A satellite orbit determination method, device, equipment and medium

Abstract

The present application provides a satellite orbit determination method, device, equipment and medium for quickly and easily realizing autonomous orbit determination of satellites. Since the present application can obtain images collected by an image acquisition device configured on a satellite, the image can be input into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to the lighting information contained in the image, and the position information of the satellite can be determined based on the position information of the target region, and then the orbit information of the satellite can be determined based on the position information of the satellite, based on which the purpose of quickly and easily carrying out autonomous orbit determination of the satellite can be achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a satellite orbit determination method, device, equipment and medium. Background Art

[0002] At present, when satellites realize autonomous orbit determination (autonomous navigation), they usually need to be equipped with multiple devices such as star sensors and horizon instruments on the satellite. Multiple devices cooperate with each other and combine multiple algorithms such as the satellite's orbital motion model and filtering algorithm to realize the satellite's autonomous orbit determination. This method requires the configuration of more devices on the satellite. In order to avoid mutual interference in the detection field of view between multiple devices, more installation locations need to be provided for these devices on the satellite, and the demand for satellite resources such as payload and power consumption is also relatively large.

[0003] Therefore, there is an urgent need for a technical solution that can quickly and easily achieve autonomous orbit determination of satellites. Summary of the invention

[0004] The present application provides a satellite orbit determination method, device, equipment and medium for quickly and easily realizing autonomous orbit determination of a satellite.

[0005] In a first aspect, the present application provides a satellite orbit determination method, the method being applied to a satellite, the method comprising:

[0006] Obtaining images acquired by an image acquisition device configured on a satellite;

[0007] Inputting the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image;

[0008] Determine the location information of the satellite based on the location information of the target area, and determine the orbit information of the satellite based on the location information of the satellite;

[0009] Wherein, determining the position information of the satellite based on the position information of the target area includes:

[0010] There are multiple target regions, and every two regions in the target regions are determined as a region group;

[0011] A first area group is determined from among the area groups, and the position information of the satellite is determined based on the position information of the target area included in the first area group.

[0012] In a possible implementation manner, determining the first regional group from the regional groups includes:

[0013] For each second regional group in each regional group, obtaining a first pixel distance between two target regions in the second regional group in the image, and a second pixel distance between each of the two target regions in the second regional group and a target pixel point at a set position in the image;

[0014] Determine a first sub-score of each second regional group according to the first pixel distance corresponding to each second regional group, and determine a second sub-score of each second regional group according to the second pixel distance corresponding to each second regional group, wherein if the first pixel distance is proportional to the first sub-score, the second pixel distance is inversely proportional to the second sub-score; if the first pixel distance is inversely proportional to the first sub-score, the second pixel distance is proportional to the second sub-score;

[0015] The score of each second regional group is determined according to the first sub-score and the second sub-score of each second regional group, and the first regional group is selected from the second regional groups according to the score of each second regional group.

[0016] In a possible implementation manner, selecting the first regional group from the second regional groups according to the score of each second regional group includes:

[0017] If the first pixel distance is proportional to the first sub-score and the second pixel distance is inversely proportional to the second sub-score, then in the second region group whose score is higher than the set score threshold, the first region group is selected;

[0018] If the first pixel distance is inversely proportional to the first sub-score and the second pixel distance is directly proportional to the second sub-score, then the first region group is selected from the second region groups whose scores are lower than the set score threshold.

[0019] In a possible implementation, the method further includes:

[0020] Based on the orbit information of the satellite, obtaining the position information of each object contained in the image;

[0021] The pre-stored position information of stars is compared with the position information of each object to determine the target stars contained in each object, and target objects other than the target stars are screened out from each object.

[0022] In a possible implementation, the method further includes:

[0023] Based on the position information of the target object contained in the multiple frames of images and a spatial target tracking algorithm, the motion trajectory of the target object is determined.

[0024] In a possible implementation, the method further includes:

[0025] If a new target object other than the target object is identified in the multiple frames of images based on a preset clustering algorithm, a preliminary orbit determination is performed on the new target object based on a space target orbit determination algorithm.

[0026] In a second aspect, the present application provides a satellite orbit determination device, which is applied to a satellite and includes a unit or module for executing any method as described in the first aspect.

[0027] In a possible implementation, the satellite orbit determination device includes:

[0028] An acquisition module, used to acquire images acquired by an image acquisition device configured on the satellite;

[0029] A determination module, used for inputting the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image;

[0030] An orbit determination module, used to determine the position information of the satellite based on the position information of the target area, and determine the orbit information of the satellite based on the position information of the satellite;

[0031] The orbit determination module is specifically used for:

[0032] There are multiple target regions, and every two regions in the target regions are determined as a region group;

[0033] A first area group is determined from among the area groups, and the position information of the satellite is determined based on the position information of the target area included in the first area group.

[0034] In a possible implementation manner, the orbit determination module is specifically used to:

[0035] For each second regional group in each regional group, obtaining a first pixel distance between two target regions in the second regional group in the image, and a second pixel distance between each of the two target regions in the second regional group and a target pixel point at a set position in the image;

[0036] Determine a first sub-score of each second regional group according to the first pixel distance corresponding to each second regional group, and determine a second sub-score of each second regional group according to the second pixel distance corresponding to each second regional group, wherein if the first pixel distance is proportional to the first sub-score, the second pixel distance is inversely proportional to the second sub-score; if the first pixel distance is inversely proportional to the first sub-score, the second pixel distance is proportional to the second sub-score;

[0037] The score of each second regional group is determined according to the first sub-score and the second sub-score of each second regional group, and the first regional group is selected from the second regional groups according to the score of each second regional group.

[0038] In a possible implementation manner, the orbit determination module is specifically used to:

[0039] If the first pixel distance is proportional to the first sub-score and the second pixel distance is inversely proportional to the second sub-score, then in the second region group whose score is higher than the set score threshold, the first region group is selected;

[0040] If the first pixel distance is inversely proportional to the first sub-score and the second pixel distance is directly proportional to the second sub-score, then the first region group is selected from the second region groups whose scores are lower than the set score threshold.

