Method and device for realizing safety protection using depth camera in standing scanning CT machine

Abstract

The present invention discloses a method and device for realizing safety protection by using a depth camera in a standing scanning CT machine, wherein the method comprises acquiring depth information collected by a depth camera arranged at a preset position of the CT machine, and fusing the depth information to obtain a detection image, wherein the depth camera is arranged in front of and on both sides of the standing position; reading the height information of the depth camera from the ground, the inner diameter of a scanning frame of the CT machine and the radius information of a safety area within the inner diameter; based on the height information of the depth camera from the ground and the radius of the safety area, a detection area is formed by the inner diameter of the scanning frame of the CT machine indicated in the field of view of the detection image, and a circular area is circled as a safety area in the detection image; a dangerous area is determined based on the detection area and the safe area; and it is determined whether an object to be protected is in the dangerous area, and if so, the position of the object to be protected in the dangerous area is determined based on the distance between the position point of the object to be protected and the center point of the image of the safety area.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method and device for achieving safety protection using a depth camera in a standing scanning CT machine. Background Art

[0002] In the standing medical CT system, the patient stands on the ground, and the system realizes the patient scanning process by lifting the patient or moving the frame. When the patient is in the standing position, he may suffer from standing imbalance or loss of consciousness, and then fall and collide. For the safety protection of this scene, three layers of motion protection measures are set: patient straps, dangerous area monitoring and pressure touch sensors. Among them, dangerous area monitoring is to use a depth camera to assist the operator to monitor the patient's position, identify the safe range and perform system warnings and protection.

[0003] In the related art, the method for area monitoring usually uses infrared device sensors to set up a "safety grating", and the sensor receives sensing information for objects entering the dangerous area. The "dangerous area" set in the standing medical CT system is an annular area formed by the inner diameter of the Gantry (CT machine scanning frame) and the human body. Multiple sensors need to be installed to receive sensing information. This method is complex to implement and sometimes there is a large error in detection accuracy. Summary of the invention

[0004] The present application provides a method and device for achieving safety protection using a depth camera in a standing scanning CT machine, so as to solve the problems existing in the related art.

[0005] In a first aspect, the present invention provides a method for achieving safety protection using a depth camera in a standing scanning CT machine, comprising: acquiring depth information collected by a depth camera set at a preset position of the CT machine, and fusing the depth information to obtain a detection image, wherein the depth camera is set in front of and on both sides of the standing position; reading the height information of the depth camera from the ground, the inner diameter of the CT machine scanning frame, and the radius information of a safe area within the inner diameter; based on the height information of the depth camera from the ground and the radius of the safe area, a detection area constituted by the inner diameter of the CT machine scanning frame indicated in the field of view of the detection image, and a circular area is circled as a safe area in the detection image; based on the detection area and the safe area, a dangerous area is determined; and if an object to be protected is in the dangerous area, determining the position of the object to be protected in the dangerous area based on the distance between the position point of the object to be protected and the center point of the safe area image is determined.

[0006] Optionally, when determining the preset position of the depth camera, it includes: setting a minimum distance between the depth camera and the scene, wherein the field of view parameters and the effective field of view size of the depth camera are determined based on the minimum distance; setting the height information of the depth camera in front of the standing position and the depth cameras on both sides of the standing position from the ground to be fixed, wherein, in the XOY plane of the three-dimensional coordinate system of the standing scanning CT machine, the coordinates of the midpoints of the connecting line between every two depth cameras, and the angle between the connecting line and the X-axis are used to describe the position of the depth camera.

[0007] Optionally, the method further verifies the recognition range and coverage of the depth camera set at a preset position, including: calculating the effective recognition range and coverage in the XOY plane at every preset step value along the Z-axis direction, wherein the effective recognition range is the effectively recognized internal area of ​​the CT scanning frame; the coverage is the ratio of the effectively recognized region of interest to the region of interest; and superimposing each XOY plane in the Z-axis direction to obtain the spatial recognition range and coverage of the depth camera.

[0008] Optionally, the method further includes: calculating the depth viewing angle and effective field of view of a single depth camera; and adjusting the minimum distance between the depth camera and the scene based on the depth viewing angle and the effective field of view, so as to determine the minimum target distance that can cover the area of ​​interest after the adjustment is completed.

