A non-contact blood supply monitoring system

Through the non-contact blood supply monitoring system, the robotic arm and image acquisition device are used to collect and track videos, and combined with image characteristics and thermal imaging data, the problem of blood supply status monitoring in the prior art relying on subjective judgment, achieving high accuracy and High reliability monitoring of blood supply status.

CN118557157BActive Publication Date: 2024-12-06UNITED IMAGING RES INST OF INTELLIGENT IMAGING +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411008914.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-12-06
Estimated Expiration
2044-07-26

AI Technical Summary

Technical Problem

In the prior art, monitoring of postoperative blood supply status relies on subjective judgment of medical staff, resulting in poor accuracy and reliability.

Method used

A contactless blood supply monitoring system is designed, including a control host, a robotic arm and an image acquisition device. Through the robotic arm, the image acquisition device is driven to move under the control of the control host, and tracking videos of the area of ​​interest are collected and determined based on the video. The blood supply state is used to objectively analyze the image characteristics and thermal imager data, eliminate subjective factors, and improve the accuracy and reliability of monitoring results.

Benefits of technology

It realizes objective and accurate monitoring of blood supply status, reduces subjective interference, improves the reliability of monitoring results, and has a small impact on patient actions, making it suitable for long-term monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118557157B_ABST
    Figure CN118557157B_ABST
Patent Text Reader

Abstract

The present application relates to a non-contact blood supply monitoring system. The system includes: a control host, a mechanical arm and an image acquisition device; the image acquisition device is connected to the mechanical arm, and the control host communicates with the mechanical arm and the image acquisition device respectively; the mechanical arm is used to drive the image acquisition device to move under the control of the control host; the image acquisition device is used to acquire tracking videos of the area of ​​interest; the control host is used to obtain tracking videos of the area of ​​interest, determine the blood supply status of the area of ​​interest based on the tracking videos, and determine the monitoring results of the area of ​​interest based on the blood supply status. The above-mentioned non-contact blood supply monitoring system is based on the linkage between various parts to obtain objective monitoring data and conduct procedural objective analysis, so as to determine the blood supply status of the area of ​​interest and obtain monitoring results, thereby eliminating the interference of subjective factors and improving the accuracy and reliability of the obtained blood supply status and monitoring results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a non-contact blood supply monitoring system. Background Art

[0002] With the development of medical technology, reconstructive surgeries such as replantation of severed fingers and limbs and skin flap transplantation have become common surgical procedures in the medical field.

[0003] Postoperative blood supply status monitoring is the key to a successful operation. In related technologies, medical staff rely on observing the epidermis of the affected area, such as color, swelling of the epidermis, and other indicators to comprehensively judge the blood supply status.

[0004] However, the related technology relies on medical staff to judge the blood supply status of the affected area, which is easily affected by the subjective factors of the medical staff, and thus there is a problem of poor accuracy and reliability of the judgment results. Summary of the invention

[0005] Based on this, it is necessary to provide a non-contact blood supply monitoring system to address the above technical issues.

[0006] The present application provides a non-contact blood supply monitoring system, comprising:

[0007] Control the host, the mechanical arm and the image acquisition device; the image acquisition device is connected to the mechanical arm, and the control host communicates with the mechanical arm and the image acquisition device respectively;

[0008] A mechanical arm, used to drive the image acquisition device to move under the control of the control host;

[0009] An image acquisition device for acquiring tracking video of an area of ​​interest;

[0010] The control host is used to obtain the tracking video of the area of ​​interest, determine the blood supply status of the area of ​​interest according to the tracking video, and determine the monitoring result of the area of ​​interest according to the blood supply status.

[0011] In one embodiment, the control host is further configured to:

[0012] Acquire a current image acquired by an image acquisition device;

[0013] Determine the target position of the robot arm according to the region of interest in the current image;

[0014] The robot arm is controlled to move to the target position so that the image acquisition device can capture the tracking video of the area of ​​interest.

[0015] In one embodiment, the blood supply status includes venous occlusion, and the control host is further configured to:

[0016] Get any frame of image to be inspected in the tracking video;

[0017] Determine the image features of the region of interest according to the image to be inspected;

[0018] Whether there is venous obstruction in the region of interest is determined according to the image features of the region of interest.

[0019] In one embodiment, the system further includes a color card, which is set within a preset range of the region of interest; the image to be inspected includes a color card area; and the control host is further used to:

[0020] Performing color correction on the region of interest in the image to be inspected according to the color card region in the image to be inspected, to obtain a corrected image of the region of interest;

[0021] Image features of the region of interest are determined based on the corrected image.

[0022] In one embodiment, the control host is further configured to:

[0023] Acquire color features of the corrected image in at least one color space;

[0024] Determine the texture feature of the corrected image according to the grayscale image of the corrected image;

[0025] The color features and texture features of the corrected image are used as image features of the region of interest.

[0026] In one embodiment, the blood supply status includes arterial blockage, and the control host is further configured to:

[0027] Determine the grayscale mean of the region of interest over time based on the tracking video;

[0028] determining a heart rate signal that varies with time according to a grayscale mean that varies with time;

[0029] Determine whether there is arterial blockage in the area of ​​interest based on the heart rate signal.

[0030] In one embodiment, the system further comprises a thermal imager; the thermal imager is connected to the robotic arm and communicates with the control host;

[0031] A thermal imager for acquiring thermal radiation images including the area of ​​interest;

[0032] The mechanical arm is also used to move the thermal imager under the control of the host computer;

[0033] The control host is also used to determine the temperature characteristics of the region of interest based on the thermal radiation image, and determine the blood supply status of the region of interest based on the temperature characteristics of the region of interest and the tracking video.

[0034] In one embodiment, the system further comprises a heat source; the heat source is connected to the robotic arm;

[0035] A heat source, used to radiate heat outward;

[0036] The robotic arm is also used to move the heat source under the control of the host computer.

[0037] In one embodiment, the heat source communicates with the control host; the blood supply state includes an abnormal blood supply state, the abnormal blood supply state includes at least one of a venous blockage and an arterial blockage, and the control host is further configured to:

[0038] When the blood supply state of the region of interest is abnormal, controlling the heat source to increase the radiation intensity, and / or reducing the distance between the heat source and the region of interest;

[0039] When the blood supply state of the region of interest is not abnormal, the heat source is controlled to maintain the current radiation intensity and / or the current distance between the heat source and the region of interest is maintained.

