Three-dimensional image imaging method and system based on stereoscopic vision

Abstract

The invention belongs to the technical field of X-rays, and particularly relates to a three-dimensional image imaging method and system based on stereoscopic vision. The three-dimensional image imaging method based on stereoscopic vision comprises the following steps: respectively acquiring X-ray image groups of an X-ray source at different orientations of an object to be imaged; the number of the orientations is at least two, and the number of the X-ray images in the X-ray image group is at least two; performing stereo imaging preprocessing on each X-ray image group to obtain a stereo vision image at each orientation; and according to the relative positions between the X-ray source and the object to be imaged and between the X-ray source and the detector at each orientation, fusing each stereoscopic vision image to obtain a three-dimensional image. A stereoscopic vision imaging technology and a digital X-ray imaging technology are combined to obtain a stereoscopic vision image, then a plurality of stereoscopic vision images at different angles are combined to obtain a three-dimensional image, the number of exposure times needed when the three-dimensional image is established is small, and radiation can be effectively reduced.

Description

Technical Field

[0001] The present invention belongs to the field of X-ray technology, and in particular relates to a three-dimensional imaging method and system based on stereoscopic vision. Background Art

[0002] Since the various tissues and organs of the human or animal body have differences in density, thickness, etc., the amount of X-rays projected on them is different, so the intensity distribution of X-rays passing through the human or animal body changes and carries information about the human or animal body, ultimately forming an X-ray information image. Based on this, people have successively developed two-dimensional film X-ray imaging technology, computer radiography (Computed Radiography, referred to as CR) and digital X-ray imaging technology (Digital Radiography, referred to as DR), as well as computed tomography (Computed Tomography, referred to as CT). X-ray imaging technology has been applied to orthopedics, interventional therapy, angiography and other surgeries, as well as industrial fields such as security inspection and quality inspection.

[0003] Among the above imaging technologies, CT, which can form the "three-dimensional" structure of the object to be detected, has the best imaging effect. However, due to the large size of CT imaging equipment, slow imaging speed, the need to perform multiple scans around the object to be detected during imaging, as well as the disadvantages of high radiation and high cost, its application scenarios are greatly limited. It is generally only used for the diagnosis of lesions in more complex parts, and only DR can be used during surgery and treatment. However, since DR can only perform two-dimensional projection imaging, the image formed is easily interfered by the tissue structure at different thicknesses inside the object to be imaged, or by interference from external substances. There is little information available for imaging, and it can only play a small role in surgery, treatment, and industrial inspection.

[0004] It should be noted that the above introduction to the technical background is only for the convenience of providing a clear and complete description of the technical solutions of the present invention and for the convenience of understanding by those skilled in the art. It cannot be considered that the above technical solutions are well known to those skilled in the art simply because these solutions are described in the background technology section of the present invention. Summary of the invention

[0005] The applicant found that the existing CT imaging technology requires multiple shots to form slice images, which has high radiation, large imaging equipment size, and slow imaging speed. The two-dimensional images formed by DR imaging technology have little available information, and the three-dimensional images generated by multiple DR reconstructions also require multiple shots, which has high radiation.

[0006] In order to solve the above technical problems, the present application aims to propose a three-dimensional imaging method and system based on stereoscopic vision, which obtains a stereoscopic vision image by combining stereoscopic vision imaging technology with digital X-ray imaging technology, and then combines multiple stereoscopic vision images at different angles to obtain a three-dimensional image. The number of exposures required to establish a three-dimensional image is small, which can effectively reduce radiation.

[0007] The technical solution of the present invention is as follows:

[0008] One aspect of the present invention provides a three-dimensional imaging method based on stereoscopic vision, comprising the following steps: Respectively acquiring X-ray image groups when the X-ray source is at different positions of the object to be imaged; the positions are at least two, and the X-ray images in the X-ray image group are at least two; Performing stereoscopic imaging preprocessing on each of the X-ray image groups to obtain a stereoscopic visual image at each of the orientations; According to the relative positions of the X-ray source, the object to be imaged and the detector at each of the orientations, each of the stereoscopic visual images is fused to obtain a three-dimensional image.

[0009] Furthermore, in the three-dimensional imaging method based on stereoscopic vision provided by the present invention, the X-ray image group includes an image at a first position and an image at a second position, and the distance between the first position and the second position conforms to the stereoscopic vision effect of the human eye.

[0010] Furthermore, the three-dimensional imaging method based on stereoscopic vision provided by the present invention, wherein each of the X-ray image groups is subjected to stereoscopic imaging preprocessing to obtain a stereoscopic vision image at each of the orientations, specifically comprises: The image at the first position and the image at the second position are subjected to binocular vision imaging processing to obtain a stereoscopic vision image at the position.

