Method for identifying quick-moving target based on inverse color feature track

Abstract

The invention provides a method for identifying a quick-moving target based on inverse color feature tracks, which comprises the following steps: acquiring a series of time sequence observation images comprising the quick-moving target and establishing an image database, the series of time sequence observation images comprising a plurality of original observation images; preprocessing the plurality of original observation images respectively; carrying out astronomical position calibration on the plurality of preprocessed original observation images respectively; any one of the series of time sequence observation images after preprocessing and astronomical position calibration is selected as a template image, and the remaining non-template images are scientific images; based on the template image, background deduction is carried out on the multiple scientific images according to the time sequence; superposing and combining the template image subjected to background deduction and a plurality of scientific images by taking an astronomical position as a reference to obtain a dynamic trajectory graph; and recognizing a quick-moving target based on the dynamic trajectory diagram. According to the method, the target can be quickly recognized only by constructing the special inverse color feature track of the quick-moving target.

Description

Technical Field

[0001] The invention relates to the technical field of astronomical target recognition, and in particular to a method for recognizing fast-moving targets based on inverted color feature trajectories. Background Art

[0002] Space debris and near-Earth asteroids are the two major space threats currently faced by mankind. With the continuous advancement of space technology and the increasing frequency of human space activities, the number of centimeter-level space debris that poses a threat to space activities has reached millions, and the number of millimeter-level space debris with potential risks has exceeded 100 million. In addition, the number of near-Earth asteroids colliding with the Earth is increasing, posing a major potential risk to the stability of human society and the survival of life on Earth. In the stage of fast-moving target recognition, it becomes difficult to distinguish between stars, planets and space debris targets due to their morphological similarities. One of the main challenges we face is how to quickly and effectively extract fast-moving targets from background images.

[0003] The existing method of using feature trajectories to identify fast-moving targets mainly aligns a series of time-series images taken according to astronomical coordinate positions and directly merges the images. Although this method can see the moving trajectory of fast-moving targets in the image, the trajectory generated by this method is mixed with a large number of bright stars and other interferences, making it difficult to quickly and accurately extract and identify. These interferences are mainly composed of several aspects, such as noise, camera hardware defects, and overexposure of bright sources. Traditional trajectory recognition methods not only cannot avoid problems, but may also cause more image interference after superposition. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above shortcomings, the main purpose of the present invention is to provide a method for identifying fast-moving targets based on inverse color feature trajectories, which can eliminate the interference of bright stellar sources and other backgrounds, and only needs to construct special inverse color feature trajectories of fast-moving targets to achieve rapid identification of targets.

[0006] (II) Technical solution

[0007] In order to achieve the above-mentioned purpose, the present invention provides a method for identifying fast-moving targets based on inverted color feature trajectories, comprising: acquiring a series of time-series observation images containing fast-moving targets and establishing an image database, wherein the series of time-series observation images include multiple original observation images; preprocessing the multiple original observation images respectively; astronomical position calibration of the multiple original observation images after preprocessing; selecting any one of the series of time-series observation images after preprocessing and astronomical position calibration as a template image, wherein the remaining images that are not template images are scientific images; based on the template image, background subtraction is performed on the multiple scientific images in chronological order; the template image after background subtraction and the multiple scientific images are superimposed and merged based on the astronomical position to obtain a dynamic trajectory map; based on the dynamic trajectory map, identifying the fast-moving target.

[0008] In the above solution, a series of time-series observation images includes at least 3 original observation images; and a plurality of original observation images in the series of time-series observation images are acquired according to a preset observation time interval.

[0009] In the above scheme, the template image is the first image obtained in a series of time-series observation images.

[0010] In the above scheme, background subtraction is performed on multiple scientific images in chronological order based on the template image, including: according to a preset observation time interval, image subtraction is performed on the template image and the multiple scientific images; after the subtraction is completed, the first target in the template image and the second target in the multiple scientific images are obtained respectively.

[0011] In the above solution, the first target and the second target are displayed in the image in opposite colors.

[0012] In the above scheme, the template image after background subtraction and multiple scientific images are superimposed and merged based on astronomical positions to obtain a dynamic trajectory map, including: searching for the characteristic trajectory of the second target; and constructing a dynamic trajectory map consisting of the first target and multiple second targets.

[0013] In the above scheme, based on the dynamic trajectory graph, the fast-moving target is identified, including: based on the dynamic trajectory graph, the time and position of the fast-moving target trajectory are extracted to obtain the fast-moving target.