[0040] In one embodiment, the system further comprises an alarm; the alarm is connected to a control host; the control host is further used for:

[0041] When the blood supply status of the region of interest is that there is venous obstruction, the control alarm sends out a first-level alarm prompt;

[0042] When the blood supply status of the region of interest is that there is arterial blockage, the control alarm sends out a secondary alarm prompt;

[0043] When the blood supply status of the region of interest is that both arterial blockage and venous blockage exist, the control alarm sends out a third-level alarm prompt.

[0044] The above-mentioned non-contact blood supply monitoring system includes: a control host, a mechanical arm and an image acquisition device; the image acquisition device is connected to the mechanical arm, and the control host communicates with the mechanical arm and the image acquisition device respectively; the mechanical arm is used to drive the image acquisition device to move under the control of the control host; the image acquisition device is used to acquire the tracking video of the area of ​​interest; the control host is used to obtain the tracking video of the area of ​​interest, determine the blood supply status of the area of ​​interest according to the tracking video, and determine the monitoring result of the area of ​​interest according to the blood supply status. The above-mentioned non-contact blood supply monitoring system is based on the linkage between various parts to obtain objective monitoring data and conduct procedural objective analysis, so as to determine the blood supply status of the area of ​​interest and obtain the monitoring results, eliminate the interference of subjective factors, and improve the accuracy and reliability of the obtained blood supply status and monitoring results. The whole system has no contact with the patient. While realizing non-contact monitoring, it has little impact on the patient's actions, which is conducive to long-term monitoring and correspondingly improves the convenience of system application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] FIG1 is a schematic structural diagram of a non-contact blood supply monitoring system in one embodiment;

[0046] FIG2 is a schematic diagram of a process of obtaining a tracking video in one embodiment;

[0047] FIG3 is a schematic diagram of a process for determining whether a vein is blocked in one embodiment;

[0048] FIG4 is a schematic diagram of a process for determining image features in one embodiment;

[0049] FIG5 is a schematic diagram of a color card in one embodiment;

[0050] FIG6 is a schematic diagram of a process for determining image features in another embodiment;

[0051] FIG. 7 is a schematic diagram of a process for determining whether an artery is blocked in one embodiment;

[0052] FIG8 is a schematic structural diagram of a non-contact blood supply monitoring system in another embodiment;

[0053] FIG9 is a schematic structural diagram of a non-contact blood supply monitoring system in another embodiment;

[0054] FIG10 is a schematic diagram of a process for providing an alarm prompt in one embodiment;

[0055] FIG11 is a schematic diagram of a process for determining monitoring results in one embodiment;

[0056] FIG12 is a structural block diagram of a blood supply monitoring device in one embodiment;

[0057] FIG. 13 is a diagram showing the internal structure of a computer device in one embodiment.

[0058] Description of reference numerals:

[0059] 100——Non-contact blood supply monitoring system;

[0060] 110——Control host;

[0061] 120——Robotic arm;

[0062] 130——Image acquisition device;

[0063] 140 – color card;

[0064] 150 – thermal imager;

[0065] 160 – heat source;

[0066] 170——Alarm. 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] In one embodiment, the present application provides a non-contact blood supply monitoring system, as shown in FIG1 , the non-contact blood supply monitoring system 100 includes:

[0069] The control host 110 , the robot arm 120 and the image acquisition device 130 .

[0070] The image acquisition device 130 is connected to the robotic arm 120 , and the control host 110 communicates with the robotic arm 120 and the image acquisition device 130 respectively.

[0071] The robotic arm 120 is used to drive the image acquisition device 130 to move under the control of the control host 110; the image acquisition device 130 is used to collect tracking videos of the area of ​​interest under the control of the control host 110; the control host 110 is used to obtain the tracking video of the area of ​​interest, determine the blood supply status of the area of ​​interest based on the tracking video, and determine the monitoring result of the area of ​​interest based on the blood supply status.

[0072] The region of interest (ROI) is the area of ​​interest for blood supply monitoring. Exemplarily, the region of interest may be a wound area, or an affected area after a repair surgery such as a finger or limb replantation surgery or a flap transplant. The tracking video of the region of interest is a video captured by the image acquisition device 130 tracking the region of interest. The blood supply status of the region of interest is the blood flow status of the region of interest. Exemplarily, the blood supply status may include unobstructed blood supply and blocked blood supply, and may also include the level of blood supply blockage.

[0073] Optionally, the mechanical arm 120 includes a movable rod and a base slide rail. The base slide rail is connected to one end of the movable rod, and the base slide rail is set on the ground, and can move along the track on the ground, and drive the movable rod to move. The other end of the movable rod is connected to the image acquisition device 130, and the movable rod can perform activities such as extension and rotation, and synchronously drive the image acquisition device 130 to move.

[0074] Optionally, the image acquisition device 130 may be a visible light camera to acquire visible light images / videos.

[0075] Optionally, the control host 110 may communicate with the robotic arm 120 and the image acquisition device 130 in a wireless or wired manner. Exemplarily, the image acquisition device 130 is integrated in the control host 110, and the control host 110 is directly connected to the robotic arm 120. It should be noted that the control host 110 may also be independent of the robotic arm 120 and the image acquisition device 130, and the communication between the control host 110 and the robotic arm 120 and the image acquisition device 130 can be maintained.

[0076] The control host 110 can obtain the image captured by the image acquisition device 130 to identify the area of ​​interest in the image, and control the movement of the robotic arm 120 through a real-time tracking algorithm to drive the image acquisition device 130 to track the area of ​​interest, so as to meet 360° automatic tracking of the area of ​​interest, thereby obtaining a tracking video of the area of ​​interest captured by the image acquisition device 130.

[0077] Optionally, after obtaining the tracking video of the region of interest, the control host 110 may analyze and process the tracking video to determine the blood supply status of the region of interest, and determine the monitoring result of the region of interest according to the blood supply status.

[0078] The blood supply state of the region of interest is the blood flow state of the region of interest. Exemplarily, the blood supply state may include normal and abnormal, may include smooth blood supply and blocked blood supply, and may also include the level of blood supply blockage.

[0079] Exemplarily, the control host 110 may identify and segment the region of interest of the video frame in the tracking video to extract the color feature of the region of interest in the video frame, and determine the blood supply status of the region of interest according to the color feature. For example, the color feature may be the mean value of the red channel component of the region of interest. The control host 110 may determine that the blood supply status of the region of interest is unobstructed when the mean value of the red channel component is greater than or equal to a preset threshold, and determine that the blood supply status of the region of interest is blocked when the mean value of the red channel component is less than a preset threshold. Among them, multiple thresholds may also be set to determine the blood supply blockage level of the region of interest according to the size relationship between the mean value of the red channel component of the region of interest and each threshold.

