Scanning method and system, storage medium, self-scanning system
By identifying the direction of facial tilt in CT scan patients and adjusting the scanning equipment or image angle, the problem of tilted scan images caused by patients' inability to straighten their heads was solved, and the acquisition of orthogonal scan images without radiation assistance was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NEUSOFT MEDICAL SYST CO LTD
- Filing Date
- 2023-01-13
- Publication Date
- 2026-06-26
AI Technical Summary
In current CT scan technology, patients cannot straighten their heads, resulting in tilted scan images and the inability to obtain an orthogonal image. Family members need to help straighten the patient's head, leading to unnecessary radiation exposure.
By acquiring facial images of the target object, identifying the facial tilt direction category, and adjusting the scanning device or image angle to output an orthogonal scan image, including processing of pitch and yaw tilt direction categories.
It enables the acquisition of orthogonal scan images without the assistance of family members, thus avoiding unnecessary radiation harm to family members.
Smart Images
Figure CN116215258B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent medical technology, and in particular to a scanning method and system, storage medium, and self-service scanning system. Background Technology
[0002] In modern medical technology, CT (Computed Tomography) is widely used in disease examinations and health checkups due to its advantages such as short scanning time and clear images.
[0003] Currently, before a CT scan, the operating physician usually needs to confirm the patient's posture. For example, a head scan requires the head to be upright. When a patient has a condition that prevents the head from being upright, the doctor can only ask a family member to accompany the patient and help straighten the head as much as possible. However, even so, in many cases, the patient still enters the scanning process with their head tilted, resulting in a tilted image. This not only fails to obtain an orthogonal image but also exposes the family member to unnecessary radiation. Therefore, there is an urgent need for a scanning method to solve these problems. Summary of the Invention
[0004] In view of this, this application provides a scanning method and system, a storage medium, and a self-service scanning system, the main purpose of which is to improve the existing technical problem that the patient cannot obtain a positive scanning image because the patient cannot straighten his head.
[0005] According to one aspect of this application, a scanning method is provided, comprising:
[0006] Acquire the facial image of the target object being scanned;
[0007] Based on the facial image, the tilt direction category of the face is obtained, and the tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category;
[0008] Based on the tilt direction category, the corresponding processing method is adopted for processing.
[0009] Preferably, if the tilt direction category matches the pitch tilt direction category, the scanning device is adjusted according to the facial tilt angle to perform tilt scanning, or the reconstruction angle of the image to be reconstructed is obtained according to the facial tilt angle, and the reconstructed image is obtained based on the reconstruction angle.
[0010] Preferably, the method further includes:
[0011] If the tilt direction category matches the yaw tilt direction category, the facial angle of the target object in the scanned image is adjusted according to the facial tilt angle so that the output scanned image is an orthogonal scanned image.
[0012] Preferably, the method further includes:
[0013] Multiple parts of the target scanned object are selected as body positioning points;
[0014] Obtain an initial overall image of the target scanning object, mark the initial positions of each body positioning point in the initial overall image, and generate a reference image;
[0015] Determine whether the target object has shifted position during the scanning process based on the reference image;
[0016] If so, an alarm message will be output, and the scan termination thread will be triggered.
[0017] Preferably, determining whether the target object has shifted position during the scanning process based on the reference image specifically includes:
[0018] Acquire a real-time overall image of the target scanning object, and mark the real-time positions of each body positioning point in the real-time overall image;
[0019] Determine the offset between the real-time position of each body positioning point and the initial position of each body positioning point in the reference image;
[0020] If the offset exceeds a preset offset threshold, it is determined that the target object has shifted its position during the scanning process.
[0021] Preferably, obtaining the facial tilt direction category based on the facial image specifically includes:
[0022] Based on the facial image, the location information of multiple facial positioning points is identified;
[0023] The multiple location information is mapped onto a pre-established three-dimensional facial model;
[0024] Based on the three-dimensional facial model obtained after mapping, the facial rotation vector of the target scanning object is determined;
[0025] The facial rotation vector is converted into a facial rotation matrix, and the facial tilt direction and facial tilt angle are determined based on the facial rotation matrix.