[0009] Optionally, before determining whether the object to be protected is in the danger zone, the method includes: converting pixels within the field of view of the detection image into coordinate values ​​in the three-dimensional coordinate system of the CT machine; traversing the pixel coordinates within the detection area and converting them into spatial coordinate values ​​in the depth camera space coordinate system; determining the Z coordinate value of the coordinate value in the three-dimensional coordinate system of the CT machine and the difference between the spatial coordinate value in the depth camera space coordinate system; if the difference is greater than the set change value, the object to be protected exists in the field of view of the detection image.

[0010] Optionally, determining whether the object to be protected is in the dangerous area includes: calculating the distance between the pixel point of the object to be protected in the field of view of the detection image and the center point of the safe area on the same XOY plane; if it is within a preset interval, the object to be protected is in the dangerous area.

[0011] Optionally, determining the position of the object to be protected in the dangerous area based on the distance between the position point of the object to be protected and the center point of the safe area image includes: determining the position in the dangerous area based on the depth of the object to be protected.

[0012] In a second aspect, the present invention provides a device for achieving safety protection using a depth camera in a standing scanning CT machine, comprising a detection image determination unit, which obtains depth information collected by a depth camera set at a preset position of the CT machine, and fuses the depth information to obtain a detection image, wherein the depth camera is set in front of and on both sides of the standing position; an information reading unit, which is configured to read the height information of the depth camera from the ground, the inner diameter of the CT machine scanning frame, and the radius information of the safety area within the inner diameter; an area calibration unit, which is configured to circle a circular area as a safety area image in the detection image based on the height information of the depth camera from the ground and the radius of the safety area indicated by the inner diameter of the CT machine scanning frame in the field of view of the detection image; a danger area determination unit, which is configured to determine the danger area based on the detection area and the safety area; a position determination unit, which is configured to determine whether the object to be protected is in the danger area, and if in the danger area, determine the position of the object to be protected in the danger area based on the distance between the position point of the object to be protected and the center point of the safety area image.

[0013] In a third aspect, the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects is implemented.

[0014] In a fourth aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the first aspect when executing the program.

[0015] The present invention discloses a method and device for realizing safety protection of a standing scanning CT machine using a depth camera, wherein the method comprises acquiring depth information collected by a depth camera set at a preset position of the CT machine, and fusing the depth information to obtain a detection image, wherein the depth camera is set in front of and on both sides of the standing position; reading the height information of the depth camera from the ground, the inner diameter of the CT machine scanning frame and the radius information of the safety area within the inner diameter; based on the height information of the depth camera from the ground and the radius of the safety area, the inner diameter of the CT machine scanning frame indicates the detection area in the field of view of the detection image, and encircling a circular area as the safety area in the detection image; determining the dangerous area based on the detection area and the safety area; determining whether the object to be protected is in the dangerous area, and if in the dangerous area, determining the position of the object to be protected in the dangerous area based on the distance between the position point of the object to be protected and the center point of the safety area image. Accurate monitoring of the dangerous area of ​​the standing scanning CT machine is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 For this application, a method for achieving safety protection using a depth camera in a standing scanning CT machine is provided;

[0018] Figure 2a This is a schematic diagram of the depth camera installation for this application;

[0019] Figure 2b This is a schematic diagram of the coordinate system of the standing scanning CT machine in this application;

[0020] Figure 3a Schematic diagram of the horizontal state of the depth camera installation for this application verification;

[0021] Figure 3b A schematic diagram of the ground safety circle and center point location for this application;

[0022] Figure 3c A schematic diagram of the height from the camera to the ground for recording purposes of this application;

[0023] Figure 4 A schematic diagram showing the location of the hazardous area calculated for this application;

[0024] Figure 5 A schematic diagram of the area within the field of view of this application;

[0025] Figure 6 This is a schematic diagram of the CT machine system coordinate system for this application;

[0026] Figure 7a A schematic diagram of the interior space of the simulated mobile Gantry for this application;

[0027] Figure 7b This is a schematic diagram of the effective spatial field of view of a depth camera simulated by three tetrahedrons in this application;

[0028] Figure 8a A schematic diagram of the interior area of ​​Gantry covered in the space of this application;

[0029] Figure 8b This is a schematic diagram of the area of ​​interest for this application;