[0041] In a possible implementation manner, the device further includes:

[0042] The identification module is used to obtain the position information of each object contained in the image based on the orbit information of the satellite; compare the pre-saved position information of the stars with the position information of the objects, determine the target stars contained in the objects, and filter out the target objects other than the target stars from the objects.

[0043] In a possible implementation manner, the identification module is further used to:

[0044] Based on the position information of the target object contained in the multiple frames of images and a spatial target tracking algorithm, the motion trajectory of the target object is determined.

[0045] In a possible implementation manner, the identification module is further used to:

[0046] If a new target object other than the target object is identified in the multiple frames of images based on a preset clustering algorithm, a preliminary orbit determination is performed on the new target object based on a space target orbit determination algorithm.

[0047] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores a program code, and when the program code is executed by the processor, the processor executes the method as described in any one of the first aspects.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program or instruction is stored. When the computer program or instruction is executed by a communication device, the method as described in any one of the first aspects is implemented.

[0049] In a fifth aspect, the present application provides a computer program product, which, when called by a computer, enables the computer to execute the method as described in any one of the first aspects.

[0050] Since the present application can obtain images captured by an image acquisition device configured on a satellite, the image can be input into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model based on the lighting information contained in the image, and the position information of the satellite can be determined based on the position information of the target region, and then the orbital information of the satellite can be determined based on the position information of the satellite. Based on this, the purpose of quickly and easily performing autonomous orbit determination of the satellite can be achieved.

[0051] In addition, compared with the related art that requires configuring more devices on the satellite, providing more installation locations for these devices on the satellite, and also placing greater demands on the satellite's payload, power consumption and other resources, the embodiment of the present application can achieve autonomous orbit determination of the satellite by configuring only one image acquisition device on the satellite, which can effectively reduce the cost of equipment hardware, etc. The equipment installation layout is simple, and the demand on the satellite's payload, power consumption and other resources can be greatly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a satellite orbit determination process provided in an embodiment of the present application;

[0054] Figure 2A A schematic diagram of a satellite provided in an embodiment of the present application;

[0055] Figure 2B A schematic diagram of an image captured by an image capture device configured on a satellite provided in an embodiment of the present application;

[0056] Figure 3 A schematic diagram of a region recognition model provided in some embodiments for determining a target region contained in an image based on lighting information contained in the image;

[0057] Figure 4A A schematic diagram of another satellite orbit determination process provided in an embodiment of the present application;

[0058] Figure 4B A schematic diagram of another satellite orbit determination process provided in an embodiment of the present application;

[0059] Figure 5 A schematic diagram of a tracking tree provided in an embodiment of the present application;

[0060] Fig. 6A A schematic diagram of a measurement information threshold value determination process provided in an embodiment of the present application;

[0061] Figure 6B A schematic diagram of establishing a path provided in an embodiment of the present application;

[0062] Figure 7 A schematic diagram of a target object tracking and detection process provided in an embodiment of the present application;

[0063] Figure 8 A schematic diagram of another target object tracking and detection process provided in an embodiment of the present application;

[0064] Fig. 9 A schematic diagram of another target object tracking and detection process provided in an embodiment of the present application;

[0065] Fig.10 A schematic diagram of the structure of a satellite orbit determination device provided in an embodiment of the present application;

[0066] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the purpose and implementation method of the present application clearer, the exemplary implementation method of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0068] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0069] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0070] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0071] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0073] For the convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

[0074] Combine the following Figure 1-Figure 11 , the embodiments of the present application are introduced.

[0075] Figure 1 A schematic diagram of a satellite orbit determination process provided in an embodiment of the present application, the process includes the following steps:

[0076] S101: Obtain images collected by an image collection device configured on a satellite.

[0077] See also Figure 2A , Figure 2A A schematic diagram of a satellite provided for an embodiment of the present application. In one possible implementation, in order to quickly and easily realize autonomous orbit determination of the satellite, an image acquisition device can be configured on the satellite. The image acquisition device can be a wide-field optical camera, etc. The image acquisition device can capture images at a certain shooting angle. Optionally, the shooting angle of the image acquisition device can be a fixed angle, or it can be an angle that changes periodically according to a set rule. This application does not make specific limitations on this. The image acquisition device can simultaneously image the surface of the earth, the edge area between the earth and the starry sky, and the entire starry sky. In other words, please refer to Figure 2B , Figure 2B A schematic diagram of an image captured by an image acquisition device configured on a satellite provided in an embodiment of the present application. The image captured by the image acquisition device within a certain observation range may include both the surface area of ​​the earth and the limbus area between the earth and the starry sky (referred to as the limbus of the earth in the figure), and the starry sky area.

[0078] In a possible implementation, the image acquisition device and the satellite can be connected in communication. After the image acquisition device acquires an image, the acquired image can be sent to the satellite, and the satellite can obtain the image acquired by the image acquisition device. In addition, the satellite can send an image capture instruction to the image acquisition device, and after the image acquisition device receives the image capture instruction, it starts to acquire images and sends the acquired images to the satellite. The present application does not specifically limit the specific process by which the satellite acquires the image acquired by the image acquisition device.

[0079] S102: Input the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image.

[0080] In one possible implementation, when the satellite is in a sunlit area, information about the earth's edge (earth's limb) area in the image can be detected based on the image captured by the image acquisition device, and the satellite's orbital information can be obtained based on the information to complete the satellite's autonomous orbit determination process, which will not be repeated here.

[0081] When a satellite is in the shadow area, the information of the Earth's limb area in the image captured by the image acquisition device configured on the satellite is not significant, and it may not be possible to obtain the orbital information of the satellite based on this information with high accuracy. In order to accurately determine the orbital information of the satellite when it is in the shadow area and accurately perform autonomous orbit determination of the satellite, the satellite can input the image captured by the image acquisition device when it is in the shadow area into a pre-trained region recognition model. Optionally, the region recognition model can be stored in the satellite's computing power module, etc. The region recognition model can determine the region contained in the image (for ease of description, referred to as the target region) based on the lighting information contained in the image, and the satellite can obtain information about the target region determined by the region recognition model.