[0011] Furthermore, the three-dimensional imaging method based on stereoscopic vision provided by the present invention, wherein the three-dimensional image is obtained by fusing the three-dimensional images according to the relative positions between the X-ray source and the object to be imaged and the detector at each position, and specifically comprises: Performing feature matching on the stereoscopic visual images at each of the positions; Based on the depth of the matched feature in the stereoscopic visual image corresponding to each of the said positions, and the relative position between the X-ray source, the object to be detected and the detector, the position of the feature in the three-dimensional image is determined; and based on the pixel value of the matched feature in the stereoscopic visual image corresponding to each of the said positions, the value of the corresponding voxel in the three-dimensional image is determined to obtain a three-dimensional image.

[0012] Furthermore, in the three-dimensional imaging method based on stereoscopic vision provided by the present invention, the image of the first position includes a high-energy image of the first position and a low-energy image of the first position; the image of the second position includes a high-energy image of the second position and a low-energy image of the second position.

[0013] Furthermore, in the three-dimensional imaging method based on stereoscopic vision provided by the present invention, the stereoscopic imaging preprocessing also includes subtraction imaging processing; and the stereoscopic vision image is a stereoscopic vision subtraction image.

[0014] Furthermore, the three-dimensional imaging method based on stereoscopic vision provided by the present invention, wherein the three-dimensional imaging preprocessing is performed on each of the X-ray image groups to obtain the stereoscopic vision image, specifically comprising: Performing subtraction imaging processing on the first position high-energy image and the first position low-energy image to obtain a first position subtraction image; Performing subtraction imaging processing on the second position high-energy image and the second position low-energy image to obtain a second position subtraction image; Performing corresponding binocular vision imaging processing on the first position subtraction image and the second position subtraction image to obtain the stereoscopic vision subtraction image; or, Performing binocular vision imaging processing on the high-energy image at the first position and the high-energy image at the second position to obtain a high-energy stereo image; Performing binocular vision imaging processing on the first position low-energy image and the second position low-energy image to obtain a low-energy stereo image; Subtraction imaging is performed on the high-energy stereo image and the low-energy stereo image to obtain the stereoscopic vision subtraction image.

[0015] Furthermore, the present invention provides a three-dimensional imaging method based on stereoscopic vision, wherein the stereoscopic vision subtraction image includes a stereoscopic vision first image and a stereoscopic vision second image; and the three-dimensional image is obtained by fusing each of the stereoscopic vision images according to the relative positions between the X-ray source and the object to be imaged and the detector at each of the orientations, specifically comprising: Performing feature matching on the stereoscopic first image at each of the positions to obtain at least one matching first image feature area; Determine the position of the first image feature area in the three-dimensional image based on the depth of the first image feature area in each of the stereoscopic first images, and the relative position between the X-ray source, the object to be detected, and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the first image feature areas, and obtain a three-dimensional image based on the stereoscopic first image; and / or, Performing feature matching on the stereoscopic second image at each of the positions to obtain at least one matching second image feature area; Determine the position of the second image feature area in the three-dimensional image based on the depth of the second image feature area in each of the stereoscopic second images and based on the relative position between the X-ray source, the object to be detected and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the second image feature areas, and obtain a three-dimensional image based on the stereoscopic second image; or, Performing feature matching on the stereoscopic first image at each of the positions to obtain at least one matching first image feature region; performing feature matching on the stereoscopic second image at each of the positions to obtain at least one matching second image feature region; Determine the position of the first image feature area in the three-dimensional image based on the depth of the first image feature area in each of the stereoscopic first images and based on the relative position between the X-ray source, the object to be detected and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the first image feature areas, and obtain a three-dimensional image based on the stereoscopic first image; Determine the position of the second image feature area in the three-dimensional image based on the depth of the second image feature area in each of the stereoscopic second images and based on the relative position between the X-ray source, the object to be detected and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the second image feature areas, and obtain a three-dimensional image based on the stereoscopic second image; The three-dimensional image based on the stereoscopic vision first image and the three-dimensional image based on the stereoscopic vision second image are fused to obtain a fused three-dimensional image.

[0016] Furthermore, in the three-dimensional imaging method based on stereoscopic vision provided by the present invention, the angle between the center points of two adjacent directions and the center point of the object to be imaged is 20°~130°; the distance between each direction and the object to be imaged is the same.

