Limb volume detection method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a limb volume detection method, device and equipment and a storage medium, the limb volume detection method, device and equipment are used for medical detection equipment, cameras in each camera group of the medical detection equipment are annularly arranged in a surrounding mode according to a preset interval, lenses of the cameras face the center area of the ring, and the ring is used for a to-be-detected limb to penetrate through; the method comprises the following steps: in response to a start instruction, controlling all cameras to perform first shooting processing on a to-be-detected limb to obtain a first image; within a first preset time, controlling all cameras to carry out second shooting processing on the to-be-detected limb to obtain a second image; performing gray scale comparison processing on the first image and the second image corresponding to the cameras with the same serial number, and determining the motion state of the to-be-detected limb according to a comparison result; when the motion state of the to-be-measured limb is non-jittering, performing limb volume measurement processing according to the first images of all the cameras to obtain volume information; the problem of low limb volume detection accuracy is solved, and the limb volume detection accuracy is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of limb volume detection, and in particular, to a limb volume detection method, device, equipment and storage medium. Background Art

[0002] Edema refers to the accumulation of excessive body fluid in the interstitial space outside blood vessels, which is a common pathological process. Edema usually indicates some internal diseases, such as hypertension, diabetes and congestive heart disease, so the detection of edema is of great clinical significance. At present, the presence of edema can be determined by measuring the volume information of the limbs and comparing the changes in the volume information.

[0003] The existing method of measuring limb volume is usually through image detection. Usually, the camera is used to shoot the limb to be measured to obtain the corresponding image; the image is processed to obtain the corresponding limb volume. However, in the actual measurement process, the limb to be measured may be shaking. When the amplitude of the shaking is large, there is a large error between the corresponding image and the actual limb to be measured, resulting in a low accuracy of the final limb volume, which in turn affects the final result of judging edema. Summary of the invention

[0004] The embodiments of the present application provide a limb volume detection method, device, equipment and storage medium, which can solve the technical problem of low accuracy of limb volume detection, improve the accuracy of limb volume detection, and improve the accuracy of edema judgment results.

[0005] In a first aspect, an embodiment of the present application provides a limb volume detection method, which is used in a medical detection device. The medical detection device is configured with at least one camera group, each camera group is configured with at least four cameras, and the cameras in the same camera group are arranged in a ring at preset intervals. The camera lenses are oriented toward the center area of ​​the ring, and the ring is used for the limb to be detected to pass through. The limb volume detection method includes:

[0006] receiving a start instruction, and in response to the start instruction, controlling all cameras to perform a first shooting process on the limb to be measured to obtain a first image;

[0007] Within a first preset time, controlling all cameras to perform a second shooting process on the limb to be measured to obtain a second image;

[0008] Perform grayscale contrast processing on the first image and the second image corresponding to the camera with the same number, and determine the motion state of the limb to be tested according to the comparison result, and the motion state includes shaking and no shaking;

[0009] When the motion state of the limb to be measured is not shaking, the limb volume measurement process is performed according to the first images of all cameras to obtain the volume information of the limb to be measured.

[0010] Further, grayscale contrast processing is performed on the first image and the second image corresponding to the camera with the same number, and the motion state of the limb to be tested is determined according to the contrast result, including:

[0011] Gray-scale the first image of each camera to obtain a first standard gray-scale image;

[0012] grayscale the second image of each camera to obtain a second standard grayscale image, wherein the first standard grayscale image and the second standard grayscale image have the same size;

[0013] Performing discrete cosine transform processing on the first standard grayscale image and the second standard grayscale image respectively to obtain corresponding first target image and second target image;

[0014] Perform grayscale contrast processing on the first target image and the second target image of the camera with the same number to obtain the image difference;

[0015] When the image difference exceeds a preset threshold, determining that the motion state of the limb to be tested is shaking;

[0016] When the image difference is below a preset threshold, it is determined that the motion state of the limb to be tested is not shaking.

[0017] Furthermore, grayscale contrast processing is performed on the first target image and the second target image of the camera with the same number to obtain the image difference, including:

[0018] Calculate the total grayscale mean of the first target image and the second target image respectively;

[0019] The first target image and the second target image are processed by dividing the blocks according to a preset unit pixel amount to obtain block sub-images, and the block sub-images in the first target image and the second target image correspond to each other one by one;

[0020] Calculate the sub-grayscale mean of each block sub-image in the first target image and the second target image respectively;

[0021] Compare the sub-grayscale mean of each sub-block in the first target image with the total grayscale mean of the first target image, and generate a binary first image fingerprint according to the comparison result;

[0022] Compare the sub-grayscale mean of each block sub-image in the second target image with the total grayscale mean of the second target image, and generate a binary second image fingerprint according to the comparison result;

[0023] The first image fingerprint and the second image fingerprint of the camera with the same number are compared to obtain the image difference.

[0024] Furthermore, the sub-grayscale mean of each sub-block sub-image in the first target image is compared with the total grayscale mean of the first target image, and a binary first image fingerprint is generated according to the comparison result, including:

[0025] When the sub-grayscale mean of the corresponding block sub-image in the first target image is greater than or equal to the total grayscale mean of the first target image, the fingerprint record of the corresponding block sub-image is determined to be 1;

[0026] When the sub-grayscale mean of the corresponding sub-block image in the first target image is less than the total grayscale mean of the first target image, the fingerprint record of the corresponding sub-block image is determined to be 0;

[0027] Generate a first image fingerprint according to the fingerprint record of each sub-block image in the first target image;

[0028] The sub-grayscale mean of each sub-image in the second target image is compared with the total grayscale mean of the second target image, and a binary second image fingerprint is generated according to the comparison result, including:

[0029] When the sub-grayscale mean of the corresponding block sub-image in the second target image is greater than or equal to the total grayscale mean of the second target image, the fingerprint record of the corresponding block sub-image is determined to be 1;

[0030] When the sub-grayscale mean of the corresponding sub-block image in the second target image is less than the total grayscale mean of the second target image, the fingerprint record of the corresponding sub-block image is determined to be 0;

[0031] A second image fingerprint is generated according to the fingerprint record of each sub-block image in the second target image.

[0032] Furthermore, the first image fingerprint and the second image fingerprint of the camera with the same number are compared to obtain the image difference, including:

[0033] Determine a sub-difference according to a difference between a fingerprint record in a first image fingerprint and a corresponding fingerprint record in a second image fingerprint of a camera with the same number, the sub-difference being the number of differences being zero;

[0034] The sub-differences corresponding to all numbered cameras are added together to obtain the image difference.