[0082] See also Figure 3 , Figure 3A schematic diagram of a region recognition model provided for some embodiments to determine a target region contained in an image based on the light information contained in the image. After the image containing the light information is input into the region recognition model, the region recognition model can determine the target region corresponding to the light information in the image based on the target detection algorithm of deep learning. For example, the light information in the image can be processed by convolution layer 1 (convolution L1), downsampling pooling layer 1 (pooling L1), convolution layer 2 (convolution L2), downsampling pooling layer 2 (pooling L2), etc., and then processed by the fully connected layer (fully connected), and finally obtain (outcome) the target region contained in the image. In addition, the detection result output by the region recognition model can also simultaneously include the two-dimensional coordinate information of the target region in the image (referred to as the center coordinate in the figure). Among them, the target detection algorithm can use a convolutional neural network as the backbone network, etc., and the target detection algorithm can be a You Only Look Once (YOLO) series algorithm, which is not specifically limited in this application. The target region can be a specific city such as Beijing and Chengdu, or it can be, for example, the Pearl River Delta region, the Yangtze River Delta region, etc., which is not specifically limited in this application.

[0083] In one possible implementation, before inputting an image containing light information into a region recognition model, the target region that may be contained in the above image may be predicted based on prior information such as the satellite's position information at the previous moment, and the target frame containing the light information corresponding to the predicted target region in the image is determined. The image carrying the target frame is input into the region recognition model, and the region recognition model may determine the target region corresponding to the light information one by one based on a deep learning target detection algorithm, and obtain the target region contained in the image. In addition, for other light information in the image that does not carry a target frame, the region recognition model may also determine the corresponding target region for this part of the light information. Of course, it is also possible not to determine the corresponding target region for this part of the light information. This application does not specifically limit this.

[0084] The iterative training process for any round of the region recognition model can be as follows:

[0085] Obtain any sample image in the sample image set, the sample image corresponds to a sample label, and the sample label is used to characterize the sample target area corresponding to the lighting information in the sample image;

[0086] The sample image is input into the region recognition model to be trained. The region recognition model to be trained determines the target region contained in the image according to the lighting information contained in the sample image, and outputs the target region recognized by the region recognition model (hereinafter referred to as recognized target region for ease of description).

[0087] The region recognition model to be trained is trained according to the sample target region and the recognition target region.

[0088] Specifically, whether the recognition result of the region recognition model is accurate can be determined based on whether the sample target region and the recognition target region are consistent. In a specific implementation, if they are inconsistent, it means that the recognition result of the region recognition model is inaccurate, and the parameters of the region recognition model need to be adjusted to train the region recognition model. When adjusting the parameters in the region recognition model, a gradient descent algorithm can be used to back-propagate the gradient of the parameters of the region recognition model to train the region recognition model.

[0089] In a possible implementation, the above operation can be performed on each sample image in the sample set, and when the preset convergence condition is met, it is determined that the training of the region recognition model is completed. The preset convergence condition can be met for the sample images in the sample image set to pass through the original region recognition model, the number of sample images correctly recognized is greater than a set number, or the number of iterations for training the region recognition model reaches a set maximum number of iterations, etc. The setting can be flexibly made in the specific implementation, and is not specifically limited here.

[0090] In a possible implementation, when training the region recognition model to be trained, the sample images in the sample set can be divided into training sample images and test sample images. The region recognition model to be trained is first trained based on the training sample images, and then the reliability of the trained region recognition model is verified based on the test sample images.

[0091] S103: Determine the location information of the satellite based on the location information of the target area, and determine the orbit information of the satellite based on the location information of the satellite.

[0092] In a possible implementation, after determining the target region included in the image, the location information of the satellite can be determined based on the location information of the target region. The number of target regions can be multiple (two or more), and when determining the location information of the satellite based on the location information of the target region, every two regions in the multiple target regions can be determined as a region group. Exemplarily, assuming that there are three target regions, namely region 1, region 2, and region 3, then region 1 and region 2, region 1 and region 3, and region 2 and region 3 can be determined as region groups, respectively, to form a total of three region groups.

[0093] The first regional group can be determined (selected) from each regional group, and the location information of the satellite can be determined based on the location information of the target region included in the first regional group. When determining the first regional group, each regional group can be determined as the first regional group, or a set number of regional groups can be randomly determined as the first regional group. In addition, the target region included in the above image can be predicted based on prior information such as the location information of the satellite at the previous moment. For ease of description, the predicted target region is referred to as the predicted region, and a regional group in which both target regions in the regional group are predicted regions is selected as the first regional group. In addition, the first regional group can be selected from the regional groups in the following manner:

[0094] In a possible implementation, considering that, on the one hand, the closer the target region is to the pixel point of the set position such as the center pixel point of the image, the more accurate the satellite position information determined based on the target region is. On the other hand, the greater the distance between two target regions, the more accurate the satellite position information determined based on the position information of the two target regions is. In order to improve the accuracy of the determined satellite position information, the first region group can be selected based on the above two aspects.

[0095] Specifically, for each second regional group in each regional group, the first pixel distance between the two target regions in the second regional group in the image and the second pixel distance between each of the two target regions in the second regional group and the target pixel point at the set position in the image can be obtained. The second regional group can be all regional groups in each regional group or part of regional groups in each regional group. When the second regional group is all regional groups in each regional group, it can be considered as the first regional group selected from all regional groups for calculating the position information of the satellite. When the second regional group is part of regional groups in each regional group, it can be considered as the first regional group selected from part of regional groups for calculating the position information of the satellite.

