Detection method and device, computer equipment, storage medium and program product

By acquiring and superimposing images between magnetic resonance equipment scanning, eliminating parallax and accurately determining the position and type of objects on the ground, the problem of inaccurate positioning in traditional technology is solved, and the accuracy and practicality of safety detection is improved.

CN119067906APending Publication Date: 2024-12-03WUHAN UNITED IMAGING HEALTHCARE SURGICAL TECH CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202310628030.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The accuracy of object safety detection in the scanning room of traditional magnetic resonance equipment is low, mainly due to inaccurate positioning due to parallax problems, and it is impossible to effectively determine whether the object is in the preset safety area.

Method used

By acquiring at least two images between the scans, projecting them to the plane where the ground is located, superimposing processing, eliminating the influence of parallax, and generating a target image, thereby accurately determining the position information of the object on the ground, and determining whether the object is in the pre-predictive position based on the position information. Set in a safe area.

Benefits of technology

It improves the accuracy of detection of object safety issues in the scanning room, ensures the practicality and efficiency of the detection method, and can more accurately determine whether the object is in the preset safety area, reducing misjudgment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067906A_ABST
    Figure CN119067906A_ABST
Patent Text Reader

Abstract

The invention relates to a detection method and device, computer equipment, a storage medium and a program product, the detection method is applied to a scanning room of magnetic equipment, at least two first images of the scanning room are obtained, the first images are projected to a plane where the ground is located, and a plurality of second images are obtained; performing superposition processing on the plurality of second images to obtain a target image; and under the condition that the target image comprises the target object, determining position information of the target object on the ground, and determining whether the target object is in a preset safety area according to the position information. By using the detection method provided by the invention, whether the target object is in the preset safety area can be more accurately determined, and the accuracy of determining whether the object has a safety problem is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of magnetic resonance equipment, and in particular to a detection method, device, computer equipment, storage medium and program product. Background Art

[0002] MRI equipment often uses superconducting magnets. Usually, the magnets are always in the "on" state, resulting in a high-intensity magnetic field around the MRI equipment. High-field MRI equipment can pose safety risks, and common risks include safety issues such as projection effects and biological effects caused by special physical environments such as static magnetic fields, gradient magnetic fields, and radio frequency pulses.

[0003] In conventional technology, the position of an object entering a scanning room where a magnetic resonance imaging device is located is usually detected to determine whether the object poses a safety problem.

[0004] However, conventional techniques for detecting whether objects in a scanning room have safety issues have low accuracy. Summary of the invention

[0005] Based on this, it is necessary to provide a detection method, device, computer equipment, read storage medium and program product that can improve the accuracy of detecting whether there are safety issues with objects in the scanning room in order to address the above technical problems.

[0006] In a first aspect, the present application provides a detection method, which is applied to a magnetic device scanning room, and the method comprises:

[0007] Acquire at least two first images between scans, and project the first images onto a plane where the ground is located to obtain a plurality of second images;

[0008] Performing superposition processing on the multiple second images to obtain a target image;

[0009] In the case where the target object is included in the target image, the position information of the target object on the ground is determined, and it is determined whether the target object is within a preset safety area according to the position information.

[0010] In one embodiment, determining the position information of the target object on the ground includes:

[0011] The contact position between the target object and the ground is used as the position information of the target object on the ground.

[0012] In one embodiment, determining whether the target object is within a preset safety area according to the location information includes:

[0013] Determine the type of target object;

[0014] Determine whether the target object is within the preset safety area based on the type and location information.

[0015] In one embodiment, determining the type of the target object includes:

[0016] Perform type recognition on the target object in the target image to obtain the type of the target object;

[0017] or,

[0018] Identify the logo of the target object in the target image and obtain a recognition result;

[0019] Determine the type of the target object based on the recognition results.

[0020] In one embodiment, performing superposition processing on a plurality of second images to obtain a target image includes:

[0021] For each second image, obtaining feature points of each second image, and matching the feature points to determine similar points;

[0022] The plurality of second images are superimposed according to the similar points to obtain a target image.

[0023] In one embodiment, a plurality of second images are superimposed based on similar points to obtain a target image, including:

[0024] Performing a superposition process on the plurality of second images according to the similar points to obtain a superimposed image;

[0025] Determine stitching information according to the object boundary of the overlapping area in the superimposed image;

[0026] The brightness of the superimposed image is processed according to the stitching information to obtain the target image.

[0027] In one embodiment, the method further comprises:

[0028] determining the location of the magnetic device in the target image;

[0029] A preset safety area is determined based on the location of the magnetic device and the isomagnetic field lines of the magnetic device.

[0030] In one embodiment, the first image is projected onto a plane where the ground is located to obtain a plurality of second images, including:

[0031] Acquire first positions of at least four marking points on the ground, and second positions of at least four marking points in any one of the first images;

[0032] Determine a homography matrix according to the first position and the second position;

[0033] According to the homography matrix, the first image is projected onto the ground to obtain a plurality of second images.

[0034] In one embodiment, the method further comprises:

[0035] When the target object is not in the preset safety area, an alarm message corresponding to the type of the target object is output.

[0036] In a second aspect, the present application provides a detection method, which is applied to a scanning room of a magnetic device, and the method comprises:

[0037] Acquire at least two first images during scanning, and project the first images onto a preset plane to obtain a plurality of second images;

[0038] Performing superposition processing on the multiple second images to obtain a target image;

[0039] In the case where the target object is included in the target image, the target image is projected onto the plane where the ground is located, the position information of the target object on the ground is determined, and it is determined whether the target object is within the preset safety area according to the position information.

