Method and system for generating an object 3D point cloud in an imaging system

Abstract

The method for generating the 3D point cloud of the object in the imaging system comprising the machine table and the scanning device comprises the steps that based on the current height of the machine table and boundary information of the machine table, effective 3D point clouds in an effective area where the machine table is located are extracted from global 3D point clouds, the global 3D point clouds comprise 3D point clouds of the object and the surrounding environment of the object, and the 3D point clouds of the object and the surrounding environment of the object are obtained; the object 3D point cloud is contained in the effective 3D point cloud; and removing an ambient 3D point cloud of an ambient environment including at least a portion of the machine from the valid 3D point cloud to obtain an object 3D point cloud. In some embodiments, a movement path of a machine in an imaging system is planned using an object 3D point cloud. In some embodiments, collision prediction of an object is performed in an imaging system using an object 3D point cloud.

Description

[0001] This invention application is a divisional application of the invention patent application with application number 201910514150.7, application date June 14, 2019, and name “Method and system for generating 3D point cloud of object in imaging system”. Technical Field

[0002] The present disclosure relates to imaging technology, and more particularly to a method and system for generating a 3D point cloud of an object in an imaging system, a method and system for planning a moving path of a machine in an imaging system, and a method and system for predicting collision of an object in an imaging system. Background Art

[0003] Computed tomography (CT) is an imaging method used primarily for medical diagnosis. In CT, an X-ray source and an X-ray detector that works with the X-ray source rotate around a table that carries the patient, and images are taken at different angular positions of the X-ray source and the X-ray detector. The table can move forward and backward along a rotation axis, also called the system axis, and can be raised and lowered in height to move the patient to the position required to perform the scan. After the scan, the scan information is processed to produce a spatial three-dimensional (3D) tomographic X-ray image.

[0004] In traditional CT scans, the operator uses a laser projected onto the patient's body to assist in positioning before the scan begins. However, before this, the operator is required to manually operate the machine to move the patient to a position where the scan can be performed. The positioning accuracy of the machine depends on the operator's experience and may introduce subjective errors of the operator. Public Content

[0005] The inventors have realized that if a 3D point cloud representing the three-dimensional contour of an object can be obtained before starting scanning, the 3D point cloud can be used to assist the operator in moving the machine to a position where the scanning can be performed, so as to reduce or eliminate the operator's manual operation and the introduction of subjective errors. Therefore, it is desirable to provide a method and system that can generate a 3D point cloud of an object in an imaging system.

[0006] One aspect of the present disclosure provides a method for generating a 3D point cloud of an object in an imaging system, wherein the imaging system includes: a platform for carrying an object to be scanned; and a scanning device, the scanning device having a scanning space allowing the platform to enter the inside thereof, the method comprising: extracting a valid 3D point cloud within a valid area where the platform is located from a global 3D point cloud based on a current height of the platform and boundary information of the platform, wherein the global 3D point cloud includes a 3D point cloud of the object and its surroundings, and the object 3D point cloud is included in the valid 3D point cloud; and obtaining the object 3D point cloud by removing an environmental 3D point cloud of the surrounding environment from the valid 3D point cloud, wherein the surrounding environment includes at least a portion of the platform.

[0007] Another aspect of the present disclosure provides a method for planning a moving path of a machine in an imaging system, wherein the imaging system includes: a machine for carrying an object to be scanned; and a scanning device, the scanning device having a scanning space allowing the machine to enter the inside thereof, the method including: determining an area to be scanned in a 3D point cloud of the object based on a scanning plan; determining the center of gravity and the height of the center of gravity of the area to be scanned; determining a target height at which the machine will be positioned based on the height of the center of gravity and the center height of the scanning space, so that when the machine is positioned at the target height, the height of the center of gravity is approximately equal to the center height of the scanning space; and planning the moving path of the machine based on the determined target height, wherein the scanning plan includes positioning information of the area to be scanned relative to the object.

[0008] Another aspect of the present disclosure provides a method for predicting collision of an object in an imaging system, wherein the imaging system includes: a platform for carrying an object to be scanned; and a scanning device, the scanning device having a scanning space allowing the platform to enter the inside thereof, the method including: predicting whether the object will collide with the surrounding environment during movement by determining whether the object's 3D point cloud will overlap with the 3D point cloud of its surrounding environment during movement of the platform along the forward and backward direction of the platform at a planned height. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a schematic diagram of an example imaging system, such as a CT system 100 , according to an embodiment.

[0010] Figure 2 is a flow chart of a method 200 for generating a 3D point cloud of an object according to an embodiment.

[0011] Figure 3 An example global 3D point cloud and an example valid region are shown according to an embodiment.

[0012] Figure 4 An example of a 3D point cloud of an object according to an embodiment is shown.

[0013] Figure 5 A comparison between a 3D point cloud of an object according to an embodiment and a DICOM image captured by a scanning device is shown.

[0014] Figure 6 is a flow chart of a method 600 for generating a 3D point cloud of an object according to another embodiment.

[0015] Figure 7 is a flow chart of a method 700 for planning a moving path of the stage 2 in the imaging system described herein according to an embodiment.

[0016] Figure 8 is a flow chart of a method 800 for performing collision prediction of an object 22 in an imaging system described herein, according to an embodiment.

[0017] Fig. 9 An example interface including security instructions according to an embodiment is shown.

[0018] Fig.10 An example interface including a collision alert is shown according to an embodiment.

[0019] Fig.11 An example interface showing a predicted collision occurrence location according to an embodiment is shown.

[0020] Fig.12 is a block diagram of an example computing device according to an embodiment.

[0021] Attached Figure 1 The various embodiments discussed in this document are generally illustrated by way of example and not by way of limitation. In the accompanying drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. DETAILED DESCRIPTION

[0022] In the following description, numerous specific details are set forth. However, it should be understood that embodiments of the present disclosure may be practiced without these specific details. In other instances, well-known circuits, structures, and techniques are not shown in detail to avoid obscuring the understanding of this description.