[0096] In addition, when determining the first pixel distance between the two target regions, the target frames in which the two target regions are located in the image can be obtained first, and then the distance between the pixels at the set positions of the two target frames can be determined as the first pixel distance between the two target regions. For example, the distance between the pixels at the upper left corners of the two target frames can be determined as the first pixel distance between the two target regions. It is also possible to determine the distance between the pixels at the lower left corners of the two target frames as the first pixel distance between the two target regions. It is also possible to determine the distance between the pixels at the upper right corners of the two target frames as the first pixel distance between the two target regions. It is also possible to determine the distance between the pixels at the lower right corners of the two target frames as the first pixel distance between the two target regions. It is also possible to determine the distance between the pixels at the center points of the two target frames as the first pixel distance between the two target regions. The present application does not specifically limit the process of determining the first pixel distance.

[0097] Optionally, when determining the second pixel distance between each of the two target areas in the second area group and the target pixel point at the set position in the image, the pixel point at the center point of the image can be selected as the target pixel point, and for each target area, the distance between the center point pixel point of the target frame of the target area and the target pixel point can be determined, and the distance is used as the second pixel distance between the target area and the target pixel point.

[0098] Optionally, for each second regional group, after determining the second pixel distances between each of the two target regions in the second regional group and the target pixel point, the average value of the second pixel distances between each of the two target regions in the second regional group and the target pixel point can be determined as the second pixel distance corresponding to the second regional group. In addition, the minimum value or maximum value of the second pixel distances between each of the two target regions in the second regional group and the target pixel point can also be determined as the second pixel distance corresponding to the second regional group, and this application does not specifically limit this.

[0099] After determining the first pixel distance between each target area in the second area group (for ease of description, the first pixel distance may be referred to as the first pixel distance corresponding to the second area group later) and the second pixel distance corresponding to the second area group, the first sub-score of each area group may be determined according to the first pixel distance corresponding to each second area group, and the second sub-score of each second area group may be determined according to the second pixel distance corresponding to each area group. Afterwards, the score of each second area group may be determined according to the first sub-score and the second sub-score of each second area group. For example, the sum of the first sub-score and the second sub-score of each second area group may be determined as the score of each second area group. Finally, the first area group for calculating the satellite position information may be selected from the second area group according to the score of each second area group.

[0100] When determining the first sub-score and the second sub-score of each regional group, it is considered that if the first pixel distance corresponding to the regional group is larger and the second pixel distance is smaller, the accuracy of the satellite position information determined based on the position information of the region in the regional group will be higher. Based on this, the first regional group can be selected in two ways:

[0101] Mode 1: When determining the first sub-score of each second regional group according to the first pixel distance corresponding to each second regional group, the larger the first pixel distance corresponding to the second regional group, the higher the first sub-score of the second regional group, that is, the first pixel distance is proportional to the first sub-score. In this case, when determining the second sub-score of each second regional group according to the second pixel distance corresponding to each second regional group, the smaller the second pixel distance corresponding to the second regional group, the higher the second sub-score of the second regional group, that is, the second pixel distance is inversely proportional to the second sub-score. Correspondingly, when the first pixel distance is proportional to the first sub-score and the second pixel distance is inversely proportional to the second sub-score, the higher the score of the second regional group determined according to the first sub-score and the second sub-score of the second regional group, the higher the accuracy of the satellite position information determined based on the position information of the target region in the second regional group will be, and the first regional group can be preferentially selected from the second regional groups with scores higher than the set score threshold. Exemplarily, each second regional group with a score higher than the set score threshold can be selected as the first regional group. The second regional group with the highest score among the second regional groups with scores higher than the set score threshold may also be selected as the first regional group, which is not specifically limited in the present application.

[0102] Method 2: When determining the first sub-score of each second regional group according to the first pixel distance corresponding to each second regional group, the larger the first pixel distance corresponding to the second regional group, the lower the first sub-score of the second regional group, that is, the first pixel distance is inversely proportional to the first sub-score. In this case, when determining the second sub-score of each second regional group according to the second pixel distance corresponding to each second regional group, the smaller the second pixel distance corresponding to the second regional group, the lower the second sub-score of the second regional group, that is, the second pixel distance is inversely proportional to the second sub-score. Correspondingly, when the first pixel distance is inversely proportional to the first sub-score and the second pixel distance is proportional to the second sub-score, the lower the score of the second regional group determined according to the first sub-score and the second sub-score of the second regional group, the higher the accuracy of the satellite position information determined based on the position information of the target region in the second regional group, and the first regional group can be preferentially selected from the second regional groups whose scores are lower than the set score threshold. For example, each second regional group with a score lower than the set score threshold can be selected as the first regional group. The second regional group with the lowest score among the second regional groups with a score lower than the set score threshold can also be selected as the first regional group, which is not specifically limited in this application.

[0103] In a possible implementation, the process of determining the position information of the satellite based on the position information of two target regions in any region group (the first region group) may be as follows:

[0104] For example, the position vector (position information) of the target area relative to the satellite position is converted into the inertial coordinate system. The first position vectors (also called direction vectors) of the two target areas are , The position vector (position information) of the target area relative to the center of the earth is converted into the inertial coordinate system. The second position vectors of the two target areas are , The position vector (position information) of the satellite relative to the center of the earth is expressed as The satellite position information can be obtained by solving the following equations: :

[0105] .

[0106] In a possible implementation manner, if there are multiple first regional groups, the position information of the satellite determined by the position information of the two target regions in each first regional group may be obtained. Then, the position information of the satellite determined by each first regional group The average value of is determined as the final satellite position information, which will not be repeated here.

[0107] In a possible implementation, after the position information of the satellite is determined, the orbit information of the satellite can be determined based on the position information of the satellite. For example, the flight direction and speed of the satellite can be obtained by combining the position information of the satellite determined by each frame of the image taken continuously in time, and then the orbit information of the satellite can be obtained, which will not be described in detail here.

[0108] Since the present application can obtain images captured by an image acquisition device configured on a satellite, the image can be input into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model based on the lighting information contained in the image, and the position information of the satellite can be determined based on the position information of the target region, and then the orbital information of the satellite can be determined based on the position information of the satellite. Based on this, the purpose of quickly and easily performing autonomous orbit determination of the satellite can be achieved.