[0017] Another aspect of the present invention provides a three-dimensional imaging system based on stereoscopic vision, comprising: An X-ray imaging mechanism, for obtaining an X-ray image group when the X-ray source is at different positions of the object to be imaged; the positions are at least two, and the X-ray images in the X-ray image group are at least two; A preprocessor, used for performing stereoscopic imaging preprocessing on each of the X-ray image groups to obtain a stereoscopic visual image at each of the orientations; The three-dimensional fusion processor is used to fuse each of the stereoscopic visual images according to the relative positions between the X-ray source, the object to be imaged and the detector at each of the orientations to obtain a three-dimensional image.

[0018] Furthermore, in the three-dimensional imaging system based on stereoscopic vision provided by the present invention, the preprocessor comprises a subtraction imaging processing module and a stereoscopic vision imaging processing module; The subtraction imaging processing module is used to perform subtraction imaging processing on the received high-energy image and low-energy image to obtain a subtraction image; The stereoscopic vision imaging processing module is used to perform stereoscopic vision imaging processing on the received image at the first position and the received image at the second position to obtain corresponding stereoscopic vision images.

[0019] The three-dimensional imaging method and system based on stereoscopic vision provided by the present invention adopt the following steps: respectively obtain X-ray image groups where the X-ray source is at different positions of the object to be imaged; the positions are at least two, and the X-ray images in the X-ray image group are at least two; perform stereoscopic imaging preprocessing on each of the X-ray image groups to obtain stereoscopic visual images at each of the positions; fuse each of the stereoscopic visual images according to the relative positions between the X-ray source, the object to be imaged and the detector at each of the positions to obtain a three-dimensional image design. The two plane X-ray images at one position are processed using the principle of stereoscopic visual imaging to obtain a stereoscopic visual image, and the stereoscopic visual images at multiple positions are fused to obtain a three-dimensional image. When fusing the three-dimensional image, imaging is performed according to the depth information and the relative position between the imaging mechanism at each position and the object to be imaged. Under the premise of ensuring the quality of the three-dimensional image, the demand for the number of plane images is greatly reduced, that is, the demand for the number of exposures is reduced. At least four images can be obtained at two positions to establish a three-dimensional image, which effectively reduces radiation and prolongs the service life of the exposure imaging mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0021] Figure 1 A schematic flow chart of an embodiment of a three-dimensional imaging method based on stereoscopic vision of the present invention is shown.

[0022] Figure 2 A schematic flow chart of an embodiment of fusing the stereoscopic vision images in the three-dimensional image imaging method based on stereoscopic vision of the present invention is shown.

[0023] Figure 3An exemplary flow chart of preprocessing the stereoscopic imaging of the X-ray image group in the three-dimensional imaging method based on stereoscopic vision of the present invention is shown.

[0024] Figure 4 Another exemplary flow chart of preprocessing the stereoscopic imaging of the X-ray image group in the three-dimensional imaging method based on stereoscopic vision of the present invention is shown.

[0025] Figure 5 The electrical connection block diagram of an embodiment of the three-dimensional imaging system based on stereoscopic vision of the present invention is shown. DETAILED DESCRIPTION

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0027] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0028] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprises" and "includes" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0029] Although the present application makes various references to certain modules or units in the system according to the embodiments of the present application, any number of different modules or units can be used and run on the client and / or server. The modules are illustrative only, and different aspects of the system and method can use different modules.

[0030] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, the various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0031] As used herein, the phrase "reconstructing an image" is not intended to exclude embodiments of the present disclosure in which data representing an image is generated rather than a visible image. Thus, as used herein, the term "image" broadly refers to both a visible image and data representing a visible image.

[0032] Figure 1 to Figure 2 This is a flowchart of the three-dimensional imaging method based on stereoscopic vision of the present application. The basic idea is to perform multiple binocular X-ray imaging at different positions of the object to be imaged, perform stereoscopic imaging processing on the X-ray image groups at each position to obtain a stereoscopic vision image containing both the internal structure information of the object to be imaged and the depth information, and then fuse each stereoscopic vision image according to the internal structure information and depth information of the object to be imaged in each stereoscopic vision image to obtain a three-dimensional image. It is possible to obtain three-dimensional image information through fewer exposures, reduce the number of exposures and reduce radiation, and also extend the service life of the imaging mechanism.

[0033] Embodiment 1

[0034] See also Figure 1 As shown, this embodiment provides a three-dimensional imaging method based on stereoscopic vision, including: S1: respectively acquiring a group of X-ray images when the X-ray source is located at different positions of the object to be imaged; the number of the positions is at least two, and the number of the X-ray images in the group of X-ray images is at least two; S2: performing stereoscopic imaging preprocessing on each of the X-ray image groups to obtain a stereoscopic visual image at each of the positions; S3: According to the relative positions of the X-ray source, the object to be imaged and the detector at each of the orientations, each of the stereoscopic visual images is fused to obtain a three-dimensional image.