[0026] Based on the facial tilt direction and the facial tilt angle, the type of facial tilt direction is determined.
[0027] Preferably, the method further includes:
[0028] If the tilt direction category does not match the pitch tilt direction category, then the scanning standard motion information is output to prompt the target scanning object to adjust its facial positioning according to the scanning standard motion information;
[0029] In response to the instruction that the positioning adjustment is complete, the updated facial image of the target scanning object after the facial positioning adjustment is reacquired, and the facial tilt direction and facial tilt angle are re-determined based on the updated facial tilt image, so as to perform scanning based on the updated facial tilt direction and facial tilt angle.
[0030] According to another aspect of this application, a scanning system is provided, comprising:
[0031] The acquisition module is used to acquire facial images of the target scanned object;
[0032] The determination module is used to obtain the tilt direction category of the face based on the facial image, wherein the tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category;
[0033] The processing module is used to process the object based on the tilt direction category using the corresponding processing method.
[0034] Preferably, if the tilt direction category matches the pitch tilt direction category, the scanning device is adjusted according to the facial tilt angle to perform tilt scanning, or the reconstruction angle of the image to be reconstructed is obtained according to the facial tilt angle, and the reconstructed image is obtained based on the reconstruction angle.
[0035] Preferably, the system further includes:
[0036] An adjustment module is used to adjust the facial angle of the target object in the scanned image according to the facial tilt angle if the tilt direction category matches the yaw tilt direction category, so that the output scanned image is an orthogonal scanned image.
[0037] Preferably, the system further includes:
[0038] The selection module is used to select multiple parts on the target scanned object as body positioning points;
[0039] The marking module is used to acquire an initial overall image of the target scanning object, mark the initial positions of each body positioning point in the initial overall image, and generate a reference image;
[0040] The judgment module is used to determine whether the target scanned object has undergone positional shift during the scanning process based on the reference image;
[0041] The termination module is used to output an alarm message and trigger the scan termination thread if the condition is met.
[0042] Preferably, the judgment module specifically includes:
[0043] A marking unit is used to acquire a real-time overall image of the target scanning object and mark the real-time position of each body positioning point in the real-time overall image;
[0044] The first determining unit is used to determine the offset between the real-time position of each body positioning point and the initial position of each body positioning point in the reference image.
[0045] The first judgment unit is used to determine that the target scanning object has shifted its position during the scanning process if the offset exceeds a preset offset threshold.
[0046] Preferably, the determining module specifically includes:
[0047] The recognition unit is used to recognize the location information of multiple facial positioning points based on the facial image;
[0048] A mapping unit is used to map the multiple location information onto a pre-established three-dimensional facial model;
[0049] The second determining unit is used to determine the facial rotation vector of the target scanning object based on the three-dimensional facial model obtained after mapping.
[0050] A conversion unit is used to convert the facial rotation vector into a facial rotation matrix, and determine the facial tilt direction and facial tilt angle based on the facial rotation matrix;
[0051] The second judgment unit is used to determine the type of facial tilt direction based on the facial tilt direction and the facial tilt angle.
[0052] Preferably, the system further includes:
[0053] The output module is used to output scanning standard motion information if the tilt direction category does not conform to the pitch tilt direction category, so as to prompt the target scanning object to adjust the facial positioning according to the scanning standard motion information;
[0054] The update module is used to respond to the instruction that the positioning adjustment is completed, re-acquire the updated facial image of the target scanning object after the facial positioning adjustment, and redetermine the facial tilt direction and facial tilt angle based on the updated facial image, so as to perform scanning based on the updated facial tilt direction and facial tilt angle.
[0055] According to another aspect of this application, a storage medium is provided that stores at least one executable instruction, which causes a processor to perform an operation corresponding to the scanning method described above.
[0056] According to another aspect of this application, a self-service scanning system is provided, comprising: a camera device disposed in a detection chamber for acquiring a facial image of a target object to be scanned; a control console connected to the camera device for receiving the facial image of the target object to be scanned, and acquiring a tilt direction category of the face based on the facial image, the tilt direction category including at least one of a pitch tilt direction category and a yaw tilt direction category, and processing the face based on the tilt direction category using a corresponding processing method; and an alarm device disposed in the detection chamber and connected to the control console for receiving alarm signals and issuing alarm information.