[0030] Figure 9a The internal area of ​​Gantry that is effectively identified for this application;

[0031] Figure 9b The area of ​​interest effectively identified for this application;

[0032] Fig.10This is a schematic diagram of the recognition range and coverage rate in the xoy plane at the corresponding z coordinates calculated in this application with 10mm as the scale;

[0033] Fig.11 A method corresponding to the present application Figure 1 Schematic diagram of an electronic device. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0035] The following is combined with Figure 1 The method of using a depth camera to achieve safety protection in a vertical scanning CT machine is exemplified. This method uses the depth camera to obtain the depth information of the image within the field of view, builds a 3D model, and defines the monitoring area through a specific calibration method, thereby achieving a safety protection effect, including the following steps:

[0036] Step 101: Acquire depth information collected by a depth camera set at a preset position of a CT machine, and fuse the depth information to obtain a detection image, wherein the depth camera is set in front of and on both sides of the standing position.

[0037] In this embodiment, reference Figure 2a There are three depth cameras installed on the front and sides of the human body. Since the light of the depth camera cannot penetrate the human body and there is an optical perspective relationship, when the center line of the camera's field of view is in the sagittal plane of the human body, there will be serious light path obstruction. At the same time, because there is a backboard behind the human body, the depth camera should be installed in front and on both sides of the outside of the human body. The depth camera is connected to the host through a data cable, and the depth data can be sent to the host in real time for analysis.

[0038] After installation, perform calibration. 1) Ensure that the three camera ports are installed in the same direction (clockwise or counterclockwise). 2) See Figure 3a Verify the camera is level, see Figure 3b Select five points in the measurement image and make sure that their height changes are within the allowable error range. 3) Mark the safety circle and center point on the ground, and set a "+" mark at the vertical position of the camera corresponding to the safety circle. The "+" mark needs to be perpendicular to the edge of the safety circle. Figure 3b 4) Record the height from the camera to the ground, and Figure 3c .

[0039] The coordinate system of the vertical CT system is that the CT rotation center axis is the Z axis, the intersection line of the human coronal plane and the mounting surface is the X axis, the intersection line of the human sagittal plane and the mounting surface is the Y axis, the intersection line of the coronal plane and the sagittal plane is on the Z axis, and the intersection point of the XYZ axis is the coordinate zero point (see Figure 2b ); Figure 2b The image seen in the camera's field of view. The camera's installation surface is the surface horizontal to this field of view. The camera's coordinate system is the origin of the coordinates at the "specific point" on the camera, and the XYZ axes of the corresponding coordinates at the installation position.

[0040] Step 102: Read the height information of the depth camera from the ground, the inner diameter of the CT scanning gantry, and the radius information of the safety area within the inner diameter.

[0041] Step 103: Based on the height information of the depth camera from the ground and the radius of the safety area indicated by the inner diameter of the CT scanning gantry in the field of view of the detection image, a circular area is circled as the safety area image in the detection image.

[0042] Step 104: Determine a dangerous area based on the detection area and the safety area.

[0043] In this embodiment, reference Figure 5 , read the height information of the depth camera from the ground, the inner diameter of the CT scanning frame, and the radius information of the safe area, and draw a circle with the safe area as the version at the height of the camera on the ground area ( Figure 5 The circle in the figure), the smaller rectangular frame area (the smaller rectangle that frames part of the circle in the figure) is the detection area, and the shaded area outside the circle and within the smaller rectangular frame area in the figure is the dangerous area at the current height; according to the contour safety warning calculation rules (which will be described in detail in subsequent embodiments), in areas gradually above the ground, the DFOV of the camera gradually becomes smaller, and the safe area in the image field of view will "gradually become larger", so it is necessary to expand the detection area, and the larger shaded rectangular area in the figure is the actual detection area.

[0044] Step 105: Determine whether the object to be protected is in the dangerous area. If it is in the dangerous area, determine the position of the object to be protected in the dangerous area based on the distance between the position point of the object to be protected and the center point of the safe area image.

[0045] As an optional implementation of this embodiment, before determining whether the object to be protected is in the danger zone, the method includes: converting pixels within the field of view of the detection image into coordinate values ​​in the three-dimensional coordinate system of the CT machine; traversing the pixel coordinates within the detection area and converting them into spatial coordinate values ​​in the depth camera space coordinate system; determining the Z coordinate value of the coordinate value in the three-dimensional coordinate system of the CT machine and the difference between the spatial coordinate value of the depth camera space coordinate system; if the difference is greater than the set change value, the object to be protected exists in the field of view of the detection image.