[0035] In this embodiment, when stereoscopic visual images at more than two of the above-mentioned directions are obtained, the information in the stereoscopic visual images at each of the above-mentioned directions can be fused according to the back-projection principle to obtain a three-dimensional image, and the voxel point information of the three-dimensional image can be obtained through the depth information in the stereoscopic visual image, which effectively replaces the need for multiple imaging around the object to be imaged in traditional three-dimensional imaging. The stereoscopic information of each voxel point can be obtained based on a large amount of planar projection data around the object to be imaged, thereby reducing the need for imaging times, reducing radiation and imaging costs, and making X-ray three-dimensional imaging applicable to more scenarios.

[0036] In the method of obtaining the X-ray image group in this embodiment, one X-ray source can be used to change the relative position between the object to be imaged and the X-ray source by moving the object to be imaged, and imaging is performed at different relative positions to obtain the X-ray image group; at least two X-ray sources can also be used, each X-ray source is at a different position of the object to be imaged, so that each X-ray source emits an X-ray beam to penetrate the object to be imaged for imaging, and obtain the X-ray image group. Different methods for obtaining the X-ray image group need to be matched with different stereoscopic imaging processing methods, and different stereoscopic imaging methods have different characteristics. One X-ray source is suitable for cooperating with monocular stereoscopic imaging to obtain stereoscopic images. This method has the characteristics of a small number of X-ray sources required and the object to be imaged is movable. When in use, the object to be imaged can be placed on a conveyor belt, and the object to be imaged can be driven by the conveyor belt. The X-ray source is controlled to perform exposure imaging at a preset time interval or when the object to be imaged is at a predetermined position on the conveyor belt, thereby obtaining a three-dimensional image. The method of one X-ray source is particularly suitable for industrial inspection. In this embodiment, two X-ray sources are suitable for cooperating with binocular visual imaging. During binocular visual imaging, the object to be imaged does not need to be moved. It is only necessary to obtain a two-dimensional plane X-ray image at two positions that are close to each other, and a stereoscopic visual image can be formed according to the distance between the two positions. This method is particularly suitable for scenes such as medical examinations or interventional surgical treatments where the object to be imaged is not suitable for movement or the X-ray source has limited space for movement. Multiple X-ray sources are suitable for stereoscopic visual imaging in conjunction with multi-eye stereoscopic visual imaging. Scenes suitable for binocular visual imaging can also use multiple X-ray sources and multi-eye stereoscopic visual imaging. In this embodiment, the principles, processing procedures, etc. of monocular stereoscopic visual imaging, binocular visual imaging, and multi-eye stereoscopic visual imaging are all existing technologies and will not be described in detail here.

[0037] Binocular vision imaging has the advantages of requiring fewer exposures and imaging times, and forming a stereoscopic vision image with higher accuracy. In this embodiment, in order to be able to perform the stereoscopic imaging preprocessing on the X-ray image group, it is necessary to obtain at least two images at each of the orientations, and the distance between the imaging mechanisms for obtaining the two images also needs to conform to the stereoscopic vision imaging effect of the human eye. Therefore, the X-ray image group includes an image at a first position and an image at a second position, and the distance between the first position and the second position conforms to the stereoscopic vision effect of the human eye.

[0038] Based on the image at the first position and the image at the second position, in this embodiment, the stereoscopic imaging preprocessing is performed on each of the X-ray image groups to obtain the stereoscopic visual image at each of the positions, specifically including: S21: Perform binocular vision imaging processing on the image at the first position and the image at the second position to obtain a stereoscopic vision image at the position.

[0039] The image obtained by binocular vision imaging processing contains both information about the X-ray energy absorbed by the object to be photographed and position information. Three-dimensional information of some internal structures can be obtained from a single image, and more three-dimensional information of the internal structure can be obtained by combining multiple images. Combining stereo vision imaging with back projection imaging effectively reduces the demand for the number of two-dimensional projection images when forming three-dimensional images. When establishing a stereoscopic vision image, binocular vision imaging is selected. Based on the requirements of binocular vision imaging, the distance between the first position and the second position is pre-determined, and then images are acquired at the first position and the second position respectively, ensuring that a stereoscopic vision image can be obtained through the acquired images. Taking advantage of the mature binocular vision imaging processing technology and the easy-to-control image acquisition method, the accuracy of the stereoscopic vision image is effectively guaranteed.