[0057] By employing the above technical solutions, the technical solutions provided in the embodiments of this application have at least the following advantages:
[0058] This application provides a scanning method, system, storage medium, and self-service scanning system. First, a facial image of the target object is acquired. Second, based on the facial image, the tilt direction category of the face is obtained, whereby the tilt direction category includes at least one of pitch tilt direction and yaw tilt direction. Finally, based on the tilt direction category, a corresponding processing method is applied for processing. Compared with existing technologies, this application's embodiments determine the facial tilt direction and angle of the target object based on its facial image, and adjust the scanning device and / or the facial angle of the target object in the scanned image according to the tilt direction category to output an orthogonal scan image. This overcomes the technical problem of not being able to obtain an orthogonal scan image because the patient cannot straighten their head. Furthermore, since no family member is required to assist in straightening the patient's head, unnecessary radiation exposure to family members is avoided.
[0059] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description
[0060] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:
[0061] Figure 1 A flowchart of a scanning method provided in an embodiment of this application is shown;
[0062] Figure 2This application provides a diagram showing the location of the camera device according to an embodiment.
[0063] Figure 3 A schematic diagram of the tilt direction categories provided in the embodiments of this application is shown;
[0064] Figure 4 A flowchart of another scanning method provided in an embodiment of this application is shown;
[0065] Figure 5 A flowchart of another scanning method provided in an embodiment of this application is shown;
[0066] Figure 6 This application provides a schematic diagram of body positioning points according to an embodiment.
[0067] Figure 7 This illustration shows a block diagram of a scanning system provided in an embodiment of this application;
[0068] Figure 8 A schematic diagram of the structure of a self-service scanning system provided in an embodiment of this application is shown. Detailed Implementation
[0069] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
[0070] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.
[0071] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.
[0072] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0073] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0074] The embodiments of this application can be applied to computer systems / servers that can operate with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with computer systems / servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems, etc.
[0075] Computer systems / servers can be described in the general context of computer system executable instructions (such as program modules) executed by the computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are performed by remote processing devices linked through a communication network. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.
[0076] This application provides a scanning method, such as... Figure 1 As shown, the method includes:
[0077] 101. Obtain the facial image of the target object being scanned.
[0078] The target scanning object can be a patient to be scanned, and the scan can include a CT scan. In this embodiment, the current execution end can be the control system of the scanning room. When the target scanning object enters the preset scanning area (e.g., the scanning bed) and is positioned to begin scanning, a camera device positioned above the scanning equipment acquires a facial image of the target scanning object. For example, the camera device may be positioned as follows: Figure 2 As shown, the camera equipment is installed on the upper part of the scanning bed in the scanning inspection chamber (for example, on the top of the scanning chamber), and can capture most of the bed area, as well as the situation within the scanning aperture.
[0079] It should be noted that when performing a head scan on a target object, in order to ensure that the scan results are close to its actual situation, the target object usually needs to straighten its head. At this time, the direction of its face can be used to determine whether the head is straight.
[0080] 102. Based on facial images, obtain the tilt direction category of the face.
[0081] The tilt direction category includes at least one of pitch tilt direction and yaw tilt direction. In this embodiment, a preset algorithm can be used to perform facial pose estimation processing on a facial image to determine the tilt direction and tilt angle of the target scanned object's face, thereby determining the tilt direction category of the face. Typically, the tilt direction category can include pitch tilt direction, yaw tilt direction, and roll tilt direction, such as... Figure 3 As shown. However, in head scanning, due to the limitations of the headrest, tilting in the roll tilt direction category is usually not observed, so it does not need to be considered. Therefore, in the embodiments of this application, the tilt direction category includes at least one of the pitch tilt direction category and the yaw tilt direction category.
[0082] 103. Based on the tilt direction category, the corresponding processing method is adopted for processing.