[0023] References in the specification to "one embodiment," "an embodiment," "an example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment may include the particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered to be within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments, whether or not explicitly described.

[0024] The embodiments of the present disclosure utilize the depth image data to obtain the object 3D point cloud through calculation, which can be applied not only to the human body, but also to any other object, such as living things other than humans, non-living things, etc., so it is referred to as "object" in this article. In addition, the embodiments of the present disclosure also utilize the object 3D point cloud to plan the movement path of the machine and predict whether the object will collide with the surrounding environment (such as a scanning device) during the movement of the random machine.

[0025] The depth image data described herein may be obtained by taking a depth camera, which may be a structured light-based camera, a stereo camera, or a time-of-flight camera. The image data obtained from a depth camera is generally referred to as RGB-D (RGB+depth) data, which generally includes an RGB image (where each pixel has an RGB value) and a depth image (where the value of each pixel corresponds to the depth or the distance of the pixel from the camera). The present disclosure primarily utilizes depth images. Exemplary CT Systems

[0026] Figure 1 is a schematic diagram of an exemplary imaging system according to an embodiment, such as a CT system 100, which includes a scanning device 1 and a table 2. The scanning device 1 includes a scanning space 12 having a system axis 10, an X-ray source 14 and an X-ray detector 16 arranged relatively on both sides of the scanning space 12, and the X-ray detector 16 can detect X-rays emitted by the X-ray source 14. The table 2 is used to place an object 22, that is, the object 22 is carried by the table 2. The table 2 can move forward and backward along the system axis 10 to enter the scanning space 12 of the scanning device 1. The table 2 can be raised and lowered in the height direction, that is, in the direction perpendicular to the ground, to facilitate the scanning object to get on and off the table 2. When taking an X-ray image (hereinafter referred to as "scanning"), the machine 2 carries the object 22 into the scanning space 12, the X-ray detector 16 and the X-ray source 14 can rotate around the system axis 10 or be stationary, and the X-ray detector 16 receives the X-rays emitted by the X-ray source 14 that pass through the object 22 located in the scanning space 12 for imaging.

[0027] In some embodiments, the CT system includes at least one depth camera 3, which is designed to photograph at least a portion of the surface of the object 22 without contact and output depth image data. In some embodiments, the depth camera 3 is mounted on the top of the room (scanning room) to reduce the field of view (FOV) blind area. In some embodiments, the depth camera 3 can be centrally positioned above the object 22 or centrally positioned above the machine 2. This makes the quality of the depth information about the object 22 and the quality of the 3D point cloud of the object 22 generated thereby as uniform as possible. In some embodiments, the depth camera 3 can be installed or integrated in or on the scanning device 1. In some embodiments, the depth camera 3 can be integrated in the rotatable part of the scanning device 1 so that it can rotate with the X-ray source 14 and the X-ray detector 16, thereby photographing the object 22 at different angles. In some embodiments, the depth camera 3 can be mounted on a positioning device such as a tripod.

[0028] In some embodiments, the CT system includes a computing device 4, which includes a processor 41, which is configured to perform the method described in the embodiments of the present disclosure. In some embodiments, the computing device 4 is designed to load a computer program into its internal memory. The computer program includes commands readable by the computing device 4 and is an inherent part of a computer program product. The computer program product can be stored in a computer-readable medium, for example. The instructions of the computer program readable by the computing device 4 are designed to implement the method according to the present disclosure when the instructions are executed by the processor 41 of the computing device 4.

[0029] Computer-readable media may include, but are not limited to, non-transitory tangible arrangements of articles manufactured or formed by a machine or apparatus, including storage media such as: a hard disk; any other type of disk, including floppy disks, optical disks, compact disk-read only memory (CD-ROM), compact disk-read and writeable (CD-RW), and magneto-optical disks; semiconductor devices such as read-only memory (ROM), random access memory (RAM) such as dynamic random access memory (DRAM) and static random access memory (SRAM), erasable programmable read-only memory (EPROM), flash memory, electrically erasable programmable read-only memory (EEPROM); phase change memory (PCM); magnetic or optical cards; or any other type of medium suitable for storing electronic instructions.

[0030] The computing device 4 is connected to an output unit 5, for example, for displaying various information. The output unit 5 is, for example, a (multiple) LCD, plasma or OLED display. In some embodiments, the output unit 5 can be installed or integrated on the scanning device 1. In addition, the computing device 4 is connected to an input unit 6. The input unit 6 is, for example, used to input information such as control instructions and scanning plans through user interaction. The input unit 6 is, for example, a keyboard, a mouse, a touch screen, or a microphone for voice input. In some embodiments, the scanning device 1 includes a control panel, which may include a flat-panel display as the output unit 5 and a button as the input unit 6. The control panel may also be a flat-panel display with a touch screen.

[0031] The computing device 4 is connected to the depth camera 3 and the scanning device 1, so that the depth image data of the object 22 obtained by the depth camera 3, the scanning data of the scanning device 1, and the real-time position information of the CT system 100 can be transmitted to the computing device 4, wherein the real-time position information of the CT system 100 includes the current position information of each part of the system, such as the current height of the platform 2 and the boundary information of the platform 2. In addition, the computing device 4 can issue instructions to the scanning device 1 and the platform 2 to control the movement of the platform 2 and the scanning of the scanning device 1.

[0032] The example of a CT system is described above, but it should be understood that the method of the present disclosure is also applicable to other imaging systems, such as an XR (X-ray radiography) system, a PET (positron emission tomography) system or an MR (magnetic resonance imaging) system. Method for generating 3D point cloud of exemplary object

[0033] Figure 2 is a flow chart of a method 200 for generating a 3D point cloud of an object according to an embodiment.