[0040] See also Figure 2 As shown, in this embodiment, according to the relative positions between the X-ray source, the object to be imaged and the detector at each of the orientations, each of the stereoscopic visual images is fused to obtain a three-dimensional image, specifically including: S31: performing feature matching on the stereoscopic visual images at each of the positions; S32: Based on the depth of the matched feature in the stereoscopic visual image corresponding to each of the said positions, and the relative position between the X-ray source, the object to be detected and the detector, determine the position of the feature in the three-dimensional image; and based on the pixel value of the matched feature in the stereoscopic visual image corresponding to each of the said positions, determine the value of the corresponding voxel in the three-dimensional image to obtain a three-dimensional image.

[0041] In this embodiment, feature matching of the stereoscopic visual images at each of the orientations may include, respectively, feature recognition of each of the stereoscopic visual images to obtain a plurality of feature regions; matching the feature regions in each of the stereoscopic visual images to obtain feature regions of each of the stereoscopic visual images representing the same structure inside the object to be imaged. Among them, matching the feature regions in each of the stereoscopic visual images may be manually marked. It may also be marked by a deep learning model. A feature relationship library may also be established, in which a subset of projection images of each structure inside the object to be imaged is stored, and images of the structure projected in various directions are stored in any subset of projection images; when matching the feature regions in each of the stereoscopic visual images, the feature regions in each of the stereoscopic visual images are compared with all the projection images in the feature relationship library, and the feature regions of the stereoscopic visual images belonging to the same subset of projection images are feature regions representing the same structure inside the object to be imaged.

[0042] In this embodiment, the position of the feature in the three-dimensional image is determined based on the depth of the matched feature in the stereoscopic image corresponding to each of the orientations, the relative position between the X-ray source, the object to be detected and the detector. It can be determined directly based on the position and depth of the matched stereoscopic image at each of the orientations. It can also be adopted to establish the relationship between the position of the projection and the structure in each direction in each projection image subset in the feature relationship library, and determine the position of the feature area in each stereoscopic image in the three-dimensional image based on the relationship.

[0043] In this embodiment, the more the number of directions is, the richer the detail features of the established three-dimensional image are. However, the more the number of directions is, the greater the amount of calculation is. Those skilled in the art can select the number of directions as needed, which will not be elaborated here.

[0044] In this embodiment, the angle between the center point of two adjacent positions and the center point of the object to be imaged is 20°, which can also be 130°, or any angle between 20° and 130°. Preferably, the angle between the center point of two of the positions and the center point of the object to be imaged is 90°. In order to facilitate the rapid and accurate establishment of a three-dimensional image based on the stereoscopic subtraction images at each position, the distance between each position and the object to be imaged is the same. If the distance is the same, there is no need to consider the spatial difference caused by the distance between each position and the object to be imaged when performing three-dimensional imaging, which helps to quickly establish a three-dimensional image.

[0045] Embodiment 2

[0046] This embodiment is an improvement on the first embodiment. This embodiment can obtain a subtracted three-dimensional image. The method for obtaining the subtracted three-dimensional image is described below. The solution that has been disclosed in the first embodiment will not be repeated here.

[0047] In this embodiment, the image of the first position includes a first position high energy image and a first position low energy image; the image of the second position includes a second position high energy image and a second position low energy image. The stereo imaging preprocessing also includes subtraction imaging processing; the stereo vision image is a stereo vision subtraction image.

[0048] See also Figure 3 As shown, in this embodiment, the stereoscopic imaging preprocessing is performed on each of the X-ray image groups to obtain the stereoscopic visual image, specifically including: S301: performing subtraction imaging processing on the high-energy image of the first position and the low-energy image of the first position to obtain a subtraction image of the first position; S302: performing subtraction imaging processing on the second position high-energy image and the second position low-energy image to obtain a second position subtraction image; S303: Perform corresponding binocular vision imaging processing on the first position subtraction image and the second position subtraction image to obtain the stereoscopic vision subtraction image.

[0049] The stereoscopic vision subtraction image can be obtained through the above steps S301 to S303; the above steps take the approach of first performing subtraction processing and then performing binocular vision imaging processing. The tissue structure in the image after subtraction processing is clearer and easier to identify. It has the characteristics of less interference information when performing binocular vision imaging and finding corresponding pixel points in the two images to be stereoscopically imaged, so that the obtained stereoscopic vision image is more accurate.