[0046] As an optional implementation method of this embodiment, determining whether the object to be protected is in the dangerous area includes: calculating the distance between the pixel point of the object to be protected in the field of view of the detection image and the center point of the safe area on the same XOY plane; if it is within a preset interval, the object to be protected is in the dangerous area.

[0047] In this optional implementation, for XOY planes with different heights, the field of view of the camera will increase as the distance from the camera increases, and conversely, the field of view will decrease as the distance from the camera decreases. Because different XOY planes are displayed differently in the image field of view, it is necessary to convert the pixels in the image field of view into XYZ spatial coordinate values ​​in the spatial coordinate system, traverse the coordinates of the pixels in the larger shadow rectangular area in the depth image, and convert them into spatial coordinate values ​​in the camera space coordinate system; take the Z value of the current XYZ coordinate value, that is, the height value of the current point, and compare it with the actual height value set by the camera. If the height difference is greater than the set change value, that is, there is an object in the current camera field of view, it is necessary to further determine whether the object is in the danger zone; to determine whether the object is in the danger zone, it is necessary to calculate the distance between the pixel point in the camera field of view and the center point of the safe area on the same XOY plane; based on the calculated distance, determine whether the current point is within the range of 400mm to 450mm, if it is within this range, it is in the danger zone.

[0048] As an optional implementation method of this embodiment, determining the position of the object to be protected in the dangerous area based on the distance between the position point of the object to be protected and the center point of the safe area image includes: determining the position in the dangerous area based on the depth of the object to be protected.

[0049] refer to Figure 5 According to the positions of the two points, the angle on the same XOY plane is calculated to calculate the position of the dangerous area. When an abnormal point appears in the dangerous area, the depth value of its projected pixel in the depth image will replace the depth value of the normal point originally projected at this pixel. Therefore, in practical applications, it is necessary to calculate the depth values ​​of all normal points in real time, that is, the Z coordinates in the camera coordinate system and the spatial coordinates of the abnormal points.

[0050] The depth camera calculates the coordinate system as follows Figure 4As shown in the figure, the baseline length of the depth camera is defined as B, the focal length is F, the left camera is Camera L, the right camera is Camera R, the coordinates of the normal point M are (x1, z1), the coordinates of the abnormal point P are (x2, z2), the distance from the projection point of point M and point P to the Z axis in the imaging plane of Camera L is D1, the distance from the projection point of point M to the Z axis in the imaging plane of Camera R is D2, and the distance from the projection point of point P to the Z axis is D3.

[0051] According to the similar triangle theorem, we can obtain that at point M: (x1-B) / (D2-b)=z1 / F, x1 / D1=z1 / F; at point P: (x2-B) / (D3-b)=z2 / F, x2 / D1=z2 / F.

[0052] Then we can get the coordinates of the normal point M: z1 = F·B / (D1-D2+B), x1 = (D1·z1) / F; the coordinates of the abnormal point P: z2 = F·B / (D1-D3+B), x2 = (D1·z2) / F;

[0053] The above is the principle and process of calculating the position of the outlier point in the dangerous area on the XOZ plane. The principle and process of calculating the position of the outlier point on the YOZ plane are the same, so the spatial coordinates of the outlier point P in the dangerous area can be obtained. Furthermore, the distance between the outlier point P and the center of the safe area can be calculated in the camera coordinate system.

[0054] As an optional implementation method of this embodiment, when determining the preset position of the depth camera, it includes: setting a minimum distance between the depth camera and the scene, wherein the field of view parameters and the effective field of view size of the depth camera are determined based on the minimum distance; setting the height information of the depth camera in front of the standing position and the depth cameras on both sides of the standing position from the ground to be fixed, wherein, in the XOY plane of the three-dimensional coordinate system of the standing scanning CT machine, the image center of each depth camera and the angle between the line between the image center and the coordinate origin and the X-axis are used to describe the position of the depth camera.

