Target motion period extraction method and device based on optical image

Abstract

The invention provides a target motion period extraction method and device based on an optical image, and can solve the problem that the target motion period cannot be extracted or the period extraction precision is not high under the condition that the optical image of a transmitting field is complex in the related technology. The method comprises the following steps: acquiring a sequence image of a target shot by optical equipment in a launching site in a flight process; establishing a background statistical model based on the cumulative mean value and variance; performing background segmentation on each frame of image in the sequence image through a background statistical model to obtain continuous frames of target binary images; extracting the contour of the target from the continuous frames of target binary images; according to the contour of the target, extracting a target area periodic change curve; and based on the target area periodic change curve, extracting a motion period of the target.

Description

Technical Field

[0001] This application relates to the field of spacecraft imaging, and in particular to a method and apparatus for extracting the motion period of a target based on optical images. Background Technology

[0002] In space launch missions, various targets (rocket stages, separation debris, etc.) exhibit different motion characteristics due to variations in rotational inertia and control methods. The main motion characteristics include the target's periodic features. With advancements in optical observation technology, equipment with long observation distances, high resolution, and high frame rates is being used to record rocket flight. Changes in the target's attitude during flight are reflected in the projection changes on the optical measurement plane. The magnitude of these changes varies depending on the observation angle, but for periodic variations, the pattern of change on the plane remains largely consistent across different observation angles. By analyzing the characteristic changes of the target in continuous imaging on optical equipment, the target's motion period can be extracted, serving as a reference for target identification.

[0003] Existing methods for extracting target motion periods mainly utilize one-dimensional or two-dimensional radar images or RCS data, and the processing techniques are relatively mature. As a different data source application, using optical images to process target motion periods is more intuitive and can serve as a supplementary method to radar data processing. Current applications of calculating target motion periods using images measured by a single optical device are limited, and the accuracy of the calculation results is not high due to factors such as complex backgrounds in the measured images and low target signal-to-noise ratios.

[0004] During flight, a target not only reflects sunlight but also radiates energy. The grayscale of the target's phase surface measured by visible light varies depending on the projection direction on the imaging surface, while the radiated energy measured by infrared light also varies (also presented in grayscale). If the target exhibits periodic motion characteristics, this will be reflected in the imaging results as periodic changes in grayscale. By extracting grayscale data from consecutive frames of the target and performing transformation analysis, a specific motion characteristic of the target can be calculated. The same motion characteristic will show different grayscale changes in the image at different stages of flight. This is mainly due to factors such as image noise, fog, and imaging device limitations, which generate significant background noise and unstable backgrounds. These factors increase the difficulty and accuracy of target grayscale data extraction, making it impossible to extract the target's motion period or resulting in low accuracy in period extraction. Summary of the Invention

[0005] This application provides a method and apparatus for extracting the target motion period based on optical images, which can solve the problem in related technologies that the target motion period cannot be extracted or the period extraction accuracy is not high under complex conditions from optical images of the launch site.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, a method for extracting the motion period of a target based on optical images is provided, including: Acquire a sequence of images of the target during its flight, captured by optical equipment at the launch site; A background statistical model is established based on the cumulative mean and variance; Background segmentation is performed on each frame of the image sequence using a background statistical model to obtain continuous frame target binary images. Extract the contour of the target from consecutive frames of binary target images; Based on the outline of the target, extract the periodic variation curve of the target area; Based on the periodic change curve of the target area, the motion period of the target is extracted.

[0007] Secondly, a target motion period extraction device based on optical images is provided, comprising: The acquisition module is used to acquire a sequence of images of the target during its flight, captured by the optical equipment at the launch site. A module is built to establish a background statistical model based on the cumulative mean and variance; The segmentation module is used to perform background segmentation on each frame of the image sequence using a background statistical model to obtain continuous frame target binary images. The first extraction module is used to extract the contour of the target from consecutive frames of binary target images; The second extraction module is used to extract the periodic change curve of the target area based on the outline of the target; The third extraction module is used to extract the motion period of the target based on the periodic change curve of the target area.