[0034] The method of this embodiment generally extracts the effective 3D point cloud of the effective area where the machine 2 is located from the global 3D point cloud including the 3D point cloud of the object 22 and its surrounding environment, and then removes the environmental 3D point cloud of the surrounding environment from the effective 3D point cloud to obtain the object 3D point cloud. Therefore, the object 3D point cloud can be generated from the global 3D point cloud including the 3D point cloud of the object 22 and its surrounding environment.

[0035] Specifically, the method of this embodiment starts at step 202, wherein, based on the current height of the machine 2 and the boundary information of the machine 2, a valid 3D point cloud within the valid area where the machine 2 is located is extracted from the global 3D point cloud, wherein the global 3D point cloud includes the 3D point cloud of the object 22 and its surrounding environment, and the object 3D point cloud is included in the valid 3D point cloud.

[0036] The current height of the platform 2 can be obtained from the real-time position information of the CT system 100. The boundary information of the platform 2 is used to determine the general outline of the platform 2. In some embodiments, the boundary information of the platform 2 can be the position information of the four corners of the platform 2, such as coordinates. It should be noted that this situation does not require the platform 2 to be a strict rectangle, and the corners can be the corners of the circumscribed quadrilateral of the platform 2.

[0037] In some embodiments, the global 3D point cloud can be obtained by converting the depth image data including the object 22 and its surroundings obtained by using the depth camera 3, thereby obtaining a global 3D point cloud including the 3D point cloud of the object 22 and its surroundings. As described above, the depth camera 3 can output RGB image data and depth image data, and the depth image data is used here. In other embodiments, the depth image data can be obtained by an independent shooting system and transmitted to the computing device 4 by wire or wirelessly.

[0038] The depth image data can be converted into point cloud information, i.e., a global 3D point cloud, by a known method. In some embodiments, the global 3D point cloud can be converted from its own coordinate system (e.g., a camera coordinate system) to the coordinate system of the CT system 100. Since the boundary information of the machine 2 is obtained from the real-time position information of the CT system 100, the coordinate system of the CT system 100 is also used as a reference. Therefore, the global 3D point cloud and the boundary information of the machine 2 can be processed in the same coordinate system to extract a valid 3D point cloud. In other embodiments, the boundary information of the machine 2 can be converted from the coordinate system of the CT system 100 to the coordinate system of the global 3D point cloud, such as the camera coordinate system, and then the global 3D point cloud and the boundary information of the machine 2 are processed in the same coordinate system to extract a valid 3D point cloud. Of course, the boundary information of the machine 2 and the global 3D point cloud can also be converted to other coordinate systems for processing, as long as the reference coordinate systems of the two are the same.

[0039] The effective area described herein may be a three-dimensional area including at least a portion of the platform 2 and the object 22 carried by the platform 2. In some embodiments, the effective area may be a three-dimensional area with the carrying surface of the platform 2 as the bottom surface. The height dimension of the effective area may be any height dimension not less than the thickness of the object 22, so as to include the entire object 22. In some embodiments, the entire area above the carrying surface of the platform 2 may be used as the effective area. In some embodiments, the effective area may be a cuboid.

[0040] The length (in the length direction of the platform 2) and the width (in the width direction of the platform 2) of the effective area can be determined based on the length and width of the platform 2 or its circumscribed quadrilateral. In some embodiments, the length and width of the effective area can be substantially equal to the length and width of the platform 2 or its circumscribed quadrilateral, respectively. In some embodiments, the length and width of the effective area can be greater than the length and width of the platform 2 or its circumscribed quadrilateral, respectively.

[0041] Figure 3 An example global 3D point cloud and an example valid region according to an embodiment are shown. Figure 3 As shown, the global 3D point cloud converted from the depth image data contains all information within the field of view of the depth camera 3, that is, the 3D point cloud of the object 22 and its surroundings. The surrounding environment includes, for example, at least a portion of the scanning device 1, the machine platform 2, the ground and / or other equipment, such as Figure 3 By executing step 202, it is possible to extract, for example, Figure 3 The effective 3D point cloud of the effective area indicated by the dotted line in FIG. Figure 3 The effective area in is just an example and can be changed arbitrarily within the scope of the present disclosure.

[0042] Although the effective 3D point cloud extracted by executing step 202 removes most of the environmental 3D point clouds (such as the 3D point cloud of the ground, most of the 3D point clouds of the scanning device 1 and other equipment), it still includes a part of the environmental 3D point cloud, such as the 3D point cloud of the machine 2, a part of the 3D point cloud of the scanning device 1, etc.

[0043] To this end, in step 204, the environment 3D point clouds are further removed from the valid 3D point cloud to obtain the object 3D point cloud.

[0044] The information of the surrounding environment (such as shape, position, and state) is known, so the 3D point cloud of the surrounding environment is also known. In some embodiments, the environmental 3D point cloud can be pre-stored in the computing device 4. In some embodiments, the surrounding environment without the object 22 can be photographed at the same position and in the same orientation using the depth camera 3 to obtain the environmental 3D point cloud of these surrounding environments. Here, it should be understood that the step of photographing the surrounding environment does not require execution every time the object 3D point cloud is generated. For example, it can be executed once after the CT system 100 and the depth camera 3 are installed and the obtained environmental 3D point cloud is saved, and then the environmental 3D point cloud is called each time the object 3D point cloud is generated. In addition, the shooting can also be performed whenever the environment changes (for example, the device position moves, other devices are added). In some embodiments, the environmental 3D point cloud can also be generated by calculation and sampling based on the real-time position information of the CT system 100.