[0080] Optionally, the control host 110 may directly use the obtained blood supply status of the region of interest as the monitoring result of the region of interest, or may further analyze and determine the monitoring result of the region of interest based on the blood supply status.

[0081] Exemplarily, the monitoring result of the region of interest may include a blood supply risk level determined according to the blood supply status of the region of interest. For example, when the blood supply status of the region of interest is unobstructed blood supply, the blood supply risk level is determined to be level 0; when the blood supply status of the region of interest is blocked blood supply, the blood supply blockage level is further determined to determine the blood supply risk level according to the blood supply blockage level. The higher the blood supply blockage level, the higher the blood supply risk level.

[0082] In the embodiment of the present application, the non-contact blood supply monitoring system provided is based on the linkage between various parts to obtain objective monitoring data and perform programmatic objective analysis, so as to determine the blood supply status of the area of ​​interest and obtain monitoring results, eliminate the interference of subjective factors, and improve the accuracy and reliability of the obtained blood supply status and monitoring results. The entire system has no contact with the patient, and while realizing non-contact monitoring, it has little impact on the patient's movements, which is conducive to long-term monitoring and correspondingly improves the convenience of system application.

[0083] To obtain the tracking video of the area of ​​interest, in one embodiment, as shown in FIG2 , the control host 110 is further configured to implement the following steps:

[0084] S210: Acquire a current image captured by an image acquisition device.

[0085] Optionally, the control host 110 may obtain an image captured by the image acquisition device 130 at the current moment in response to a tracking start instruction triggered by the user as the current image.

[0086] S220: Determine the target position of the robot arm according to the region of interest in the current image.

[0087] The target position of the robot arm 120 is the position that the end of the robot arm 120 is expected to reach. In practical applications, the image acquisition device 130 is connected to the end of the robot arm 120, and the target position of the robot arm 120 corresponds to the position that the image acquisition device 130 is expected to reach.

[0088] Optionally, after obtaining the current image acquired by the image acquisition device 130, the control host 110 may identify the region of interest in the current image based on its integrated graphics processing unit (GPU) and segmentation model, so as to determine the target position of the robot 120 according to the position of the region of interest in the current image. The GPU integrated in the control host 110 may be a portable GPU computing cluster.

[0089] The segmentation model is a segmentation model trained by using images with regions of interest marked as training samples. Exemplarily, the segmentation model can be trained based on a Mask Region Convolutional Neural Networks (Mask R-CNN).

[0090] Exemplarily, after identifying the region of interest in the current image, the control host 110 can obtain the coordinates of the center point of the region of interest in the current image as the position of the region of interest in the current image. The control host 110 converts the position to the world coordinate system according to a pre-calibrated conversion relationship to obtain the target position of the robotic arm 120.

[0091] S230, controlling the robot arm to move to a target position so that the image acquisition device can acquire the tracking video of the area of ​​interest.

[0092] Optionally, after obtaining the target position of the robotic arm 120, the control host 110 feeds back the target position to the robotic arm 120, thereby controlling the robotic arm 120 to move to the target position, and synchronously drives the image acquisition device 130 to move to the target position, so that the image acquisition device 130 can capture the tracking video of the area of ​​interest.

[0093] In an embodiment of the present application, the non-contact blood supply monitoring system provided obtains the current image captured by the image acquisition device, determines the target position of the robotic arm based on the region of interest in the current image, thereby controlling the robotic arm to move to the target position, and drives the image acquisition device to move by the robotic arm, thereby realizing real-time tracking of the region of interest, and acquiring tracking video of the region of interest, thereby realizing long-term monitoring of the patient, so as to determine the blood supply status and monitoring results based on the long-term monitoring data, and can correspondingly improve the accuracy and reliability of the obtained blood supply status and monitoring results.

[0094] The blood supply status includes venous obstruction. Based on this, in one embodiment, as shown in FIG3 , the control host 110 is further used to implement the following steps when determining the blood supply status of the region of interest based on the tracking video:

[0095] S310, obtaining any frame of an image to be inspected in the tracking video.

[0096] Wherein, whether there is venous obstruction in the region of interest can be directly reflected by an image including the region of interest. The image to be inspected is a video frame used to determine whether there is venous obstruction in the region of interest.

[0097] Optionally, the control host 110 may obtain any frame of the tracking video as the image to be inspected. For example, the control host 110 may obtain the video frame corresponding to the current moment in the tracking video as the image to be inspected when receiving the state acquisition instruction. The state acquisition instruction may be passively triggered based on the user's operation on the control host 110, or may be automatically triggered based on a preset time period.

[0098] S320: Determine image features of the region of interest according to the image to be inspected.

[0099] The image feature of the region of interest is a picture feature presented by the region of interest in the image to be inspected. Exemplarily, the image feature may include a color feature, a brightness feature, or a texture feature.

[0100] Optionally, after the control host 110 obtains the image to be inspected, it can perform image processing on the image to be inspected, segment the image of the region of interest therefrom, perform feature extraction, and obtain the image features of the region of interest. The image processing includes but is not limited to processes such as cropping, scaling, and registration.

[0101] Exemplarily, in the case where the image feature is a brightness feature, the control host 110 may refer to the image registration value to be tested under the reference pose and convert it into a grayscale image, and intercept the image of the region of interest from the grayscale image to obtain the average grayscale value of the image of the region of interest as the image feature of the region of interest; in the case where the image feature is a color feature, the control host 110 may refer to the image registration value to be tested under the reference pose and intercept the image of the region of interest therefrom to obtain different color channel values ​​of the image of the region of interest, thereby obtaining the color feature of the region of interest. For example, the control host 110 may obtain the R channel average value (i.e., red component), the G channel average value (i.e., green component), and the B channel average value (i.e., blue component) of all pixels in the image of the region of interest as the color feature of the region of interest.

[0102] S330, determining whether there is venous obstruction in the region of interest according to the image features of the region of interest.

[0103] Optionally, after obtaining the image features of the region of interest, the control host 110 may determine whether there is venous obstruction in the region of interest based on the image features. Exemplarily, the control host 110 may determine whether there is venous obstruction based on the feature similarity between the image features of the region of interest and the reference image, or may directly input the image features of the region of interest into a pre-trained state recognition model, and the state recognition model outputs whether there is venous obstruction in the region of interest.

[0104] The reference image may be an image for determining that there is no venous blockage in the region of interest, and may be an image for determining that there is venous blockage in the region of interest. The display effect of the region of interest in the image is different when there is venous blockage and when there is no venous blockage. Therefore, it can be determined whether there is venous blockage in the region of interest based on the feature similarity between the image feature of the region of interest and the reference image.