[0109] In addition, compared with the related art that requires configuring more devices on the satellite, providing more installation locations for these devices on the satellite, and also placing greater demands on the satellite's payload, power consumption and other resources, the embodiment of the present application can achieve autonomous orbit determination of the satellite by configuring only one image acquisition device on the satellite, which can effectively reduce the cost of equipment hardware, etc. The equipment installation layout is simple, and the demand on the satellite's payload, power consumption and other resources can be greatly reduced.

[0110] For ease of understanding, the satellite orbit determination process provided by the present application is explained below through a specific embodiment. Figure 4A , Figure 4A A schematic diagram of another satellite orbit determination process provided in an embodiment of the present application, the process includes:

[0111] S401: Obtain images collected by an image collection device configured on a satellite.

[0112] S402: Inputting the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image.

[0113] S403: There are multiple target regions, and every two regions in the target regions are determined as a region group; a first region group is determined from the region groups, and based on the position information of the target regions included in the first region group, the position information of the satellite is determined, and based on the position information of the satellite, the orbital information of the satellite is determined.

[0114] For ease of understanding, the satellite orbit determination process provided by the present application is explained below through a specific embodiment. Figure 4B , Figure 4BA schematic diagram of another satellite orbit determination process provided in an embodiment of the present application, the process includes:

[0115] S501: Obtain images collected by an image collection device configured on a satellite.

[0116] S502: Inputting the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image.

[0117] S503: There are multiple target regions, and every two regions in the target regions are determined as a region group. For each second region group in each region group, obtain the first pixel distance between the two target regions in the second region group in the image, and the second pixel distance between the two target regions in the second region group and the target pixel point at the set position in the image; determine the first sub-score of each second region group according to the first pixel distance corresponding to each second region group, and determine the second sub-score of each second region group according to the second pixel distance corresponding to each second region group, wherein if the first pixel distance is proportional to the first sub-score, the second pixel distance is inversely proportional to the second sub-score; if the first pixel distance is inversely proportional to the first sub-score, the second pixel distance is proportional to the second sub-score; determine the score of each second region group according to the first sub-score and the second sub-score of each second region group. If the first pixel distance is proportional to the first sub-score and the second pixel distance is inversely proportional to the second sub-score, the first region group may be selected from the second region group whose scores are higher than the set score threshold. If the first pixel distance is inversely proportional to the first sub-score and the second pixel distance is proportional to the second sub-score, the first region group may be selected from the second region group whose scores are lower than the set score threshold.

[0118] S504: Determine the position information of the satellite based on the position information of the target area included in the first area group, and determine the orbit information of the satellite based on the position information of the satellite.

[0119] In one possible implementation, please refer again to Figure 2B As shown, the image captured by the image acquisition device may include not only the surface area of ​​the earth, but also the limb area of ​​the earth and the starry sky area. In order to track and detect the target object in space (outer space), after acquiring the image captured by the image acquisition device, the position information of each object contained in the image can be obtained based on the orbital information of the satellite and by performing target centroid extraction, etc. Among them, the process of determining the position information of each object contained in the image can adopt the existing technology, which will not be repeated here. The position information of each object contained in the image can be the position information of each object in the starry sky area. Each object in the starry sky area may include both stars and other objects except stars (hereinafter referred to as target objects for the convenience of description).

[0120] In a possible implementation, the position information of the star can be compared with the position information of each object contained in the image based on the position information of the star in the pre-saved star catalog file (the position information of the star in the inertial system), and the object whose position information matches the position information of the star in each object is determined as the target star, so as to identify the target star contained in the image. After identifying the target star contained in the image, the position information of the target star contained in the image can be converted to the satellite coordinate system according to the installation matrix of the image acquisition device, and the position information, orientation information and other attitude information of the satellite can be obtained based on the position information of the target star contained in the image and the multi-vector attitude determination algorithm to realize the autonomous orbit determination of the satellite, which will not be described in detail here.

[0121] In a possible implementation, after the target star contained in the image is identified, the target object other than the target star can be further screened out from the objects contained in the image. Based on this, the target object (also called a moving target) in space can be identified and the tracking and detection process of the target object can be performed, thereby improving the situational awareness capability of space targets. Among them, the target object can be space debris, important space detection targets, etc., which is not specifically limited in this application.

[0122] In a possible implementation, when tracking and detecting the target object, the motion trajectory of the target object can be determined based on the position information of the target object contained in multiple frames of images and a spatial target tracking algorithm to achieve tracking and detection of the target object.

[0123] Specifically, the space target tracking algorithm may be a space target tracking algorithm based on multiple hypothesis tracking (Multiple Hypothesis Tracking, MHT), and tracking detection (tracking and orbit determination) of the target object may be achieved based on the space target tracking algorithm.

[0124] Among them, the target tracking tree is the core data structure of the spatial target tracking algorithm. This data structure establishes corresponding hypothetical branches for each possible situation, uses a tree structure to save all hypothetical paths of the target object, and selects the global optimal tracking path by scoring each hypothetical branch. At the same time, the spatial target tracking algorithm can regularly perform pruning operations on hypothetical branches (hypothetical paths) with lower scores in the target tracking tree to reduce the amount of calculation.

[0125] See also Figure 5 , Figure 5A tracking tree diagram provided in an embodiment of the present application. A tracking tree of each target object can be established for each target object. The tracking tree of each target object can be composed of tracking nodes. For example, for target object 1, the tracking tree of target object 1 can be composed of tracking nodes H10, H1 00 、H1 01 、H1 000 、H1 010 、H1 011 The tracking tree of target object 2 can be composed of tracking nodes H20, H2 00 、H2 000 、H2 001 It is composed of multiple tracking nodes.

[0126] Optionally, each tracking node may correspond to the measurement time t (i.e., the image capture time), the pixel position information of the target object in the image (also referred to as measurement information (x, y)), and the track estimate of the target object. (in, is the location information of the target object, is the speed information of the target object), the filtering state quantity of the target object , track key data such as node score N.