[0035] Further, grayscale contrast processing is performed on the first image and the second image corresponding to the camera with the same number, and the motion state of the limb to be tested is determined according to the contrast result, including:

[0036] Determine a first area image containing a preset target object in the first image, and determine a second area image containing the target object in the second image, the first area image and the second area image have the same size, and the target object is a limb to be measured;

[0037] The grayscale contrast processing is performed on the first area image and the second area image corresponding to the camera with the same number, and the movement state of the limb to be tested is determined according to the contrast result.

[0038] Furthermore, when the motion state of the limb to be measured is not shaking, the limb volume measurement process is performed according to the first image to obtain the volume information of the limb to be measured, including:

[0039] When the motion state of the limb to be tested is not shaking, data processing is performed according to the first images of all cameras according to the preset spatial calibration relationship to obtain point cloud data;

[0040] Perform three-dimensional modeling processing according to the point cloud data to obtain a target three-dimensional limb model;

[0041] Volume measurement is performed based on the target three-dimensional limb model to obtain volume information of the limb to be measured.

[0042] In a second aspect, an embodiment of the present application provides a limb volume detection device for a medical detection device, wherein the medical detection device is configured with at least one camera group, each camera group is configured with at least four cameras, and the cameras in the same camera group are arranged in a ring at preset intervals, and the camera lenses are oriented toward the central area of ​​the ring, and the ring is used for the limb to be detected to pass through, and the limb volume detection device includes:

[0043] A first shooting module is used to receive a start instruction, and in response to the start instruction, control all cameras to perform a first shooting process on the limb to be measured to obtain a first image;

[0044] A second shooting module is used to control all cameras to perform a second shooting process on the limb to be tested within a first preset time to obtain a second image;

[0045] A comparison module, used for performing grayscale comparison processing on the first image and the second image corresponding to the camera with the same number, and determining the motion state of the limb to be tested according to the comparison result, the motion state including shaking and no shaking;

[0046] The volume measurement module is used to perform limb volume measurement processing according to the first images of all cameras when the motion state of the limb to be measured is not shaking, so as to obtain the volume information of the limb to be measured.

[0047] In a third aspect, an embodiment of the present application provides a limb volume detection device, comprising:

[0048] memory and one or more processors;

[0049] A memory for storing one or more programs;

[0050] When one or more programs are executed by one or more processors, the one or more processors implement the limb volume detection method according to the first aspect.

[0051] In a fourth aspect, an embodiment of the present application provides a storage medium storing computer executable instructions, where the computer executable instructions are used to perform the limb volume detection method of the first aspect when executed by a computer processor.

[0052] In the embodiment of the present application, when detecting the volume of a limb, all cameras are controlled to perform a first shooting process on the limb to be tested to obtain a first image, and within a first preset time, all cameras are controlled to perform a second shooting process on the limb to be tested to obtain a second image, grayscale contrast processing is performed on the first image and the second image corresponding to the cameras with the same number, and the motion state of the limb to be tested is determined according to the comparison result. When the motion state of the limb to be tested is not shaking, limb volume measurement processing is performed according to the first images of all cameras to obtain volume information of the limb to be tested. By adopting the above technical means, it is possible to determine whether the limb to be tested has a large amplitude of shaking by comparing the grayscale contrast processing results of the first image and the second image obtained by two shots of the camera with the same number in a short period of time. When it is determined that the limb to be tested has not shaken, image detection is performed based on the first image to determine the volume information of the limb to be tested, thereby avoiding the technical problem of low accuracy of the limb volume obtained by image detection due to shaking of the limb to be tested, thereby improving the accuracy of limb volume detection, and further improving the accuracy of edema judgment results.

[0053] The beneficial effects of the limb volume detection device, limb volume detection equipment and storage medium provided above can refer to the beneficial effects of the limb volume detection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of a single group of camera distribution provided in an embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of the relationship between the position of a camera and a limb provided in an embodiment of the present application;

[0056] Figure 3 is a flow chart of a limb volume detection method provided in an embodiment of the present application;

[0057] Figure 4 is a flow chart of a method for detecting limb movement status provided by an embodiment of the present application;

[0058] Figure 5 is a schematic diagram of a regional image provided in an embodiment of the present application;

[0059] Figure 6 is a structural schematic diagram of a limb volume detection device provided in an embodiment of the present application;

[0060] Figure 7 It is a structural schematic diagram of a limb volume detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0062] The existing method of measuring limb volume is usually through image detection. Usually, the camera is used to shoot the limb to be measured to obtain the corresponding image; the image is processed to obtain the corresponding limb volume. However, in the actual measurement process, the acquisition process takes about 1-2 seconds, or even longer. Therefore, the limb to be measured may shake during the acquisition process. When the amplitude of the shake is large, there is a large error between the corresponding image and the actual limb to be measured, resulting in a low accuracy of the final limb volume, which in turn affects the final result of judging edema.

[0063] Based on this, a limb volume detection method, apparatus, equipment and storage medium are provided in the embodiments of the present application, which are intended to control all cameras to perform a first shooting process on the limb to be measured to obtain a first image during limb volume detection, control all cameras to perform a second shooting process on the limb to be measured to obtain a second image within a first preset time, perform grayscale contrast processing on the first image and the second image corresponding to the cameras with the same number, determine the movement state of the limb to be measured according to the comparison result, and when the movement state of the limb to be measured is not shaking, perform limb volume measurement processing based on the first images of all cameras to obtain volume information of the limb to be measured. By adopting the above-mentioned technical means, it is possible to determine whether there is a large-scale shaking of the limb to be tested by comparing the grayscale contrast processing results of the first image and the second image obtained by two shots of the camera with the same number within a short period of time. Compared with the existing method of directly performing volume detection on the collected image, this embodiment performs image detection based on the first image to determine the volume information of the limb to be tested when it is determined that the movement state of the limb to be tested is not shaking, that is, when the shaking of the limb to be tested is within the error range. This can avoid the technical problem of low accuracy of the limb volume obtained by image detection due to shaking of the limb to be tested, thereby improving the accuracy of limb volume detection and further improving the accuracy of edema judgment results.

