Microcirculation image sequence jitter elimination method, device, equipment and storage medium
By extracting the blood vessel areas of the microcirculation image for overlap comparison and affine transformation, the problem of data accuracy degradation caused by jitter during microcirculation image acquisition is solved, and high-precision calculations are achieved in the case of artificial jitter and light changes.
Patent Information
- Application Number
- CN202211253445.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-10-13
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-10-13
AI Technical Summary
When collecting microcirculation blood vessel images, the jitter of the operator causes relative jitter, rotation and scaling of the blood vessel images in the video, resulting in a decrease in the accuracy of the calculated microcirculation data, especially for microcirculation blood vessel images with irregular characteristics. The existing feature point matching method is not suitable.
By acquiring the microcirculation image sequence, extracting the blood vessel area, performing overlap comparisons to obtain the jitter numerical sequence, and performing affine transformation to eliminate jitter, improving the calculation accuracy.
Even in the case of severe jitter, light changes or lens distortion, the jitter data between two frames can be accurately calculated, the accuracy of calculating the human microcycle data and the stability during video recording.
Smart Images

Figure CN115778315B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical image processing, and in particular to a method, device, equipment and storage medium for eliminating jitter of a microcirculation image sequence. Background Art
[0002] Microcirculation is the blood circulation in the capillaries between arterioles and venules, and is the most basic structural and functional unit in the circulatory system. It includes the circulation of body fluids in arterioles, venules, capillary lymphatic vessels and tissue ducts. Every organ and every tissue cell in the human body needs to be provided with oxygen and nutrients, transfer energy, exchange information, and eliminate carbon dioxide and metabolic waste by microcirculation. Microcirculation reflects the physiological state and physiological changes of the human body, and studies have confirmed that inconsistent changes in systemic circulation and microcirculation indicate organ dysfunction and poor prognosis.
[0003] At present, the invention of handheld live microscope (HVM) has realized the visualization of microcirculation. During the monitoring process, the handheld live microscope needs to be operated manually to obtain microcirculation blood vessel imaging pictures from the video taken by the handheld live microscope. During the acquisition process, due to the operator's hand shaking or excessive pressure on the acquisition site, the extracted blood vessels in each frame of the video will produce relative shaking, rotation and scaling, resulting in a decrease in the accuracy of the calculated microcirculation data or even inability to calculate.
[0004] In order to eliminate jitter, the method currently used is the feature point matching method, that is, by tracking the movement of several feature points in two consecutive frame images T1 and T2, by matching the position of the feature points of T1 to T2, the displacement, rotation and scaling parameters of the feature point set are calculated. Then, the above parameters are substituted into T1 for geometric transformation, and the anti-shake effect from T1 to T2 can be obtained. However, this method is only suitable for image sets with fewer and obvious features, and it is not suitable for images with irregular features such as microcirculation vascular images, which are prone to image geometric transformation distortion. Summary of the invention
[0005] The purpose of the present invention is to provide a method, device, equipment and storage medium for eliminating jitter of a microcirculation image sequence, so as to eliminate the artificial jitter in the video recording process before calculating the human microcirculation data and improve the calculation accuracy.
[0006] To achieve the purpose of the present invention, the following technical solutions are adopted:
[0007] In a first aspect, the present invention provides a method for eliminating jitter in a microcirculation image sequence, comprising the following steps:
[0008] Step S1: obtaining a microcirculation image sequence to be dejittered and extracting the vascular region of each frame of the microcirculation image, and caching it in the vascular sequence;
[0009] Step S2: Overlap and compare the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a jitter value sequence;
[0010] Step S3: performing affine transformation on the microcirculation image sequence to be de-jittered according to the jitter value sequence to obtain the microcirculation image sequence after de-jittering.