[0008] Thirdly, an electronic device is provided, characterized in that it comprises: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the method as described in the first aspect.

[0009] Fourthly, a computer program product is provided, comprising a computer program or instructions that, when run on a computer, cause the computer to perform the method described in the first aspect.

[0010] The beneficial effects of this invention are: Using target sequence images captured by optical equipment, a deep learning-based image processing platform performs precise background segmentation and target extraction, eliminating background interference. Furthermore, the motion cycle is extracted using the grayscale data changes of the target image, solving the problem in related technologies where the motion cycle of the target cannot be extracted or the cycle extraction accuracy is low under complex conditions using optical images of the launch site. Attached Figure Description

[0011] Figure 1 The diagram illustrates the steps of a method for extracting the motion cycle of a target based on optical images.

[0012] Figure 2 The diagram illustrates the curve of the target axis projected onto the phase plane as a function of time.

[0013] Figure 3 Three typical background images are illustrated schematically.

[0014] Figure 4 This illustration shows how image quality can lead to inaccurate extraction results.

[0015] Figure 5 This is a background statistical image for sample one.

[0016] Figure 6 This is the background statistical image for Sample 2.

[0017] Figure 7 High-order and low-order scene images were created for Sample 1.

[0018] Figure 8 The high-order and low-order scene images created for Sample 2.

[0019] Figure 9 The flowchart illustrates a method for background segmentation based on cumulative mean and variance.

[0020] Figure 10 This is the background segmentation result for Sample 1.

[0021] Figure 11 This is the background segmentation result for Sample 2.

[0022] Figure 12 This is a graph showing the periodic change in the target area.

[0023] Figure 13 for Figure 12 The signal curve diagram.

[0024] Figure 14 A block diagram of a target motion cycle extraction device based on optical images is shown schematically.

[0025] Figure 15A block diagram of an electronic device is shown schematically.

[0026] Figure 16 A block diagram of a computer-readable medium is shown schematically. Detailed Implementation

[0027] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this application will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0028] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0029] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0030] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0031] It should be understood that although the terms first, second, third, etc., may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Therefore, the first component discussed below may be referred to as the second component without departing from the teachings of this application. As used herein, the term "and / or" includes all combinations of any and one or more of the listed applications.

[0032] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of exemplary embodiments, and the modules or processes in the drawings are not necessarily essential for implementing this application, and therefore cannot be used to limit the scope of protection of this application.

[0033] This application extracts the target's motion period based on optical equipment at the launch site. During flight, the target's projection relative to the phase plane of the measuring equipment varies at different times. Figure 1 The curve describing the periodicity of the target's projection onto the phase plane is described. Figure 1 The left image in the diagram shows the changes in the target phase plane projection; Figure 1 The right image in the diagram is a partial view of the projection transformation. For example... Figure 1 As shown, when periodic motion occurs, the phase projection also exhibits certain periodic changes. The magnitude of these changes varies with time and the distance from the station, but the periodic pattern remains unchanged.

[0034] During actual flight, due to the combined influence of various external factors, the target imaging background may contain interference factors such as noise and uneven grayscale. Figure 3 The illustration shows typical background images corresponding to three types of samples, such as Figure 3 As shown, the presence of interfering background factors significantly impacts background segmentation and edge recognition. If the target image is weak or the grayscale changes within a period are not significant, periodic extraction may fail or erroneously. Figure 4 As shown, Figure 4 This illustration shows how image quality can lead to inaccurate extraction results.

[0035] This invention proposes using optical equipment to capture a sequence of target images, followed by precise background segmentation and target extraction. The target motion period is then extracted using Fourier transform or a classical periodicity extraction algorithm. According to a first specific embodiment of the invention, as... Figure 1 As shown, the present invention provides a method for extracting the motion period of a target based on optical images, comprising: S11: Acquire a sequence of images of the target during its flight, captured by the optical equipment at the launch site.