[0064] The limb volume detection method provided in the embodiment of the present application is used for medical detection equipment, which is equipped with at least one camera group, each camera group is equipped with at least four cameras, and the cameras in the same camera group are arranged in a ring at a preset interval. Each camera is a binocular camera. Figure 1 This is a schematic diagram of a single camera group distribution provided in an embodiment of the present application, referring to Figure 1 , a camera group in a medical detection device is used as an example for explanation, assuming that the camera group is configured with four cameras 10. The four cameras 10 in the camera group are arranged in a ring at a preset interval, and the lenses of the four cameras 10 are oriented toward the central area of ​​the ring H1, and the ring H1 is used for the limb to be detected to pass through. The medical detection device provided in this embodiment is provided with at least one camera group, and at least four cameras 10 are arranged in each camera group. Figure 2 is a schematic diagram of the relationship between the camera and the limb position provided in an embodiment of the present application, referring to Figure 2 , taking two camera groups in a medical detection device as an example, the two camera groups are camera group 1 and camera group 2, and camera group 1 and camera group 2 are respectively as follows Figure 1 The four cameras 10 in the group shown are arranged in a ring at a preset interval, and the lenses of the four cameras 10 face the central area of ​​the ring H1, and the ring H1 is used for the limb to be tested to pass through. It should be noted that Figure 2 In the above description, the limb to be tested is an arm. In actual testing, the limb to be tested may be other limbs besides the arm, such as a leg. Figure 2As shown, camera group 1 and camera group 2 are arranged at a preset interval. The limb to be measured passes through the inside of the ring H1 surrounded by the cameras 10 of each camera group, approximately at the center line X position inside the ring H1.

[0065] Figure 3 A flow chart of a limb volume detection method provided in an embodiment of the present application is given. The limb volume detection method provided in this embodiment can be executed by a limb volume detection device, which can be implemented by software and / or hardware. The limb volume detection device can be composed of two or more physical entities, or can be composed of one physical entity. Generally speaking, the limb volume detection device can be a medical detection device, such as a three-dimensional scanner.

[0066] The following description is made by taking a medical detection device as an example to implement the limb volume detection method. Figure 3 The limb volume detection method is used for medical detection equipment. The medical detection equipment is equipped with at least one camera group. Each camera group is equipped with at least four cameras. The cameras in the same camera group are arranged in a ring at preset intervals. The camera lenses are oriented toward the center area of ​​the ring. The ring is used for the limb to be detected to pass through. The limb volume detection method specifically includes:

[0067] S101, receiving a start instruction, and in response to the start instruction, controlling all cameras to perform a first shooting process on a limb to be measured to obtain a first image.

[0068] The medical detection device provided in this embodiment is as follows Figure 1 and Figure 2 As shown, the medical detection device includes at least one camera group, each camera group is equipped with at least four cameras 10, and the at least four cameras 10 are arranged in a ring at a preset interval, and the lenses of the at least four cameras 10 are oriented toward the central area of ​​the ring H1, and the ring H1 is used for the limb to be detected to pass through. When the limb to be detected passes through the ring H1 surrounded by the cameras 10, as shown in FIG. Figure 2 As shown, the start instruction can be triggered manually or automatically by the medical detection device. The medical detection device receives the start instruction, and in response to the start instruction, controls all cameras to simultaneously perform a first shooting process on the limb to be detected to obtain a first image. Each camera correspondingly obtains a first image. Exemplarily, the first image is an RGB image.

[0069] At this time, if the limb volume measurement of the limb to be measured is directly based on the first image obtained by all cameras, if the limb to be measured has a large degree of shaking during the image acquisition process, it may cause the final volume measurement result to be inaccurate, so it is necessary to first determine the motion state of the current limb to be measured during image acquisition. The motion state can be understood as the shaking amplitude. If the shaking amplitude is within an acceptable range, that is, the shaking amplitude is within a preset error range, then the motion state of the limb to be measured is determined to be non-shaking, and the limb volume measurement of the limb to be measured can be performed based on the first image obtained by all cameras; if the shaking amplitude is not within an acceptable range, that is, the shaking amplitude exceeds the preset error range, then the motion state of the limb to be measured is determined to be shaking, and the limb to be measured needs to be photographed again until the shaking amplitude of the limb to be measured is within an acceptable range, and then the limb volume measurement of the limb to be measured can be performed based on the image obtained by shooting. Therefore, the motion state of the limb to be measured during image acquisition can be determined by the following steps S102-S103.

[0070] S102: Control all cameras to perform a second shooting process on the limb to be measured within a first preset time to obtain a second image.

[0071] After obtaining the first image, within the first preset time, all cameras are controlled to simultaneously perform a second shooting process on the limb to be measured to obtain a second image. It should be noted that the specific time within the first preset time can be set according to actual conditions, but is usually set to a shorter time, such as 0.5 seconds or 1 second. Each camera correspondingly obtains a second image. Exemplarily, the second image is an RGB image.

[0072] S103, performing grayscale contrast processing on the first image and the second image corresponding to the camera with the same number, and determining the motion state of the limb to be tested according to the contrast result, where the motion state includes shaking and no shaking.

[0073] The grayscale comparison process is performed on the first image and the second image corresponding to the camera with the same number, and the motion state of the limb to be tested is determined according to the comparison result, and the motion state includes shaking or not shaking. By comparing the grayscale of the two images obtained by the same camera twice, it is judged whether the limb to be tested has a large amplitude of shaking, so as to ensure that the limb volume measurement process is performed only when the limb to be tested shakes a small amplitude, that is, it can be understood as not shaking, so as to improve the accuracy of volume measurement.

[0074] It should be noted that, in the process of collecting the limb to be tested, there must be a certain amount of shaking. When the shaking amplitude is small, the relative error of the limb volume information obtained by image detection is low; but when the shaking amplitude is large, the relative error of the limb volume information obtained by image detection is large. Therefore, the magnitude of the shaking amplitude can be determined by the limb movement state detection method of S1031-S1037 below. When the shaking amplitude of the limb to be tested is large, the limb movement state is determined to be shaking; when the shaking amplitude of the limb to be tested is small, the limb movement state is determined to be non-shaking.

[0075] Figure 4 is a flow chart of a method for detecting limb movement status provided in an embodiment of the present application, referring to Figure 4 , the limb movement state detection method specifically includes:

[0076] S1031 , grayscale the first image of each camera to obtain a first standard grayscale image.