[0014] (III) Beneficial effects

[0015] The technical solution of the embodiment of the present invention has at least the following beneficial effects:

[0016] (1) The trajectory feature image generated by this method using the inverted color feature trajectory to identify fast-moving targets can not only ensure the uniqueness of the extracted fast-moving targets, but also the background of the constructed trajectory feature image is purer, with almost no bright sources and other potential interference, thereby providing more accurate and stable recognition features and improving the efficiency and accuracy of recognition.

[0017] (2) This method uses the inverted color feature trajectory to quickly locate and identify these fast-moving targets, ensuring timely monitoring of fast-moving targets such as space debris targets and near-Earth asteroids. It can detect crisis moments in time and intervene in time to avoid loss of life and property.

[0018] (3) This method can batch process observation images in time-series observation images, reduce the manpower and time costs of identifying fast-moving targets, and improve the accuracy of recognition and the stability of recognition rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of a method for identifying fast-moving targets based on inverted color feature trajectories according to an embodiment of the present invention is schematically shown;

[0020] Figure 2 shows a template image according to an embodiment of the present invention;

[0021] Figure 3 shows a scientific image according to an embodiment of the present invention;

[0022] Figure 4 The images after background subtraction of scientific images based on the template image according to the embodiment of the present invention are shown;

[0023] Figure 5 An image of a dynamic trajectory diagram obtained by superposition according to an embodiment of the present invention is shown;

[0024] Figure 6 The effect diagram of the inverted color feature trajectory according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0025] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0026] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0027] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0028] Figure 1 The flowchart of the method for identifying fast-moving targets based on inverted color feature trajectories according to an embodiment of the present invention is schematically shown.

[0029] Please refer to Figure 1 In an embodiment of the present invention, the method for identifying fast-moving targets based on inverse color feature trajectories specifically includes steps S110 to S170.

[0030] Step S110 , acquiring a series of time-series observation images containing fast-moving targets and establishing an image database, wherein the series of time-series observation images includes a plurality of original observation images.

[0031] In an embodiment of the present invention, a series of time-series observation images includes at least three original observation images; and a plurality of original observation images in the series of time-series observation images are acquired according to a preset observation time interval.

[0032] Specifically, in order to obtain the position change of the fast-moving target, the observation shooting time of the multiple original observation images constituting the database needs to be at a certain interval, for example, in the range of several minutes to half an hour.

[0033] It should be noted that when observing and shooting the target, in order to obtain better motion trajectory features, the target is generally photographed at the same time interval, but different intervals can also be used. In addition, in order to obtain a complete motion trajectory and more motion trajectory data points, it is necessary to ensure that the number of original observation images in the observed series of time-series images is greater than 3.

[0034] For example, take multiple FITS format images containing fast-moving targets and establish a processing database. The background of a normal FITS image is gray, and the white bright sources are various celestial bodies. When photographing the observation target, take pictures of the target with the same exposure time and the same interval time, and save the time-series observation images for subsequent processing.

[0035] Step S120, pre-processing the multiple original observation images respectively.

[0036] In an embodiment of the present invention, a plurality of original observation images are preprocessed respectively, wherein the preprocessing includes: correcting the background image and the flat field image of each of the plurality of original observation images; and removing cosmic rays of each original observation image.

[0037] Specifically, in order to eliminate the interference items brought by the machine to the original observation images, multiple original observation images are preprocessed separately to correct the background image and the flat field image, and to remove cosmic rays from each original observation image.

[0038] Step S130, performing astronomical position calibration on the preprocessed multiple original observation images respectively.

[0039] In an embodiment of the present invention, astronomical position calibration is performed on the preprocessed multiple original observation images respectively, including: performing astronomical position calibration on the original observation images respectively through WCS (World Coordinate System) to determine that the pixel points on the original observation images are mapped to specific positions on the celestial sphere.

[0040] Specifically, astronomical position calibration of multiple pre-processed original observation images is an important step in astronomical data processing, which ensures the precise alignment of images and the accuracy of subsequent analysis.

[0041] The WCS (World Coordinate System) system is used for astronomical position calibration. It is a coordinate system for astronomical images, which describes the geometric transformation relationship between image pixel coordinates and celestial coordinates. WCS can map the pixel points on the original observation image to a specific position on the celestial sphere, so as to accurately determine the relative relationship between the position of the celestial body and the original observation image.

[0042] Step S140, selecting any one of a series of time-series observation images after preprocessing and astronomical position calibration as a template image, wherein the remaining images other than the template images are scientific images.