[0083] In this embodiment, different tilt direction categories correspond to different processing methods. For example, if a tilt in the direction of pitch is detected on the face of the target scan object, taking a CT scanner as an example, the tilt angle of the rotating support of the scanning device can be adjusted according to the tilt angle of the face so that the center of the scanning device is aligned with the frontal direction of the target scan object's face (i.e., the center of the scanning device is parallel to the axial direction of the target scan object's head) to perform a tilt scan, thereby obtaining a positive scan image and meeting the diagnostic requirements of doctors. Alternatively, before image reconstruction, the image reconstruction angle can be determined according to the tilt angle of the face, and image reconstruction can be performed based on the image reconstruction angle, so that the output scan image is a positive scan image, thereby simplifying the doctor's operation process.
[0084] Compared with the prior art, the embodiments of this application determine the facial tilt category of the target scanning object based on the facial image of the target scanning object, and adjust the scanning device and / or adjust the facial angle of the target scanning object in the scanning image according to the facial tilt category to output an orthogonal scanning image. This overcomes the technical problem that the patient cannot get an orthogonal scanning image because the patient cannot straighten his head. At the same time, since no family member is needed to straighten the patient's head, it avoids unnecessary radiation damage to the family member.
[0085] This application provides another scanning method, such as... Figure 4 As shown, the method includes:
[0086] 201. Obtain the facial image of the target object being scanned.
[0087] In this embodiment of the application, when the target object enters the preset scanning area and aligns its body position to prepare for scanning, the facial image of the target object is acquired by a camera device located above the scanning device.
[0088] 202. Based on the facial image, obtain the tilt direction category of the face.
[0089] In this embodiment, a three-dimensional facial model containing multiple facial positioning points is first created, for example, including six facial positioning points: left corner of the eye, right corner of the eye, tip of the nose, left corner of the mouth, right corner of the mouth, and chin. Then, the position information of each of these facial positioning points in the facial image is obtained and mapped onto the three-dimensional facial model. Next, after initializing the camera intrinsics, the solvePnP function (i.e., corner detection algorithm) in OpenCV is called to determine the facial rotation vector of the target scanning object. The facial rotation vector can represent any rotation in three-dimensional space based on a three-dimensional vector (θ*x, θ*y, θ*z), where (x, y, z) represents a unit vector. The facial rotation vector is further converted into a facial rotation matrix [cos(θ / 2), x*sin(θ / 2), y*sin(θ / 2), z*sin(θ / 2)]. Finally, the facial rotation matrix is converted into Euler angles, namely pitch, yaw, and roll, to determine the facial tilt direction and angle. Furthermore, the tilt direction category of the face is determined based on the tilt direction. Typically, tilt direction categories can include pitch, yaw, and roll categories, such as... Figure 3 As shown. However, in head scanning, due to the limitations of the headrest, tilting in the tumbling tilt direction category is usually not observed, so it does not need to be considered. Therefore, in this embodiment, the tilt direction category includes at least one of the pitch tilt direction category and the yaw tilt direction category. Accordingly, step 202 of the embodiment specifically includes: identifying the position information of multiple facial positioning points based on the facial image; mapping the multiple position information to a pre-established three-dimensional facial model; determining the facial rotation vector of the target scanning object based on the three-dimensional facial model obtained after mapping; converting the facial rotation vector into a facial rotation matrix, and determining the facial tilt direction and facial tilt angle according to the facial rotation matrix; and determining the tilt direction category of the face based on the facial tilt direction and the facial tilt angle.
[0090] If the tilt direction category matches the pitch tilt direction category, step 203 or step 204 can be executed, or steps 203 and 204 can be executed simultaneously.
[0091] 203. If the tilt direction category matches the pitch tilt direction category, adjust the scanning device according to the facial tilt angle to perform a tilt scan.
[0092] In this embodiment of the application, during the actual scanning process, due to the target scanning object's incomplete familiarity with the headrest, the target scanning object may lie on the upper or lower part of the headrest. At this time, in the facial image, the target scanning object will have a head tilted up or down posture, resulting in a tilt of the face. In this case, the center of the scanning device can be adjusted to the front direction of the target scanning object's face according to the facial tilt angle identified in step 202 of the embodiment, so as to perform tilt scanning and obtain a positive scanning image, thereby meeting the doctor's diagnostic requirements.