[0055] In this optional implementation, after setting the depth camera position, the contour safety warning calculation can be achieved:

[0056] ① DFOV and field of view of the depth camera: According to the technical documentation, when the resolution is 1280×720, the distance between the depth camera and the scene must be more than 450mm. Therefore, the effective visual range of the depth camera in the z direction is ≧-2240, and distance_min is 450mm (i.e. Z=-2240 in the coordinate system), then HFOV=59.74(±3)°, VFOV=40(±1)°, DFOV=68.33(±2)°, and the effective field of view size is 516mm×327mm.

[0057] ② No camera is placed behind the backboard of the CT system, and the camera placement is simulated on the XOY plane: Considering that the patient is against the backboard in vertical CT, the backboard can not only help the patient position, but also prevent the patient from falling backwards. At the same time, the range of motion of the human joints is limited, and the probability of various parts of the patient entering the unsafe area behind is very small, so the setting of the depth camera mainly focuses on the unsafe area in front of and on both sides of the patient. However, in order to enable the patient to be in the center of the field of vision, the backboard is adjustable in the y-axis mode (adjustment range 0 to -385mm). Therefore, in order to facilitate calculation and simulation, the backboard is set at the position of y = -105 (about half the thickness of the head and shoulders). In the subsequent section, we will discuss the redundancy of the camera when the bed board is in different positions. In the highest XOY plane (z = -2240, distance = 450mm), the effective field of view is the smallest. Whether the camera can irradiate the entire area of ​​interest on this plane is the first necessary condition to meet the overall system requirements. However, since this plane is too close to the depth camera and the effective field of view is too small, it is impossible to cover the entire Gantry internal area. Therefore, the first goal is to cover as many areas of interest as possible. Figure 5 As shown in the figure, the circle (diameter 1000mm) represents the area inside Gantry, the inner ring (inner diameter 400m, outer diameter 450mm) represents the safety warning area, the straight line represents the coordinate position of y=-105, the safety warning area below the straight line is regarded as the area of ​​interest, and the three rectangles represent the effective fields of view of the three depth cameras on this surface.

[0058] The installation position of the depth camera is described by the coordinates of the midpoint of the line connecting the two cameras in the depth camera and the angle between the line and the x-axis. Since the installation height of the camera is fixed (z = -2690, 2800mm from the ground), the z coordinate of the camera is no longer described. (The spatial coordinate system used is the vertical CT system coordinate system as shown in Figure 6 shown).

[0059] ③ Three-dimensional model simulation: The effective field of view of the depth camera is positively correlated with the distance between the camera and the scene and DFOV. DFOV is also positively correlated with the distance between the camera and the scene, but its change curve is logarithmic. When the distance exceeds 450mm, its change is small. Therefore, the enlargement of the effective field of view is mainly due to the increase in the distance between the camera and the scene. Therefore, in order to facilitate simulation and calculation, DFOV is taken as the effective depth angle under distance = 450mm (DFOV = H: 59.74°, V: 40°, D: 68.33°). In solidworks, the internal space of the mobile Gantry is simulated by a cylinder (bottom diameter 1000m, height 2350mm) as shown in Figure 7(a), and the effective spatial field of view of the depth camera is simulated by three tetrahedrons as shown in Figure 7(b).

[0060] As an optional implementation of this embodiment, the method also verifies the recognition range and coverage of the depth camera set at a preset position, including: along the Z-axis direction, calculating the effective recognition range and coverage in the XOY plane at every preset step value, wherein the effective recognition range is the effectively recognized Gantry internal area; the coverage is the ratio of the effectively recognized area of ​​interest to the area of ​​interest; each XOY plane is superimposed in the Z-axis direction to obtain the spatial recognition range and coverage of the depth camera.

[0061] In this optional implementation, the recognition range and coverage calculation: In order to verify whether the depth camera setting can meet the system requirements in space, it is necessary to calculate the spatial recognition range of the depth camera (the spatial coverage of the internal area of ​​Gantry, see Figure 8a ) and the region of interest (see Figure 8b ) can be quantitatively analyzed by calculating the recognition range and coverage on each XOY plane and then superimposing it in the z direction. In SolidWorks, the redundant parts are cut off to obtain the solid section at the corresponding z coordinate, that is, the area that the depth camera can effectively recognize for the area of ​​interest on the xoy plane can be measured.