[0077] The first image of each camera is compressed or expanded to obtain an image of a preset standard size, such as an image of 32*32. It should be noted that the preset standard size can be set according to actual conditions, and the aforementioned size of 32*32 is only an example. The image obtained by the compression or expansion process is grayed to obtain a first standard gray image corresponding to each camera. For example, the image obtained by the compression or expansion process is grayed to obtain a gray image of 32*32 corresponding to each camera.

[0078] S1032. Perform discrete cosine transform processing on the first standard grayscale image to obtain a corresponding first target image.

[0079] The first standard grayscale image corresponding to each camera obtained above is subjected to discrete cosine transform processing to obtain the corresponding first target image. By performing discrete cosine transform processing on the first standard grayscale image, the image can be compressed and image features can be extracted, thereby reducing the amount of image processing calculations and thus improving the overall speed of image processing.

[0080] S1033: grayscale the second image of each camera to obtain a second standard grayscale image, wherein the first standard grayscale image and the second standard grayscale image have the same size.

[0081] The second image of each camera is compressed or expanded to obtain an image of a preset standard size, such as an image of 32*32 in size. It should be noted that the preset standard size can be set according to actual conditions, and the aforementioned size of 32*32 is only for example. Among them, the preset standard size corresponding to the first image is the same as the preset standard size corresponding to the second image. The image obtained by the compression or expansion process is grayed to obtain a second standard grayscale image corresponding to each camera. For example, the image obtained by the compression or expansion process is grayed to obtain a grayscale image of 32*32 in size corresponding to each camera.

[0082] S1034. Perform discrete cosine transform processing on the second standard grayscale image to obtain a corresponding second target image.

[0083] The second standard grayscale image corresponding to each camera obtained above is subjected to discrete cosine transform processing to obtain the corresponding second target image. By performing discrete cosine transform processing on the second standard grayscale image, the image can be compressed and image features can be extracted, thereby reducing the amount of image processing calculations and thus improving the overall speed of image processing.

[0084] S1035 , performing grayscale contrast processing on the first target image and the second target image of the camera with the same number to obtain image difference.

[0085] The total grayscale mean of the first target image and the second target image is calculated respectively, for example, the first total grayscale mean of the first target image is calculated, and the second total grayscale mean of the second target image is calculated. The grayscale value of each pixel can be determined by traversing each pixel in the first target image, and the total grayscale value of all pixels can be calculated. The size of the first target image (i.e., the preset standard size mentioned above) is obtained, and the total number of pixels is calculated according to the size of the first target image (i.e., the width and height). The total grayscale value of the first target image is divided by the total number of pixels to obtain the first total grayscale mean corresponding to the first target image. The grayscale value of each pixel can be determined by traversing each pixel in the second target image, and the total grayscale value of all pixels is calculated. The size of the second target image (i.e., the preset standard size mentioned above) is obtained, and the total number of pixels is calculated according to the size of the second target image (i.e., the width and height). The total grayscale value of the second target image is divided by the total number of pixels to obtain the second total grayscale mean corresponding to the second target image.

[0086] The first target image and the second target image are divided into blocks according to a preset unit pixel amount to obtain block sub-images, and the block sub-images in the first target image and the second target image correspond to each other one by one. It should be noted that the preset unit pixel amount can be set according to actual conditions, and the minimum can be set to 1 pixel. The sub-grayscale mean of each block sub-image in the first target image and the second target image is calculated respectively. For example, the sum of the grayscale values ​​and the total number of pixels in each block sub-image in the first target image can be calculated, and the sum of the grayscale values ​​of the corresponding block sub-image is divided by the total number of pixels, so that the sub-grayscale mean of the corresponding block sub-image can be obtained. The sum of the grayscale values ​​and the total number of pixels in each block sub-image in the second target image can be calculated, and the sum of the grayscale values ​​of the corresponding block sub-image is divided by the total number of pixels, so that the sub-grayscale mean of the corresponding block sub-image can be obtained.

[0087] It should be noted that when the number of pixels in the block sub-image is 1 pixel, the corresponding sub-grayscale mean is the grayscale value of the corresponding pixel.

[0088] The sub-grayscale mean of each sub-image in the first target image is compared with the total grayscale mean of the first target image, and a binary first image fingerprint is generated according to the comparison result. Exemplarily, when the sub-grayscale mean of the corresponding sub-image in the first target image is greater than or equal to the total grayscale mean of the first target image, the fingerprint record of the corresponding sub-image is determined to be 1; when the sub-grayscale mean of the corresponding sub-image in the first target image is less than the total grayscale mean of the first target image, the fingerprint record of the corresponding sub-image is determined to be 0; the first image fingerprint is generated according to the fingerprint record of each sub-image in the first target image. Therefore, the first image fingerprint is a set of binary character strings.

[0089] The sub-grayscale mean of each sub-block image in the second target image is compared with the total grayscale mean of the second target image, and a binary second image fingerprint is generated according to the comparison result. Exemplarily, when the sub-grayscale mean of the corresponding sub-block image in the second target image is greater than or equal to the total grayscale mean of the second target image, the fingerprint record of the corresponding sub-block image is determined to be 1; when the sub-grayscale mean of the corresponding sub-block image in the second target image is less than the total grayscale mean of the second target image, the fingerprint record of the corresponding sub-block image is determined to be 0; the second image fingerprint is generated according to the fingerprint record of each sub-block image in the second target image. Therefore, the second image fingerprint is a set of binary character strings.

[0090] The first image fingerprint and the second image fingerprint of the camera with the same number are compared for difference to obtain the image difference. Exemplarily, the fingerprint record in the first image fingerprint of the camera with the same number is compared with the fingerprint record in the second image fingerprint, and the difference of each corresponding fingerprint record, that is, the difference of each corresponding fingerprint record of the block sub-image, is determined, and the number of zero differences is determined to obtain the sub-difference of each numbered camera. For example, if the fingerprint record in the first image fingerprint of the camera with the same number is 1, and the corresponding fingerprint record in the second image fingerprint is also 1, then the difference between the two is 0. For another example, if the fingerprint record in the first image fingerprint of the camera with the same number is 0, and the corresponding fingerprint record in the second image fingerprint is also 0, then the difference between the two is 0. For another example, if the fingerprint record in the first image fingerprint of the camera with the same number is 1, and the corresponding fingerprint record in the second image fingerprint is also 0, then the difference between the two is 1, that is, not 0. Therefore, when the fingerprint records corresponding to the two image fingerprints are the same, the corresponding difference is zero, and the difference of zero means that the two fingerprint records are the same. When the fingerprint records corresponding to the two image fingerprints are different, the corresponding difference is zero. A difference of zero means that the two fingerprint records are different, that is, there is a difference in the grayscale of the corresponding sub-block area, that is, there may be jitter in the corresponding position. Therefore, the sub-difference can be understood as the number of non-zero corresponding differences between the two image fingerprints, that is, the sub-difference is the number of differences between the fingerprint records in the first image fingerprint and the corresponding fingerprint records in the second image fingerprint of the camera with the same number that are greater than or less than zero. Add the sub-differences corresponding to all numbered cameras to obtain the image difference. The image difference is the number of differences between the corresponding fingerprint records in the two images taken two times before and after that are greater than or less than zero obtained by all cameras, that is, the number of different corresponding fingerprint records in the two images taken two times before and after that are obtained by all cameras.