[0045] Figure 4 An example of the object 3D point cloud generated by step 204 is shown, Figure 5 FIG. 1 shows a comparison between the object 3D point cloud and a DICOM (Digital Imaging and Communications in Medicine) image captured by a scanning device (X-ray source 14 and X-ray detector 16). Figure 4 As shown, the object 3D point cloud hardly contains the environment 3D point cloud, and can clearly reflect the structural features of the object 22. Figure 5 In the figure, the dot pattern represents the 3D point cloud of the object described in this article, and the white solid line represents the DICOM image as described above. Figure 5 It can be seen that the object 3D point cloud generated by the method of this embodiment is highly matched with the DICOM image of the object actually photographed, and the object 3D point cloud reflects the structural information of the object 22. Moreover, the method 200 of this embodiment does not need to generate a model of the object to match the preset model, so it can be applied to various objects and is not limited to the human body.

[0046] In some cases, for example, due to the position and posture of the object 22 relative to the platform 2, some part(s) of the object 22 may exceed the boundary of the platform 2. In order to preserve the complete 3D point cloud of the object, the valid area ( Figure 3 The length and width of the effective area (part shown by the dotted line) can be further expanded to prevent the part from being removed. In some embodiments, the width of the effective area can be expanded from the width of the platform 2 (or its circumscribed quadrilateral) to the maximum width of the scanning space 12. In addition, in some cases, an additional mechanism may be provided to the platform 2 and at least a portion of the object 22 is carried on the additional mechanism. If the effective area is set with the length of the platform 2, the object 3D point cloud on the additional mechanism will be removed. To this end, in some embodiments, the length of the effective area can be further expanded based on the length of the platform 2.

[0047] In some embodiments, the object 3D point cloud can be subjected to noise reduction processing. The noise reduction processing can include performing filtering and clustering algorithms. The filtering can be, for example, a Gaussian filter or a moving average filter, which is used to smooth the object 3D point cloud. Clustering can be implemented, for example, using functions in PCL (Point Cloud Library). All points will be clustered into several classes, and then the points of the noise class (e.g., scanning device 1, machine 2) will be deleted.

[0048] In some embodiments, the object 3D point cloud may be downsampled and voxelized to obtain better computational performance.

[0049] In some embodiments, a structural model of the object (eg, a mesh model) may be further generated based on the 3D point cloud of the object to match the model preset in the system.

[0050] Figure 6 FIG. 6 is a flow chart of a method 600 for generating a 3D point cloud of an object according to another embodiment. Figure 2 The difference of the method 200 shown is that an environment 3D point cloud excluding the object 22 is first acquired, and then the environment 3D point cloud is removed from the global 3D point cloud without extracting a valid 3D point cloud.

[0051] Specifically, the method of this embodiment starts at step 601, wherein, before the object 22 is carried on the platform 2, the computing device 4 first receives the depth image data of the surrounding environment that does not include the object 22. The depth image data can be obtained as described above, for example, by being photographed by the depth camera 3. Then, in step 602, the depth image data received in step 601 is converted into a 3D point cloud of the environment.

[0052] Next, in step 603, after the object 22 is carried on the platform 2, a depth image including the object 22 and its surroundings is captured by the depth camera 3 at the same position and orientation as when the depth image of the surroundings is captured in step 601, and then the depth image data is transmitted to the computing device 4. Next, in step 604, the depth image data received in step 603 is converted into a global 3D point cloud.

[0053] Since the position and orientation of the camera for taking the depth images in step 601 and step 603 are the same, the environment 3D point cloud included in the global 3D point cloud can be considered to be the same as the environment 3D point cloud obtained in step 601 .

[0054] Therefore, in step 605 , the environment 3D point cloud obtained in step 602 may be directly removed from the global 3D point cloud to generate the object 3D point cloud.

[0055] The object 3D point cloud generated by methods 200 and 600 described in the embodiments of the present disclosure can enable the operator to intuitively and accurately grasp the contour information of the object 22, and can further use the object 3D point cloud to assist subsequent scanning. Exemplary machine movement path planning method

[0056] Figure 7 is a flow chart of a method 700 for planning a movement path of a stage in an imaging system described herein, according to an embodiment.

[0057] The movement of the platform 2 mainly includes two parts: lifting and moving the platform. Lifting refers to the platform being adjusted from an initial height to a certain height, and moving the platform refers to the platform moving forward or backward along the system axis 10 to a certain position. The planning of the platform movement path described in this article refers to determining the target height that the platform needs to be positioned to perform scanning and planning the movement path of the platform accordingly.

[0058] Specifically, the method of this embodiment starts at step 702, wherein an area to be scanned in the 3D point cloud of the object is determined according to a scanning plan.

[0059] The object 3D point cloud may be generated using the method described in the embodiments of the present disclosure, or may be obtained in other ways, such as converting an object contour model obtained by laser scanning into an object 3D point cloud.

[0060] The area to be scanned can be all or part of the object, such as the human chest, head, or other parts indicated by positioning information. In some embodiments, the scanning plan can be input into the computing device 4 by the operator, for example, including the positioning information of the part to be scanned relative to the object and the shooting parameters of the precise process required to perform the scanning. In some embodiments, the positioning information indicates the position of the area to be scanned relative to the object. In another embodiment, the positioning information is a boundary marker indicating the boundary of the area to be scanned. In the case where the object is a living organism, the boundary marker can be an anatomical landmark of the object, such as a joint landmark, including left and right eyes, left and right knees, left and right waist, groin, left and right wrists, left and right elbows, left and right ribs, center of the chest, bottom of the head, and top of the head.

[0061] In step 704, the center of gravity of the area to be scanned and the height of the center of gravity are determined.

[0062] Next, in step 706, based on the center of gravity height of the area to be scanned and the center height of the scanning space 12 of the scanning device 1, the target height to which the machine platform will be positioned is determined, so that when the machine platform 2 is positioned at the target height, the center of gravity height of the area to be scanned is approximately equal to the center height of the scanning space 12. Here, the center of gravity height and the center height can be referenced to the machine platform 2 or the ground. The determined target height will ensure that the center of gravity of the area to be scanned is approximately at the center of the scanning space 12.