[0105] It should be noted that, in the case of multiple types of image features, the image features can be normalized, such as processing all image features into values ​​between 0 and 1, and then input into the state recognition model to obtain whether there is venous obstruction in the region of interest. The state recognition model is a pre-trained binary classification model for identifying whether there is venous obstruction, which can be specifically trained based on random forest, adaptive boosting (Adaptive Boosting, AdaBoost) iterative algorithm and voting classifier.

[0106] Optionally, when the blood supply status includes venous obstruction, the control host 110 may directly use whether there is venous obstruction in the region of interest as the monitoring result of the region of interest when determining the monitoring result of the region of interest based on the blood supply status, or may further analyze the level of venous obstruction as the monitoring result of the region of interest, or may comprehensively determine the monitoring result of the region of interest in combination with other information.

[0107] Exemplarily, the monitoring result of the region of interest may include a venous blockage level determined by further analysis. For example, if there is no venous blockage in the region of interest, the venous blockage level is determined to be level 0; if there is venous blockage in the region of interest, the venous blockage level is determined in combination with the duration of the venous blockage. The longer the duration of the venous blockage, the higher the venous blockage level.

[0108] In the embodiment of the present application, the control host is used to obtain any frame of the image to be inspected in the tracking video, and determine the image features of the region of interest based on the image to be inspected, so as to determine whether there is venous blockage in the region of interest based on the image features of the region of interest. Whether there is venous blockage in the region of interest can be intuitively reflected by the image including the region of interest, so as to determine whether there is venous blockage based on a single image, thereby improving the convenience and efficiency of state determination and simultaneously improving the timeliness of monitoring.

[0109] In order to reduce the interference of the environment on the image features, in one embodiment, the non-contact blood supply monitoring system 100 further includes a color card 140 set within a preset range of the region of interest. The image to be inspected includes a color card area accordingly. As shown in FIG4 , when the control host 110 determines the image features of the region of interest according to the image to be inspected, it is also used to implement the following steps:

[0110] S410 , color correction is performed on a region of interest in the image to be inspected according to a color card region in the image to be inspected, to obtain a corrected image of the region of interest.

[0111] The color card 140 is a marker including blocks of multiple colors. The color card 140 is set within a preset range of the region of interest, so that when the image acquisition device 130 tracks the region of interest, the captured video frame also includes the color card 140. The color card area is the area where the color card 140 is located in the image to be seen.

[0112] When the image to be inspected is an RGB image, the color card 140 includes at least four color blocks, namely a red block, a green block, a blue block, and a block of another color.

[0113] Optionally, the image to be inspected includes a color card area and an area of ​​interest, and the control host 110 can identify and locate the color card area in the image to be inspected, determine a color correction relationship based on the color card area and the template color card, and use the color correction relationship to perform color correction on the area of ​​interest in the image to be inspected to obtain a corrected image of the area of ​​interest. The color, size, and position of the color blocks included in the template color card and the color card area correspond one to one.

[0114] Exemplarily, determining the color correction relationship based on the color card area and the template color card includes: controlling the host 110 to determine the position of each color block in the color card area according to the positional relationship of each color block in the color card 140 to extract the R channel mean, G channel mean and B channel mean of each color block, and establishing a color mapping according to the R channel mean, G channel mean and B channel mean of each color block in the preset template color card, and using a polynomial transformation algorithm to obtain a color correction matrix between the color card area in the image to be inspected and the template color card, that is, the above-mentioned color correction relationship.

[0115] It should be noted that there are many ways to identify the color card area in the image to be tested. Optionally, the control host 110 can extract the area whose contour shape matches the shape of the color card in the image to be tested based on the shape of the color card 140 as the color card area, and use the geometric center position of the color card area to characterize the position of the color card area. Optionally, the color card 140 includes not only a color block, but also a positioning block. The control host 110 can locate the color card area in the image to be tested based on the positioning block, such as locating the position of the positioning block in the image to be tested based on the color, shape or texture features of the positioning block, and determine the position of the color card area in the image to be tested according to the positional relationship of the positioning block in the color card, and then reversely infer the color card area in the image to be tested in combination with the shape and size of the color card 140.

[0116] Exemplarily, as shown in FIG5 , the color card 140 is rectangular, and includes a black and white positioning block located at at least one vertex of the rectangle (the positioning blocks in FIG5 are located at the three vertexes of the rectangular color card). The control host 110 can locate the three vertex positions of the color card area in the image to be inspected based on the three positioning blocks, and then use the rectangular characteristics to obtain the fourth vertex position of the color card area, thereby determining the color card area in the image to be inspected and the position of the color card area according to the positions of the four vertex positions of the color card area in the image to be inspected.

[0117] S420: Determine image features of the region of interest according to the corrected image.

[0118] Optionally, after obtaining the corrected image of the region of interest, the control host 110 may perform image processing on the corrected image and perform feature extraction to obtain image features of the region of interest, such as color features, brightness features, or texture features.

[0119] In the embodiment of the present application, the non-contact blood supply monitoring system provided also includes a color card set within a preset range of the region of interest, and the image to be inspected correspondingly includes a color card area. The control host can perform color correction on the region of interest in the image to be inspected based on the color card area in the image to be inspected, thereby reducing the interference of the environment on the image features, thereby improving the restoration and uniformity of the image features, and correspondingly improving the accuracy of the blood supply status determined based on the image features.

[0120] The image features may include multiple types. In one embodiment, as shown in FIG6 , when the control host 110 determines the image features of the region of interest based on the corrected image, it is also used to implement the following steps:

[0121] S610: Acquire color features of a corrected image in at least one color space.

[0122] Optionally, the control host 110 may obtain the color features of the corrected image in the RGB color space and the color features in the HSV color space. Exemplarily, when the corrected image is an RGB image, the control host 110 may obtain the mean of the R channel, the mean of the G channel and the mean of the B channel of the corrected image in the RGB color space, and may also obtain the difference between the means of any two color channels, such as at least one of the difference between the mean of the R channel and the mean of the G channel, as the color feature of the corrected image in the RGB color space. At the same time, the corrected image is converted to the HSV color space to obtain the mean of the H channel, the mean of the S channel and the mean of the V channel of the corrected image in the HSV color space, and the standard deviation and skewness of each color channel may also be obtained as the color feature of the corrected image in the HSV color space.

[0123] S620: Determine texture features of the corrected image according to the grayscale image of the corrected image.

[0124] Optionally, the control host 110 may convert the corrected image into a grayscale image to determine the texture features of the corrected image based on the grayscale image. Exemplarily, the control host 110 may determine a grayscale co-occurrence matrix based on the grayscale image, and calculate at least one of the gradient, contrast, dissimilarity, homogeneity, and local binary pattern (LBP) features of the grayscale co-occurrence matrix as the texture features of the corrected image.