[0091] Exemplarily, this embodiment provides a schematic table of image fingerprints of a first image and a second image, as shown in the following table:

[0092] First image fingerprint 1 1 0 0 1 1 1 0 0 1 Second image fingerprint 1 0 0 0 0 0 1 0 0 0 Difference 0 1 0 0 1 1 0 0 0 1

[0093] It can be seen from the table that among the differences between the first image fingerprint and the second image fingerprint of the camera with this number, the number of differences that are zero is 6, and the number of differences that are not 0 is 4, so it can be obtained that the sub-difference degree of the camera with this number is 4.

[0094] Therefore, the sub-differences corresponding to all numbered cameras can be added together to obtain the image difference. Assuming there are 4 cameras, the corresponding sub-differences are 4, 3, 2 and 1 respectively, then the image difference can be 10.

[0095] S1036: When the image difference exceeds a preset threshold, determine that the motion state of the limb to be tested is shaking.

[0096] When the image difference exceeds the preset threshold, it is considered that there are many positions with grayscale value differences in the images obtained by the two previous shots, and the grayscale value difference represents that there is jitter at the position. When there are many positions with grayscale value differences, that is, the image difference exceeds the preset threshold, it means that the limb to be tested may have a large amplitude of jitter, and thus the motion state of the limb to be tested is determined to be jitter. At this time, it is necessary to re-perform the first shooting process and the second shooting process on the limb to be tested, until the corresponding image difference is below the preset threshold, and then the subsequent volume measurement process is performed. Exemplarily, assuming that the image difference is 10 and the preset threshold is 8, then the image difference exceeds the preset threshold at this time, and then the motion state of the limb to be tested is determined to be jitter, then it is necessary to re-perform the first shooting process and the second shooting process on the limb to be tested, until the corresponding image difference is below 8, and then the subsequent volume measurement process is performed.

[0097] S1037: When the image difference is below a preset threshold, determine that the motion state of the limb to be tested is not shaking.

[0098] When the image difference is below the preset threshold, it is considered that there are fewer locations with grayscale value differences in the images obtained by the two previous shots. The difference in grayscale value means that there is jitter at that location. When there are fewer locations with grayscale value differences, that is, the image difference is below the preset threshold, it means that there is a small amplitude jitter in the limb to be tested. The amplitude of jitter is within the negligible error range for limb volume detection, so it can be determined that the motion state of the limb to be tested is not jittering. At this time, the subsequent volume measurement process can be performed. For example, assuming that the image difference is 2 and the preset threshold is 8, then the image difference is below the preset threshold at this time, and it is determined that the motion state of the limb to be tested is not jittering, and the subsequent volume measurement process is performed.

[0099] As mentioned above, the similarity between two images is determined by comparing the image fingerprints. Compared with the traditional pixel-level comparison, the comparison of image fingerprints can significantly reduce the amount of calculation, thereby improving the overall detection speed of limb movement state detection, and further improving the overall work efficiency of limb volume detection. In addition, even if the image is rotated, scaled or cropped, the image fingerprint can still remain relatively stable. Therefore, when the image quality is not high, the similarity of the two images can still be determined by comparing the image fingerprints, thereby improving the robustness of the image comparison and further improving the overall detection speed of the limb movement state detection.

[0100] In one embodiment, when determining the movement state of the limb to be measured, in order to further reduce the amount of data processing and improve the data processing speed, a first area image containing a preset target object in the first image can be determined first, and a second area image containing the target object in the second image can be determined. The first area image and the second area image have the same size, and the target object is the limb to be measured. Figure 5 is a schematic diagram of a regional image provided in an embodiment of the present application, referring to Figure 5 , take the first image A11 and the second image A12 of one of the numbered cameras as an example for explanation, assuming that the first image A11 and the second image A12 are taken by camera 1 of camera group 1. Based on the fact that the limb to be measured is the target object of the limb volume detection, therefore, as long as the regional image containing the target object is analyzed, the motion state of the limb to be measured can be determined. Based on the fact that the first image A11 and the second image A12 are taken by the same camera, when the camera parameters are not changed, the sizes of the first image A11 and the second image A12 are the same. Target object recognition is performed on the first image A11 and the second image A12 to determine the first regional image A110 containing the preset target object (limb to be measured) in the first image A11, and to determine the second regional image A120 containing the target object (limb to be measured) in the second image A12, the sizes of the first regional image A110 and the second regional image A120 are the same, and the position of the first regional image A110 in the first image A11 and the position of the second regional image A120 in the second image A12 are also the same.

[0101] The first area image and the second area image corresponding to the camera with the same number are subjected to grayscale contrast processing, and the motion state of the limb to be tested is determined according to the contrast result. Exemplarily, the first area image in the first image of each camera is intercepted, and the first area image of each camera is subjected to grayscale processing to obtain a third standard grayscale image, and the third standard grayscale image is subjected to discrete cosine transform processing to obtain a corresponding third target image. The second area image in the second image of each camera is intercepted, and the second area image of each camera is subjected to grayscale processing to obtain a fourth standard grayscale image, and the third standard grayscale image and the fourth standard grayscale image have the same size. The fourth standard grayscale image is subjected to discrete cosine transform processing to obtain a corresponding fourth target image. The third target image and the third target image of the camera with the same number are subjected to grayscale contrast processing to obtain the image difference. The method for determining the image difference is the same as the aforementioned S1035, and is not repeated here. When the image difference exceeds a preset threshold, it is determined that the motion state of the limb to be tested is shaking. When the image difference is below the preset threshold, it is determined that the motion state of the limb to be tested is not shaking.