[0063] Finally, in step 708, the moving path of the platform 2 is planned based on the target height determined in step 706. Specifically, the platform 2 can be raised or lowered from an initial height to a target height, wherein the initial height is, for example, a height when the object 22 is carried on the platform 2.

[0064] By adopting the method 700 described in this embodiment, the moving path required for the machine 2 to execute the scanning plan can be automatically planned according to the object 3D point cloud and the scanning plan, thereby avoiding manual operation.

[0065] In some embodiments, the maximum depth that the machine 2 will enter into the scanning device 1 to execute the scanning plan can be further determined based on the position of the boundary of the area to be scanned in the forward and backward direction of the machine (system axis 10) and the scanning range of the scanning device 1. The boundary position of the area to be scanned can be determined based on the positioning information of the part to be scanned included in the scanning plan. Therefore, the movement path of the machine 2 in its forward and backward direction (system axis 10) can be further planned based on the maximum depth. Exemplary Collision Prediction Method

[0066] Figure 8 8 is a flow chart of a method 800 for predicting collision of an object 22 in an imaging system described herein according to an embodiment. The method of this embodiment predicts whether the object 22 will collide with its surroundings during the process of the platform 2 moving forward and backward at the planned height according to the planned height of the platform 2. The planned height of the platform can be obtained based on the exemplary platform movement path planning method described herein.

[0067] The method 800 of this embodiment starts at step 801 , wherein a region to be scanned in the object 3D is determined according to a scanning plan.

[0068] The object 3D point cloud may be generated using the method described in the embodiments of the present disclosure, or may be obtained in other ways, such as converting an object contour model obtained by laser scanning into an object 3D point cloud.

[0069] The area to be scanned may be all or part of the object, such as the human chest, head, or other parts indicated by positioning information. In some embodiments, the scanning plan includes positioning information indicating the part to be scanned. In some embodiments, the positioning information indicates the position of the area to be scanned relative to the object. In another embodiment, the positioning information is a boundary marker indicating the boundary of the area to be scanned. In the case where the object is a living being, the boundary marker may be an anatomical landmark of the object, such as a joint landmark, including left and right eyes, left and right knees, left and right waist, groin, left and right wrists, left and right elbows, left and right ribs, center of the chest, bottom of the head, and top of the head.

[0070] In step 802, the center of gravity of the area to be scanned and the height of the center of gravity are determined.

[0071] Next, in step 803, based on the centroid height of the area to be scanned and the center height of the scanning space 12 of the scanning device 1, the target height to which the machine will be positioned is determined as the planning height, so that when the machine 2 is positioned at the target height, the centroid height of the area to be scanned is approximately equal to the center height of the scanning space 12. Here, the centroid height and the center height can be referenced to the machine 2 or the ground. The determined target height will ensure that the centroid of the area to be scanned is approximately at the center of the scanning space 12.

[0072] Next, in step 804, by determining whether the object 3D point cloud of object 22 will overlap with the environment 3D point cloud during the movement of the platform 2 at the planned height along the forward and backward direction (system axis 10) of the platform 2 determined in step 803, it is predicted whether the object 22 will collide with the surrounding environment during the movement.

[0073] The 3D point cloud of the environment is known as described above, or can be obtained by taking a depth camera.

[0074] When it is predicted in step 804 that the object 22 will not collide with the surrounding environment when the machine 2 moves, the process proceeds to step 805. In step 805, an indication indicating that the object can be safely moved to the scanning position and will not collide with the surrounding environment during the scanning process, i.e., a safety indication, may be presented to the operator. The safety indication may be displayed in the form of text, images, animations, etc., which is not limited in the present disclosure.

[0075] Fig. 9 FIG. 4 shows an example interface including a safety instruction according to an embodiment. The safety instruction may be presented in the human-computer interaction interface of the output unit 5, for example. Fig. 9 As shown, the outer thick solid line represents the scanning space 12, the inner thin solid line represents the boundary of the safe area where no collision occurs, and the figure within the thin solid line is a simulated image of the object 22. Therefore, it goes without saying that a safety margin can be added when predicting a collision, that is, when determining whether the object 3D point cloud will overlap with the environment 3D point cloud during movement. In addition, the simulated image of the object 22 can be generated in real time based on the object 3D point cloud, for example, an image obtained by observing the object 3D point cloud along the system axis 10.

[0076] Since the predicted object 22 will not collide with the surrounding environment when moving with the machine 2, Fig. 9 In the interface shown, it can be observed that all parts of the object are within the circle represented by the thin solid line and a safety indication is presented on the interface. The operator can judge that there will be no collision and can use the automatic movement function of the CT system 100 to automatically move the machine table 2 according to the scanning plan to perform the scan. Fig. 9In the interface shown, the button for confirming the automatic movement of the machine is in an activated state to allow the operator to enable the automatic movement function. It should be understood that Fig. 9 The interface shown is just an example, and each display component can be designed as needed. Fig. 9 The interface shown may be displayed in the output device 5, or on the control panel of the scanning apparatus 1, or both.

[0077] When the operator confirms the automatic movement and performs the scan at the planned height in step 807 , the process ends.

[0078] If it is predicted in step 804 that the object 22 will collide with the surrounding environment as the machine 2 moves, the process proceeds to step 805. In step 805, a collision alarm indicating a collision risk is presented to the operator. The collision alarm may be displayed in the form of text, image, animation, etc., which is not limited in the present disclosure. Fig.10 FIG. 2 shows an example interface including a collision alert according to an embodiment. Since it is predicted that the object 22 will collide with the surrounding environment, Fig.10 As shown, a portion of the object is presented as exceeding the safety boundary represented by the thin solid line, and a "danger" alarm is displayed. In this case, the automatic movement of the machine 2 is prohibited, and the position of the object 22 needs to be changed to eliminate the risk of collision or the operator needs to manually control the movement of the machine 2. Therefore, Fig.10 The button for confirming the automatic movement of the machine 2 on the shown interface becomes disabled.