[0036] S12, establish a background statistical model based on the cumulative mean and variance.

[0037] Due to limitations of the equipment itself and environmental factors of the target object, the captured image sequence may exhibit uneven grayscale, complex noise, and complex backgrounds. Consequently, classic background removal algorithms fail to achieve satisfactory results due to adaptability issues.

[0038] Background removal methods based on cumulative mean and variance primarily address the problem of accurate target extraction against complex backgrounds. The method extends the basic pixel-independent model to include the brightness of neighboring pixels, i.e., scene modeling. Through background model learning, the image is segmented into foreground and background regions, and range detection is used to segment the target image. The calculation process and algorithm are as follows.

[0039] Step S12 may include the following steps: S121, calculate the mean background image and variance background image of the background sequence images.

[0040] Assuming the background sequence image is The mean background image is The variance background image is ,but: (1) (2) Where x and y are image coordinates. It should be noted that the background sequence images are consecutive frames of background images without a target. For example, statistical analysis can be performed using background images without a target from two separate tasks (a total of 20 frames). Please refer to [reference needed for the statistical results]. Figure 5 and Figure 6 , Figure 5 For the background statistical image of sample one, Figure 6 This is the background statistical image for sample two. Figure 5 In the image, the left image is the original image of Sample 1, the middle image is the mean image of Sample 1, and the right image is the variance image of Sample 1; Figure 6 In the image, the left image is the original image of sample two, the middle image is the mean image of sample two, and the right image is the variance image of sample two.

[0041] Depend on Figure 5 and Figure 6 As can be seen, the variance images of Sample 1 and Sample 2 reflect the grayscale changes of the background image within 20 frames. If a simple frame difference method is used, calculation errors will be introduced, resulting in noise of different shapes. Next is scene establishment. The purpose of scene establishment is mainly to use a statistical background model to create background and foreground regions, i.e., to execute step S122.

[0042] S122, based on the mean background image and variance image, the image is divided into a background region and a foreground region.

[0043] In this context, the foreground region generally refers to the valuable target area that needs to be separated from the image. During the imaging process, factors such as illumination and coatings can cause the target image's grayscale value to be either higher or lower than the background area. Therefore, both types of foreground regions need to be considered in the calculation. According to the calculation results in S121, if the mean image... The variance image represents the background ground truth for a selected time period. This can be viewed as the background "error" during this period, i.e., the background drift value, denoted as . If a certain drift region is set as the background based on this drift value, then the portion of the image outside this region that cannot be interpreted by the background model can be used as the foreground. Let the background be... Foreground 1 is Foreground 2 is ,but: Background drift value for: (3) Background area for: (4) Given a grayscale range of 0~255, the foreground region is: (5) Among them, foreground region 1 is Foreground area 2 is .

[0044] based on Figure 5 The sample in the first scene is established. Figure 7 High-order and low-order scene images were created for Sample 1. For example... Figure 7 As shown, Figure 7 The left image in the image is a high-order scene image, and the right image is a low-order scene image. Based on Figure 6 The second sample in the scenario is used to establish the scenario. Figure 8 The high-order and low-order scene images created for Sample 2. For example... Figure 8 As shown, Figure 8 The left image in the image is a high-order scene image, and the right image is a low-order scene image. The high-order image refers to the mean image. Add background drift value The resulting background image; low-order image refers to the mean image. Subtract background drift value The resulting background image.

[0045] By utilizing the established background model and scene boundary delineation, background segmentation of the target image can be completed. Next, step S13 is executed.

[0046] S13, perform background segmentation on each frame of the sequence of images using a background statistical model to obtain continuous frame target binary images.