[0102] As described above, by intercepting the area image containing the target object in the first image and the second image, and detecting the limb movement state based on the area image, the data processing amount can be reduced, the speed of limb movement state detection can be further improved, and the overall work efficiency of limb volume detection can be improved.

[0103] S104 , when the motion state of the limb to be measured is not shaking, perform limb volume measurement processing according to the first images of all cameras to obtain volume information of the limb to be measured.

[0104] Through the aforementioned limb movement state detection method of S1031-S1037, the current movement state of the limb to be tested can be determined, that is, whether the limb to be tested is shaking or not shaking during the image acquisition process. When the movement state of the limb to be tested is not shaking, it means that during the process of acquiring the first image, the limb to be tested is not shaking, or the amplitude of the shaking is within a preset error range, so the limb volume measurement processing can be performed based on the first images of all cameras to obtain the volume information of the limb to be tested.

[0105] In one embodiment, when the motion state of the limb to be measured is not shaking, data processing is performed according to the first images of all cameras according to the preset spatial calibration relationship to obtain point cloud data corresponding to multiple cameras. It should be noted that the point cloud data is point cloud data after de-duplication fusion. Three-dimensional modeling is performed according to the point cloud data to obtain a target three-dimensional limb model. Volume measurement is performed according to the target three-dimensional limb model to obtain volume information of the limb to be measured. Exemplarily, slice processing and center of gravity analysis processing are performed according to the target three-dimensional limb model to determine the center of gravity of the joint. The target three-dimensional limb model is re-sliced ​​according to the center of gravity of the joint to obtain target slice data. Parameter calculation processing is performed according to the target slice data to obtain volume information of each target slice data, wherein the volume information includes the thickness and cross-sectional area of ​​the slice. The volume information of each target slice data is integrated to obtain the overall volume information of the limb to be measured.

[0106] As described above, by detecting the motion state of the limb to be measured, only when it is detected that the motion state of the limb to be measured is not shaking, the volume measurement processing of the limb is performed based on the first image of all cameras to determine the volume of the limb to be measured. Based on the fact that the motion state of the limb to be measured is not shaking, the volume detection error caused by limb shaking can be greatly reduced, thereby improving the accuracy of limb volume detection. In addition, when performing volume measurement processing of the volume to be measured based on the first image, the target three-dimensional limb model obtained by three-dimensional modeling is preliminarily sliced ​​to determine the joint center of gravity, and re-sliced ​​based on the joint center of gravity, and sliced ​​separately with the joint center of gravity as the boundary, thereby improving the accuracy of slicing, and then improving the accuracy of volume calculation.

[0107] In the above, during limb volume detection, all cameras are controlled to perform a first shooting process on the limb to be tested to obtain a first image, and within a first preset time, all cameras are controlled to perform a second shooting process on the limb to be tested to obtain a second image, and the first image and the second image corresponding to the cameras with the same number are subjected to grayscale contrast processing, and the motion state of the limb to be tested is determined according to the comparison result. When the motion state of the limb to be tested is not shaking, the limb volume measurement process is performed according to the first images of all cameras to obtain the volume information of the limb to be tested. By adopting the above technical means, it is possible to determine whether the limb to be tested has a large amplitude of shaking through the comparison result of the grayscale contrast processing of the first image and the second image obtained by two shots of the camera with the same number in a short period of time. When it is determined that the limb to be tested has not shaken, image detection is performed based on the first image to determine the volume information of the limb to be tested, thereby avoiding the technical problem of low accuracy of the limb volume obtained by image detection due to shaking of the limb to be tested, thereby improving the accuracy of limb volume detection, and further improving the accuracy of edema judgment results.

[0108] Based on the above embodiments, Figure 6 This is a schematic diagram of the structure of a limb volume detection device provided in an embodiment of the present application. Figure 6 The limb volume detection device provided in this embodiment is used for medical detection equipment. The medical detection equipment is configured with at least one camera group, each camera group is configured with at least four cameras, and the cameras in the same camera group are arranged in a ring at preset intervals. The camera lenses are directed to the central area of ​​the ring, and the ring is used for the limb to be detected to pass through. The limb volume detection device specifically includes: a first shooting module 21, a second shooting module 22, a comparison module 23 and a volume measurement module 24.

[0109] The first shooting module 21 is used to receive a start instruction, and in response to the start instruction, control all cameras to perform a first shooting process on the limb to be tested to obtain a first image;

[0110] The second shooting module 22 is used to control all cameras to perform a second shooting process on the limb to be tested within a first preset time to obtain a second image;

[0111] A comparison module 23 is used to perform grayscale comparison processing on the first image and the second image corresponding to the camera with the same number, and determine the motion state of the limb to be tested according to the comparison result, and the motion state includes shaking and no shaking;

[0112] The volume measurement module 24 is used to perform limb volume measurement processing according to the first images of all cameras when the motion state of the limb to be measured is not shaking, so as to obtain volume information of the limb to be measured.

[0113] In one embodiment, the comparison module 23 includes: a first grayscale processing submodule, a second grayscale processing submodule, a cosine transform processing submodule, a comparison submodule, a first state determination submodule, and a second state determination submodule;

[0114] A first grayscale processing submodule, used for grayscale processing the first image of each camera to obtain a first standard grayscale image;

[0115] A second grayscale processing submodule is used to grayscale the second image of each camera to obtain a second standard grayscale image, and the first standard grayscale image and the second standard grayscale image have the same size;

[0116] A cosine transform processing submodule, used to perform discrete cosine transform processing on the first standard grayscale image and the second standard grayscale image respectively to obtain a corresponding first target image and a second target image;

[0117] A comparison submodule is used to perform grayscale comparison processing on the first target image and the second target image of the camera with the same number to obtain the image difference;

[0118] A first state determination submodule is used to determine that the motion state of the limb to be tested is shaking when the image difference exceeds a preset threshold;

[0119] The second state determination submodule is used to determine that the movement state of the limb to be tested is not shaking when the image difference is below a preset threshold.