[0050] See also Figure 4 As shown, in this embodiment, of course, a stereoscopic imaging process can be performed first, and then a subtraction process can be performed to obtain a stereoscopic visual subtraction image. At this time, the stereoscopic imaging preprocessing is performed on each of the X-ray image groups to obtain the stereoscopic visual image, which specifically includes: S311: performing binocular vision imaging processing on the high-energy image at the first position and the high-energy image at the second position to obtain a high-energy stereo image; S312: performing binocular vision imaging processing on the first position low-energy image and the second position low-energy image to obtain a low-energy stereo image; S313: Perform subtraction imaging processing on the high-energy stereo image and the low-energy stereo image to obtain the stereoscopic vision subtraction image.

[0051] It is chosen to first establish a stereo image, and then perform high- and low-energy subtraction on the stereo image to establish a subtracted stereo image. The basic image when establishing the stereo image contains rich information, which helps to ensure the richness of the stereo image information.

[0052] In this embodiment, the stereoscopic visual subtraction image includes a stereoscopic visual first image and a stereoscopic visual second image; the fusion of each stereoscopic visual image according to the relative position between the X-ray source and the object to be imaged and the detector at each position to obtain a three-dimensional image specifically includes the following steps: S401: performing feature matching on the stereoscopic first image at each of the positions to obtain at least one matching first image feature area; S402: Determine the position of the first image feature area in the three-dimensional image based on the depth of the first image feature area in each of the stereoscopic first images and the relative position between the X-ray source, the object to be detected and the detector; S403: determining the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the first image feature regions, to obtain a three-dimensional image based on the stereoscopic first image; And / or, the step of fusing the stereoscopic images to obtain a three-dimensional image according to the relative positions of the X-ray source, the object to be imaged and the detector at each of the positions specifically comprises the following steps: S411: performing feature matching on the stereoscopic second image at each of the positions to obtain at least one matching second image feature area; S412: Determine the position of the second image feature area in the three-dimensional image based on the depth of the second image feature area in each of the stereoscopic second images and based on the relative position between the X-ray source, the object to be detected and the detector; S413: Determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the second image feature areas, and obtain a three-dimensional image based on the stereoscopic vision second image.

[0053] Through the above steps S401 to S403, S411 to S413, a three-dimensional image is established for one of the stereoscopic subtraction images. When only one type of three-dimensional image is established, only this type of three-dimensional image can be displayed. When three-dimensional images are established for both stereoscopic subtraction images, two three-dimensional images can be displayed. When displayed, they can be displayed simultaneously in split screens, or one type of three-dimensional image can be displayed as needed and selected. When subtraction imaging of soft tissue and bone tissue of a human or animal body is performed, the established three-dimensional image can be a soft tissue three-dimensional image or a bone tissue three-dimensional image. Those skilled in the art can select subtraction imaging parameters as needed to obtain the required subtraction image, and then obtain the required type of three-dimensional image. Setting different subtraction imaging parameters according to the required subtraction image type is a prior art and will not be described in detail here.

[0054] By selecting any type of stereoscopic subtraction image for fusion, a corresponding type of three-dimensional image can be obtained. In order to enrich the content of the three-dimensional image information, two different types of images of the stereoscopic subtraction image can also be fused. At this time, according to the relative position between the X-ray source and the object to be imaged and the detector at each of the said positions, each of the said stereoscopic images is fused to obtain a three-dimensional image, specifically including: S421: performing feature matching on the stereoscopic first image at each of the positions to obtain at least one matching first image feature area; S422: performing feature matching on the stereoscopic second image at each of the positions to obtain at least one matching second image feature area; S423: determining a position of the first image feature region in the three-dimensional image based on the depth of the first image feature region in each of the stereoscopic first images and based on the relative position between the X-ray source, the object to be detected and the detector; S424: determining the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the first image feature areas, to obtain a three-dimensional image based on the stereoscopic first image; S425: determining a position of the second image feature area in the three-dimensional image based on the depth of the second image feature area in each of the stereoscopic second images and based on the relative position between the X-ray source, the object to be detected and the detector; S426: determining the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the second image feature regions, to obtain a three-dimensional image based on the stereoscopic second image; S427: Fusing the three-dimensional image based on the stereoscopic vision first image and the three-dimensional image based on the stereoscopic vision second image to obtain a fused three-dimensional image.

[0055] This embodiment adopts the method of first separately obtaining two types of three-dimensional images corresponding to the stereoscopic visual subtraction image, and then fusing the two types of three-dimensional images. The corresponding tissue features are enhanced in the subtracted stereoscopic visual image, and the corresponding tissue structure is clearer. The two subtracted three-dimensional images with clear structures are fused to improve the clarity of the obtained three-dimensional image.