[0093] 204. If the tilt direction category matches the pitch tilt direction category, obtain the reconstruction angle of the image to be reconstructed based on the facial tilt angle, and obtain the reconstructed image based on the reconstruction angle.
[0094] If the tilt direction category matches the yaw tilt direction category, proceed to step 205.
[0095] 205. If the tilt direction category matches the yaw tilt direction category, then adjust the facial angle of the target object in the scanned image according to the facial tilt angle so that the output scanned image is an orthogonal scanned image.
[0096] Specifically, if the tilt direction category matches the yaw tilt direction category, the facial angle of the target scanned object in the scanned image is adjusted according to the facial tilt angle. That is, the acquired scanned image is rotated according to the facial tilt angle so that the output scanned image is an orthogonal scanned image. In this embodiment, for some special cases of scanned objects (e.g., patients with cerebral thrombosis), the head cannot be turned to one side and cannot be straightened. In this case, the target scanned object will appear to be looking to the left or right in the facial image, resulting in a yaw tilt direction category of the face. In this case, before sending for printing, the tilt angle of the face in the image can be adjusted according to the facial tilt angle identified in step 202 of the embodiment, so that the output scanned image is an orthogonal scanned image, thereby simplifying the doctor's operation process.
[0097] As an optional implementation, if the tilt direction category includes the pitch tilt direction category and the yaw tilt direction category, then any combination of steps 203 and 205, steps 204 and 205, and steps 203, 204 and 205 can be implemented.
[0098] As an optional implementation, in this embodiment of the application, the method further includes: if the tilt direction category does not conform to the pitch tilt direction category, outputting scanning standard action information to prompt the target scanning object to adjust its facial positioning according to the scanning standard action information; in response to the instruction that the positioning adjustment is completed, re-acquiring the updated facial image of the target scanning object after adjusting its facial positioning, and redetermining the facial tilt direction and facial tilt angle according to the updated facial image, so as to perform scanning according to the updated facial tilt direction and facial tilt angle.
[0099] The standard motion information is used to characterize the expected motion of the scanned object. For example, if step 202 of the embodiment detects a yaw tilt in the face of the target scanned object, a video or animated image that indicates left or right facial adjustment can be played on a designated screen to prompt the scanned object to adjust itself. Furthermore, based on the positioning adjustment completion command issued by the scanned object, its facial image can be re-acquired for re-detection, and scanning can be performed based on the updated detection results.
[0100] Compared with the prior art, the embodiments of this application determine the facial tilt direction and facial tilt angle of the target scanning object based on the facial image of the target scanning object, and adjust the scanning device and / or adjust the facial angle of the target scanning object in the scanning image according to the tilt direction category of the facial tilt direction, so as to output an orthogonal scanning image. This overcomes the technical problem that the patient cannot get an orthogonal scanning image because the patient cannot straighten his head. At the same time, since no family member is required to straighten the patient's head, it avoids unnecessary radiation damage to the family member.
[0101] This application provides another scanning method, such as... Figure 5 As shown, the method includes:
[0102] 301. Select multiple parts on the target scan object as body positioning points.
[0103] It is understandable that during the scanning process, if the scanned object undergoes significant body movement, it can easily lead to deviations in the acquired scanned image. In this embodiment, multiple body parts are first selected on the target scanned object as body positioning points, such as... Figure 6 As shown.
[0104] 302. Obtain the initial overall image of the target object, mark the initial positions of each body positioning point in the initial overall image, and generate a reference image.
[0105] In this embodiment of the application, before the target object is positioned and begins the scanning process, an overall image of its initial state is first obtained, and the initial positions of each body positioning point selected in step 301 of the embodiment are marked in the initial overall image as a reference image.
[0106] 303. Determine whether the target object has shifted position during the scanning process based on the reference image.