[0062] like Figure 9a and Figure 9b As shown, the area of ​​the Gantry internal region that can be effectively identified on the XOY plane at z = -2240 is 358107.12 mm 2 The effective identified area of ​​interest is 75436.15mm 2 , and it is known that the total area of ​​the Gantry internal area and the area of ​​interest are 496908.87mm2 and 77369.11mm 2, the corresponding division results show that the Gantry internal area coverage is 72.07% and the area of ​​interest coverage is 97.50%.

[0063] Repeat the same operation, and calculate the recognition range and coverage rate of the xoy surface at the corresponding z coordinate in 10mm scale, as shown in Fig.10 As shown (the area unit is square millimeter, the horizontal axis is the z coordinate).

[0064] As an optional implementation of this embodiment, the method also includes: calculating the depth viewing angle and effective field of view of a single depth camera; adjusting the minimum distance between the depth camera and the scene based on the depth viewing angle and the effective field of view, so as to determine the minimum target distance that can cover the area of ​​interest after the adjustment is completed.

[0065] In this optional implementation, when calculating the installation position: In order to determine the installation position of the depth camera and calculate the recognition range, it is necessary to first calculate important parameters such as the depth viewing angle and effective field of view of a single depth camera. The depth viewing angle and effective field of view of the depth camera are related to the distance between the camera and the scene (Distance of Scene from Depth Module, hereinafter referred to as Z). The larger Z is, the larger the depth viewing angle and effective field of view are.

[0066] ① Depth Field of View: According to the Intel Realsense D400 Series technical documentation, the numerical relationship between the depth field of view (DFOV) and Z is shown in formula (1):

[0067]

[0068] Among them, HFOV = 65 degrees, which is the horizontal field of view of the left imager on the depth module; B = 55 mm, which is the baseline, that is, the distance between the two imagers in the depth camera.

[0069] ② Effective field of view: To facilitate the calculation of the effective field of view, the invalid field of view must be obtained first. The invalid field of view is reflected as a "black hole" in the depth image. According to the Intel Realsense D400 Series technical document, the ratio (DBR) between the width of the invalid field of view and the full horizontal field of view image is as shown in formula (2):

[0070]

[0071] Among them, HFOV = 65 degrees, which is the horizontal field of view of the left imager on the depth module; B = 55 mm, which is the baseline, that is, the distance between the two imagers in the depth camera.

[0072] The width and height of the full field of view image can be obtained by equation (3) and equation (4) respectively. Then, DRB can be obtained by equation (2). Then, the width and height of the effective field of view can be obtained, as follows: Fig.10 shown.

[0073] valid_view_h-2*Z*(tan(HFOV / 2))(3); validd_view_v-2*Z*(tan(VFOV / 2))(4) where HFOV=65 degrees, which is the horizontal field of view of the left imager on the depth module; VFOV=40 degrees, which is the vertical field of view of the left imager on the depth module.

[0074] From the above, we can see that the depth viewing angle and effective field of view are related to Z. When Z is very small, the effective field of view is also small. Therefore, it is necessary to determine the minimum value of Z (Z_min) and obtain the minimum effective field of view to ensure that the depth camera can cover all areas of interest at any Z.

[0075] ③Z_min: In theory, Z_min can be taken as the difference between the camera height and the highest point of the human body. Since people have to stand on steps in the actual use of vertical CT, Z_min = depth camera height - human height - step height. According to "Human Dimensions for Adults" (GB / T 10000-1988) and "Human Dimensions for Minors" (GB / T 26158-2010), human height can be taken as 1850mm. In addition, the camera installation height is 2800mm and the step height is 110mm, so Z_min = 840mm. In summary, in order to avoid the influence of other problems such as the shortening of the actual distance caused by the installation of the camera, Z_min is taken as 750mm. Then when Z = Z_min = 750mm, according to equations (1)-(4), it can be calculated that DFOV_750 = 61.91, and the effective field of view size is 937mm×545mm.

[0076] ④ Simulation of the effective field of view coverage of the depth camera: Considering that the patient in the vertical CT is leaning against the backrest, the backrest can not only help the patient to position himself, but also prevent the patient from falling backwards. At the same time, the range of motion of the human joints is limited, and the probability of various parts of the patient entering the unsafe area behind is very small. Therefore, one camera is mainly set to radiate the unsafe area behind the body, and two cameras are set to focus on the unsafe areas in front and on both sides of the body to ensure that when one camera fails, the recognition range of the remaining cameras can still meet the system usage requirements.