[0047] Let the sequence of images of the target during its flight be... The target binary image is ,but: (6) Figure 9This diagram illustrates a flowchart of a background segmentation method based on cumulative mean and variance. Figure 10 This is the background segmentation result for Sample 1. Figure 11 This is the background segmentation result for Sample 2. The processing flowchart based on mean and variance is as follows: Figure 9 As shown, Figure 10 and Figure 11 These are the results of segmenting images at different imaging time periods. Figure 10 In the image, the left image is the original image of the starting frame of Sample 1, and the right image is the result of background segmentation of the original image of the starting frame of Sample 1. Figure 11 In the image, counting from left to right, the first image on the far left is the original image of the starting frame of Sample 2; the second image is the result of background segmentation of the original image of the starting frame of Sample 2; the third image is the original image of Sample 2 at 300 frames interval; and the fourth image is the result of background segmentation of the original image of Sample 2 at 300 frames interval.

[0048] from Figure 10 and Figure 11 As can be seen from the two sets of segmentation results, the target is completely separated, and the influence of the background is basically eliminated. Furthermore, if noise appears in the background segmentation, it can be removed by connectivity detection (a classic method, which will not be elaborated further).

[0049] After background segmentation, proceed to step S14.

[0050] S14, Extract the contour of the target from the binary image of the target in consecutive frames.

[0051] Target motion parameters are reflected on a single image plane as changes in target contour features. However, due to projection relationships and target motion, the target attitude changes very little in a single frame image, resulting in insignificant changes in the target contour on the image plane. The following methods are primarily used to extract planar motion parameters: a) By refining the single-frame data, the contour features are enhanced, and the target image is refined. Image preprocessing techniques are used to extract the target contour.

[0052] b) Enhance variation features through statistical analysis of multi-frame contours. Using target contour data extracted from a single frame, statistical calculations of contour features from consecutive multi-frame frames are employed to analyze the changes in the target axis phase plane attitude and extract planar motion parameters.

[0053] Step S14 may include the following steps: S141, Perform contour optimization processing on the target binary image.

[0054] Directly segmented binary targets may suffer from the following problems: rough edges, jagged and uneven; voids, with small black dots inside the target caused by noise or uneven grayscale; breaks, with discontinuous edges appearing broken; and tiny noise points, with isolated white noise pixels possibly present near the target area. To eliminate these defects and obtain a "clean," "complete," and "smooth" target contour, making the extracted features (such as area, perimeter, and orientation) more accurate and reducing jitter, single-frame data refinement is used to enhance contour features. This refers to processing each frame of the segmented binary target image (i.e., an image where the target area is white and the background is black) to make the target edges clearer, more complete, and smoother, thus laying the foundation for subsequent accurate calculation of contour features such as area and principal axis orientation.

[0055] Specifically, the contour optimization process includes morphological processing of the binary image of the target region, wherein the morphological processing includes morphological closing operation to fill holes inside the target and morphological opening operation to eliminate isolated noise points.

[0056] S142, extract the pixel-level contour of the target.

[0057] The extraction method can be implemented using an edge detection algorithm. Furthermore, the extracted pixel-level contours can be approximated using polygons or fitted with curves to smooth the contours.

[0058] S15, Based on the outline of the target, extract the periodic change curve of the target area.

[0059] The extracted target area periodic change curve is as follows Figure 12 As shown by the green curve in the image, the curve exhibits periodic changes, with some interference signals around the peaks and troughs. To enhance the periodicity and facilitate subsequent extraction, the periodic change curve of the extracted target area needs to be filtered and fitted. Further, using polynomial smoothing filtering (the best fit of FFT), the fitted curve is shown below. Figure 12 The red curve in the image. Figure 12 The fitting results show that the fitted red curve has good unimodal characteristics.

[0060] S16, Based on the periodic change curve of the target area, extract the motion period of the target.

[0061] Step S16 may include the following steps: S161, Calculate the inflection point of the periodic change curve of the target area.

[0062] S162, Calculate the time interval between adjacent inflection points to extract the motion cycle of the target.