[0079] In some embodiments, Fig. 9 and Fig.10 The interface shown changes in real time according to the prediction result of step 804 , so that the operator can know the result of the collision prediction in real time and intuitively.

[0080] In some embodiments, the location where the collision is predicted to occur may be further presented in the human-computer interaction interface. Fig.11An example interface showing the predicted collision site according to an embodiment is shown, which further shows the site where the object will collide with, for example, the scanning device 1, and the right hand is represented by a dotted line in the figure. This can help the operator quickly identify the site with a collision risk so as to adjust the position and posture of the object to eliminate the collision risk. The collision site is the site corresponding to the part of the object 3D point cloud that is determined in step 804 to overlap with the environment 3D point cloud during movement. In some embodiments, information is displayed in the interface to prompt the operator that there is a collision risk and to suggest adjusting the object position or manual control. In some embodiments, the interface corresponds to the prediction result of step 804 in real time. In some embodiments, the part predicted to collide is highlighted in a manner different from other parts, and this method is not limited in any way herein. In some embodiments, the degree of collision is further determined according to the degree of overlap between the object 3D point cloud and the environment 3D point cloud during movement, so that the site predicted to collide is presented in the human-computer interaction interface in a manner corresponding to the degree of collision. For example, the more serious the collision, the more eye-catching the site predicted to collide is presented.

[0081] It should be noted that the collision prediction shown in step 804 is performed periodically. Once the collision risk is eliminated by adjusting the position and posture of the object, the process proceeds to step 806. On the contrary, even if it is determined that there is no collision risk, if the position and posture of the object change before the start of scanning and the collision risk re-occurs, the process proceeds to step 805 again via step 804 and a collision alarm is issued.

[0082] In addition, Figure 8 In the method 800 shown, the planned height of the platform 2 is obtained by executing steps 802 and 803. In other embodiments, the current height of the platform 2 may be used as the planned height without executing the moving path planning of the platform 2.

[0083] In addition, Figure 8 In the method 800 shown, collision prediction is performed based on the planned height of the platform 2. However, the following situation may exist: assuming that the position and posture of the object 22 remain unchanged, scanning the entire object 22 may lead to a collision risk, but scanning only a part of the object 22 may not have a collision risk. This is because the areas to be scanned determined according to the scanning plan are different. Therefore, in some embodiments, the movement range of the platform 2 in the forward and backward direction (system axis 10) during the movement process can be further determined based on the position of the boundary of the area to be scanned in the forward and backward direction (system axis 10) of the platform 2 and the scanning range of the scanning device 1. In this way, when performing a collision prediction, the movement range of the platform 2 along the forward and backward direction (system axis 10) can be determined based on the scanning plan, so that a more accurate collision prediction result can be obtained. Exemplary Computing Devices

[0084] Fig.12 1 is a block diagram of an example computing device 1200 according to an embodiment. The computing device 1200 may be, for example, a personal computer (PC), a portable computer, a tablet device, a workstation, or any machine capable of executing instructions (sequentially or otherwise) that specify actions to be taken by the machine. In some embodiments, the computing device 1200 includes, for example: one or more processors 1220; a storage device 1210 for storing one or more programs, which, when executed by the one or more processors 1220, enable the one or more processors 1220 to implement the methods described in the embodiments of the present disclosure. The processor is, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0085] Fig.12 The computing device 1200 shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present disclosure.

[0086] like Fig.12 As shown, the components of computing device 1200 may also be connected to a bus 1250 that connects various system components including storage 1210 and processor 1220 .

[0087] Bus 1250 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0088] The computing device 1200 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 1200, including volatile and non-volatile media, removable and non-removable media.

[0089] Storage device 1210 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1211 and / or cache memory 1212. Computing device 1200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 1213 may be used to read and write non-removable, non-volatile magnetic media ( Fig.12 not shown, usually called a "hard drive"). Although Fig.12 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 1250 via one or more data medium interfaces. The storage device 1210 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0090] A program / utility 1214 having a set (at least one) of program modules 1215 may be stored, for example, in a storage device 1210, such program modules 1215 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. The program modules 1215 generally perform the functions and / or methods of any embodiment described in the present disclosure.

[0091] The computing device 1200 may also communicate with one or more input devices 1260 (e.g., keyboards, pointing devices, etc.) and output devices 1270 (e.g., displays), and may also communicate with one or more devices that enable a user to interact with the computing device 1200, and / or any device that enables the computing device 1200 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through an input / output (I / O) interface 1230. Furthermore, the computing device 1200 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 1240. Fig.12 As shown, the network adapter 1240 communicates with other modules of the computing device 1200 via the bus 1250. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the computing device 1200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0092] The processor 1220 executes various functional applications and data processing by running the programs stored in the storage device 1210, such as implementing the object 3D point cloud generation method, the machine movement path planning method and / or the collision prediction method described in the embodiments of the present disclosure.

[0093] The program code can be implemented in a high-level procedural programming language or an object-oriented programming language to communicate with the processing system. If necessary, the program code can also be implemented in assembly language or machine language. In fact, the mechanism described herein is not limited to the scope of any particular programming language. In any case, the language can be a compiled language or an interpreted language. Example

[0094] The following examples relate to particular inventive embodiments and indicate specific features, elements or steps that may be used or otherwise combined in implementing those embodiments.