[0056] In this embodiment, the subtraction image obtained after subtraction processing and stereo imaging processing not only contains three-dimensional information such as depth, but also enhances the required tissue structure. For example, the stereoscopic image of bone tissue mainly shows the structure and depth of the bone, and the edge structure of the bone is clear. When medical staff read the film, they can quickly identify the position of the bone in the image, which makes identification easy.

[0057] Embodiment 3

[0058] This embodiment provides a system for implementing the above-mentioned three-dimensional image forming method based on stereoscopic vision.

[0059] See also Figure 5 As shown, the three-dimensional imaging system based on stereoscopic vision provided in this embodiment includes: An X-ray imaging mechanism 501 is used to obtain an X-ray image group when the X-ray source is located at different positions of the object to be imaged; the positions are at least two, and the X-ray images in the X-ray image group are at least two; A preprocessor 502, configured to perform stereoscopic imaging preprocessing on each of the X-ray image groups to obtain a stereoscopic visual image at each of the orientations; The three-dimensional fusion processor 503 is used to fuse each of the stereoscopic visual images according to the relative positions between the X-ray source, the object to be imaged and the detector at each of the orientations to obtain a three-dimensional image.

[0060] The X-ray imaging mechanism is electrically connected to the preprocessor, the preprocessor is electrically connected to the three-dimensional fusion processor, and the three-dimensional image processor is electrically connected to a display; the display is used to display the fused three-dimensional image.

[0061] In this embodiment, the preprocessor includes a subtraction imaging processing module and a stereoscopic vision imaging processing module electrically connected to each other; The subtraction imaging processing module is used to perform subtraction imaging processing on the received high-energy image and low-energy image to obtain a subtraction image; The stereoscopic vision imaging processing module is used to perform stereoscopic vision imaging processing on the received image at the first position and the received image at the second position to obtain corresponding stereoscopic vision images.

[0062] In this embodiment, the X-ray imaging mechanism includes a first imaging exposure mechanism placed at a first position and a second imaging exposure mechanism placed at a second position, and a detector arranged opposite to the first imaging exposure mechanism and the second imaging exposure mechanism; the detector is arranged at intervals between the first imaging exposure mechanism and the second imaging exposure mechanism, and a storage table for accommodating the object to be imaged is arranged between the detector and the first imaging exposure mechanism and the second imaging exposure mechanism. Preferably, the storage table is placed in the middle between the first imaging exposure mechanism and the second imaging exposure mechanism.

[0063] The present invention also relates to a storage medium on which computer program code is stored. When the program code is executed, various embodiments of the method of the present invention can be implemented. The storage medium can be a tangible storage medium, such as a CD, a USB flash drive, a floppy disk, a hard disk, etc.

[0064] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted on a transmission medium or a communication link via a data signal carried in a carrier. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, and the like. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0065] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0066] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or replace features of other embodiments.

[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A three-dimensional imaging method based on stereoscopic vision, characterized in that: The following steps are involved: Respectively acquiring X-ray image groups when the X-ray source is at different positions of the object to be imaged; the positions are at least two, and the X-ray images in the X-ray image group are at least two; Performing stereoscopic imaging preprocessing on each of the X-ray image groups to obtain a stereoscopic visual image at each of the orientations; According to the relative positions of the X-ray source, the object to be imaged and the detector at each of the orientations, each of the stereoscopic visual images is fused to obtain a three-dimensional image.

2. The three-dimensional imaging method based on stereoscopic vision according to claim 1, characterized in that: The X-ray image group includes an image at a first position and an image at a second position, and the distance between the first position and the second position conforms to the stereoscopic vision effect of human eyes.

3. The three-dimensional imaging method based on stereoscopic vision according to claim 2, characterized in that: The performing stereoscopic imaging preprocessing on each of the X-ray image groups to obtain a stereoscopic visual image at each of the orientations specifically includes: The image at the first position and the image at the second position are subjected to binocular vision imaging processing to obtain a stereoscopic vision image at the position.

4. The three-dimensional imaging method based on stereoscopic vision according to claim 3, characterized in that: According to the relative positions between the X-ray source, the object to be imaged and the detector at each of the positions, the three-dimensional visual images are fused to obtain a three-dimensional image, specifically including: Performing feature matching on the stereoscopic visual images at each of the positions; Based on the depth of the matched feature in the stereoscopic visual image corresponding to each of the said positions, and the relative position between the X-ray source, the object to be detected and the detector, the position of the feature in the three-dimensional image is determined; and based on the pixel value of the matched feature in the stereoscopic visual image corresponding to each of the said positions, the value of the corresponding voxel in the three-dimensional image is determined to obtain a three-dimensional image.