[0107] In this embodiment, a real-time overall image of the target object during the scanning process can be acquired, and the real-time positions of each of the aforementioned body positioning points can be marked in the image. Then, the offset between the real-time position and the initial position can be calculated. If the offset exceeds a preset offset threshold, it is determined that the target object has shifted position during the scanning process. Accordingly, step 303 of the embodiment specifically includes: acquiring a real-time overall image of the target object; marking the real-time positions of each body positioning point in the real-time overall image; determining the offset between the real-time position of each body positioning point and its initial position in the reference image; and if the offset exceeds a preset offset threshold, it is determined that the target object has shifted position during the scanning process.
[0108] 304. If yes, output an alarm message and trigger the scan termination thread.
[0109] In this embodiment, if the offset exceeds a preset offset threshold, it indicates that it is affecting the scan results. In this case, an alarm message can be output, and a scan termination thread can be triggered to effectively reduce radiation dose, save doctor's time, and improve equipment efficiency. Optionally, a manual confirmation step can be configured in the scan termination thread to ask the scanning operator whether they are sure they want to stop the scan.
[0110] This application provides a scanning method. First, a facial image of the target object is acquired. Second, based on the facial image, the tilt direction category of the face is obtained, whereby the tilt direction category includes at least one of pitch tilt direction and yaw tilt direction. Finally, based on the tilt direction category, a corresponding processing method is applied for processing. Compared with the prior art, the embodiments of this application determine the facial tilt direction and angle of the target object based on the facial image, and adjust the scanning device and / or adjust the facial angle of the target object in the scanned image according to the tilt direction category to output an orthogonal scan image. This overcomes the technical problem that an orthogonal scan image cannot be obtained because the patient cannot straighten their head. Furthermore, since no family member is required to assist in straightening the patient's head, unnecessary radiation exposure to family members is avoided.
[0111] Furthermore, as a response to the above Figure 1The implementation of the method shown in this application provides a scanning system, such as... Figure 7 As shown, the system includes:
[0112] Get module 41, determine module 42, process module 43.
[0113] Acquisition module 41 is used to acquire the facial image of the target scan object;
[0114] The determination module 42 is used to obtain the tilt direction category of the face based on the facial image, wherein the tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category;
[0115] The processing module 43 is used to process the tilt direction category using the corresponding processing method.
[0116] In specific application scenarios, if the tilt direction category matches the pitch tilt direction category, the scanning device is adjusted according to the facial tilt angle to perform tilt scanning, or the reconstruction angle of the image to be reconstructed is obtained according to the facial tilt angle, and the reconstructed image is obtained based on the reconstruction angle.
[0117] In specific application scenarios, the system also includes:
[0118] An adjustment module is used to adjust the facial angle of the target object in the scanned image according to the facial tilt angle if the tilt direction category matches the yaw tilt direction category, so that the output scanned image is an orthogonal scanned image.
[0119] In specific application scenarios, the system also includes:
[0120] The selection module is used to select multiple parts on the target scanned object as body positioning points;
[0121] The marking module is used to acquire an initial overall image of the target scanning object, mark the initial positions of each body positioning point in the initial overall image, and generate a reference image;
[0122] The judgment module is used to determine whether the target scanned object has undergone positional shift during the scanning process based on the reference image;
[0123] The termination module is used to output an alarm message and trigger the scan termination thread if the condition is met.
[0124] In specific application scenarios, the judgment module specifically includes:
[0125] A marking unit is used to acquire a real-time overall image of the target scanning object and mark the real-time position of each body positioning point in the real-time overall image;
[0126] The first determining unit is used to determine the offset between the real-time position of each body positioning point and the initial position of each body positioning point in the reference image.
[0127] The first judgment unit is used to determine that the target scanning object has shifted its position during the scanning process if the offset exceeds a preset offset threshold.
[0128] In specific application scenarios, the determining module specifically includes:
[0129] The recognition unit is used to recognize the location information of multiple facial positioning points based on the facial image;
[0130] A mapping unit is used to map the multiple location information onto a pre-established three-dimensional facial model;
[0131] The second determining unit is used to determine the facial rotation vector of the target scanning object based on the three-dimensional facial model obtained after mapping.
[0132] A conversion unit is used to convert the facial rotation vector into a facial rotation matrix, and determine the facial tilt direction and facial tilt angle based on the facial rotation matrix;
[0133] The second judgment unit is used to determine the type of facial tilt direction based on the facial tilt direction and the facial tilt angle.