[0127] The target object tracking tree (target tracking tree) can grow over time. Figure 5 Taking the tracking tree of target object 1 in the figure as an example, a tracking node H10 is created at time t0. After receiving a new batch of measurement information at time t1, for tracking node H10, after the target object's position information prediction and measurement information threshold value determination, assuming that two measurement information (measurement information can also be called observation) meet the requirements, a new tracking node H1 can be established after the corresponding orbit estimation and score determination. 00 and H1 01 The above process is repeated over time, and the size of the tracking tree grows rapidly. The spatial target tracking algorithm can calculate the optimal tracking path of the target object according to the score of each tracking node. For example, the optimal tracking path of target object 1 can be the tracking nodes H10-H1 01 —H1 010 The optimal tracking path of the target object 2 can be composed of tracking nodes H20-H2 00 —H2 001 In addition, the size of the tracking tree can be controlled by pruning, deleting invalid target objects, deleting invalid tracking nodes, etc. The optimal tracking path can also be obtained by clustering the target tracking tree, associating the optimal tracking nodes, etc., which will not be repeated here.

[0128] The following is an introduction to the process of predicting the location information of the target object mentioned above, determining the measurement information threshold value, and establishing a new tracking node.

[0129] When predicting the location information of the target object, it is assumed that the time corresponding to receiving the new measurement information is t c , the space target tracking algorithm can first recursively calculate the orbit estimation data of the target object of each leaf node in the target tracking tree to time t c The trajectory estimate is Among them, when calculating the orbit estimation, a high-precision orbit recursion model such as J4 or Simplified General Perturbations (SGP4) can be used. I will not go into details here. In addition, the satellite can obtain its own orbital position at the current moment from the spacecraft platform, etc. , the normalized direction vector of the target object relative to the satellite can be calculated based on the following formula: (Also called position vector): .in, Represents the normalization function of the vector. After obtaining the normalized direction vector of the target object, the two-dimensional coordinate prediction value of the target object in the image at the current moment can be obtained by combining the posture and configuration parameters of the camera at the current moment, and the predicted value of the position information of the target object is obtained, thus completing the process of predicting the position information of the target object. I will not go into details here.

[0130] The purpose of determining the measurement information threshold is to select the measurement values ​​that meet the determination threshold according to the predicted value of the target object's position information (where the measurement value can be the position information of the object contained in the image), and to establish the corresponding tracking nodes and hypothesized path branches. Fig. 6A , Fig. 6A A schematic diagram of a measurement information threshold value determination process provided in an embodiment of the present application, after predicting the position information of the target object according to the position of the target object at the previous moment, the predicted value (predicted position) of the position information of the target object at the current moment is obtained. Assuming that there are three measurement values ​​at the current moment, namely, measurement value M1, measurement value M2 and measurement value M3, assuming that the measurement values ​​that meet the judgment threshold standard are measurement value M1 and measurement value M3, and measurement value M2 does not meet the judgment threshold standard, refer to Figure 6B , Figure 6B A path establishment schematic diagram provided in an embodiment of the present application can establish a tracking node H corresponding to the measurement value M1 01 And the assumed path, the tracking node H corresponding to the measurement value M3 03 and the assumed path. In addition, please note that Figure 6B, you can also establish the tracking node H corresponding to the predicted value (predicted position) of the target object location information 00 and the assumed path. This tracking node can be considered as a virtual tracking node. This is mainly because the features of some dim target objects are not significant, and the target detection algorithm may have a high probability of missing such target objects. In order to achieve stable tracking of such target objects, a virtual tracking node can be established to deal with the possible missed detection of the target object.

[0131] Among them, the judgment threshold standard can be simply designed based on the Euclidean distance of the two-dimensional coordinates of the measured value and the predicted value, or multiple judgment conditions can be set in combination with the orbital dynamics characteristics of the target object, so as to improve the accuracy of screening valid measurement values. The judgment threshold standard can be flexibly set according to needs and will not be repeated here.

[0132] Among them, when establishing a new tracking node, algorithms such as Kalman filtering (KF), extended Kalman filtering (EKF) or cubature Kalman filtering (CKF) can be used to optimally estimate the orbit of the target object at the current moment. According to the filtered state quantity and filtered orbit of the target object output by these algorithms, this information is saved in the corresponding tracking node of the target tracking tree to complete the establishment of the new tracking node.

[0133] In a possible implementation, considering that some target objects may not be found due to missed detection when screening target objects in images, in order to mine possible new target objects, the two-dimensional coordinates of unused objects in multiple consecutive frames of images (unused objects can be objects in the image that are neither identified as target objects nor stars) can be used as input, and clustering algorithms such as Density-Based Spatial Clustering of Applications with Noise (DBSCAN) can be used to search for two-dimensional coordinates that may belong to the same object. If the number of two-dimensional coordinates meets the target initial orbit estimation requirements, and the distribution range of the two-dimensional coordinates is within the set threshold In the case of a new target object being found, it can be considered that a new target object other than the target object is identified in multiple consecutive frames of images based on a preset clustering algorithm. In this case, the process of performing preliminary orbit determination on the new target object can be based on a space target orbit determination algorithm. The preliminary orbit determination is the process of roughly making a preliminary orbit estimate of the new target object using a small amount of observation data (such as azimuth angle measurement information of the new target object). The space target orbit determination algorithm can be a traditional Laplace algorithm, or an improved algorithm of the traditional Laplace algorithm, or a heuristic algorithm, such as a genetic algorithm. This application does not make specific limitations on this.

[0134] For ease of understanding, the target object tracking and detection process provided by the present application is explained below through a specific embodiment. Figure 7 , Figure 7 A schematic diagram of a target object tracking detection process provided in an embodiment of the present application, the process includes the following steps:

[0135] S701: Based on the orbit information of the satellite, obtain the position information of each object contained in the image captured by the image acquisition device.

[0136] S702: Compare the pre-saved position information of stars with the position information of the above-mentioned objects, determine the target stars contained in each object, and filter out target objects other than the target stars from each object.