5. The three-dimensional imaging method based on stereoscopic vision according to any one of claims 2 to 4, characterized in that: The image of the first position includes a first position high-energy image and a first position low-energy image; the image of the second position includes a second position high-energy image and a second position low-energy image.

6. The three-dimensional imaging method based on stereoscopic vision according to claim 5, characterized in that: The stereoscopic imaging preprocessing also includes subtraction imaging processing; the stereoscopic vision image is a stereoscopic vision subtraction image.

7. The three-dimensional imaging method based on stereoscopic vision according to claim 6, characterized in that: The step of performing stereoscopic imaging preprocessing on each of the X-ray image groups to obtain the stereoscopic visual image specifically includes: Performing subtraction imaging processing on the first position high-energy image and the first position low-energy image to obtain a first position subtraction image; Performing subtraction imaging processing on the second position high-energy image and the second position low-energy image to obtain a second position subtraction image; Performing corresponding binocular vision imaging processing on the first position subtraction image and the second position subtraction image to obtain the stereoscopic vision subtraction image; or, Performing binocular vision imaging processing on the high-energy image at the first position and the high-energy image at the second position to obtain a high-energy stereo image; Performing binocular vision imaging processing on the first position low-energy image and the second position low-energy image to obtain a low-energy stereo image; Subtraction imaging is performed on the high-energy stereo image and the low-energy stereo image to obtain the stereoscopic vision subtraction image.

8. The three-dimensional imaging method based on stereoscopic vision according to claim 7, characterized in that: The stereoscopic visual subtraction image includes a stereoscopic visual first image and a stereoscopic visual second image; the fusion of each stereoscopic visual image according to the relative position between the X-ray source and the object to be imaged and the detector at each position to obtain a three-dimensional image specifically includes: Performing feature matching on the stereoscopic first image at each of the positions to obtain at least one matching first image feature area; Determine the position of the first image feature area in the three-dimensional image based on the depth of the first image feature area in each of the stereoscopic first images, and the relative position between the X-ray source, the object to be detected, and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the first image feature areas, and obtain a three-dimensional image based on the stereoscopic first image; and / or, Performing feature matching on the stereoscopic second image at each of the positions to obtain at least one matching second image feature area; Determine the position of the second image feature area in the three-dimensional image based on the depth of the second image feature area in each of the stereoscopic second images and based on the relative position between the X-ray source, the object to be detected and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the second image feature areas, and obtain a three-dimensional image based on the stereoscopic second image; or, Performing feature matching on the stereoscopic first image at each of the positions to obtain at least one matching first image feature region; performing feature matching on the stereoscopic second image at each of the positions to obtain at least one matching second image feature region; Determine the position of the first image feature area in the three-dimensional image based on the depth of the first image feature area in each of the stereoscopic first images and based on the relative position between the X-ray source, the object to be detected and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the first image feature areas, and obtain a three-dimensional image based on the stereoscopic first image; Determine the position of the second image feature area in the three-dimensional image based on the depth of the second image feature area in each of the stereoscopic second images and based on the relative position between the X-ray source, the object to be detected and the detector; determine the value of the corresponding voxel in the three-dimensional image according to the pixel value of each of the second image feature areas, and obtain a three-dimensional image based on the stereoscopic second image; The three-dimensional image based on the stereoscopic vision first image and the three-dimensional image based on the stereoscopic vision second image are fused to obtain a fused three-dimensional image.

9. The three-dimensional imaging method based on stereoscopic vision according to claim 8, characterized in that: The angle formed by the line connecting the center points of two adjacent directions and the center point of the object to be imaged is 20° to 130°; and the distance between each direction and the object to be imaged is the same.

10. A three-dimensional imaging system based on stereoscopic vision, characterized in that: include: An X-ray imaging mechanism, for obtaining an X-ray image group when the X-ray source is at different positions of the object to be imaged; the positions are at least two, and the X-ray images in the X-ray image group are at least two; A preprocessor, used for performing stereoscopic imaging preprocessing on each of the X-ray image groups to obtain a stereoscopic visual image at each of the orientations; A three-dimensional fusion processor, used for fusing each of the stereoscopic visual images according to the relative positions between the X-ray source, the object to be imaged and the detector at each of the orientations to obtain a three-dimensional image; Wherein, the preprocessor includes a subtraction imaging processing module and a stereoscopic vision imaging processing module; The subtraction imaging processing module is used to perform subtraction imaging processing on the received high-energy image and low-energy image to obtain a subtraction image; The stereoscopic vision imaging processing module is used to perform stereoscopic vision imaging processing on the received image at the first position and the received image at the second position to obtain corresponding stereoscopic vision images.

Images