[0043] For example, in the series of time-series observation images after preprocessing and astronomical position calibration, the first image obtained in the series of time-series observation images can be selected as the template image, and the image not obtained for the first time in the series of time-series observation images can also be selected as the template image. After the template image is selected, the other images in the series of time-series observation images are all scientific images.

[0044] Step S150, based on the template image, background subtraction is performed on the multiple scientific images in chronological order.

[0045] In an embodiment of the present invention, background subtraction is performed on multiple scientific images in chronological order based on a template image, including: performing image subtraction on the template image and the multiple scientific images according to a preset observation time interval; after the subtraction, a first target in the template image and a second target in the multiple scientific images are obtained, wherein the first target and the second target are displayed in the image as inverted colors.

[0046] Specifically, the template image is used to perform stellar background subtraction with the scientific image in chronological order, and the interval time between the two subtracted images can be selected by referring to the target movement speed or the observation time interval to ensure that the object movement trajectory achieves the ideal effect.

[0047] Furthermore, after the image subtraction is completed, only the first target in the template image (eg, the first target may be represented as a white target in the image) and the subtracted second target in the scientific image (eg, the second target may be represented as an inverted (black) target in the image) remain.

[0048] Step S160 , superimposing and merging the template image after background subtraction and a plurality of scientific images based on astronomical positions to obtain a dynamic trajectory map.

[0049] Specifically, a series of images that have undergone image subtraction are superimposed based on the astronomical position, and then the characteristic trajectory of the second target is searched to construct a dynamic trajectory map that includes the first target and multiple second targets.

[0050] Exemplarily, the dynamic trajectory graph may be presented as a dynamic trajectory graph composed of white and a series of black dots or short lines.

[0051] Step S170, identifying fast-moving targets based on the dynamic trajectory graph.

[0052] Specifically, based on the dynamic trajectory graph, the time and position of the fast-moving target trajectory are extracted to obtain the fast-moving target.

[0053] Based on the above-mentioned method for identifying fast-moving targets based on inverted color feature trajectories, in an embodiment of the present invention, for the observation of fast-moving targets, it is necessary to continuously take a number of target images at intervals based on the same exposure time. Usually, the first image is used as a background reference template, called a template image, and the subsequent observation images are called scientific images of the template image.

[0054] Furthermore, the positions of the stars seen in the observed images are fixed in the astronomical coordinate system. The observed scientific images are aligned with the template images based on the astronomical positions, and the data is subtracted between the two images. The remaining target is the signal of the captured moving celestial body.

[0055] In an embodiment of the present invention, in order to ensure the inverted (black) color trajectory, it is necessary to use a template image to subtract the scientific image, and then superimpose several images of the remaining fast-moving target celestial body to obtain a clear motion trajectory of the fast-moving target. The first trajectory point of the characteristic trajectory is a white target, and the subsequent trajectory targets are all black, which has a strong recognition. The trajectory feature image generated by the method of identifying fast-moving targets using inverted color feature trajectories can not only ensure the uniqueness of the extracted fast-moving targets, but also the constructed trajectory feature image has a purer background, with almost no bright sources and other potential interference, thereby providing more accurate and stable identification features, improving the efficiency and accuracy of identification, and laying a solid foundation for the subsequent precise supervision of fast-moving targets.

[0056] Through the embodiments of the present invention, the interference of bright stellar sources and other backgrounds can be eliminated, and only the special inverted color characteristic trajectory of the fast-moving target can be constructed to achieve rapid identification of the target, ensure timely monitoring of fast-moving targets such as space debris targets and near-Earth asteroids, and be able to promptly discover crisis moments and intervene in time to avoid loss of life and property.

[0057] Based on the above method for identifying fast-moving targets based on inverse color feature trajectories, the present invention is described using a series of time-series observation images as an example.

[0058] Figure 2 A template image according to an embodiment of the present invention is shown.

[0059] Obtain a series of time-series observation images containing fast-moving targets, which include multiple original observation images in FITS format, pre-process the multiple original observation images respectively, and then perform astronomical position calibration on the pre-processed multiple original observation images respectively. Select one of them as the template image, such as Figure 2 As shown, in this template image, the white target sources in the green circle are near-Earth asteroids, and the other white target sources are stars.

[0060] Figure 3 A scientific image according to an embodiment of the present invention is shown.

[0061] Furthermore, after the template image is selected, all other images in a series of time-series observation images are scientific images. Figure 3 Shown are three scientific images selected from several scientific images. The white target sources in the green circle are near-Earth asteroids, and the other white target sources are stars.