[0077] The above is a method provided by one or more embodiments of the present application. Based on the same idea, the present application also provides a corresponding device for realizing safety protection by using a depth camera in a standing scanning CT machine. The detection image determination unit obtains the depth information collected by the depth camera set at the preset position of the CT machine, and fuses the depth information to obtain a detection image, wherein the depth camera is set in front of and on both sides of the standing position; the information reading unit is configured to read the height information of the depth camera from the ground, the inner diameter of the CT machine scanning gantry and the radius information of the safe area within the inner diameter; the area calibration unit is configured to circle a circular area as a safe area image in the detection image based on the height information of the depth camera from the ground and the radius of the safe area indicated by the inner diameter of the CT machine scanning gantry in the field of view of the detection image; the dangerous area determination unit is configured to determine the dangerous area based on the detection area and the safe area; the position determination unit is configured to determine whether the object to be protected is in the dangerous area, and if it is in the dangerous area, the position of the object to be protected in the dangerous area is determined based on the distance between the position point of the object to be protected and the center point of the safe area image.

[0078] Fig.11 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Fig.11 As shown, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503; wherein the processor 501 and the memory 502 communicate with each other through the bus 503; the processor 501 is used to call the program instructions in the memory 502 to execute the methods provided by the above-mentioned method embodiments.

[0079] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above method embodiments.

[0080] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various storage media that can store program codes.

[0081] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0082] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0083] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for achieving safety protection using a depth camera in a standing scanning CT machine, characterized in that: include: Acquire the depth information collected by the depth camera set at the preset position of the standing scanning CT machine, and fuse the depth information to obtain the detection image, wherein the depth camera is set in front of and on both sides of the standing position, and when determining the preset position of the depth camera, it includes: setting the minimum distance between the depth camera and the scene, wherein the field of view parameter of the depth camera is determined based on the minimum distance, wherein the field of view parameter includes the effective field of view size; set the height of the depth camera in front of the standing position and the depth cameras on both sides of the standing position from the ground, wherein, in the XOY plane of the three-dimensional coordinate system of the standing scanning CT machine, the coordinates of the midpoints of the connecting line of every two depth cameras, and the angle between the connecting line and the X-axis are used to describe the position of the depth camera; wherein, the coordinate system of the standing scanning CT machine is a rotation center axis of the standing scanning CT machine as the Z axis, an intersection line of the human coronal plane and the installation surface of the depth camera as the X axis, an intersection line of the human sagittal plane and the installation surface of the depth camera as the Y axis, an intersection line of the human coronal plane and the human sagittal plane on the Z axis, and an intersection point of the XYZ axis as the coordinate zero point; Read the height information of the depth camera from the ground, the inner diameter of the scanning gantry of the standing scanning CT machine, and the radius information of the safe area within the inner diameter; Based on the height information of the depth camera from the ground and the radius information of the safety area, a circular area is circled in the detection area formed by the inner diameter of the scanning gantry of the standing scanning CT machine within the field of view of the detection image as the safety area in the detection image; Determine a dangerous area based on the detection area and the safety area; Determine whether the object to be protected is in the dangerous area. If it is in the dangerous area, determine the position of the object to be protected in the dangerous area based on the distance between the position point of the object to be protected and the center point of the safe area. Before determining whether the object to be protected is in the dangerous area, the method includes: converting the pixel coordinates in the field of view of the detection image into coordinate values ​​in the three-dimensional coordinate system of the standing scanning CT machine; traversing the pixel coordinates in the detection area and converting them into spatial coordinate values ​​in the depth camera space coordinate system; determining the difference between the Z coordinate value of the converted coordinate value in the three-dimensional coordinate system of the standing scanning CT machine and the spatial coordinate value of the converted depth camera space coordinate system; if the difference is greater than the set change value, the object to be protected exists in the field of view of the detection image; The safety protection method also verifies the recognition range and coverage of the depth camera set at a preset position, wherein the verification includes: along the Z-axis direction, calculating the effective recognition range and coverage in the XOY plane at every preset step value, wherein the effective recognition range is the internal area of ​​the scanning frame of the standing scanning CT machine that is effectively recognized; the coverage is the ratio of the effectively recognized area of ​​interest to the area of ​​interest; each XOY plane is superimposed in the Z-axis direction to obtain the spatial recognition range and coverage of the depth camera.