[0125] S630: Use the color features and texture features of the corrected image as image features of the region of interest.

[0126] Optionally, after the control host 110 obtains the color features and texture features of the corrected image, the color features and texture features of the corrected image may be used as image features of the region of interest.

[0127] In an embodiment of the present application, the control host uses multiple features as image features of the region of interest, enriches the types and dimensions of features, improves the matching degree between the region of interest and the image features, so as to comprehensively and fully restore the region of interest, and correspondingly improves the reliability of the blood supply status determined based on the image features.

[0128] The blood supply status may include arterial blockage. Based on this, in one embodiment, as shown in FIG7 , the control host 110 is further configured to perform the following steps when determining the blood supply status of the region of interest based on the tracking video:

[0129] S710 , determining the grayscale mean of the region of interest that changes over time according to the tracking video.

[0130] Optionally, the control host 110 can obtain a video segment of a preset length in the tracking video, capture a region of interest in each frame in the video segment to form a video segment of interest, and convert each frame in the video segment of interest into a grayscale image to obtain the grayscale mean of each grayscale image in the video segment of interest, thereby obtaining the grayscale mean of the region of interest that changes with time.

[0131] S720: Determine a heart rate signal that varies with time according to the grayscale mean that varies with time.

[0132] Among them, heart rate is the fundamental reason that affects the change of grayscale mean value in the region of interest, so the grayscale mean value that changes with time can be equivalently converted into a heart rate signal that changes with time.

[0133] Optionally, after obtaining the grayscale mean of the region of interest that varies with time, the control host 110 may convert the grayscale mean that varies with time into a heart rate signal that varies with time. The conversion process includes but is not limited to filtering, time-frequency conversion and other processing processes. Exemplarily, the control host 110 may perform Chebyshev bandpass filtering on the grayscale mean that varies with time to extract the portion of the heart rate signal corresponding to a frequency between 60-100 Hz, perform Fourier transform, convert the time domain to the frequency domain, and then perform Gaussian filtering to obtain a heart rate signal that varies with time.

[0134] S730: Determine whether there is arterial blockage in the region of interest according to the heart rate signal.

[0135] Among them, heart rate affects the propagation speed of the pulse wave, and the propagation speed of the pulse wave can intuitively indicate whether there is arterial blockage.

[0136] Optionally, after obtaining the heart rate signal, the control host 110 can determine the propagation speed of the pulse wave according to the heart rate signal, so as to determine whether there is arterial blockage in the region of interest according to the propagation speed of the pulse wave. Among them, the control host 110 can use the complex characteristics of the heart rate signal to determine the phase of the heart rate signal based on the real part and the imaginary part of the heart rate signal, and determine the propagation speed of the pulse wave according to the fluctuation of the phase. Exemplarily, the control host 110 can track the signal with a phase of π in the heart rate signal, determine the signal period, and determine the propagation speed of the heart rate signal using the signal wavelength and the signal period, and use this as the propagation speed of the pulse wave.

[0137] Optionally, after obtaining the propagation speed of the pulse wave, the control host 110 may determine whether there is arterial blockage based on the magnitude relationship between the propagation speed and a preset speed threshold, and determine that there is no arterial blockage in the region of interest when the propagation speed is greater than or equal to the preset speed threshold. When the propagation speed is less than the preset speed threshold, it is determined that there is arterial blockage in the region of interest.

[0138] Wherein, if the propagation speed of the pulse wave is greater than or equal to the preset speed threshold, it indicates that the propagation speed of the pulse wave is relatively large, the blood circulation in the corresponding region of interest is unobstructed, and there is no arterial blockage. If the propagation speed of the pulse wave is less than the preset speed threshold, it indicates that the propagation speed of the pulse wave is relatively small, the blood circulation in the corresponding region of interest is obstructed, and there is arterial blockage.

[0139] Optionally, when the blood supply status includes arterial blockage, the control host 110 may directly use whether there is arterial blockage in the region of interest as the monitoring result of the region of interest when determining the monitoring result of the region of interest based on the blood supply status, or may further analyze the level of arterial blockage as the monitoring result of the region of interest, or may comprehensively determine the monitoring result of the region of interest in combination with other information.

[0140] Exemplarily, the monitoring result of the region of interest may include an arterial blockage level determined by further analysis. For example, if there is no arterial blockage in the region of interest, the arterial blockage level is determined to be level 0; if there is arterial blockage in the region of interest, the arterial blockage level is determined in combination with the duration of the arterial blockage. The longer the duration of the arterial blockage, the higher the arterial blockage level.

[0141] In the embodiment of the present application, the control host utilizes the fact that whether there is arterial blockage in the area of ​​interest can be intuitively reflected through a video including the area of ​​interest, thereby using the video to determine the heart rate signal, and then determining whether there is arterial blockage in the area of ​​interest based on the pulse wave propagation speed reflected by the heart rate signal. The pulse wave propagation speed is a key indicator for determining whether there is arterial blockage, thereby improving the accuracy of determining whether there is arterial blockage based on the pulse wave propagation speed.

[0142] In order to obtain the temperature of the region of interest, in one embodiment, as shown in FIG. 8 , the non-contact blood supply monitoring system 100 further includes a thermal imager 150 .

[0143] The thermal imager 150 is connected to the mechanical arm 120 and communicates with the control host 110;

[0144] The mechanical arm 120 is also used to drive the thermal imager 150 to move under the control of the control host 110; the thermal imager 150 is used to collect thermal radiation images including the region of interest. The control host 110 is also used to determine the temperature characteristics of the region of interest based on the thermal radiation image, and determine the blood supply status of the region of interest based on the temperature characteristics of the region of interest and the tracking video.

[0145] The thermal imager 150 is used to receive radiation energy and generate a thermal radiation image. For example, the thermal imager 150 is an infrared thermal imager. The control host 110 controls the mechanical arm 120 to move to track the area of ​​interest. The image acquisition device 130 and the thermal imager 150 have the same acquisition angle of view. The mechanical arm 120 can synchronously drive the image acquisition device 130 and the thermal imager 150 to track the area of ​​interest.

[0146] Optionally, when the blood supply status includes venous obstruction, after the control host 110 obtains the tracking video and thermal radiation image of the region of interest, it can determine the image characteristics and temperature characteristics of the region of interest at the same acquisition time to determine whether there is venous obstruction in the region of interest.