[0137] S703: Determine the motion trajectory of the target object based on the position information of the target object contained in the multiple frames of images and the spatial target tracking algorithm.

[0138] For ease of understanding, the target object tracking and detection process provided by the present application is explained below through a specific embodiment. Figure 8 , Figure 8 A schematic diagram of another target object tracking detection process provided in an embodiment of the present application, the process includes the following steps:

[0139] S801: Based on the orbit information of the satellite, obtain the position information of each object contained in the image captured by the image acquisition device.

[0140] S802: Compare the pre-saved position information of stars with the position information of the above-mentioned objects, determine the target stars contained in each object, and filter out target objects other than the target stars from each object.

[0141] S803: Determine the motion trajectory of the target object based on the position information of the target object contained in the multiple frames of images and the spatial target tracking algorithm.

[0142] S804: If a new target object other than the target object is identified in the multiple frames of images based on the preset clustering algorithm, a preliminary orbit determination is performed on the new target object based on the space target orbit determination algorithm.

[0143] For ease of understanding, the target object tracking and detection process provided by the present application is explained below through a specific embodiment. Fig. 9 , Fig. 9 A schematic diagram of another target object tracking detection process provided in an embodiment of the present application, the process includes the following steps:

[0144] S901: Obtain an image acquired by an image acquisition device configured on a satellite; input the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to the lighting information contained in the image; determine the position information of the satellite based on the position information of the target region, and determine the orbital information of the satellite based on the position information of the satellite.

[0145] S902: Based on the orbit information of the satellite, obtain the position information of each object contained in the image captured by the image acquisition device.

[0146] S903: Compare the pre-saved position information of stars with the position information of the above-mentioned objects, determine the target stars contained in each object, and filter out target objects other than the target stars from each object.

[0147] S904: Determine the motion trajectory of the target object based on the position information of the target object contained in the multiple frames of images and the spatial target tracking algorithm.

[0148] S905: If a new target object other than the target object is identified in the multiple frames of images based on the preset clustering algorithm, a preliminary orbit determination is performed on the new target object based on the space target orbit determination algorithm.

[0149] Based on the same technical concept, the present application provides a satellite orbit determination device, which may include a unit or module for executing the method corresponding to the above satellite. Fig.10 , Fig.10 A schematic diagram of the structure of a satellite orbit determination device 1000 provided in an embodiment of the present application. When the satellite orbit determination device 1000 executes the method corresponding to the above satellite, the device includes:

[0150] An acquisition module 1001 is used to acquire images acquired by an image acquisition device configured on a satellite;

[0151] A determination module 1002 is used to input the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image;

[0152] The orbit determination module 1003 is used to determine the position information of the satellite based on the position information of the target area, and determine the orbit information of the satellite based on the position information of the satellite;

[0153] The orbit determination module 1003 is specifically used for:

[0154] There are multiple target regions, and every two regions in the target regions are determined as a region group;

[0155] A first area group is determined from among the area groups, and the position information of the satellite is determined based on the position information of the target area included in the first area group.

[0156] In a possible implementation manner, the orbit determination module 1003 is specifically configured to:

[0157] For each second regional group in each regional group, obtaining a first pixel distance between two target regions in the second regional group in the image, and a second pixel distance between each of the two target regions in the second regional group and a target pixel point at a set position in the image;

[0158] Determine a first sub-score of each second regional group according to the first pixel distance corresponding to each second regional group, and determine a second sub-score of each second regional group according to the second pixel distance corresponding to each second regional group, wherein if the first pixel distance is proportional to the first sub-score, the second pixel distance is inversely proportional to the second sub-score; if the first pixel distance is inversely proportional to the first sub-score, the second pixel distance is proportional to the second sub-score;

[0159] The score of each second regional group is determined according to the first sub-score and the second sub-score of each second regional group, and the first regional group is selected from the second regional groups according to the score of each second regional group.

[0160] In a possible implementation manner, the orbit determination module 1003 is specifically configured to:

[0161] If the first pixel distance is proportional to the first sub-score and the second pixel distance is inversely proportional to the second sub-score, then in the second region group whose score is higher than the set score threshold, the first region group is selected;

[0162] If the first pixel distance is inversely proportional to the first sub-score and the second pixel distance is directly proportional to the second sub-score, then the first region group is selected from the second region groups whose scores are lower than the set score threshold.

[0163] In a possible implementation manner, the device further includes:

[0164] The identification module 1004 is used to obtain the position information of each object contained in the image based on the orbit information of the satellite; compare the pre-saved position information of the stars with the position information of the objects, determine the target stars contained in the objects, and filter out the target objects other than the target stars from the objects.

[0165] In a possible implementation manner, the identification module 1004 is further configured to:

[0166] Based on the position information of the target object contained in the multiple frames of images and a spatial target tracking algorithm, the motion trajectory of the target object is determined.

[0167] In a possible implementation manner, the identification module 1004 is further configured to:

[0168] If a new target object other than the target object is identified in the multiple frames of images based on a preset clustering algorithm, a preliminary orbit determination is performed on the new target object based on a space target orbit determination algorithm.

[0169] Based on the same technical concept, on the basis of the above embodiments, the present application embodiment further provides an electronic device, see Fig.11 , Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, the communication device includes: a processor 1101, a communication interface 1102, a memory 1103 and a communication bus 1104, wherein the processor 1101, the communication interface 1102, and the memory 1103 communicate with each other through the communication bus 1104;

[0170] The memory 1103 stores a computer program. When the program is executed by the processor 1101, the processor 1101 performs the following steps:

[0171] Obtaining images acquired by an image acquisition device configured on a satellite;

[0172] Inputting the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image;

[0173] Determine the location information of the satellite based on the location information of the target area, and determine the orbit information of the satellite based on the location information of the satellite;

[0174] The processor 1101 is specifically configured to:

[0175] There are multiple target regions, and every two regions in the target regions are determined as a region group;

[0176] A first area group is determined from among the area groups, and the position information of the satellite is determined based on the position information of the target area included in the first area group.