[0040] In a third aspect, the present application provides a detection device, the detection device comprising an image collector and a processor, the image collector being arranged in a magnetic device scanning room;

[0041] An image collector, for acquiring at least two first images between scans and transmitting the first images to a processor;

[0042] A processor is used to execute the steps of the method provided in the first aspect and the second aspect as described above.

[0043] In a fourth aspect, the present application provides a detection device, the detection device comprising:

[0044] An acquisition module, used for acquiring at least two first images during scanning, and projecting the first images onto a plane where the ground is located to obtain a plurality of second images;

[0045] A superposition module, used for superimposing a plurality of second images to obtain a target image;

[0046] The determination module is used to determine the position information of the target object on the ground when the target image includes the target object, and determine whether the target object is within a preset safety area according to the position information.

[0047] In a fifth aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the first and second aspects above are implemented.

[0048] In a sixth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first and second aspects above.

[0049] In a seventh aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method provided in the first and second aspects above.

[0050] The above detection method, device, computer equipment, storage medium and program product obtain at least two first images in the scanning room, project the first images onto the plane where the ground is located, and obtain multiple second images; superimpose the multiple second images to obtain a target image; when the target image includes the target object, determine the position information of the target object on the ground, and determine whether the target object is in a preset safety area based on the position information. In this embodiment, multiple second images are obtained by projecting the acquired first image onto the plane where the ground is located; superimpose the multiple second images to eliminate the influence of parallax and obtain a panoramic image of the magnetic device scanning room in the coordinate system where the ground is located, that is, the target image, so that when the target object is included in the target image, the position information of the target object on the ground can be accurately determined, and then it can be more accurately judged whether the target object is in the preset safety area, thereby improving the accuracy of detecting safety issues of objects in the scanning room, so that the detection method has high practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a schematic structural diagram of a detection device in one embodiment;

[0052] Figure 2 A schematic diagram of a detection method in an embodiment;

[0053] Figure 3 A schematic diagram of the steps of a detection method in another embodiment;

[0054] Figure 4 A schematic diagram of the steps of a detection method in another embodiment;

[0055] Figure 5 A schematic diagram of the steps of a detection method in another embodiment;

[0056] Figure 6 A schematic diagram of the steps of a detection method in another embodiment;

[0057] Figure 7 A schematic diagram of the steps of a detection method in another embodiment;

[0058] Figure 8A schematic diagram of the steps of a detection method in another embodiment;

[0059] Fig. 9 A schematic diagram of the steps of a detection method in another embodiment;

[0060] Fig.10 A schematic diagram of the steps of a detection method in another embodiment;

[0061] Fig.11 is a schematic diagram of a first image in one embodiment;

[0062] Fig.12 is a schematic diagram of a first image in one embodiment;

[0063] Fig.13 is a schematic diagram of superimposing images in one embodiment;

[0064] Fig.14 is a schematic structural diagram of a detection device in one embodiment;

[0065] Fig.15 is a schematic structural diagram of a detection device in another embodiment;

[0066] Fig.16 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] The serial numbers assigned to the components in this article, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0069] Before specifically introducing the technical solution of the embodiment of the present application, the technical background or technical evolution context on which the embodiment of the present application is based is first introduced. Superconducting magnets are commonly used in magnetic resonance equipment. Usually, the magnet is always in the "on" state, which generates a high-intensity magnetic field around the magnetic resonance equipment. Magnetic resonance equipment with high field strength may have safety risks. Common risks involve safety issues such as projection effects and biological effects caused by special physical environments such as static magnetic fields, gradient magnetic fields and radio frequency pulses. Due to the particularity of the environment in which the magnetic resonance equipment is located, there are strict restrictions on objects entering the scanning room where the magnetic resonance equipment is located. If non-magnetic compatible objects (such as wheelchair stretchers, etc.) are brought into the magnetic field range of the magnetic resonance equipment, the magnetic resonance equipment will be seriously damaged, and even casualties will occur. In order to solve this problem, in traditional technology, the position of the object entering the scanning room where the magnetic resonance equipment is located is usually detected to determine whether the object is within the magnetic field range of the magnetic resonance equipment, which poses a safety problem. Specifically, a camera is used to detect objects entering the scanning room. However, due to the limited height of the scanning room, the camera installation angle cannot be completely aligned with the ground, resulting in parallax between cameras at different positions, which in turn leads to inaccurate positioning, and it is impossible to accurately determine whether the object in the scanning room is within the magnetic field range of the magnetic resonance device. In this regard, the present application provides a detection method.

[0070] The following is an introduction to the technical solutions involved in the embodiments of the present application in combination with the scenarios in which the embodiments of the present application are applied.

[0071] The detection method provided in this application can be applied to a detection device, such as Figure 1 As shown, the detection device 10 includes an image collector 11 and a processor 12. The image collector 11 is arranged in a magnetic device scanning room, and the image collector 11 is communicatively connected with the processor 12. The magnetic device includes a magnetic resonance device or a nuclear magnetic device. The magnetic device scanning room refers to a space where the magnetic device is placed. The image collector 11 can be a plurality of cameras arranged at different positions in the magnetic device scanning room. This embodiment does not limit the specific structure and quantity of the image collector 11, as long as its function can be achieved. The processor 12 can be a processor in a computer device.