[0147] Exemplarily, the control host 110 may identify and segment the region of interest of the thermal radiation image, extract the temperature value of each pixel in the region of interest in the thermal radiation image, and determine the temperature characteristics of the region of interest, such as obtaining the average temperature of all pixels in the region of interest as the temperature characteristics of the region of interest. The process of acquiring image characteristics can be referred to the aforementioned embodiment and will not be repeated here. The control host 110 may determine whether there is venous blockage in the region of interest based on the image characteristics and temperature characteristics of the region of interest at the same acquisition time. For example, the control host 110 may normalize the image characteristics and temperature characteristics of the region of interest at the same acquisition time and input them into the state recognition model to determine whether there is venous blockage in the region of interest.

[0148] Optionally, when the blood supply status includes arterial blockage, after the control host 110 obtains the tracking video and thermal radiation image of the area of ​​interest, it can determine the heart rate signal that changes with time based on a video segment of a preset duration in the tracking video, and use signal phase tracking to determine the propagation speed of the heart rate signal, and determine multiple temperature features based on multiple frames of thermal radiation images of the area of ​​interest in the same time period, so as to determine whether there is arterial blockage in the area of ​​interest based on the propagation speed and multiple temperature features.

[0149] Exemplarily, for each frame of thermal radiation image, the control host 110 may obtain the average temperature of all pixels in the region of interest in the thermal radiation image as the temperature feature of the region of interest. The acquisition process of the propagation speed can refer to the above-mentioned embodiment and will not be repeated here. After the control host 110 obtains multiple temperature features corresponding to multiple frames of thermal radiation images, it can obtain the temperature average of the multiple temperature features to determine whether there is arterial blockage in the region of interest according to the temperature average and the propagation speed. For example, the control host 110 may compare the temperature average with a preset temperature threshold, and compare the propagation speed with a preset speed threshold, and determine whether there is arterial blockage in the region of interest according to the comparison results of the two. Among them, the control host 110 may determine that there is no arterial blockage in the region of interest when the temperature average is greater than or equal to the preset temperature threshold and the propagation speed is greater than or equal to the preset speed threshold; conversely, the control host 110 may determine that there is arterial blockage in the region of interest when the temperature average is less than the preset temperature threshold or the propagation speed is less than the preset speed threshold.

[0150] It should be noted that, when determining whether there is arterial blockage in the region of interest, in addition to the above-mentioned threshold comparison method, the determined multiple temperature features and propagation speeds can also be input into a pre-trained state recognition model to obtain whether there is arterial blockage in the region of interest. The state recognition model and the state recognition model for identifying whether there is venous blockage can be independent models or two independent submodules in the same model. Exemplarily, the state recognition model can be a Convolutional Neural Networks (CNN) model.

[0151] In the embodiment of the present application, the non-contact blood supply monitoring system provided also includes a thermal imager. The control host can obtain a thermal radiation image including the region of interest through the thermal imager to determine the temperature of the region of interest, thereby improving the comprehensiveness of monitoring, and the control host can also determine the blood supply status of the region of interest based on the temperature characteristics of the region of interest and the tracking video, thereby enriching the richness of the data based on which the status determination is based, thereby improving the accuracy and reliability of the obtained blood supply status.

[0152] In order to promote the recovery of the wound area / affected area, the wound area / affected area needs to be heated. Based on this, in one embodiment, as shown in FIG9 , the non-contact blood supply monitoring system 100 further includes a heat source 160 .

[0153] The heat source 160 is connected to the robot arm 120. The heat source 160 is used to radiate heat outward, and can achieve heating of the area of ​​interest. The robot arm 120 is also used to drive the heat source 160 to move under the control of the control host 110, and synchronously track the area of ​​interest. Exemplarily, the heat source 160 can be a light heat source.

[0154] In an optional embodiment, the heat source 160 may communicate with the control host 110, and the control host 110 is also used to control the working parameters, such as the radiation direction, of the heat source 160. For example, the control host 110 may control the heat source 160 to adjust the radiation direction to align with the region of interest based on the position of the region of interest in the video frame.

[0155] Optionally, the control host 110 may also control the heat source 160 to adjust the radiation intensity and / or the distance between the heat source 160 and the region of interest based on the blood supply status of the region of interest.

[0156] The blood supply state includes an abnormal blood supply state. The abnormal blood supply state includes at least one of a venous blockage and an arterial blockage. Exemplarily, when the blood supply state of the region of interest is an abnormal blood supply state, the control host 110 may control the heat source 160 to increase the radiation intensity, and / or drive the mechanical arm 120 to move to reduce the distance between the heat source 160 and the region of interest; when the blood supply state of the region of interest is a non-abnormal blood supply state, the control host 110 may control the heat source 160 to maintain the current radiation intensity, and / or maintain the mechanical arm 120 stationary to maintain the current distance between the heat source 160 and the region of interest.

[0157] Increasing the radiation intensity and / or reducing the distance between the heat source 160 and the region of interest can increase the heat radiated by the heat source 160 to the region of interest, thereby heating up the region of interest to accelerate blood flow and delay deterioration of blood supply to the region of interest.

[0158] In the embodiment of the present application, the non-contact blood supply monitoring system provided also includes a heat source. The heat source can synchronously track and heat the region of interest under the drive of the mechanical arm to promote the recovery of the wound area / affected area, and the control host can also automatically adjust the radiation energy of the heat source and the distance between the heat source and the region of interest based on the actual blood supply status, thereby improving the flexibility and efficiency of heating adjustment for the region of interest.

[0159] To improve the monitoring effect, in one embodiment, as shown in FIG9 , the non-contact blood supply monitoring system 100 further includes an alarm 170. The alarm 170 is connected to the control host 110. As shown in FIG10 , the control host 110 is also used to implement the following steps:

[0160] S1010. When the blood supply status of the region of interest is that there is venous obstruction, the alarm is controlled to issue a first-level alarm prompt.

[0161] S1020. When the blood supply status of the region of interest indicates that an artery is blocked, the alarm is controlled to issue a secondary alarm prompt.

[0162] S1030. When the blood supply status of the region of interest is that both arterial blockage and venous blockage exist, the alarm is controlled to issue a third-level alarm prompt.

[0163] Among them, the first-level alarm prompts, the second-level alarm prompts, and the third-level alarm prompts are not the same.

[0164] Optionally, the first-level alarm prompt, the second-level alarm prompt and the third-level alarm prompt include but are not limited to alarm prompts in the form of sound, light or vibration. For example, the first-level alarm prompt may be an alarm prompt in the form of a combination of vibration and light; the second-level alarm prompt may be an alarm prompt in the form of a combination of sound and light; and the third-level alarm prompt may be an alarm prompt in the form of a combination of sound, light and vibration.