[0011] A further improvement is that the specific method of obtaining the microcirculation image sequence to be dejittered and extracting the blood vessel region of each frame of the microcirculation image and caching it in the blood vessel sequence in step S1 includes:
[0012] Step S10: inputting the original microcirculation video;
[0013] Step S11: presetting the size of the blood vessel sequence to 0, and taking out one frame of the microcirculation image as the current frame of the microcirculation image;
[0014] Step S12: judging whether the quality of the microcirculation image of the current frame is good or not, if so, executing step S13, if not, judging whether the size of the blood vessel sequence reaches the first preset threshold, if so, executing step S2, if not, clearing the blood vessel sequence, resetting the size of the blood vessel sequence to 0 and taking out the next frame of microcirculation image as the current frame of microcirculation image and re-executing step S12;
[0015] Step S13: extract the blood vessel area of the microcirculation image of the current frame, cache it in the blood vessel sequence, and increase the size of the blood vessel sequence by 1.
[0016] A further improvement is that the specific method of obtaining the microcirculation image sequence to be dejittered and extracting the blood vessel region of each frame of the microcirculation image and caching it in the blood vessel sequence in step S1 further includes:
[0017] Step S14: Determine whether the size of the blood vessel sequence reaches a second preset threshold. If so, execute step S2. If not, take out the next frame of microcirculation image as the current frame of microcirculation image and execute step S12 again.
[0018] A further improvement is that the jitter value sequence includes at least one of a moving distance sequence, a rotation angle sequence, and a zoom multiple sequence.
[0019] A further improvement is that the specific method of performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain the moving distance sequence includes:
[0020] Assuming that the vascular area of the current frame microcirculation image is V1, and the vascular area of the next adjacent frame microcirculation image is V2, V1 is moved vertically and horizontally in the image size range in both positive and negative directions to determine whether V1 reaches the maximum overlap area with V2. If so, the movement value is cached in the movement distance sequence. If not, V1 continues to be moved.
[0021] A further improvement is that the specific method of performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a rotation angle sequence includes:
[0022] Assuming that the vascular area of the current frame microcirculation image is V1-1, and the vascular area of the next adjacent frame microcirculation image is V2, rotate V1-1 around the image center within a certain range to determine whether V1-1 reaches the maximum overlap area with V2. If so, cache the rotation angle value to the rotation angle sequence. If not, continue to rotate V1-1.
[0023] A further improvement is that the specific method of performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a zoom multiple sequence includes:
[0024] Assuming that the vascular area of the current frame microcirculation image is V1-2, and the vascular area of the next adjacent frame microcirculation image is V2, V1-2 is scaled around the image center within a certain range to determine whether V1-2 reaches the maximum overlap area with V2. If so, the scaling factor value is cached in the scaling factor sequence. If not, V1-2 continues to be scaled.
[0025] In a second aspect, the present invention provides a device for eliminating jitter of a microcirculation image sequence, comprising:
[0026] An acquisition module is used to acquire a microcirculation image sequence to be dejittered and extract a blood vessel region of each frame of the microcirculation image, and cache the region in a blood vessel sequence;
[0027] The overlap comparison module is used to compare the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a jitter value sequence;
[0028] The affine transformation processing module is used to perform affine transformation on the microcirculation image sequence to be de-jittered according to the jitter value sequence to obtain the microcirculation image sequence after de-jittering.
[0029] In a third aspect, the present invention proposes an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for eliminating jitter of a microcirculation image sequence as described in any one of the first aspects.
[0030] In a fourth aspect, the present invention proposes a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a method for eliminating jitter of a microcirculation image sequence as described in any one of the first aspects.