[0062] Figure 4 The images are shown after background subtraction is performed on the scientific images based on the template image according to an embodiment of the present invention.

[0063] In the embodiment of the present invention, the template image is used to subtract the scientific image to obtain three subtracted images. Figure 4 As shown in the figure, the stars in the three subtracted images are basically completely subtracted, and the images only contain moving targets, as shown in the green frame of the area in the figure. The white target (i.e. the first target) in the frame is the near-Earth asteroid in the template image, and the black target (i.e. the second target) represents the near-Earth asteroid in the scientific image. In the three green frames, the position of the white dots remains unchanged, while the positions of the near-Earth asteroids in the other scientific images will change.

[0064] Figure 5 An image of a dynamic trajectory diagram obtained by superposition according to an embodiment of the present invention is shown.

[0065] Furthermore, a series of subtracted images are superimposed based on the astronomical position, and then the characteristic trajectory of the second target is searched to construct a dynamic trajectory map including the first target and multiple second targets. Figure 5 As shown in Figure 1, the three images are superimposed into one image based on the astronomical position to obtain the inverted characteristic trajectory of a near-Earth asteroid, see Figure 5 The green box in the image shows a dynamic trajectory diagram consisting of a white target and three black targets.

[0066] Figure 6 The effect diagram of the inverted color feature trajectory according to an embodiment of the present invention is shown.

[0067] Furthermore, Figure 6 The effect diagram of the inverted feature trajectory for different types of fast-moving targets. Figure 6 1 to 4 represent the inverted characteristic tracks of space debris targets. Figure 6 The 5 in the middle represents the inverted characteristic track of the near-Earth asteroid target. In addition to the fast-moving target, there is no interference from other targets in the image, which can achieve the goal of quickly and accurately identifying the fast-moving target.

[0068] Through the embodiments of the present invention, the trajectory feature image generated by the method of identifying fast-moving targets using inverted color feature trajectories can not only ensure the uniqueness of the extracted fast-moving targets, but also the background of the constructed trajectory feature image is purer, with almost no bright sources and other potential interferences, thereby providing more accurate and stable recognition features and improving recognition efficiency and accuracy.

[0069] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying fast-moving targets based on inverted color feature trajectories, characterized in that: The method comprises: Acquire a series of time-series observation images containing fast-moving targets and establish an image database, wherein the series of time-series observation images include a plurality of original observation images; Preprocessing the multiple original observation images respectively; Perform astronomical position calibration on multiple pre-processed original observation images respectively; One of the time-series observation images after preprocessing and astronomical position calibration is selected as a template image, wherein the remaining images other than the template images are scientific images; Based on the template image, background subtraction is performed on a plurality of scientific images in chronological order; The template image after background subtraction is superimposed and merged with multiple scientific images based on astronomical positions to obtain a dynamic trajectory map; Based on the dynamic trajectory diagram, a fast-moving target is identified.

2. The method for identifying fast-moving targets based on inverse color feature trajectories according to claim 1, characterized in that: The series of time-series observation images includes at least 3 original observation images; and A plurality of original observation images in the series of time-series observation images are acquired according to a preset observation time interval.

3. The method for identifying fast-moving targets based on inverse color feature trajectories according to claim 1 or 2, characterized in that: The template image is the first image acquired in the series of time-series observation images.

4. The method for identifying fast-moving targets based on inverse color feature trajectories according to claim 1 or 2, characterized in that: The step of performing background subtraction on the plurality of scientific images in chronological order based on the template image comprises: According to the preset observation time interval, the template image and the multiple scientific images are subjected to image subtraction; After the subtraction is completed, the first target in the template image and the second target in the plurality of scientific images are obtained respectively.

5. The method for identifying fast-moving targets based on inverse color feature trajectories according to claim 4, characterized in that: The first object and the second object are displayed in the image in opposite colors.

6. The method for identifying fast-moving targets based on inverse color feature trajectories according to claim 1 or 5, characterized in that: The template image after background subtraction is superimposed and merged with multiple scientific images based on astronomical positions to obtain a dynamic trajectory map, including: searching for a characteristic trajectory of the second target; Construct a dynamic trajectory graph including the first target and multiple second targets.

7. The method for identifying fast-moving targets based on inverse color feature trajectories according to claim 1, characterized in that: The identifying of the fast-moving target based on the dynamic trajectory graph includes: Based on the dynamic trajectory graph, the time and position of the fast-moving target trajectory are extracted to obtain the fast-moving target.

Images