[0072] In one embodiment, Figure 2 As shown, a method for detecting a scanning space of a magnetic device is provided. This embodiment uses the method applied to a processor as an example. In this embodiment, the method includes the following steps:

[0073] Step 200: Acquire at least two first images during scanning, and project the first images onto a plane where the ground is located to obtain a plurality of second images.

[0074] The first images may be images of different areas in the scanning room acquired at different angles by an image collector in the detection device, and there are overlapping areas in the two first images.

[0075] In an optional embodiment, the method for acquiring the first image may include: at least two image collectors are arranged at different positions in the scanning room, and the first image of the scanning room is acquired by each image collector, and each image collector transmits the acquired first image to the processor. The processor receives at least two first images acquired by at least two image collectors. Each image collector may acquire multiple images of the scanning room, and after receiving the multiple images acquired by each image collector, the processor selects the best image from the multiple images acquired by each image collector as the first image.

[0076] In an optional embodiment, the method for acquiring the first image may further include: providing a rotatable image collector in the scanning room. By rotating the image collector, multiple images of the scanning room at different angles can be collected, and the collected images are transmitted to the processor. There may be a situation where multiple images are collected at the same angle. After obtaining the multiple images, the processor will analyze and process the multiple images, and select at least two first images from the multiple images to ensure that the multiple first images include an image at the same angle.

[0077] After receiving at least two first images, the processor projects the received first images onto the plane where the ground is located, and can obtain multiple second images. The first image is acquired by an image collector, and the first image received by the processor is in the coordinate system where the image collector is located. The processor converts the first image to the coordinate system where the ground is located, and obtains multiple second images. This embodiment does not limit the specific method by which the processor projects the received first image onto the plane where the ground is located, as long as its function can be achieved.

[0078] In an optional embodiment, the processor stores a conversion relationship between the coordinate system where the image collector is located and the coordinate system where the ground is located. After obtaining at least two first images, the processor converts the first images to the coordinate system where the ground is located according to the conversion relationship to obtain multiple second images.

[0079] Step 210: Overlay the multiple second images to obtain a target image.

[0080] After obtaining the plurality of second images, the processor performs superposition processing on the plurality of second images to obtain a target image. The plurality of second images are all images in the scanning room, and there will be overlapping areas between the plurality of second images. After receiving the plurality of second images, the processor performs superposition processing on the overlapping areas to obtain a target image, that is, a panoramic image of the scanning room.

[0081] Step 220: When the target image includes the target object, determine the position information of the target object on the ground, and determine whether the target object is within a preset safety area according to the position information.

[0082] Target objects may include people entering the scanning room, magnetically compatible devices, and non-magnetically compatible devices. The preset safety zone refers to the area in the scanning room where the target object will not affect the magnetic device. The preset safety zone can be pre-divided by the user, and different target objects have different safety zones.

[0083] The target objects can be divided into two categories, one is people and the other is equipment. After the processor determines the target image, it will determine whether the target image includes the target object. This embodiment does not limit the specific method of the processor to determine whether the target image includes the target object, as long as its function can be achieved.

[0084] In an optional embodiment, the processor may input the target image into a pre-trained person detection model, and determine whether the target image includes the target object (person) according to the output result of the person detection model. The processor may also input the target image into a pre-trained device detection model, and determine whether the target image includes the target object (device) according to the output result of the device detection model.

[0085] In another optional embodiment, the processor may segment the object in the target image by using a background subtraction method or an optical flow method to obtain the target object in the target image.

[0086] When the processor determines that the target image includes the target object, it determines the position information of the target object on the ground, that is, the coordinate value of the target object in the coordinate system of the ground. After determining the position information of the target object, the processor determines whether the target object is within the preset safety area based on the position information. The preset safety area is a position range, and the processor determines whether the target object is within the preset safety area by determining whether the position information of the target object is within the position range.

[0087] The detection method provided in this embodiment is applied to the scanning room of the magnetic equipment, by acquiring at least two first images in the scanning room, projecting the first images onto the plane where the ground is located, and obtaining multiple second images; superimposing the multiple second images to obtain a target image; in the case where the target image includes the target object, determining the position information of the target object on the ground, and determining whether the target object is within a preset safety area based on the position information. In this embodiment, multiple second images are obtained by projecting the acquired first images onto the plane where the ground is located; superimposing the multiple second images can eliminate the influence of parallax, and obtain a panoramic image of the scanning room of the magnetic equipment in the coordinate system where the ground is located, that is, the target image, so that when the target object is included in the target image, the position information of the target object on the ground can be accurately determined, and then whether the target object is within the preset safety area can be more accurately judged, thereby improving the accuracy of detecting safety issues of objects in the scanning room, and making the detection method highly practical.

[0088] In one embodiment, a method for determining the position information of a target object on the ground is provided, and the method includes:

[0089] The contact position between the target object and the ground is used as the position information of the target object on the ground.

[0090] The target image is in the coordinate system of the ground, and the position information of the target object on the ground is the contact position between the target object and the ground in the target map. When the processor determines that the target image includes the target object, it determines the contact position between the target object and the ground in the target image, and uses the contact position as the position information of the target object on the ground. The contact position between the target object and the ground is an area, and the position information of the ground refers to the position information of the area.

[0091] In an optional embodiment, after determining the contact area corresponding to the contact position between the target object and the ground, the processor can calculate the position information of four points corresponding to the circumscribed rectangle of the contact area, and determine the position information of these four points as the position information of the target object on the ground; it can also determine the position information of at least 4 points on the boundary of the contact area as the position information of the target object on the ground.