[0031] Beneficial effects of the present invention:
[0032] The present invention is based on the overlap comparison of the extracted blood vessel areas. Therefore, even in the case of severe jitter, sudden changes in lighting conditions, slight distortion of the lens, etc., as long as the field of view is not completely lost, the jitter data between two frames can be accurately calculated. This can eliminate the artificial jitter in the video recording process before calculating the human microcirculation data, thereby improving the calculation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0034] Figure 1 It is an overall flow chart of a method for eliminating jitter of a microcirculation image sequence according to the present invention;
[0035] Figure 2 A flowchart of a specific method of obtaining a microcirculation image sequence to be dejittered and extracting a blood vessel region of each frame of the microcirculation image and caching it in a blood vessel sequence according to the present invention;
[0036] Figure 3 This is a flow chart of a specific method for obtaining a jitter value sequence by performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in a vascular sequence according to the present invention;
[0037] Figure 4 is the original blood vessel region of each frame of the microcirculation image of the blood vessel sequence of the present invention;
[0038] Figure 5 for Figure 4 Aligned blood vessel regions after affine transformation;
[0039] Figure 6 A structural diagram of a microcirculation image sequence jitter elimination device according to the present invention;
[0040] Figure 7 The figure is a schematic diagram of an electronic device according to the present invention. DETAILED DESCRIPTION
[0041] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0043] Please refer to the attached Figure 1 -Attached Figure 7 ,like Figure 1 As shown, a first aspect of an embodiment of the present invention provides a method for eliminating jitter of a microcirculation image sequence, comprising the following steps:
[0044] Step S1: obtaining a microcirculation image sequence to be dejittered and extracting the vascular region of each frame of the microcirculation image, and caching it in the vascular sequence;
[0045] Step S2: Overlap and compare the vascular regions of two adjacent frames of microcirculation images in the vascular sequence, and when the maximum overlap area is reached, obtain the jitter value to obtain a jitter value sequence;
[0046] It should be noted that when the vascular area overlap effect of two frames of microcirculation images is optimal, that is, the maximum overlap area is reached, it can be considered that the jitter between the two frames of microcirculation images is eliminated. When the maximum overlap area is reached, the jitter value is recorded to form a jitter value sequence.
[0047] Step S3: performing affine transformation on the microcirculation image sequence to be de-jittered according to the jitter value sequence to obtain the microcirculation image sequence after de-jittering, that is, obtaining the anti-jitter image queue.
[0048] Among them, microcirculation is the blood circulation in the capillaries between arterioles and venules, and is the most basic structural and functional unit in the circulatory system. It includes the circulation of body fluids in arterioles, venules, capillary lymphatic vessels and tissue ducts.
[0049] In this embodiment, the specific method of obtaining the microcirculation image sequence to be dejittered and extracting the blood vessel region of each frame of the microcirculation image and caching it in the blood vessel sequence in step S1 includes:
[0050] Step S10: inputting the original microcirculation video; the original microcirculation video can be obtained by manually operating a handheld living microscope during the monitoring process. The total number of frames of the video should be within the range of [120,∞).
[0051] Step S11: presetting the size of the blood vessel sequence to 0, traversing the microcirculation image sequence, and taking out one frame of the microcirculation image as the current frame of the microcirculation image;
[0052] Step S12: judging whether the quality of the microcirculation image of the current frame is good or not, if so, executing step S13, if not, judging whether the size of the blood vessel sequence reaches the first preset threshold, if so, executing step S2, if not, clearing the blood vessel sequence, resetting the size of the blood vessel sequence to 0 and taking out the next frame of microcirculation image as the current frame of microcirculation image and re-executing step S12;
[0053] Step S13: extract the blood vessel area of the microcirculation image of the current frame, cache it in the blood vessel sequence, and increase the size of the blood vessel sequence by 1.
[0054] The specific method of obtaining the microcirculation image sequence to be dejittered in step S1 and extracting the blood vessel region of each frame of the microcirculation image and caching it in the blood vessel sequence also includes:
[0055] Step S14: Determine whether the size of the blood vessel sequence reaches a second preset threshold. If so, execute step S2. If not, take out the next frame of microcirculation image as the current frame of microcirculation image and execute step S12 again.
[0056] In some embodiments, the clarity is used as a standard to determine whether the quality of the microcirculation image of the current frame is good, that is, to determine whether the clarity of the image meets the standard. Specifically, the clarity can be evaluated by the Brenner gradient function. The Brenne gradient function is the simplest gradient evaluation function, which simply calculates the square of the grayscale difference between two adjacent pixels.