[0120] In one embodiment, the comparison submodule includes: a total grayscale calculation unit, a block division unit, a sub-grayscale mean calculation unit, a first image fingerprint generation unit, a second image fingerprint generation unit and a difference comparison unit;

[0121] A total grayscale calculation unit, used to calculate the total grayscale mean values ​​of the first target image and the second target image respectively;

[0122] A blocking unit, used for performing blocking processing on the first target image and the second target image according to a preset unit pixel amount to obtain blocked sub-images, wherein the blocked sub-images in the first target image and the second target image correspond to each other one by one;

[0123] A sub-grayscale mean value calculation unit, used to calculate the sub-grayscale mean value of each sub-block sub-image in the first target image and the second target image respectively;

[0124] A first image fingerprint generating unit, configured to compare the sub-grayscale mean of each sub-block image in the first target image with the total grayscale mean of the first target image, and generate a binary first image fingerprint according to the comparison result;

[0125] A second image fingerprint generating unit, configured to compare the sub-grayscale mean of each sub-block image in the second target image with the total grayscale mean of the second target image, and generate a binary second image fingerprint according to the comparison result;

[0126] The difference comparison unit is used to compare the first image fingerprint and the second image fingerprint of the camera with the same number to obtain the image difference.

[0127] In one embodiment, the first image fingerprint generation unit includes: a first fingerprint record determination subunit, a second fingerprint record determination subunit, and a first image fingerprint generation subunit;

[0128] A first fingerprint record determination subunit is used to determine that the fingerprint record of the corresponding sub-block image is 1 when the sub-grayscale mean value of the corresponding sub-block image in the first target image is greater than or equal to the total grayscale mean value of the first target image;

[0129] A second fingerprint record determination subunit is used to determine that the fingerprint record of the corresponding sub-block image is 0 when the sub-grayscale mean value of the corresponding sub-block image in the first target image is less than the total grayscale mean value of the first target image;

[0130] A first image fingerprint generating subunit, configured to generate a first image fingerprint according to the fingerprint record of each sub-block image in the first target image;

[0131] The second image fingerprint generating unit includes: a third fingerprint record determining subunit, a fourth fingerprint record determining subunit, and a second image fingerprint generating subunit;

[0132] A third fingerprint record determination subunit is used to determine that the fingerprint record of the corresponding sub-block image is 1 when the sub-grayscale mean value of the corresponding sub-block image in the second target image is greater than or equal to the total grayscale mean value of the second target image;

[0133] The fourth fingerprint record determination subunit is used to determine that the fingerprint record of the corresponding sub-block image is 0 when the sub-grayscale mean value of the corresponding sub-block image in the second target image is less than the total grayscale mean value of the second target image;

[0134] The second image fingerprint generating subunit is used to generate a second image fingerprint according to the fingerprint record of each sub-block image in the second target image.

[0135] In one embodiment, the difference comparison unit includes: a sub-difference determination sub-unit and an image difference determination sub-unit;

[0136] A sub-difference determination subunit, used to determine a sub-difference according to a difference between a fingerprint record in a first image fingerprint and a corresponding fingerprint record in a second image fingerprint of a camera with the same number, wherein the sub-difference is the number of differences of zero;

[0137] The image difference determination subunit is used to add up the sub-differences corresponding to all numbered cameras to obtain the image difference.

[0138] In one embodiment, the comparison module 23 includes: a region image determination submodule;

[0139] A region image determination submodule is used to determine a first region image containing a preset target object in the first image, and to determine a second region image containing a target object in the second image, wherein the first region image and the second region image have the same size, and the target object is a limb to be measured;

[0140] Based on the above-mentioned embodiment, the comparison submodule is further used to perform grayscale comparison processing on the first area image and the second area image corresponding to the cameras with the same number, and determine the movement state of the limb to be tested according to the comparison result.

[0141] In one embodiment, the volume measurement module 24 includes: a point cloud data determination submodule, a modeling submodule, and a volume measurement submodule;

[0142] A point cloud data determination submodule is used to perform data processing according to a preset spatial calibration relationship based on the first images of all cameras to obtain point cloud data when the motion state of the limb to be tested is not shaking;

[0143] A modeling submodule is used to perform three-dimensional modeling processing based on point cloud data to obtain a target three-dimensional limb model;

[0144] The volume measurement submodule is used to perform volume measurement processing according to the target three-dimensional limb model to obtain the volume information of the limb to be measured.

[0145] The limb volume detection device provided in the embodiment of the present application can be used to execute the limb volume detection method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0146] The present application embodiment provides a limb volume detection device, referring to Figure 7 The limb volume detection device includes: a processor 31, a memory 32, a communication module 33, an input device 34 and an output device 35. The number of processors in the limb volume detection device can be one or more, and the number of memories in the limb volume detection device can be one or more. The processor, memory, communication module, input device and output device of the limb volume detection device can be connected via a bus or other means.

[0147] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the limb volume detection method of any embodiment of the present application (for example, the first shooting module, the second shooting module, the comparison module and the volume measurement module in the limb volume detection device). The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device or other non-volatile solid-state storage device. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0148] The communication module 33 is used for data transmission.

[0149] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory, that is, realizes the above-mentioned limb volume detection method.

[0150] The input device 34 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 35 may include a display device such as a display screen.

[0151] The limb volume detection device provided above can be used to execute the limb volume detection method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0152] An embodiment of the present application also provides a storage medium storing computer executable instructions, which are used to execute a limb volume detection method when executed by a computer processor. The limb volume detection method includes: receiving a start instruction, and in response to the start instruction, controlling all cameras to perform a first shooting process on the limb to be measured to obtain a first image; controlling all cameras to perform a second shooting process on the limb to be measured within a first preset time to obtain a second image; performing grayscale contrast processing on the first image and the second image corresponding to the cameras with the same number, and determining the movement state of the limb to be measured according to the comparison result, the movement state including shaking and not shaking; when the movement state of the limb to be measured is not shaking, performing limb volume measurement processing according to the first images of all cameras to obtain volume information of the limb to be measured.

[0153] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system, which is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0154] Of course, the computer executable instructions of a storage medium storing computer executable instructions provided in an embodiment of the present application are not limited to the above limb volume detection method, and can also execute related operations in the limb volume detection method provided in any embodiment of the present application.

[0155] The limb volume detection device, storage medium and limb volume detection equipment provided in the above embodiments can execute the limb volume detection method provided in any embodiment of the present application. For technical details not described in detail in the above embodiments, please refer to the limb volume detection method provided in any embodiment of the present application.