[0092] In another optional embodiment, after determining the contact area corresponding to the contact position between the target object and the ground, the processor may calculate the centroid of the contact area and use the centroid of the contact area as the position information of the target object on the ground.

[0093] In this embodiment, the target image is in the coordinate system of the ground, and the processor can directly use the contact position between the target object and the ground in the target image as the position information of the target object on the ground. This method of determining the position information is simple, easy to implement, and can obtain accurate position information.

[0094] In one embodiment, different target objects have different safety zones. An implementation method for determining whether the target object is within the preset safety zone based on the position information is as follows: Figure 3 As shown, the steps of this implementation method include:

[0095] Step 300: Determine the type of the target object.

[0096] When the processor determines that the target image includes the target object, it will judge the type of the target object to determine whether the target object is a person, a magnetically compatible device, or a non-magnetically compatible device. This embodiment does not limit the specific method for the processor to determine the type of the target object, as long as its function can be achieved.

[0097] In an optional embodiment, the target image may include one or more target objects. When there are multiple target objects in the target image, the types of the multiple target objects may be the same or different. For example, the multiple target objects in the target image are all people, or the target image includes two types of target objects: people and non-compatible magnetic devices.

[0098] In one embodiment, Figure 4 As shown, there are two implementation methods for determining the type of the target object, and the user can choose any one of the two to determine the type of the target object. One implementation method for determining the type of the target object includes:

[0099] Step 400: Perform type recognition on the target object in the target image to obtain the type of the target object.

[0100] The processor determines the type of the target object by performing type recognition on the target object in the target image.

[0101] In an optional embodiment, the processor uses a pre-trained person recognition model to identify whether the target object in the target image is a person. The processor uses a pre-trained device recognition model to identify whether the target object in the target image is a device and the type of the device.

[0102] Another implementation of determining the type of the target object includes:

[0103] Step 410: Identify the identifier of the target object in the target image to obtain a recognition result.

[0104] Step 420: Determine the type of the target object according to the recognition result.

[0105] Different objects entering the scanning room are marked with different labels. When the processor determines that the target image includes the target object, it identifies the label of the target object in the target image to obtain a recognition result. The type of the target object is determined based on the recognition result. The recognition result can be represented by numbers or characters. For example, a recognition result of 1 indicates that the type of the target object is a person; a recognition result of 2 indicates that the type of the target object is a magnetically compatible device; and a recognition result of 3 indicates that the type of the target object is a non-magnetically compatible device. This embodiment does not limit the specific representation of the recognition result, as long as its function can be achieved.

[0106] The method for determining whether a target object is included in a target image as described in the above embodiment can identify whether the target object is a person or a device. When the target object is a device, the processor also needs to identify the type of the device to determine the type of the target object.

[0107] In an optional embodiment, when the target object is a device, the method for determining the type of the device may include: a processor inputting the target object into a pre-trained type recognition model, and determining the type of the device according to an output result of the type recognition model.

[0108] The method for determining the type of device may also include: adding different identifiers to different devices entering the scanning room, the processor inputting the target object into a pre-trained identifier recognition model, and determining the type of device based on the output result of the identifier recognition model.

[0109] The method for determining the type of device may also include: adding an identifier to the magnetically compatible device entering the scanning room, the processor detecting the identifier on the target object, and if the identifier is detected, determining that the target object is a magnetically compatible device; if the identifier is not detected, determining that the target object is a non-magnetically compatible device. Since the types of magnetically compatible devices in medical scenarios are limited and controllable, adding identifiers only to the magnetically compatible devices entering the scanning room can reduce the workload of adding identifiers while accurately identifying the type of the target object.

[0110] Step 310: Determine whether the target object is within a preset safety area based on the type and location information.

[0111] Different types of target objects correspond to different preset safety areas. After determining the type of the target object, the processor obtains the preset safety area corresponding to the type, and determines whether the target object is within the corresponding preset safety area based on the position information of the target object.

[0112] In this embodiment, different types of target objects have different preset safety zones. When determining whether a target object is in a preset safety zone, the processor first determines the type of the target object, and then determines whether the target object is in the preset safety zone corresponding to its type based on the position information of the target object. In this way, it is possible to determine whether different types of target objects are in the corresponding preset safety zones, which can improve the practicality of the detection method.

[0113] In one embodiment, Figure 5 As shown, a method for obtaining a target image by superimposing multiple second images is involved, and the steps of the method include:

[0114] Step 500: For each second image, obtain feature points of each second image, match the feature points, and determine similar points.

[0115] After acquiring the plurality of second images, the processor extracts feature points from each second image to obtain feature points of each second image.

[0116] In an optional embodiment, the processor may use SIFT (Scale Invariant Feature Transform), SURF (Speeded Up Robust Features) or ORB (Oriented FAST and Rotated BRIEF) to extract feature points from each second image.

[0117] After obtaining the characteristic points of each second image, the processor matches the characteristic points corresponding to each second image to determine similar points, that is, characteristic points with higher similarity among the characteristic points. The processor can calculate the similarity between the characteristic points and determine two characteristic points whose similarity reaches a preset threshold as similar points.

[0118] Step 510: Superimpose multiple second images according to similar points to obtain a target image.

[0119] After determining the similarity of the feature points in each second image, the processor performs superposition processing on the multiple second images according to the similarity, that is, superimposes the similarity points in the multiple second images, thereby superimposing the multiple second images to obtain a target image.

[0120] In this embodiment, by matching the feature points of each second image to obtain similar points, multiple second images are superimposed based on the similar points, and the multiple second images can be spliced ​​into a target image. In this way, a panoramic image of the scanning period, i.e., the target image, can be obtained quickly and accurately.