[0063] Using simulation data, the time series curve of the extracted parameters exhibits waveform changes, satisfying periodic characteristics; the time interval between two peaks (or troughs) is the period. The waveform curve is shown below. Figure 13 As shown, Figure 13 for Figure 12 The signal curve is shown. Statistical analysis can be performed using the derivative properties of the curve, as detailed below: Plot a curve for the extracted signal, assuming the equation of the curve is... Then through a point on the curve The equation of the tangent line is (7) in, As the derivative of the curve, it has the following properties: 1) The increasing or decreasing nature of the curve set up exist It exists above.

[0064] like >0, then It is an increase; like <0, then It is decreasing.

[0065] 2) Sufficient conditions for the extrema of a curve =0 (or does not exist), pass Time-varying sign, and exist If the points are continuous, then It is an extreme value; As x gradually increases, hour, If it changes from positive to negative, then It is the maximum value; As x gradually decreases, it passes through hour, If it changes from negative to positive, then It is the minimum value; =0, and ,but It is an extreme value.

[0066] when When <0, then It is the maximum value; when When >0, then It is the minimum value; 3) Convexity and concavity of the curve and inflection points exist superior exist: like If the value is greater than 0, the curve will be concave upwards; like If the value is less than 0, the curve will bulge upwards. like =0, then as x gradually increases through hour, Change the sign, then This is the inflection point.

[0067] Based on the above-mentioned curve derivative characteristics, the inflection points of the curve can be calculated, and the periodic characteristics of the curve can be extracted by statistically analyzing the time interval between two inflection points.

[0068] This invention utilizes target sequence images captured by optical equipment. Based on a deep learning image processing platform, it performs precise background segmentation and target extraction, eliminating background influences. Furthermore, it extracts the motion cycle using grayscale data changes in the target image, solving the problem in related technologies where the target motion cycle cannot be extracted or the cycle extraction accuracy is low under complex conditions from optical images of the launch site.

[0069] According to a second specific embodiment of the present invention, such as Figure 14 As shown, the present invention provides a target motion period extraction device 100 based on optical images, comprising: The acquisition module 110 is used to acquire a sequence of images of the target during flight captured by the optical equipment at the launch site; Module 120 is established to build a background statistical model based on the cumulative mean and variance; The segmentation module 130 is used to perform background segmentation on each frame of the sequence of images using a background statistical model to obtain continuous frame target binary images. The first extraction module 140 is used to extract the contour of the target in consecutive frame binary images of the target; The second extraction module 150 is used to extract the periodic change curve of the target area based on the outline of the target; The third extraction module 160 is used to extract the motion period of the target based on the periodic change curve of the target area.

[0070] According to a third specific embodiment of the present invention, the present invention provides an electronic device, such as... Figure 15 As shown, Figure 15 This is a block diagram illustrating an electronic device according to an exemplary embodiment.

[0071] The following reference Figure 15 To describe an electronic device 200 according to this embodiment of the present application. Figure 15 The electronic device 200 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0072] like Figure 15 As shown, the electronic device 200 is presented in the form of a general-purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one storage unit 220, a bus 230 connecting different system components (including storage unit 220 and processing unit 210), a display unit 240, etc.

[0073] The storage unit stores program code that can be executed by the processing unit 210, causing the processing unit 210 to perform the steps described in this specification according to various exemplary embodiments of this application. For example, the processing unit 210 can perform actions such as... Figure 1 The steps are shown in the figure.

[0074] The storage unit 220 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 2201 and / or a cache storage unit 2202, and may further include a read-only memory unit (ROM) 2203.

[0075] The storage unit 220 may also include a program / utility 2204 having a set (at least one) program module 2205, such program module 2205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0076] Bus 230 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0077] Electronic device 200 can also communicate with one or more external devices 200' (e.g., keyboard, pointing device, Bluetooth device, etc.), enabling users to communicate with devices that interact with electronic device 200, and / or any device that allows electronic device 200 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 250. Furthermore, electronic device 200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 260. Network adapter 260 can communicate with other modules of electronic device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0078] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware.