[0156] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the protection scope of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for detecting limb volume, characterized in that: For medical detection equipment, the medical detection equipment is configured with at least one camera group, each camera group is configured with at least four cameras, the cameras in the same camera group are arranged in a ring at preset intervals, the lenses of the cameras are oriented to the central area of ​​the ring, and the ring is used for a limb to be detected to pass through, the method comprising: receiving a start instruction, and in response to the start instruction, controlling all cameras to perform a first shooting process on the limb to be measured to obtain a first image; Within a first preset time, controlling all cameras to perform a second shooting process on the limb to be tested to obtain a second image; Performing grayscale contrast processing on the first image and the second image corresponding to the camera with the same number, and determining the motion state of the limb to be tested according to the contrast result, wherein the motion state includes shaking and no shaking; When the motion state of the limb to be measured is not shaking, limb volume measurement processing is performed according to the first images of all cameras to obtain volume information of the limb to be measured.

2. The method according to claim 1, characterized in that The grayscale contrast processing of the first image and the second image corresponding to the cameras with the same number, and determining the motion state of the limb to be tested according to the contrast result, comprises: Gray-scale the first image of each camera to obtain a first standard gray-scale image; gray-scale the second image of each camera to obtain a second standard gray-scale image, wherein the first standard gray-scale image and the second standard gray-scale image have the same size; Performing discrete cosine transform processing on the first standard grayscale image and the second standard grayscale image respectively to obtain corresponding first target image and second target image; Perform grayscale contrast processing on the first target image and the second target image of the camera with the same number to obtain the image difference; When the image difference exceeds a preset threshold, determining that the motion state of the limb to be tested is shaking; When the image difference is below a preset threshold, it is determined that the movement state of the limb to be tested is not shaking.

3. The method according to claim 2, characterized in that The grayscale contrast processing of the first target image and the second target image of the camera with the same number is performed to obtain the image difference, including: Calculating the total grayscale mean of the first target image and the second target image respectively; The first target image and the second target image are processed by dividing the blocks according to a preset unit pixel amount to obtain block sub-images, wherein the block sub-images in the first target image and the second target image correspond to each other one by one; Calculating the sub-grayscale mean of each block sub-image in the first target image and the second target image respectively; Comparing the sub-grayscale mean of each sub-image in the first target image with the total grayscale mean of the first target image, and generating a binary first image fingerprint according to the comparison result; Comparing the sub-grayscale mean of each block sub-image in the second target image with the total grayscale mean of the second target image, and generating a binary second image fingerprint according to the comparison result; The first image fingerprint and the second image fingerprint of the camera with the same number are compared for difference to obtain the image difference degree.

4. The method according to claim 3, characterized in that The step of comparing the sub-grayscale mean of each sub-image block in the first target image with the total grayscale mean of the first target image and generating a binary first image fingerprint according to the comparison result includes: When the sub-grayscale mean of the corresponding block sub-image in the first target image is greater than or equal to the total grayscale mean of the first target image, determining that the fingerprint record of the corresponding block sub-image is 1; When the sub-grayscale mean of the corresponding block sub-image in the first target image is less than the total grayscale mean of the first target image, determining that the fingerprint record of the corresponding block sub-image is 0; Generate the first image fingerprint according to the fingerprint record of each sub-block image in the first target image; The step of comparing the sub-grayscale mean of each sub-image block in the second target image with the total grayscale mean of the second target image and generating a binary second image fingerprint according to the comparison result includes: When the sub-grayscale mean of the corresponding block sub-image in the second target image is greater than or equal to the total grayscale mean of the second target image, determining that the fingerprint record of the corresponding block sub-image is 1; When the sub-grayscale mean of the corresponding block sub-image in the second target image is less than the total grayscale mean of the second target image, determining that the fingerprint record of the corresponding block sub-image is 0; The second image fingerprint is generated according to the fingerprint record of each block sub-image in the second target image.

5. The method according to claim 4, characterized in that The step of comparing the first image fingerprint and the second image fingerprint of the camera with the same number to obtain the image difference comprises: Determine a sub-difference according to a difference between a fingerprint record in a first image fingerprint and a corresponding fingerprint record in a second image fingerprint of a camera with the same number, wherein the sub-difference is the amount by which the difference is greater than or less than zero; The sub-differences corresponding to all numbered cameras are added together to obtain the image difference.

6. The method according to claim 1, characterized in that The grayscale contrast processing of the first image and the second image corresponding to the cameras with the same number, and determining the motion state of the limb to be tested according to the contrast result, comprises: Determine a first area image containing a preset target object in the first image, and determine a second area image containing a target object in the second image, the first area image and the second area image have the same size, and the target object is the limb to be detected; The first area image and the second area image corresponding to the cameras with the same number are subjected to grayscale contrast processing, and the motion state of the limb to be tested is determined according to the contrast result.

7. The method according to claim 1, characterized in that When the motion state of the limb to be measured is not shaking, performing limb volume measurement processing according to the first image to obtain volume information of the limb to be measured includes: When the motion state of the limb to be tested is not shaking, data processing is performed according to a preset spatial calibration relationship based on the first images of all cameras to obtain point cloud data; Performing three-dimensional modeling processing according to the point cloud data to obtain a target three-dimensional limb model; Volume measurement processing is performed according to the target three-dimensional limb model to obtain volume information of the limb to be measured.

8. A limb volume detection device, characterized in that: Used in medical detection equipment, the medical detection equipment is configured with at least one camera group, each camera group is configured with at least four cameras, the cameras in the same camera group are arranged in a ring at preset intervals, the lenses of the cameras are oriented to the central area of ​​the ring, the ring is used for the limb to be detected to pass through, the device comprises: A first shooting module is used to receive a start instruction, and in response to the start instruction, control all cameras to perform a first shooting process on the limb to be measured to obtain a first image; A second shooting module is used to control all cameras to perform a second shooting process on the limb to be tested within a first preset time to obtain a second image; A comparison module, used for performing grayscale comparison processing on the first image and the second image corresponding to the camera with the same number, and determining the motion state of the limb to be tested according to the comparison result, wherein the motion state includes shaking and no shaking; The volume measurement module is used to perform limb volume measurement processing according to the first images of all cameras when the motion state of the limb to be measured is not shaking, so as to obtain the volume information of the limb to be measured.

9. A limb volume detection device, characterized in that: include: memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A storage medium storing computer executable instructions, characterized in that: The computer executable instructions are used to perform the method according to any one of claims 1 to 7 when executed by a processor.

Images