[0134] In specific application scenarios, the system also includes:
[0135] The output module is used to output scanning standard motion information if the tilt direction category does not conform to the pitch tilt direction category, so as to prompt the target scanning object to adjust the facial positioning according to the scanning standard motion information;
[0136] The update module is used to respond to the instruction that the positioning adjustment is completed, re-acquire the updated facial image of the target scanning object after the facial positioning adjustment, and redetermine the facial tilt direction and facial tilt angle based on the updated facial image, so as to perform scanning based on the updated facial tilt direction and facial tilt angle.
[0137] This application provides a scanning system that first acquires a facial image of the target object; secondly, based on the facial image, it acquires the tilt direction category of the face, which includes at least one of pitch tilt direction and yaw tilt direction; finally, based on the tilt direction category, it processes the image using a corresponding processing method. Compared with the prior art, this application's embodiment determines the facial tilt direction and angle based on the target object's facial image, and adjusts the scanning device and / or the facial angle of the target object in the scanned image according to the tilt direction category to output an orthogonal scan image. This overcomes the technical problem of not being able to obtain an orthogonal scan image because the patient cannot straighten their head. Furthermore, since it eliminates the need for family members to assist in straightening the patient's head, it avoids unnecessary radiation exposure for family members.
[0138] According to one embodiment of this application, a storage medium is provided, the storage medium storing at least one executable instruction that can perform the scanning method in any of the above method embodiments.
[0139] Figure 8 The diagram shows a structural schematic of a self-service scanning system according to one embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the self-service scanning system.
[0140] like Figure 8 As shown, the self-service scanning system may include: a camera device 51, a control console 52, and an alarm device 53.
[0141] Among them, the camera device 51 is installed in the detection chamber and is used to acquire facial images of the target scanning object;
[0142] Console 52, located in the control room and connected to the camera device, is used to receive facial images of the target scanned object, and based on the facial images, to obtain the tilt direction category of the face, wherein the tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category, and to process the image based on the tilt direction category using a corresponding processing method.
[0143] An alarm device 53 is installed in the control room and connected to the console. It is used to receive the alarm signal and issue alarm information.
[0144] Used to perform the following operations:
[0145] Acquire the facial image of the target object being scanned;
[0146] Based on the facial image, the tilt direction category of the face is obtained, and the tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category;
[0147] Based on the tilt direction category, the corresponding processing method is adopted for processing.
[0148] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the scanned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.
[0149] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0150] The methods and systems of this application may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this application are not limited to the order specifically described above, unless otherwise specifically stated. Furthermore, in some embodiments, this application may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this application. Thus, this application also covers recording media storing programs for performing the methods according to this application.
[0151] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.
[0152] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.
Claims
1. A scanning method, characterized in that, include: Acquire the facial image of the target object being scanned; Based on the facial image, the tilt direction category of the face is obtained, and the tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category; Based on the tilt direction category, the corresponding processing method is adopted for processing; The step of obtaining the tilt direction category of the face based on the facial image specifically includes: Based on the facial image, the location information of multiple facial positioning points is identified; The multiple location information is mapped onto a pre-established three-dimensional facial model; Based on the three-dimensional facial model obtained after mapping, the facial rotation vector of the target scanning object is determined; The facial rotation vector is converted into a facial rotation matrix, and the facial tilt direction and facial tilt angle are determined based on the facial rotation matrix. Based on the facial tilt direction and the facial tilt angle, determine the type of facial tilt direction; The processing based on the tilt direction category, using the corresponding processing method, includes: If the tilt direction category matches the pitch tilt direction category, the scanning device is adjusted according to the facial tilt angle to perform tilt scanning, and / or, the reconstruction angle of the image to be reconstructed is obtained according to the facial tilt angle, and the reconstructed image is obtained based on the reconstruction angle. If the tilt direction category matches the yaw tilt direction category, the facial angle of the target object in the scanned image is adjusted according to the facial tilt angle so that the output scanned image is an orthogonal scanned image.