[0057] It should be noted that, in the preferred solution of this embodiment, the size of the first preset threshold is 80, and the size of the second preset threshold is 120. That is, the number of continuous clear frames of the microcirculation image sequence must reach 80 frames. If unclear frames appear before reaching 80 frames, the previously accumulated blood vessel sequence is cleared, and the next frame of microcirculation image is reselected to re-judge the image quality and extract the blood vessel area. If the size of the blood vessel sequence has reached 80 when an unclear image appears, the traversal of the microcirculation image sequence can be stopped, and the step of overlapping and comparing the blood vessel areas of two adjacent frames of microcirculation images in the blood vessel sequence to obtain a jitter value sequence is entered. If the number of continuous clear frames reaches 120 frames, the traversal of the microcirculation image sequence is also stopped, and the step of overlapping and comparing the blood vessel areas of two adjacent frames of microcirculation images in the blood vessel sequence to obtain a jitter value sequence is entered.
[0058] In this embodiment, the jitter value sequence includes at least one of a moving distance sequence, a rotation angle sequence, and a zoom multiple sequence, that is, the jitter value sequence may include any one, any two, or all three of the above three sequences.
[0059] It should be noted that, since the comparison is made between the overlapping frames of the previous and next frames, the size of the obtained jitter value sequences is the size of the blood vessel sequence minus one.
[0060] The following takes the jitter value sequence including the moving distance sequence, the rotation angle sequence, and the scaling multiple sequence as an example to illustrate the specific method of obtaining the moving distance sequence, the rotation angle sequence, and the scaling multiple sequence:
[0061] The specific method of performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a moving distance sequence includes:
[0062] Assuming that the vascular area of the current frame of microcirculation image is V1, and the vascular area of the next adjacent frame of microcirculation image is V2, V1 is moved vertically and horizontally in the image size range in both positive and negative directions to determine whether V1 reaches the maximum overlap area with V2. If so, the movement value is cached in the movement distance sequence and the microcirculation image V1-1 after the movement is obtained. If not, V1 continues to be moved.
[0063] After obtaining the moved microcirculation image V1-1, the specific method of further performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a rotation angle sequence includes:
[0064] Rotate V1-1 around the image center in the range of [-10°, 10°] to determine whether V1-1 reaches the maximum overlap area with V2. If so, cache the rotation angle value to the rotation angle sequence and obtain the rotated microcirculation image V1-2. If not, continue to rotate V1-1.
[0065] After obtaining the rotated microcirculation image V1-2, the specific method of further performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a zoom multiple sequence includes:
[0066] Scale V1-2 around the image center in the range of [0.9,1.1] times to determine whether V1-2 reaches the maximum overlap area with V2. If so, cache the scaling factor value to the scaling factor sequence. If not, continue to scale V1-2.
[0067] It should be noted that the acquisition order of the above moving distance sequence, rotation angle sequence, and zoom multiple sequence is not unique, and those skilled in the art can adjust the order arbitrarily according to the actual situation, for example, the moving distance sequence can be obtained first, then the zoom multiple sequence can be obtained, and finally the rotation angle sequence can be obtained. In addition, when the jitter value sequence only includes any two of the moving distance sequence, the rotation angle sequence, and the zoom multiple sequence, the acquisition order can also be adjusted arbitrarily. These adjustments are all within the protection scope of this embodiment.
[0068] After obtaining the jitter value sequence (including any one or more of the moving distance sequence, the rotation angle sequence, and the zoom multiple sequence), the microcirculation image sequence to be jitter-free can be subjected to affine transformation according to the jitter values of the jitter value sequence.
[0069] Affine transformation refers to a linear transformation of a vector space followed by a translation in geometry to transform it into another vector space. For example, if the displacement distance is -1px horizontally and 2px vertically, and the displacement starting point is the origin in the upper left corner, then after performing an affine transformation on a frame of image, it can be moved to the upper left corner.