[0121] In one embodiment, Figure 6 As shown, it involves a method of obtaining a target image by superimposing multiple second images according to similar points, and the steps of the method include:

[0122] Step 600: Perform superposition processing on multiple second images according to similar points to obtain a superimposed image.

[0123] After obtaining the similar points among the feature points of each second image, the processor performs superposition processing on the multiple second images according to the similar points, that is, overlaps the same parts of the multiple second images together to obtain a superimposed image.

[0124] Step 610: Determine stitching information according to the object boundaries in the overlapping area of ​​the superimposed image.

[0125] After acquiring the superimposed image, the processor determines the overlapping area in the superimposed image, that is, the same area in the plurality of second images, analyzes the objects in the overlapping area, determines the boundaries of each object, and determines the stitching information according to the boundaries of each object.

[0126] In an optional embodiment, when the objects in the overlapping area are static objects, the boundaries of each object are directly determined as the stitching information; when the objects in the overlapping area are people or moving equipment, the stitching information is dynamically corrected according to the moving people and equipment to ensure that the stitching information bypasses the moving people or equipment.

[0127] Step 620: Perform brightness processing on the superimposed image according to the stitching information to obtain a target image.

[0128] After determining the stitching information in the superimposed image, the processor performs brightness processing on the superimposed image according to the stitching information to obtain the target image. That is, the brightness of the pixels in the superimposed image is averaged according to the stitching information, that is, for the stitching in the superimposed image determined according to the stitching information, the average pixel value of the pixel within the preset distance from the stitching is calculated, and the pixel values ​​of the pixel within the preset distance from the stitching are all modified to the average pixel value.

[0129] In this embodiment, when a plurality of second images are superimposed according to similar points to obtain a target image, the plurality of second images are first superimposed according to similar points to obtain a superimposed image; the seam information is determined according to the object boundary of the overlapping area in the superimposed image; and the superimposed image is brightness processed according to the seam information to obtain the target image. In this way, brightness processing of the superimposed image according to the seam information can avoid obvious seams in the target image and improve the quality of the target image. In addition, when the target image includes moving personnel or equipment, the integrity of the moving personnel or equipment in the target image can be ensured.

[0130] In one embodiment, Figure 7 As shown, the steps of determining the preset safety area in the detection method include:

[0131] Step 700: Determine the location of the magnetic device in the target image.

[0132] The target image is a panoramic image of the scanning room, and the target image includes the magnetic device. After obtaining the target image, the processor analyzes the target image to determine the position of the magnetic device in the target image, that is, the coordinate value of the magnetic device.

[0133] Step 710: Determine a preset safety area according to the position of the magnetic device and the isomagnetic field lines of the magnetic device.

[0134] After obtaining the position of the magnetic device in the target image, the processor can calibrate a series of isomagnetic field lines with the magnetic device as the center according to the position of the magnetic device, that is, the isomagnetic field lines of the magnetic device. The processor divides the isomagnetic field lines of the magnetic device according to relevant standards to determine the preset safety area.

[0135] In an optional embodiment, for different types of target objects, the processor may divide the isomagnetic field lines of the magnetic device into a plurality of different regions according to relevant standards to determine preset safety regions corresponding to different types of target objects.

[0136] In this embodiment, after acquiring an accurate target image, the processor can obtain the accurate position of the magnetic device and the isomagnetic field lines of the magnetic device, and can accurately and quickly determine the preset safety area based on the position of the magnetic device and the isomagnetic field lines of the magnetic device.

[0137] In this embodiment, when the target image is acquired for the first time, a preset safety area is determined; if the position of the magnetic device does not change and the preset safety area does not change when the target image is acquired again subsequently, the preset safety area acquired when the target image is acquired for the first time can be directly used.

[0138] In one embodiment, Figure 8 As shown, a method for obtaining a plurality of second images by projecting a first image onto a plane where the ground is located is provided. The steps of the method for obtaining a plurality of second images include:

[0139] Step 800: Obtain the first positions of at least four marking points on the ground and the second positions of at least four marking points in any first image.

[0140] The at least four marking points on the ground may be points pre-set by a user and whose position information in the coordinate system of the ground is known. Each first image acquired during scanning by the image collector includes at least four marking points on the ground. In some embodiments, the acquisition angle of the image collector for acquiring the first image may be pre-set so that each first image includes at least four marking points on the ground.

[0141] The processor obtains the position information of at least four marking points on the ground in the coordinate system where the ground is located, that is, the coordinate value of each marking point on the ground in the coordinate system where the ground is located, that is, the first position. The processor can determine the position information of at least four marking points on the ground in each first image based on each first image obtained from the image collector, that is, the coordinate value of each marking point on the ground in each first image in the coordinate system where the image collector is located, that is, the second position.

[0142] Step 810: Determine a homography matrix according to the first position and the second position.

[0143] The homography matrix describes the conversion relationship between points in the same plane in different images. After determining the first position and the second position of at least four marking points on the ground, the processor can calculate the homography matrix according to the first position information and the second position, that is, the conversion relationship between the ground and the first image for each marking point on the ground. This embodiment does not limit the specific method of determining the homography matrix according to the first position and the second position, as long as its function can be achieved.

[0144] In an optional embodiment, the processor calculates the homography matrix according to the following formula.

[0145] Among them, (x a ,y a , w a ) represents the first position of the marker point, (x b ,y b , w b ) represents the second position of the marker point, and H represents the homography matrix.