2. The method according to claim 1, characterized in that, The method further includes: Multiple parts of the target scanned object are selected as body positioning points; Obtain an initial overall image of the target scanning object, mark the initial positions of each body positioning point in the initial overall image, and generate a reference image; Determine whether the target object has shifted position during the scanning process based on the reference image; If so, an alarm message will be output, and the scan termination thread will be triggered.
3. The method according to claim 2, characterized in that, The step of determining whether the target object has shifted position during the scanning process based on the reference image specifically includes: Acquire a real-time overall image of the target scanning object, and mark the real-time positions of each body positioning point in the real-time overall image; Determine the offset between the real-time position of each body positioning point and the initial position of each body positioning point in the reference image; If the offset exceeds a preset offset threshold, it is determined that the target object has shifted its position during the scanning process.
4. The method according to claim 1, characterized in that, The method further includes: If the tilt direction category does not match the pitch tilt direction category, then the scanning standard motion information is output to prompt the target scanning object to adjust its facial positioning according to the scanning standard motion information; In response to the instruction that the positioning adjustment is complete, the updated facial image of the target scanning object after the facial positioning adjustment is reacquired, and the facial tilt direction and facial tilt angle are re-determined based on the updated facial tilt image, so as to perform scanning based on the updated facial tilt direction and facial tilt angle.
5. A scanning system, characterized in that, include: The acquisition module is used to acquire facial images of the target scanned object; The determination module is used to obtain the tilt direction category of the face based on the facial image, wherein the tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category; The processing module is used to process the tilt direction category using the corresponding processing method. The determining module specifically includes: The recognition unit is used to recognize the location information of multiple facial positioning points based on the facial image; A mapping unit is used to map the multiple location information onto a pre-established three-dimensional facial model; The second determining unit is used to determine the facial rotation vector of the target scanning object based on the three-dimensional facial model obtained after mapping. A conversion unit is used to convert the facial rotation vector into a facial rotation matrix, and determine the facial tilt direction and facial tilt angle based on the facial rotation matrix; The second judgment unit is used to determine the type of facial tilt direction based on the facial tilt direction and the facial tilt angle; The system also includes an adjustment module, used to adjust the scanning device according to the facial tilt angle to perform tilt scanning if the tilt direction category matches the pitch tilt direction category, or to obtain the reconstruction angle of the image to be reconstructed according to the facial tilt angle and obtain the reconstructed image based on the reconstruction angle; if the tilt direction category matches the yaw tilt direction category, to adjust the facial angle of the target scanning object in the scanned image according to the facial tilt angle so that the output scanned image is an orthogonal scanned image.
6. A storage medium storing at least one executable instruction, characterized in that, The executable instructions cause the processor to perform the operation corresponding to the scanning method as described in any one of claims 1-4.
7. A self-service scanning system, characterized in that, include: A camera device, installed in the detection chamber, is used to acquire facial images of the target object being scanned; A control console, located in a control room and connected to the camera device, is used to receive facial images of the target scanning object and, based on the facial images, obtain the tilt direction category of the face. The tilt direction category includes at least one of pitch tilt direction category and yaw tilt direction category. The console is also used to process the image based on the tilt direction category using a corresponding processing method, including: if the tilt direction category matches the pitch tilt direction category, adjusting the scanning device according to the facial tilt angle to perform tilt scanning; and / or, obtaining the reconstruction angle of the image to be reconstructed based on the facial tilt angle, and obtaining the reconstructed image based on the reconstruction angle; if the tilt direction category matches the yaw tilt direction category, adjusting the facial angle of the target scanning object in the scanned image according to the facial tilt angle so that the output scanned image is an orthogonal scanned image. An alarm device, located in the control room and connected to the console, is used to receive alarm signals and issue alarm information; The console is used to obtain the tilt direction category of the face based on the facial image, specifically including: identifying the position information of multiple facial positioning points based on the facial image; mapping the multiple position information to a pre-established three-dimensional facial model; determining the facial rotation vector of the target scanning object based on the obtained three-dimensional facial model after mapping; converting the facial rotation vector into a facial rotation matrix, and determining the facial tilt direction and facial tilt angle based on the facial rotation matrix; and determining the tilt direction category of the face based on the facial tilt direction and the facial tilt angle.