibular feature points from the camera coordinate system to the world coordinate system, which references the ground plane equation, is as follows:

[0121]

[0122] in, For three-dimensional coordinate points in the world coordinate system, Let R be the three-dimensional coordinate point in the camera coordinate system, T be the rotation matrix, and T be the translation vector. R and T are determined by the equation of the ground plane.

[0123] The formula for calculating the distance d from the mandible to the ground using the three-dimensional coordinates of mandibular feature points in the world coordinate system is as follows:

[0124]

[0125] Where, x w y w , z w The coordinates of the mandible are in the three-dimensional coordinates of the world coordinate system.

[0126] The shooting device in this invention is an integration of an RGB camera and a point cloud depth camera.

[0127] In one embodiment, obtaining a subset of the face region point cloud from the face point cloud image includes:

[0128] A 3D search space is constructed based on the center of the face bounding box, and points that meet the filtering criteria constitute a subset of the face region point cloud.

[0129] By creating a subset of the face region point cloud, the amount of data to be processed is reduced, thereby increasing the processing speed.

[0130] In one embodiment, constructing the spatial ray equation based on the two-dimensional coordinates of the mandibular feature points and the intrinsic parameters of the camera device capturing the face image includes:

[0131] Input the two-dimensional coordinates of the mandibular feature points, and normalize the two-dimensional coordinates using the intrinsic parameters of the camera device;

[0132] Determine the ray direction vector;

[0133] The spatial ray equation is constructed based on the normalized two-dimensional coordinates and the ray direction vector, where the ray direction vector is:

[0134]

[0135] Where K is the intrinsic parameter of the camera device, x c y c Two-dimensional coordinate points;

[0136] The equation of space ray is

[0137]

[0138] Where t represents the distance the ray extends along the direction of the ray direction vector after being triggered by the optical center.

[0139] By constructing spatial ray equations, we can prepare for finding the three-dimensional coordinates of mandibular feature points.

[0140] In one embodiment, finding the point closest to the ray represented by the spatial ray equation from the subset of face region point clouds as the three-dimensional coordinate point of the mandibular feature point includes:

[0141] The calculation formula is:

[0142]

[0143] Where o is the origin of the camera coordinate system, Let P be the three-dimensional coordinate point of the mandibular feature point, and P be the nearest point.

[0144] By finding the three-dimensional coordinates of the mandibular feature points, input data is prepared for fitting the ground plane equation.

[0145] In one embodiment, obtaining the three-dimensional coordinates of at least three mandibular feature points and fitting the ground plane equation includes:

[0146] The least squares method was used to fit the ground plane equation Ax + By + Cz + D = 0;

[0147] Where A, B, C, and D are the plane parameters to be determined;

[0148] Input the three-dimensional coordinates of the mandibular feature points into the ground plane equation and solve for the optimal plane parameters.

[0149] When solving for the optimal plane parameters, singular value decomposition (SVD) and normal equation formulas can be used.

[0150] For example, the process of solving using the normal equation formula is as follows:

[0151]

[0152] Solution:

[0153] At this point, C is the negative of the coefficient of Z.

[0154] M is the design matrix, Z is the observation vector, M T It is the transpose of M, (M T M) - 1 is matrix M T The inverse of M.

[0155] The SVD solution method involves decomposing the original matrix M and utilizing its pseudoinverse M. + We can directly calculate the solution. Both methods are mature algorithms and will not be elaborated upon here.

[0156] In one embodiment, a reference measurement H is introduced. ref To make the fitted ground plane equation consistent with the actual ground, H ref For the actual measured distance from the mandibular point to the ground, the planar parameters must meet the following conditions:

[0157]

[0158] Among them, X ref Y ref Z ref These are the three-dimensional coordinate points of the mandible being measured.

[0159] To accurately determine the ground position, an additional baseline measurement value obtained by conventional measurement methods (such as a handheld laser rangefinder) is required. This baseline measurement value is the actual distance H from the tester's chin point to the ground while maintaining a level gaze.ref via H ref The introduction of this makes the fitted ground plane equation consistent with the actual ground.

[0160] By incorporating the fitted ground plane equation and actual measurement data, the plane parameters are optimized and adjusted to ensure that the fitted ground plane is consistent with the actual ground height, thus obtaining the accurate plane parameters of the ground plane equation.

[0161] In one embodiment, the step of transforming the three-dimensional coordinates of the mandibular feature points from the camera coordinate system to a world coordinate system referenced by the ground plane equation, and calculating the distance from the mandible to the ground using the three-dimensional coordinates of the mandibular feature points in the world coordinate system, includes:

[0162] The formula for transforming the three-dimensional coordinates of the mandibular feature points from the camera coordinate system to the world coordinate system, which references the ground plane equation, is as follows:

[0163]

[0164] in, For three-dimensional coordinate points in the world coordinate system, Let R be the three-dimensional coordinate point in the camera coordinate system, T be the rotation matrix, and T be the translation vector. R and T are determined by the equation of the ground plane.

[0165] The formula for calculating the distance d from the mandible to the ground using the three-dimensional coordinates of mandibular feature points in the world coordinate system is as follows:

[0166]

[0167] Where, x w y w , z w The coordinates of the mandible are in the three-dimensional coordinates of the world coordinate system.

[0168] The calculated distance d from the mandible to the ground can help physicians efficiently adjust the height of the standing detector assembly. Alternatively, the height of the standing detector assembly can be precisely adjusted using an automatic height adjustment method, thereby improving the image quality of DR.