[0070] It is understandable that the present invention is based on the overlap comparison of the extracted blood vessel areas, so even if the jitter is very severe, or the lighting conditions change suddenly, the lens is slightly distorted, etc., as long as the field of view is not completely lost, the jitter data between two frames can be calculated.
[0071] The specific method of obtaining the anti-shake image queue by affine transformation processing includes:
[0072] Input the jitter data AS (size is N) in the jitter value sequence, traverse the blood vessel sequence (size is N+1), take out a frame of microcirculation image Fi (i≥0 and i<N), perform affine transformation on Fi according to AS[i] to obtain Fi', then determine whether the anti-shake image queue is empty, if it is empty, cache Fi' to the anti-shake image queue, if it is not empty, perform affine transformation on the anti-shake image queue according to AS[i] and cache Fi' to the anti-shake image queue.
[0073] It should be noted that since the calculated jitter value sequence is the calculation result of each frame and the next frame, when eliminating jitter in the image sequence, it is necessary to constantly accumulate the previous jitter values so that the image sequence is always aligned with the latest frame.
[0074] A second aspect of the present invention provides a device for eliminating jitter in a microcirculation image sequence, see Figure 6 , is a structural schematic diagram of a microcirculation image sequence de-jittering device provided in accordance with an embodiment of the present invention, which corresponds to a microcirculation image sequence de-jittering method provided in the above-mentioned embodiment of the present invention. Since a microcirculation image sequence de-jittering device provided in the embodiment of the present invention corresponds to a microcirculation image sequence de-jittering method provided in the above-mentioned embodiment of the present invention, the implementation method of the above-mentioned microcirculation image sequence de-jittering method is also applicable to a microcirculation image sequence de-jittering device provided in this embodiment.
[0075] Specifically, Figure 6 As shown, a device for eliminating jitter of a microcirculation image sequence comprises:
[0076] An acquisition module 100 is used to acquire a microcirculation image sequence to be dejittered and extract a blood vessel region of each frame of the microcirculation image, and cache the region in a blood vessel sequence;
[0077] The overlap comparison module 200 is used to perform overlap comparison on the blood vessel regions of two adjacent frames of microcirculation images in the blood vessel sequence to obtain a jitter value sequence;
[0078] The affine transformation processing module 300 is used to perform affine transformation on the microcirculation image sequence to be de-jittered according to the jitter value sequence to obtain the microcirculation image sequence after de-jittering.
[0079] The specific functions of the modules of the microcirculation image sequence de-jittering device in this embodiment may refer to the microcirculation image sequence de-jittering method in the above embodiment.
[0080] See also Figure 7 , an embodiment of the present invention also provides an electronic device and a computer-readable storage medium.
[0081] like Figure 7The figure shows a schematic diagram of an electronic device provided by an embodiment of the present invention. The electronic device of this embodiment includes: a processor 11, a memory 12, and a computer program stored in the memory and executable on the processor 11. When the processor 11 executes the computer program, the steps in the above-mentioned microcirculation image sequence de-jittering method embodiment are implemented. Alternatively, when the processor 11 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.
[0082] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor 11 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.
[0083] The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of an electronic device and does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the diagram, or may combine certain components, or different components, for example, the electronic device may also include an input / output device, a network access device, a bus, etc.
[0084] The processor 11 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.
[0085] The memory 12 can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system 121, an application 122 required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0086] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.
[0087] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.