[0146] In another optional embodiment, the processor may solve the homography matrix through a specific function.

[0147] Step 820: Project the first image onto the ground according to the homography matrix to obtain a plurality of second images.

[0148] After determining the homography matrix, that is, the conversion relationship between the first image and the ground, the processor can project each first image onto the ground through the homography matrix to obtain multiple second images. In other words, the processor calculates the product between the position of each first image and the homography matrix, and can convert the first image from the coordinate system where the image collector is located to the coordinate system where the ground is located to obtain multiple second images.

[0149] In this embodiment, a homography matrix is ​​determined by first positions of at least four marking points on the ground and second positions of at least four marking points in the first image; the first image can be projected onto the ground using the homography matrix to obtain multiple second images. This method of determining the second image is simple, fast, and easy to implement, and can improve the efficiency and practicality of the detection method.

[0150] In one embodiment, the detection method further comprises:

[0151] When the target object is not in the preset safety area, an alarm message corresponding to the type of the target object is output.

[0152] If the processor determines that the target object is not within the preset safety zone based on the position information of the target object on the ground, indicating that the position of the target object will affect the magnetic device, the processor will output an alarm message corresponding to the type of the target object. Different types of target objects have different corresponding alarm messages when they are not within the preset safety zone, and the specific alarm levels are different. This embodiment does not limit the specific type of alarm information, as long as its function can be achieved.

[0153] In an optional embodiment, if the target object is a non-magnetic compatible device, the alarm information corresponding to the target object is a warning bell; if the target object is a magnetic compatible device, the alarm information corresponding to the target object is a warning light; if the target object is a person, the alarm information corresponding to the target object is a warning bell and a warning light, or a voice prompt message.

[0154] In this embodiment, for different types of target objects, when the processor is not in the preset safety zone, that is, different security events, different alarm information will be output. In this way, different alarm information is output for different security events, making the alarm for security events more flexible and targeted, so that users can distinguish different security events according to the alarm information and take corresponding treatment measures in time.

[0155] See also Fig. 9 An embodiment of the present application provides a detection method, which is applied to a scanning room of a magnetic device, and the method includes:

[0156] Step 900: Acquire at least two first images during scanning, and project the first images onto a preset plane to obtain a plurality of second images.

[0157] The preset plane may be a plane preset by a user, and the preset plane may be a plane parallel to the ground or a plane not parallel to the ground.

[0158] The description of the method for obtaining the first image can refer to the above Figure 2 The specific description of the illustrated embodiments will not be repeated here.

[0159] The processor pre-stores a transformation relationship between the first image and the preset plane. After acquiring at least two first images between scans, the processor uses the transformation relationship between the first image and the preset plane to project the first image onto the preset plane to obtain a plurality of second images. The first image is in the coordinate system where the image collector is located, and the second image is in the coordinate system where the preset plane is located.

[0160] Step 910: Perform superposition processing on multiple second images to obtain a target image.

[0161] The processor performs superposition processing on multiple second images to obtain a target image. Figure 2 The specific description of the illustrated embodiments will not be repeated here.

[0162] Step 920: When the target image includes the target object, the target image is projected onto the plane where the ground is located, the position information of the target object on the ground is determined, and whether the target object is within the preset safety area is determined based on the position information.

[0163] For the description of the target object and the preset safe area, please refer to the above Figure 2 The detailed description of the illustrated embodiments will not be repeated here.

[0164] After obtaining the target image, the processor determines whether the target image includes the target object. When the processor determines that the target image includes the target object, it will project the target image onto the plane where the ground is located, that is, convert the target image from the coordinate system where the preset plane is located to the coordinate system where the ground is located, and obtain the converted image; determine the position information of the converted image target object on the ground, that is, the contact position between the converted target object and the ground. After determining the position information of the target object, the processor will determine whether the target object is within the preset safety area based on the position information. The transformation relationship between the coordinate system where the preset plane is located and the coordinate system where the ground is located can be pre-acquired by the user and stored in the processor.

[0165] The detection method provided in this embodiment is applied to the scanning room of the magnetic equipment, by acquiring at least two first images in the scanning room, projecting the first images onto a preset plane, and obtaining a plurality of second images; superimposing the plurality of second images to obtain a target image; when the target image includes the target object, projecting the target image onto the plane where the ground is located, determining the position information of the target object on the ground, and determining whether the target object is within the preset safety area based on the position information. In this embodiment, by superimposing the plurality of second images, the influence of parallax can be eliminated, and a panoramic image of the scanning room of the magnetic equipment in the coordinate system where the preset plane is located, that is, the target image, can be obtained; when the target image includes the target object, projecting the target image onto the plane where the ground is located, the position information of the target object on the ground can be accurately determined; thereby, it is possible to more accurately judge whether the target object is within the preset safety area, improve the accuracy of detecting the safety issues of the objects in the scanning room, and thereby make the detection method highly practical.