[0165] Exemplarily, the alarm 170 may be a buzzer.

[0166] Optionally, in addition to the above-mentioned alarm 170, the non-contact blood supply monitoring system 100 may also include other functional modules, such as a communication module, a storage module, and the like. Exemplarily, the communication module may be a wireless network (Wireless Fidelity, WiFi) module or a Bluetooth module. The storage module may be a solid state drive (SSD) or a mechanical hard disk (HDD). The communication module is used to realize the communication between the non-contact blood supply monitoring system 100 and the external terminal, so that the control host 110 can receive the data or instructions sent by the external terminal, and can also feed back the video or monitoring results obtained by itself to the external terminal. The storage module is used to store the collected image data (such as visible light images, thermal radiation maps) and the monitoring result data (such as blood supply status, monitoring results).

[0167] The functional modules in the non-contact blood supply monitoring system 100 can be independently arranged from the control host 110 and communicate with the control host 110, or can be integrated inside the control host 110. For example, as shown in FIG9 , the alarm 170 and the communication module can be integrated inside the control host 110.

[0168] In the embodiment of the present application, the non-contact blood supply monitoring system provided also includes an alarm. The control host can control the alarm to give different alarm prompts based on the monitored blood supply status, so that the user can clearly understand the current blood supply status and take corresponding improvement measures in time, thereby improving the monitoring effect.

[0169] In practical applications, the blood supply status includes not only venous blockage but also arterial blockage. Therefore, in one embodiment, as shown in FIG11 , the control host 110 is further configured to perform the following steps when determining the monitoring result of the region of interest according to the blood supply status:

[0170] S1110. Determine the blood supply status level of the region of interest according to whether there is venous blockage and arterial blockage in the region of interest.

[0171] Optionally, after the control host 110 obtains whether there is venous blockage and arterial blockage in the region of interest, it can comprehensively determine the blood supply status level of the region of interest.

[0172] The blood supply status level is used to indicate whether the blood supply status is good. For example, the higher the blood supply status level, the worse the blood supply status; conversely, the lower the blood supply status level, the better the blood supply status.

[0173] Exemplarily, when there is no venous blockage and no arterial blockage in the region of interest, the control host 110 determines that the blood supply state level of the region of interest is level 0; when there is venous blockage but no arterial blockage in the region of interest, the control host 110 determines that the blood supply state level of the region of interest is level 1; when there is no venous blockage but arterial blockage in the region of interest, the control host 110 determines that the blood supply state level of the region of interest is level 2; when there is venous blockage and arterial blockage in the region of interest, the control host 110 determines that the blood supply state level of the region of interest is level 3. Level 0, level 1, level 2, and level 3 are increased in sequence.

[0174] S1120. Determine monitoring results of the region of interest according to the blood supply status level.

[0175] Optionally, after obtaining the blood supply status level of the region of interest, the control host 110 may directly use the blood supply status level as the monitoring result of the region of interest.

[0176] Optionally, the control host 110 may synchronously output the monitoring results through a display, and issue an alarm in the event of venous blockage and / or arterial blockage, to inform the user of the current blood supply status of the area of ​​interest so that the user can take improvement measures in a timely manner.

[0177] In an embodiment of the present application, the blood supply status includes venous blockage and arterial blockage. The control host can further analyze and determine the blood supply status level based on whether there is venous blockage and arterial blockage in the monitored area of ​​interest, so as to quantify the status level of the monitoring results, thereby improving the intuitiveness and simplicity of the monitoring results.

[0178] Those skilled in the art will understand that the structures shown in FIG. 1 , FIG. 8 and FIG. 9 are merely block diagrams of partial structures related to the embodiments of the present application, and do not constitute a limitation on the non-contact blood supply monitoring system to which the embodiments of the present application are applied. The specific non-contact blood supply monitoring system may include more or fewer components than those shown in the figures, or combine certain components, or have a different arrangement of components.

[0179] 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.

[0180] Based on the same inventive concept, the embodiment of the present application also provides a blood supply monitoring method, comprising:

[0181] Get tracking video of the area of ​​interest;

[0182] Determine the blood supply status of the region of interest based on the tracking video;

[0183] The monitoring results of the region of interest are determined according to the blood supply status.

[0184] In one embodiment, obtaining a tracking video of an area of ​​interest includes:

[0185] Acquire a current image acquired by an image acquisition device;

[0186] Determine the target position of the robot arm according to the region of interest in the current image;

[0187] The robot arm is controlled to move to the target position so that the image acquisition device can capture the tracking video of the area of ​​interest.

[0188] In one embodiment, the blood supply status includes venous occlusion; and determining the blood supply status of the region of interest based on the tracking video includes:

[0189] Get any frame of image to be inspected in the tracking video;

[0190] Determine the image features of the region of interest according to the image to be inspected;

[0191] Whether there is venous obstruction in the region of interest is determined according to the image features of the region of interest.

[0192] In one embodiment, determining whether there is venous obstruction in the region of interest based on image features of the region of interest includes:

[0193] Determine the temperature characteristics of the area of ​​interest based on the thermal radiation image;

[0194] Whether there is venous obstruction in the region of interest is determined based on the image features and temperature features of the region of interest at the same acquisition time.

[0195] In one embodiment, determining the image features of the region of interest according to the image to be inspected includes:

[0196] Performing color correction on the region of interest in the image to be inspected according to the color card region in the image to be inspected, to obtain a corrected image of the region of interest;

[0197] Image features of the region of interest are determined based on the corrected image.

[0198] In one embodiment, determining the image features of the region of interest based on the corrected image includes:

[0199] Acquire color features of the corrected image in at least one color space;

[0200] Determine the texture feature of the corrected image according to the grayscale image of the corrected image;

[0201] The color features and texture features of the corrected image are used as image features of the region of interest.

[0202] In one embodiment, the blood supply status includes arterial blockage; determining the blood supply status of the region of interest based on the tracking video includes:

[0203] Determine the grayscale mean of the region of interest over time based on the tracking video;

[0204] determining a heart rate signal that varies with time according to a grayscale mean that varies with time;

[0205] Determine whether there is arterial blockage in the area of ​​interest based on the heart rate signal.

[0206] In one embodiment, determining whether there is arterial blockage in a region of interest based on a heart rate signal includes:

[0207] Determine multiple temperature features of the region of interest based on multiple frames of thermal radiation images;

[0208] Determine the propagation speed based on the heart rate signal;

[0209] Multiple temperature signatures and propagation velocities are used to determine if an arterial blockage is present.