[0095] An example of the present disclosure provides a method for generating a 3D point cloud of an object in an imaging system, wherein the imaging system comprises: a platform for carrying an object to be scanned; and a scanning device having a scanning space allowing the platform to enter the inside thereof, the method comprising: extracting a valid 3D point cloud within a valid area where the platform is located from a global 3D point cloud based on a current height of the platform and boundary information of the platform, wherein the global 3D point cloud includes a 3D point cloud of the object and its surroundings, and the object 3D point cloud is included in the valid 3D point cloud; and obtaining the object 3D point cloud by removing an environmental 3D point cloud of the surroundings from the valid 3D point cloud, wherein the surroundings include at least a portion of the platform.

[0096] In one example of the method, the imaging system is a computed tomography (CT) system.

[0097] In an example of the method, the boundary information of the platform includes position information of four corners of the platform, and the effective area is in the shape of a cuboid.

[0098] In one example of the method, in the width direction of the platform, the width of the effective area is greater than the maximum width of the scanning space.

[0099] In one example of the method, the length of the effective area in the length direction of the platform is greater than the length of the platform.

[0100] In one example of the method, a bottom surface height of the effective area is not higher than a current height of the platform.

[0101] In one example of the method, the surrounding environment also includes at least a portion of the scanning device.

[0102] In an example of the method, the method further includes: converting the global 3D point cloud and the boundary information of the machine into the same coordinate system by performing coordinate conversion on at least one of the global 3D point cloud and the boundary information of the machine.

[0103] In one example of the method, the same coordinate system is the coordinate system of the global 3D point cloud itself or the coordinate system of the imaging system.

[0104] In one example of the method, the method further includes: receiving depth image data of the object and its surroundings; and converting the depth image data into the global 3D point cloud through coordinate transformation.

[0105] In one example of the method, the method further includes: voxelizing the object 3D point cloud; and clustering the voxelized object 3D point cloud to remove noise points.

[0106] In an example of the method, the environment 3D point cloud is pre-stored in the imaging system, or is obtained by photographing the surrounding environment with a depth camera before the object is placed on the machine.

[0107] An example of the present disclosure provides a method for planning a moving path of a machine in an imaging system, wherein the imaging system includes: the machine, used to carry an object to be scanned; and a scanning device, the scanning device having a scanning space allowing the machine to enter its interior, the method including: determining an area to be scanned in a 3D point cloud of the object based on a scanning plan; determining the center of gravity of the area to be scanned and the height of the center of gravity; determining a target height at which the machine will be positioned based on the height of the center of gravity and the center height of the scanning space, so that when the machine is positioned to the target height, the height of the center of gravity is approximately equal to the center height of the scanning space; and planning the moving path of the machine based on the determined target height, wherein the scanning plan includes positioning information of the area to be scanned relative to the object.

[0108] In an example of the method, the object 3D point cloud is an object 3D point cloud obtained by using the method described in the above example.

[0109] In one example of the method, it also includes: determining the maximum depth that the machine will enter into the scanning device based on the position of the boundary of the area to be scanned in the forward and backward direction of the machine and the scanning range of the scanning device, and planning the moving path of the machine based on the determined target height and the maximum depth.

[0110] An example of the present disclosure provides a method for predicting collision of an object in an imaging system, wherein the imaging system comprises: a platform for carrying an object to be scanned; and a scanning device having a scanning space allowing the platform to enter the inside thereof, the method comprising: predicting whether the object will collide with the surrounding environment during the movement by determining whether a 3D point cloud of the object will overlap with a 3D point cloud of its surrounding environment during the movement of the platform along the forward and backward directions of the platform at a planned height.

[0111] In an example of the method, the object 3D point cloud is an object 3D point cloud obtained by using the method described in the above example.

[0112] In one example of the method, the planned height is determined by the following steps: determining the area to be scanned in the 3D point cloud of the object based on a scanning plan; determining the center of gravity of the area to be scanned and the height of the center of gravity; and determining the target height at which the machine will be positioned as the planned height based on the height of the center of gravity and the center height of the scanning space, so that when the machine is positioned to the target height, the height of the center of gravity is approximately equal to the center height of the scanning space, wherein the scanning plan includes positioning information of the area to be scanned relative to the object.

[0113] In one example of the method, the planned height is the current height of the platform.

[0114] In one example of the method, it also includes: determining the movement range of the platform along the forward and backward direction during the movement based on the position of the boundary of the area to be scanned in the forward and backward direction and the scanning range of the scanning device.

[0115] In one example of the method, it also includes: when the prediction result is that the object will not collide with the surrounding environment during the movement, providing a safety indication indicating that there will be no collision, and allowing the machine to automatically move into the scanning device for scanning based on the scanning plan, and when the prediction result is that the object will collide with the surrounding environment during the movement, providing a collision alarm indicating that a collision is about to occur and a predicted collision site indication of the site where the collision is predicted to occur.

[0116] In an example of the method, when the prediction result is that the object will collide with the surrounding environment during the movement, the automatic movement of the platform is prohibited.

[0117] In an example of the method, when the prediction result is that the object will collide with the surrounding environment during the movement, manual control of the movement of the platform is allowed.

[0118] In one example of the method, the object 3D point cloud, the safety indication, and the collision alarm are presented in a human-computer interaction interface.

[0119] In one example of the method, the predicted collision location indication is presented in the human-computer interaction interface on a portion of the object 3D point cloud where a collision is predicted to occur.

[0120] In an example of the method, it also includes: when the prediction result is that the object will collide with the surrounding environment during the movement, determining the degree of the collision according to the degree of overlap between the object 3D point cloud and the environment 3D point cloud during the movement.

[0121] In one example of the method, the portion predicted to collide is presented in the human-computer interaction interface in a manner corresponding to the degree of the collision.

[0122] In one example of the method, the display of the human-computer interaction interface changes in real time according to the prediction result.