[0166] See also Fig.10 An embodiment of the present application provides a detection method, the steps of which include:

[0167] Step 101, acquiring at least two first images during scanning;

[0168] Step 102: obtaining first positions of at least four marking points on the ground and second positions of at least four marking points in any first image;

[0169] Step 103, determining a homography matrix according to the first position and the second position;

[0170] Step 104: project the first image onto the ground according to the homography matrix to obtain a plurality of second images;

[0171] Step 105: for each second image, obtain feature points of each second image, match the feature points, and determine similar points;

[0172] Step 106, performing superposition processing on the plurality of second images according to the similar points to obtain a superimposed image;

[0173] Step 107, determining the stitching information according to the object boundary of the overlapping area in the superimposed image;

[0174] Step 108: Perform brightness processing on the superimposed image according to the stitching information to obtain a target image;

[0175] Step 109: when the target image includes the target object, the contact position between the target object and the ground is used as the position information of the target object on the ground;

[0176] Step 110: performing type recognition on the target object in the target image to determine the type of the target object;

[0177] Step 111: Determine whether the target object is within a preset safety area based on the type and location information;

[0178] Step 112: When the target object is not in the preset safety area, output alarm information corresponding to the type of the target object.

[0179] In an optional embodiment, the two first images between the scans are acquired as follows: Fig.11 and Fig.12 shown. Fig.11 and Fig.12 The dotted box in the figure represents the door of the scanning room and the equipment in the scanning room. The corresponding superimposed image of the scanning room is shown in Fig.13 shown. Fig.13 The thick solid lines in the figure represent the stitching information in the superimposed image.

[0180] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0181] In one embodiment, the present application also provides a detection device, such as Figure 1 As shown, the detection device 10 includes an image collector 11 and a processor 12. The image collector 11 is arranged in the magnetic device scanning room; the image collector 11 is used to obtain at least two first images in the scanning room and transmit the first images to the processor 12. The processor 12 is used to execute the steps of the detection method described in the above embodiment. The specific description of the image collector 11 and the processor 12 can refer to the description in the above embodiment, and will not be repeated here.

[0182] In this embodiment, the detection device includes a processor, and the processor is used to execute the steps of the detection method. The detection device has all the beneficial effects of the detection method, which will not be repeated here.

[0183] Based on the same inventive concept, the embodiment of the present application also provides a detection device for implementing the detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more detection device embodiments provided below can refer to the limitations on the detection method above, and will not be repeated here.

[0184] In one embodiment, Fig.14 As shown, a detection device 20 is provided, comprising: an acquisition module 21, a superposition module 22 and a determination module 23, wherein:

[0185] The acquisition module 21 is used to acquire at least two first images during scanning, and project the first images onto a plane where the ground is located to obtain a plurality of second images.

[0186] The superposition module 22 is used to perform superposition processing on the multiple second images to obtain a target image.

[0187] The determination module 23 is used to determine the position information of the target object on the ground when the target image includes the target object, and determine whether the target object is within a preset safety area according to the position information.

[0188] In one embodiment, the determination module 23 is specifically configured to use the contact position between the target object and the ground as the position information of the target object on the ground.

[0189] In one embodiment, the determination module 23 includes a type determination unit and an area determination unit. The type determination unit is used to determine the type of the target object; the area determination unit is used to determine whether the target object is within a preset safety area according to the type and position information.

[0190] In one embodiment, the type determination unit is specifically used to perform type recognition on the target object in the target image to obtain the type of the target object; or, to recognize the logo of the target object in the target image to obtain a recognition result; and to determine the type of the target object according to the recognition result.

[0191] In one embodiment, the superposition module 22 includes an acquisition unit and a superposition unit. The acquisition unit is used to acquire feature points of each second image, match the feature points, and determine similar points; the superposition unit is used to superimpose multiple second images according to the similar points to obtain a target image.

[0192] In one embodiment, the superposition unit is specifically used to superimpose multiple second images according to similar points to obtain a superimposed image; determine stitching information according to object boundaries in overlapping areas of the superimposed image; and perform brightness processing on the superimposed image according to the stitching information to obtain a target image.

[0193] In one embodiment, the determination module 23 is further used to determine the position of the magnetic device in the target image; and determine the preset safety area according to the position of the magnetic device and the isomagnetic field lines of the magnetic device.

[0194] In one embodiment, the acquisition module 21 is specifically used to acquire the first position of at least four marking points on the ground, and the second position of at least four marking points in any one of the first images; determine the homography matrix based on the first position and the second position; and project the first image onto the ground based on the homography matrix to obtain multiple second images.

[0195] In one embodiment, the detection device 20 further includes an output module. The output module is used to output alarm information corresponding to the type of the target object when the target object is not in the preset safety area.

[0196] In one embodiment, Fig.15 As shown, a detection device 30 is provided, and the detection device 30 includes an image acquisition module 31, a processing module 32 and a region determination module 33.

[0197] An image acquisition module 31 is used to acquire at least two first images during scanning, and project the first images onto a preset plane to obtain a plurality of second images;

[0198] A processing module 32, used for performing superposition processing on the multiple second images to obtain a target image;

[0199] The area determination module 33 is used to project the target image onto the plane where the ground is located when the target image includes the target object, determine the position information of the target object on the ground, and determine whether the target object is within the preset safety area based on the position information.

[0200] Each module in the above detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0201] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.16As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a detection method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the computer device housing, or an external keyboard, touch pad or mouse, etc.

[0202] Those skilled in the art will understand that Fig.16 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0203] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0204] Acquire at least two first images between scans, and project the first images onto a plane where the ground is located to obtain a plurality of second images;

[0205] Performing superposition processing on the multiple second images to obtain a target image;

[0206] In the case where the target object is included in the target image, the position information of the target object on the ground is determined, and it is determined whether the target object is within a preset safety area according to the position information.

[0207] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0208] Acquire at least two first images during scanning, and project the first images onto a preset plane to obtain a plurality of second images;

[0209] Performing superposition processing on the multiple second images to obtain a target image;

[0210] In the case where the target object is included in the target image, the target image is projected onto the plane where the ground is located, the position information of the target object on the ground is determined, and it is determined whether the target object is within the preset safety area according to the position information.