[0177] In a possible implementation manner, the processor 1101 is specifically configured to:

[0178] For each second regional group in each regional group, obtaining a first pixel distance between two target regions in the second regional group in the image, and a second pixel distance between each of the two target regions in the second regional group and a target pixel point at a set position in the image;

[0179] Determine a first sub-score of each second regional group according to the first pixel distance corresponding to each second regional group, and determine a second sub-score of each second regional group according to the second pixel distance corresponding to each second regional group, wherein if the first pixel distance is proportional to the first sub-score, the second pixel distance is inversely proportional to the second sub-score; if the first pixel distance is inversely proportional to the first sub-score, the second pixel distance is proportional to the second sub-score;

[0180] The score of each second regional group is determined according to the first sub-score and the second sub-score of each second regional group, and the first regional group is selected from the second regional groups according to the score of each second regional group.

[0181] In a possible implementation manner, the processor 1101 is specifically configured to:

[0182] If the first pixel distance is proportional to the first sub-score and the second pixel distance is inversely proportional to the second sub-score, then in the second region group whose score is higher than the set score threshold, the first region group is selected;

[0183] If the first pixel distance is inversely proportional to the first sub-score and the second pixel distance is directly proportional to the second sub-score, then the first region group is selected from the second region groups whose scores are lower than the set score threshold.

[0184] In a possible implementation manner, the processor 1101 further includes:

[0185] Based on the orbital information of the satellite, the position information of each object contained in the image is obtained; the pre-saved position information of the stars is compared with the position information of the objects to determine the target stars contained in the objects, and the target objects other than the target stars are screened out from the objects.

[0186] In a possible implementation manner, the processor 1101 is further configured to:

[0187] Based on the position information of the target object contained in the multiple frames of images and a spatial target tracking algorithm, the motion trajectory of the target object is determined.

[0188] In a possible implementation manner, the processor 1101 is further configured to:

[0189] If a new target object other than the target object is identified in the multiple frames of images based on a preset clustering algorithm, a preliminary orbit determination is performed on the new target object based on a space target orbit determination algorithm.

[0190] The communication bus mentioned in the above communication device (electronic device) can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0191] The communication interface 1102 is used for communication between the above-mentioned apparatus (electronic device) and other devices.

[0192] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0193] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (NP), etc.; it can also be a digital signal processing processor (DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0194] Based on the same inventive concept, the embodiment of the present application provides a computer-readable storage medium, and the computer program product includes: computer program code, when the computer program code is run on a computer, the computer executes any of the methods discussed above. Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to that of the above-mentioned method, the implementation of the above-mentioned computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0195] The above-mentioned computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor in the electronic device, including but not limited to magnetic storage such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc., optical storage such as CDs, DVDs, BDs, HVDs, etc., and semiconductor storage such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drives (SSD), etc.

[0196] Based on the same inventive concept, the embodiment of the present application further provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes any of the methods discussed above. Since the principle of solving the problem by the above computer program product is similar to that of the above method, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be repeated.

[0197] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0198] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0199] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0200] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0201] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A satellite orbit determination method, characterized in that: The method is applied to a satellite, and the method comprises: Obtaining images acquired by an image acquisition device configured on a satellite; Inputting the image into a pre-trained region recognition model to obtain a target region contained in the image determined by the region recognition model according to lighting information contained in the image; Determine the location information of the satellite based on the location information of the target area, and determine the orbit information of the satellite based on the location information of the satellite; Wherein, determining the position information of the satellite based on the position information of the target area includes: There are multiple target regions, and every two regions in the target regions are determined as a region group; A first regional group is determined from the regional groups, and the position information of the satellite is determined based on the position information of the target region included in the first regional group; wherein the first regional group is any one of the regional groups.

2. The method according to claim 1, characterized in that The determining of the first regional group from the regional groups includes: For each second area group in each area group, obtaining a first pixel distance between two target areas in the second area group in the image, and a second pixel distance between each of the two target areas in the second area group and a target pixel point at a set position in the image; Determine a first sub-score of each second regional group according to the first pixel distance corresponding to each second regional group, and determine a second sub-score of each second regional group according to the second pixel distance corresponding to each second regional group, wherein if the first pixel distance is proportional to the first sub-score, the second pixel distance is inversely proportional to the second sub-score; if the first pixel distance is inversely proportional to the first sub-score, the second pixel distance is proportional to the second sub-score; The score of each second regional group is determined according to the first sub-score and the second sub-score of each second regional group, and the first regional group is selected from the second regional groups according to the score of each second regional group.

3. The method according to claim 2, characterized in that The step of selecting the first regional group from the second regional groups according to the score of each second regional group includes: If the first pixel distance is proportional to the first sub-score and the second pixel distance is inversely proportional to the second sub-score, then in the second region group whose score is higher than the set score threshold, the first region group is selected; If the first pixel distance is inversely proportional to the first sub-score and the second pixel distance is directly proportional to the second sub-score, then the first region group is selected from the second region groups whose scores are lower than the set score threshold.

4. The method according to claim 1, characterized in that: The method further comprises: Based on the orbit information of the satellite, obtaining the position information of each object contained in the image; The pre-stored position information of stars is compared with the position information of each object to determine the target stars contained in each object, and target objects other than the target stars are screened out from each object.

5. The method according to claim 4, characterized in that The method further comprises: Based on the position information of the target object contained in the multiple frames of images and a spatial target tracking algorithm, the motion trajectory of the target object is determined.

6. The method according to claim 5, characterized in that The method further comprises: If a new target object other than the target object is identified in the multiple frames of images based on a preset clustering algorithm, a preliminary orbit determination is performed on the new target object based on a space target orbit determination algorithm.

7. A satellite orbit determination device, characterized in that: The device is applied to a satellite, and comprises a unit or a module for executing the method according to any one of claims 1 to 6.

8. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores a program code, and when the program code is executed by the processor, the processor executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or instruction. When the computer program or instruction is executed by the communication device, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the computer program product is called by a computer, the computer executes the method according to any one of claims 1 to 6.

Images