[0123] An example of the present disclosure provides an imaging system, comprising: a platform for carrying an object to be scanned; a scanning device, the scanning device having a scanning space allowing the platform to enter the inside thereof; a depth camera, for acquiring depth image data of the object and its surrounding environment; and a computing device, the computing device being coupled to the scanning device and the depth camera, for receiving scanning information from the scanning device and the depth image data from the depth camera, and the computing device comprising a processor, the processor being configured to execute a method as described in any one of the above examples.

[0124] In one example of the imaging system, the depth camera is mounted on the ceiling of a room.

[0125] An example of the present disclosure provides a device for use in an imaging system, comprising means for performing the steps in the method as described in any one of the above examples.

[0126] An example of the present disclosure provides a non-transitory computer-readable medium storing a plurality of instructions, which, when executed by a processor, causes the processor to perform a method as described in any one of the above examples.

[0127] The preferred embodiments of the present disclosure are described in detail above. However, it should be understood that the present disclosure can adopt various embodiments and variations without departing from its broad spirit and scope. A person of ordinary skill in the art can make many modifications and changes based on the concept of the present disclosure without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present disclosure on the basis of the prior art should fall within the scope of protection determined by the claims of the present disclosure.

Claims

1. A method for planning a moving path of a machine in an imaging system, wherein the imaging system comprises: The machine is used to carry the object to be scanned; and A scanning device having a scanning space inside which the machine platform is allowed to enter, The method comprises: Determine an area to be scanned in a 3D point cloud of the object based on the scanning plan; Determining the center of gravity of the area to be scanned and the height of the center of gravity; Determining a target height at which the platform will be positioned based on the height of the center of gravity and the center height of the scanning space, so that when the platform is positioned at the target height, the height of the center of gravity is substantially equal to the center height of the scanning space; and Based on the determined target height, planning the moving path of the machine, The scanning plan includes positioning information of the area to be scanned relative to the object.

2. The method according to claim 1, characterized in that The method for obtaining the 3D point cloud of the object includes: Based on the current height of the platform and the boundary information of the platform, extracting a valid 3D point cloud within a valid area where the platform is located from a global 3D point cloud, wherein the global 3D point cloud includes a 3D point cloud of the object and its surroundings, and the object 3D point cloud is included in the valid 3D point cloud; and The object 3D point cloud is obtained by removing the environment 3D point cloud of the surrounding environment from the effective 3D point cloud, wherein the surrounding environment includes at least a part of the machine platform.

3. The method according to claim 1, characterized in that Also includes: The maximum depth that the platform will enter into the scanning device is determined based on the position of the boundary of the area to be scanned in the forward and backward direction of the platform and the scanning range of the scanning device. The step of planning a moving path of the platform plans the moving path of the platform based on the determined target height and the maximum depth.

4. A method for performing collision prediction of an object in an imaging system, wherein the imaging system comprises: A machine platform, used to carry the object to be scanned; and A scanning device having a scanning space inside which the machine platform is allowed to enter, The method comprises: By judging whether the 3D point cloud of the object will overlap with the 3D point cloud of its surrounding environment when the platform moves along the forward and backward direction of the platform at the planned height, it is predicted whether the object will collide with the surrounding environment during the movement.

5. The method according to claim 4, characterized in that The method for obtaining the 3D point cloud of the object includes: Based on the current height of the platform and the boundary information of the platform, extracting a valid 3D point cloud within a valid area where the platform is located from a global 3D point cloud, wherein the global 3D point cloud includes a 3D point cloud of the object and its surroundings, and the object 3D point cloud is included in the valid 3D point cloud; and The object 3D point cloud is obtained by removing the environment 3D point cloud of the surrounding environment from the effective 3D point cloud, wherein the surrounding environment includes at least a part of the machine platform.

6. The method according to claim 4, characterized in that The planning height is determined by the following steps: Determine the area to be scanned in the 3D point cloud of the object based on the scanning plan; Determining the center of gravity of the area to be scanned and the height of the center of gravity; as well as Based on the height of the center of gravity and the center height of the scanning space, a target height at which the platform will be positioned is determined as the planned height, so that when the platform is positioned at the target height, the height of the center of gravity is approximately equal to the center height of the scanning space, The scanning plan includes positioning information of the area to be scanned relative to the object.

7. The method according to claim 4, characterized in that The planned height is the current height of the machine.

8. The method according to claim 4, characterized in that Also includes: The moving range of the platform along the forward and backward direction during the movement is determined based on the position of the boundary of the area to be scanned in the forward and backward direction and the scanning range of the scanning device.

9. The method according to claim 4, characterized in that Also includes: When the prediction result is that the object will not collide with the surrounding environment during the movement, a safety indication indicating that there will be no collision is provided, and the platform is allowed to automatically move into the scanning device for scanning based on the scanning plan, and When the prediction result is that the object will collide with the surrounding environment during the movement, a collision alarm indicating that a collision is about to occur and a predicted collision location indication of a location where a collision is predicted to occur are provided.

10. The method according to claim 9, characterized in that When the prediction result is that the object will collide with the surrounding environment during the movement, the automatic movement of the machine is prohibited.

11. The method according to claim 9, characterized in that When the prediction result is that the object will collide with the surrounding environment during the movement, manual control of the movement of the platform is allowed.

12. The method according to claim 9, characterized in that The object 3D point cloud, the safety indication, and the collision alarm are presented in a human-computer interaction interface.

13. The method according to claim 12, characterized in that The predicted collision location indication is presented in the human-computer interaction interface on the portion of the object 3D point cloud where a collision is predicted to occur.

14. The method of claim 12, further comprising: When the prediction result is that the object will collide with the surrounding environment during the movement, the degree of the collision is determined according to the degree of overlap between the object 3D point cloud and the environment 3D point cloud during the movement.

15. The method according to claim 14, characterized in that The portion predicted to collide is presented in the human-computer interaction interface in a manner corresponding to the degree of the collision.

16. The method according to claim 12, characterized in that The display of the human-computer interaction interface changes in real time according to the prediction result.

Images