[0211] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0212] Acquire at least two first images between scans, and project the first images onto a plane where the ground is located to obtain a plurality of second images;

[0213] Performing superposition processing on the multiple second images to obtain a target image;

[0214] In the case where the target object is included in the target image, the position information of the target object on the ground is determined, and it is determined whether the target object is within a preset safety area according to the position information.

[0215] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0216] Acquire at least two first images during scanning, and project the first images onto a preset plane to obtain a plurality of second images;

[0217] Performing superposition processing on the multiple second images to obtain a target image;

[0218] In the case where the target object is included in the target image, the target image is projected onto the plane where the ground is located, the position information of the target object on the ground is determined, and it is determined whether the target object is within the preset safety area according to the position information.

[0219] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0220] Acquire at least two first images between scans, and project the first images onto a plane where the ground is located to obtain a plurality of second images;

[0221] Performing superposition processing on the multiple second images to obtain a target image;

[0222] In the case where the target object is included in the target image, the position information of the target object on the ground is determined, and it is determined whether the target object is within a preset safety area according to the position information.

[0223] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0224] Acquire at least two first images during scanning, and project the first images onto a preset plane to obtain a plurality of second images;

[0225] Performing superposition processing on the multiple second images to obtain a target image;

[0226] In the case where the target object is included in the target image, the target image is projected onto the plane where the ground is located, the position information of the target object on the ground is determined, and it is determined whether the target object is within the preset safety area according to the position information.

[0227] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0228] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0229] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A detection method, applied to a scanning room of a magnetic device, characterized in that: The method comprises: Acquire at least two first images in the scanning room, and project the first images onto a plane where the ground is located to obtain a plurality of second images; Performing a superposition process on the multiple second images to obtain a target image; In the case where the target image includes a target object, position information of the target object on the ground is determined, and whether the target object is within a preset safety area is determined according to the position information.

2. The method according to claim 1, characterized in that The determining the position information of the target object on the ground includes: The contact position between the target object and the ground is used as the position information of the target object on the ground.

3. The method according to claim 1 or 2, characterized in that: The determining, according to the position information, whether the target object is within a preset safety area includes: determining the type of the target object; Determine whether the target object is within the preset safety area according to the type and the position information.

4. The method according to claim 3, characterized in that The determining the type of the target object comprises: Performing type recognition on the target object in the target image to obtain the type of the target object; or, Identify the identifier of the target object in the target image to obtain a recognition result; The type of the target object is determined according to the recognition result.

5. The method according to claim 1 or 2, characterized in that: The step of performing superposition processing on the plurality of second images to obtain a target image comprises: For each of the second images, acquiring feature points of each of the second images, and matching the feature points to determine similar points; The target image is obtained by superimposing a plurality of the second images according to the similar points.

6. The method according to claim 5, characterized in that The step of performing superposition processing on the plurality of second images according to the similar points to obtain the target image comprises: Performing a superposition process on a plurality of the second images according to the similar points to obtain a superimposed image; Determining stitching information according to the object boundary of the overlapping area in the superimposed image; The superimposed image is subjected to brightness processing according to the stitching information to obtain the target image.

7. The method according to claim 1 or 2, characterized in that: The method further comprises: determining a location of the magnetic device in the target image; The preset safety area is determined according to the position of the magnetic device and the isomagnetic field lines of the magnetic device.

8. The method according to claim 1 or 2, characterized in that: The step of projecting the first image onto a plane where the ground is located to obtain a plurality of second images comprises: Acquire first positions of at least four marking points on the ground, and second positions of the at least four marking points in any one of the first images; Determine a homography matrix according to the first position and the second position; According to the homography matrix, the first image is projected onto the ground to obtain a plurality of the second images.

9. The method according to claim 1 or 2, characterized in that: The method further comprises: When the target object is not in the preset safety area, alarm information corresponding to the type of the target object is output.

10. A detection method, applied to a scanning room of a magnetic device, characterized in that: The method comprises: Acquire at least two first images in the scanning room, and project the first images onto a preset plane to obtain a plurality of second images; Performing a superposition process on the multiple second images to obtain a target image; In the case where the target image includes a target object, the target image is projected onto a plane where the ground is located, position information of the target object on the ground is determined, and whether the target object is within a preset safety area is determined based on the position information.

11. A detection device, characterized in that: The detection device includes an image collector and a processor, and the image collector is arranged in a magnetic device scanning room; The image collector is used to acquire at least two first images in the scanning room and transmit the first images to the processor; The processor is used to execute the steps of the method according to any one of claims 1 to 10.

12. A detection device, characterized in that: The device comprises: An acquisition module, used for acquiring at least two first images between scans, and projecting the first images onto a plane where the ground is located to obtain a plurality of second images; A superposition module, used for superimposing the plurality of second images to obtain a target image; The determination module is used to determine the position information of the target object on the ground when the target image includes the target object, and determine whether the target object is within a preset safety area according to the position information.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Citation Information

Patent Citations

  • Real-time video stitching algorithm based on optimal stitching line updating

    CN111553841A

  • Systems and methods for security column

    CN114375410A

  • Method and device for determining safety interval of mobile nuclear magnetic equipment

    CN114863360A

  • On -vehicle environment identification system and all -round vision module based on multisensor

    CN206611521U

  • Vehicle surroundings monitoring apparatus

    US20070269079A1