[0088] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0089] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for eliminating jitter in microcirculation image sequences. It is characterized in that The following steps are involved: Step S1: obtaining a microcirculation image sequence to be dejittered and extracting the vascular region of each frame of the microcirculation image, and caching it in the vascular sequence; Step S2: Overlap and compare the vascular regions of two adjacent frames of microcirculation images in the vascular sequence, and when the maximum overlap area is reached, obtain a jitter value to obtain a jitter value sequence, wherein the jitter value sequence includes at least one of a moving distance sequence, a rotation angle sequence, and a zoom multiple sequence; The specific method for performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a moving distance sequence includes: assuming that the vascular region of the current frame of the microcirculation image is V1, and the vascular region of the next adjacent frame of the microcirculation image is V2, moving V1 in the forward and reverse directions vertically and horizontally within the image size range, and judging whether V1 reaches the maximum overlap area with V2, if so, caching the moving value into the moving distance sequence, if not, continuing to move V1; The specific method for obtaining a rotation angle sequence by performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence includes: assuming that the vascular region of the current frame of the microcirculation image is V1-1, and the vascular region of the next adjacent frame of the microcirculation image is V2, rotating V1-1 around the image center within a certain range, and judging whether V1-1 reaches the maximum overlap area with V2, if so, caching the rotation angle value into the rotation angle sequence, if not, continuing to rotate V1-1; The specific method for performing overlap comparison on the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a zoom multiple sequence includes: assuming that the vascular region of the current frame of the microcirculation image is V1-2, and the vascular region of the next adjacent frame of the microcirculation image is V2, scaling V1-2 around the image center within a certain range, and determining whether V1-2 reaches the maximum overlap area with V2, if so, caching the zoom multiple value into the zoom multiple sequence, if not, continuing to scale V1-2; Step S3: performing affine transformation on the microcirculation image sequence to be de-jittered according to the jitter value sequence to obtain the microcirculation image sequence after de-jittering.
2. According to the method for eliminating jitter of microcirculation image sequence according to claim 1, It is characterized in that The specific method of obtaining the microcirculation image sequence to be dejittered and extracting the blood vessel region of each frame of the microcirculation image and caching it in the blood vessel sequence in step S1 includes: Step S10: inputting the original microcirculation video; Step S11: presetting the size of the blood vessel sequence to 0, and taking out one frame of the microcirculation image as the current frame of the microcirculation image; Step S12: judging whether the quality of the microcirculation image of the current frame is good or not, if so, executing step S13, if not, judging whether the size of the blood vessel sequence reaches the first preset threshold, if so, executing step S2, if not, clearing the blood vessel sequence, resetting the size of the blood vessel sequence to 0 and taking out the next frame of microcirculation image as the current frame of microcirculation image and re-executing step S12; Step S13: extract the blood vessel area of the microcirculation image of the current frame, cache it in the blood vessel sequence, and increase the size of the blood vessel sequence by 1.
3. A method for eliminating jitter of a microcirculation image sequence according to claim 2, It is characterized in that The specific method of obtaining the microcirculation image sequence to be dejittered in step S1 and extracting the blood vessel region of each frame of the microcirculation image and caching it in the blood vessel sequence also includes: Step S14: Determine whether the size of the blood vessel sequence reaches a second preset threshold. If so, execute step S2. If not, take out the next frame of microcirculation image as the current frame of microcirculation image and execute step S12 again.
4. A device for eliminating jitter of microcirculation image sequence, It is characterized in that A method for eliminating jitter of a microcirculation image sequence according to any one of claims 1 to 3, comprising: An acquisition module is used to acquire a microcirculation image sequence to be dejittered and extract a blood vessel region of each frame of the microcirculation image, and cache the region in a blood vessel sequence; The overlap comparison module is used to compare the vascular regions of two adjacent frames of microcirculation images in the vascular sequence to obtain a jitter value sequence; The affine transformation processing module is used to perform affine transformation on the microcirculation image sequence to be de-jittered according to the jitter value sequence to obtain the microcirculation image sequence after de-jittering.
5. An electronic device, It is characterized in that The invention comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a method for eliminating jitter of a microcirculation image sequence as claimed in any one of claims 1 to 3 is implemented.
6. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute a method for eliminating jitter of a microcirculation image sequence according to any one of claims 1 to 3.
Citation Information
Patent Citations
Rapid image mosaic method based on corner matching
CN102903085A
Microcirculation imaging device
CN106901712A
Face recognition and skin detection system based on high-speed wide-range scanning optical micro contrast imaging
CN107307848A
Fast image-stabilizing method based on centric mapping
CN107680127A
A method and apparatus for image processing
CN109285122A