[0210] In one embodiment, the blood supply state includes an abnormal blood supply state, and the abnormal blood supply state includes at least one of venous blockage and arterial blockage; the method further includes:

[0211] When the blood supply state of the region of interest is abnormal, controlling the heat source to increase the radiation intensity, and / or reducing the distance between the heat source and the region of interest;

[0212] When the blood supply state of the region of interest is not abnormal, the heat source is controlled to maintain the current radiation intensity and / or the current distance between the heat source and the region of interest is maintained.

[0213] In one embodiment, the method further comprises:

[0214] When the blood supply status of the region of interest is that there is venous obstruction, the control alarm sends out a first-level alarm prompt;

[0215] When the blood supply status of the region of interest is that there is arterial blockage, the control alarm sends out a secondary alarm prompt;

[0216] When the blood supply status of the region of interest is that both arterial blockage and venous blockage exist, the control alarm sends out a third-level alarm prompt.

[0217] In one embodiment, the blood supply status includes venous blockage and arterial blockage; and determining the monitoring result of the region of interest according to the blood supply status includes:

[0218] Determine the blood supply status of the region of interest based on whether there is venous occlusion and arterial occlusion in the region of interest;

[0219] The monitoring results of the region of interest are determined according to the blood supply status level.

[0220] It should be noted that the implementation solution provided by this method to solve the problem is similar to the implementation solution recorded in the above-mentioned system. Therefore, the specific limitations in one or more blood supply monitoring method embodiments provided above can be referred to the above limitations on the non-contact blood supply monitoring system, and will not be repeated here.

[0221] Based on the same method concept, the present application also provides a blood supply monitoring device, as shown in FIG12 , the blood supply monitoring device includes: a data acquisition module 1201, a state determination module 1202 and a monitoring result module 1203, wherein:

[0222] The data acquisition module 1201 is used to acquire the tracking video of the area of ​​interest;

[0223] The state determination module 1202 is used to determine the blood supply state of the region of interest based on the tracking video;

[0224] The monitoring result module 1203 is used to determine the monitoring result of the region of interest according to the blood supply status.

[0225] Each module in the above blood supply monitoring device can be implemented in whole or in part by software, hardware or 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.

[0226] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG13. 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 implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a blood supply monitoring method is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0227] Those skilled in the art will understand that the structure shown in FIG. 13 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0228] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of any of the above-mentioned blood supply monitoring methods when executing the computer program.

[0229] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned blood supply monitoring methods are implemented.

[0230] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of any blood supply monitoring method when executed by a processor.

[0231] 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 this 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.

[0232] 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.

[0233] 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 non-contact blood supply monitoring system, characterized in that: The system comprises: A control host, a mechanical arm and an image acquisition device; the image acquisition device is connected to the mechanical arm, and the control host communicates with the mechanical arm and the image acquisition device respectively; The mechanical arm is used to drive the image acquisition device to move under the control of the control host; The image acquisition device is used to acquire tracking video of the area of ​​interest; The control host is used to obtain a tracking video of the region of interest, determine a blood supply status of the region of interest according to the tracking video, and determine a monitoring result of the region of interest according to the blood supply status; The system further comprises: a heat source; the heat source is connected to the mechanical arm; the heat source is used to radiate heat outward; the mechanical arm is also used to drive the heat source to move under the control of the control host; the heat source communicates with the control host; The blood supply status includes an abnormal blood supply status; the control host is also used for: When the blood supply state of the region of interest is abnormal, controlling the heat source to increase the radiation intensity, and / or reducing the distance between the heat source and the region of interest; When the blood supply state of the region of interest is not abnormal, the heat source is controlled to maintain a current radiation intensity and / or a current distance between the heat source and the region of interest.

2. The system according to claim 1, characterized in that The control host is also used for: Acquire the current image captured by the image acquisition device; Determine the target position of the robotic arm according to the region of interest in the current image; The robotic arm is controlled to move to the target position so that the image acquisition device can acquire the tracking video of the area of ​​interest.

3. The system according to claim 1 or 2, characterized in that: The blood supply status includes venous blockage, and the control host is further used for: Acquire any frame of image to be inspected in the tracking video; Determining image features of the region of interest according to the image to be inspected; It is determined whether there is venous obstruction in the region of interest according to the image features of the region of interest.

4. The system according to claim 3, characterized in that The system further includes a color card, which is set within a preset range of the region of interest; the image to be inspected includes a color card area; and the control host is further used to: Performing color correction on a region of interest in the image to be inspected according to a color card region in the image to be inspected, to obtain a corrected image of the region of interest; The image features of the region of interest are determined according to the corrected image.

5. The system according to claim 4, characterized in that The control host is also used for: Acquire color features of the corrected image in at least one color space; Determining texture features of the corrected image according to a grayscale image of the corrected image; The color features and texture features of the corrected image are used as image features of the region of interest.

6. The system according to claim 3, characterized in that The control host is also used for: Determining whether there is venous obstruction in the region of interest based on feature similarity between the image features of the region of interest and the reference image; or; The image features of the region of interest are input into a pre-trained state recognition model, and an output is given as to whether there is venous obstruction in the region of interest.

7. The system according to claim 1 or 2, characterized in that: The blood supply status includes arterial blockage, and the control host is further used for: Determine the grayscale mean of the region of interest that changes over time according to the tracking video; Determining a heart rate signal that varies with time according to the grayscale mean that varies with time; Determine whether there is artery blockage in the region of interest according to the heart rate signal.

8. The system according to claim 1 or 2, characterized in that: The system further comprises a thermal imager; the thermal imager is connected to the mechanical arm and communicates with the control host; The thermal imager is used to collect a thermal radiation image including the region of interest; The mechanical arm is also used to drive the thermal imager to move under the control of the control host; The control host is further used to determine the temperature characteristics of the region of interest based on the thermal radiation image, and determine the blood supply status of the region of interest based on the temperature characteristics of the region of interest and the tracking video.

9. The system according to claim 8, characterized in that The control host is also used for: The region of interest is identified and segmented in the thermal radiation image, the temperature value of each pixel in the region of interest in the thermal radiation image is extracted, and the temperature feature of the region of interest is determined.

10. The system according to claim 1 or 2, characterized in that: The system further comprises an alarm; the alarm is connected to the control host; the control host is also used for: When the blood supply state of the region of interest is that there is venous obstruction, controlling the alarm to issue a first-level alarm prompt; When the blood supply state of the region of interest indicates that artery blockage exists, controlling the alarm to issue a secondary alarm prompt; When the blood supply state of the region of interest is that arterial blockage and venous blockage exist simultaneously, the alarm is controlled to issue a third-level alarm prompt.