[0079] Therefore, according to a fourth specific embodiment of the present invention, the present invention provides a computer-readable medium. For example... Figure 16 As shown, the technical solution according to the embodiments of the present invention can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, mobile hard drive, etc.) or on a network, and includes several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the above-described method according to the embodiments of the present invention.

[0080] The software product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0082] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0083] The aforementioned computer-readable medium carries one or more programs, which, when executed by a device, cause the computer-readable medium to perform the functions of the first embodiment.

[0084] Those skilled in the art will understand that the above modules can be distributed in the device as described in the embodiments, or they can be modified to be uniquely different from one or more devices in this embodiment. The modules in the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0085] Through the description of the above embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions of the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of the present invention.

[0086] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for extracting the motion period of a target based on optical images, characterized in that, include: Acquire a sequence of images of the target during its flight, captured by optical equipment at the launch site; A background statistical model is established based on the cumulative mean and variance; Background segmentation is performed on each frame of the image sequence using a background statistical model to obtain continuous frame target binary images. Extract the contour of the target from consecutive frames of binary target images; Based on the outline of the target, extract the periodic variation curve of the target area; Based on the periodic change curve of the target area, the motion period of the target is extracted.

2. The method according to claim 1, characterized in that, The background statistical model established based on cumulative mean and variance includes: Calculate the mean background image and variance background image of the background sequence images; wherein, the background sequence images are consecutive frames of background images without a target. Based on the mean background image and variance image, the image is divided into a background region and a foreground region; wherein the foreground region includes the target region separated from the image.

3. The method according to claim 2, characterized in that, The calculation of the mean background image and variance background image of the background sequence image includes: Assuming the background sequence image is The mean background image is The variance background image is ,but: ； (1) ； (2) Where x and y are the image coordinates; The step of dividing the image into background and foreground regions based on the mean background image and variance image includes: If the mean background image is set to the true background value within a selected time period, and the variance background image is set to the background drift value within the selected time period, then: Background drift value for: (3) Background area for: (4) Given a grayscale range of 0~255, the foreground region is: (5) Among them, foreground region 1 is Foreground area 2 is .

4. The method according to claim 3, characterized in that, The step of performing background segmentation on each frame of the image sequence using a background statistical model to obtain consecutive frame target binary images includes: Let the sequence of images of the target during its flight be... The target binary image is ,but: (6) 。 5. The method according to claim 4, characterized in that, Extracting the contour of the target from consecutive frame binary images of the target includes: Perform contour optimization processing on the target binary image; Extract the pixel-level contour of the target.

6. The method according to claim 5, characterized in that, The contour optimization processing of the target binary image includes: The extracted pixel-level contours are approximated by polygons or fitted with curves to smooth the contours.

7. The method according to claim 6, characterized in that, Before extracting the motion period of the target, the method further includes: The extracted periodic variation curve of the target area is filtered to enhance its periodicity.

8. The method according to claim 7, characterized in that, The filtering process for the extracted target area periodic variation curve includes: The periodic variation curve of the extracted target area is fitted by polynomial smoothing filter.

9. The method according to claim 8, characterized in that, The step of extracting the motion period of the target based on the periodic change curve of the target area includes: Calculate the inflection point of the periodic change curve of the target area; The time interval between adjacent inflection points is counted to extract the motion cycle of the target.

10. A target motion period extraction device based on optical images, characterized in that, include: The acquisition module is used to acquire a sequence of images of the target during its flight, captured by the optical equipment at the launch site. A module is built to establish a background statistical model based on the cumulative mean and variance; The segmentation module is used to perform background segmentation on each frame of the image sequence using a background statistical model to obtain continuous frame target binary images. The first extraction module is used to extract the contour of the target from consecutive frames of binary target images; The second extraction module is used to extract the periodic change curve of the target area based on the outline of the target; The third extraction module is used to extract the motion period of the target based on the periodic change curve of the target area.

Images