[0169] The technical solution proposed in this embodiment can achieve three-dimensional spatial positioning of the mandible in real time without the patient's need for additional actions, which significantly improves the quality of DR chest X-ray images, reduces patient discomfort, and helps improve the efficiency and accuracy of medical diagnosis.

[0170] The method for calculating the distance from the mandibular feature point to the ground provided in this embodiment is as follows in practical applications:

[0171] I. Preliminary Deployment

[0172] 1. At a certain angle to the standing detector assembly and near the ceiling in the DR inspection room, install vision equipment: an RGB camera and a point cloud depth camera. The orientation of both devices should be aligned with the position of the standing detector assembly where the person being inspected will ultimately be captured. This equipment will be used to acquire real-time RGB images and depth point cloud images of the person being inspected. The field of view of the vision equipment should cover the front or side of the person's face within a certain range to facilitate effective localization by the facial recognition algorithm.

[0173] 2. Relevant operators (non-specific) enter the field of view of the vision device and sequentially collect facial jaw feature points {P} from multiple non-collinear locations. chin,i3D At least 3 points are required; collecting more points, such as 5 to 7, will further improve accuracy. In this case, the coordinate system of the 3D feature point set is the coordinate system of the visual device.

[0174] 3. Personnel, while maintaining eye level, should use other high-precision distance measuring devices, such as a handheld laser rangefinder, to measure the height H of the chin from the ground. ref .

[0175] 4. After obtaining an effective set of feature points for plane fitting and the height of facial features relative to the ground, the plane geometry parameters of the plane containing the ground are obtained using the fitted ground plane equation. Using this plane as a reference, the transformation from the visual device coordinate system (camera coordinate system) to the indoor world coordinate system is completed.

[0176] 5. After completing the initial deployment and coordinate system transformation, the invention enters the real-time usage phase. When the patient stands in front of the positioning detector component to prepare for DR image capture, the system automatically starts the RGB camera and point cloud depth camera in real time to acquire the patient's RGB image and depth point cloud data. Subsequently, the system automatically performs the following real-time positioning process:

[0177] (1) Detect the patient's face region in RGB images in real time and locate the two-dimensional coordinates of the mandibular feature points;

[0178] (2) Using the calibrated camera intrinsic parameter model, the spatial ray equation is calculated through the two-dimensional position of the mandible to determine the three-dimensional coordinates of the mandible in the camera coordinate system;

[0179] (3) The three-dimensional coordinates of the mandible obtained above are converted in real time to the previously determined indoor world coordinate system;

[0180] (4) The actual vertical distance (height) from the patient's chin to the ground is calculated in real time and displayed intuitively on the operation interface. This allows doctors or automated adjustment devices to quickly and accurately adjust the height of the standing detector component or guide the patient to adjust their posture based on the real-time feedback information, ultimately achieving the best DR image capture quality and significantly improving shooting efficiency and patient comfort.

[0181] The above real-time process requires no additional cooperation or action from the patient, operates completely imperceptibly, and will not cause interference or additional discomfort to the patient, thus having good clinical applicability and user experience advantages.

Claims

1. A system for automatically adjusting a standing position detector assembly, characterized in that, include: The data processing and control equipment, as well as the visual acquisition equipment, interactive control terminal, and chest X-ray imaging equipment connected to the data processing and control equipment, wherein the interactive control terminal and chest X-ray imaging equipment are connected by wired or wireless means. The chest X-ray equipment includes: a height adjustment device, a standing detector assembly mounted on the height adjustment device, and a wireless receiver; The data processing and control equipment integrates a wireless controller, which sends control signals to the wireless receiver.

2. The system for automatically adjusting a standing position detector assembly according to claim 1, characterized in that, Laser rangefinders or ultrasonic sensors are installed above or on the ceiling outside the visual acquisition equipment.

3. The system for automatically adjusting a standing position detector assembly according to claim 1, characterized in that, The height adjustment device is equipped with an encoder or pressure sensor.

4. The system for automatically adjusting a standing position detector assembly according to claim 1, characterized in that, The installation height of the visual acquisition device is greater than 2.3 meters and less than 2.5 meters, and the pitch angle range of the visual acquisition device is 35 degrees and 55 degrees at both ends.

5. The system for automatically adjusting a standing position detector assembly according to claim 1, characterized in that, The visual acquisition device includes: a mounting bracket, an angle adjustment mechanism, a housing, an RGB camera assembly, a depth camera assembly, and a data transmission interface; One end of the angle adjustment mechanism is connected to the mounting bracket, and the other end is connected to the housing. The RGB camera assembly and the depth camera assembly are installed inside the housing, and the data transmission interface is located on the outside of the housing.

6. The system for automatically adjusting a standing position detector assembly according to claim 5, characterized in that, The visual acquisition device also includes: heat dissipation holes and indicator lights located inside the housing.

7. A system for automatically adjusting a standing position detector assembly according to any one of claims 1-6, characterized in that, The interactive control terminal includes: a display screen, a desktop stand, a control panel, and a speaker assembly; A desktop stand is placed on the control panel, the display screen is placed on the desktop stand, the speaker assembly is located on the side of the display screen, and the desktop stand integrates a rotation adjustment device. The display area of ​​the display screen body includes: the position detector component control system area and the control button area.

8. The system for automatically adjusting a standing position detector assembly according to claim 7, characterized in that, The position detector assembly control system area includes: a system status sub-area and a position detector assembly height control sub-area.

9. The system for automatically adjusting a standing position detector assembly according to claim 7, characterized in that, The control button area includes three buttons: Confirm, Cancel, and Emergency Stop.

Images