2. The method for implementing safety protection using a depth camera in a standing scanning CT machine according to claim 1, characterized in that: The method further comprises: Calculate the depth viewing angle and effective field of view of a single depth camera; The minimum distance between the depth camera and the scene is adjusted based on the depth viewing angle and the effective field of view, so as to determine the minimum target distance that can cover the area of ​​interest after the adjustment is completed.

3. The method for implementing safety protection using a depth camera in a standing scanning CT machine according to claim 2, characterized in that: Determining whether the object to be protected is in the danger zone includes: Calculate the distance between the pixel point of the object to be protected within the field of view of the detection image and the center point of the safety area on the same XOY plane; If it is within the preset interval, the object to be protected is in the danger zone.

4. The method for implementing safety protection using a depth camera in a standing scanning CT machine according to claim 3, characterized in that: Determining the position of the object to be protected in the dangerous area based on the distance between the position point of the object to be protected and the center point of the safe area image includes: Based on the depth of the object to be protected, the position in the danger zone is determined.

5. A device for realizing safety protection of a standing scanning CT machine using a depth camera, characterized in that: include: A detection image determination unit is configured to obtain depth information collected by a depth camera set at a preset position of a standing scanning CT machine, and fuse the depth information to obtain a detection image, wherein the depth camera is set in front of and on both sides of the standing position; when determining the preset position of the depth camera, it includes: setting a minimum distance between the depth camera and the scene, wherein the field of view parameter of the depth camera is determined based on the minimum distance, wherein the field of view parameter includes: setting the height of the depth camera in front of the standing position and the depth cameras on both sides of the standing position from the ground, wherein in the XOY plane of the three-dimensional coordinate system of the standing scanning CT machine, the coordinates of the midpoints of the connecting line of each two depth cameras, and the angle between the connecting line and the X-axis are used to describe the position of the depth camera; wherein the coordinate system of the standing scanning CT machine is a Z-axis with the rotation center axis of the standing scanning CT machine, an X-axis with the intersection of the human coronal plane and the mounting surface, an Y-axis with the intersection of the human sagittal plane and the mounting surface, the intersection of the coronal plane and the sagittal plane on the Z-axis, and the intersection of the XYZ axes as the coordinate zero point; An information reading unit is configured to read information about the height of the depth camera from the ground, an inner diameter of a scanning gantry of a standing scanning CT machine, and radius information of a safety area within the inner diameter; The area calibration unit is configured to delimit a circular area in a detection area formed by an inner diameter of a scanning gantry of a standing scanning CT machine within a detection image field of view based on the height information of the depth camera from the ground and the radius information of the safety area as a safety area image in the detection image; a dangerous area determination unit, configured to determine a dangerous area based on the detection area and the safety area; A position determination unit is configured to determine whether the object to be protected is in a dangerous area. If it is in the dangerous area, the position of the object to be protected in the dangerous area is determined based on the distance between the position point of the object to be protected and the center point of the safe area image. Before determining whether the object to be protected is in the dangerous area, the device includes: converting pixel coordinates in the field of view of the detection image into coordinate values ​​in the three-dimensional coordinate system of the standing scanning CT machine; traversing the pixel coordinates in the detection area and converting them into spatial coordinate values ​​in the depth camera space coordinate system; determining the difference between the Z coordinate value of the converted coordinate value in the three-dimensional coordinate system of the standing scanning CT machine and the spatial coordinate value of the converted depth camera space coordinate system; if the difference is greater than the set change value, the object to be protected exists in the field of view of the detection image; The device also verifies the recognition range and coverage of the depth camera set at a preset position, including: along the Z-axis direction, calculating the effective recognition range and coverage in the XOY plane at every preset step value, wherein the effective recognition range is the internal area of ​​the scanning frame of the standing scanning CT machine that is effectively recognized; the coverage is the ratio of the effectively recognized area of ​​interest to the area of ​​interest; each XOY plane is superimposed in the Z-axis direction to obtain the recognition range and coverage of the depth camera in space.

6. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to claim 1 is implemented.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to claim 1 is implemented.

Images