A method and apparatus for locating space debris

Abstract

The application discloses a space debris positioning method and device, and relates to the technical field of computer vision. Sparse event stream original data of space debris is collected through a dynamic visual sensor; filtering processing is performed on the sparse event stream original data based on the space-time density of the obtained sparse event stream original data, so that target data of the sparse event stream is obtained; a time window is determined according to the time domain length of the target data of the sparse event stream, the target data of the sparse event stream is sliced based on the time window, so that a target data segment of the sparse event stream is obtained; a target function is constructed based on the space-time density of the sparse event stream original data; the target coordinate point and the target function value corresponding to the target coordinate point are calculated by using a meta-heuristic optimization algorithm based on the target function and the target data segment of the sparse event stream; and the motion trajectory of the space debris is determined based on the target coordinate point and the target function value corresponding to the target coordinate point. In this way, the space debris can be accurately positioned.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and in particular to a method and apparatus for locating spatial debris. Background Technology

[0002] With the increasing frequency of human space activities, the amount of space debris has grown dramatically, creating many difficulties for future space development and utilization. Against this backdrop, the continuous observation and cataloging of space debris has become a core task in ensuring the safety of space assets and the sustainability of the space environment.

[0003] In related technologies, dynamic vision sensors are used to observe space debris. Each pixel responds independently, asynchronously, and differentially to local illumination changes and outputs a sparse event stream, inherently possessing microsecond-level temporal resolution, ultra-high dynamic range, and extremely low data bandwidth and power consumption. These characteristics precisely address the problems existing in the aforementioned space optical observation and perception. However, the output signal of a dynamic vision sensor is an asynchronous spatiotemporal event stream completely different from traditional image frames, rendering mature image-frame-based computer vision algorithms unsuitable. Therefore, a method for space debris target detection and tracking using dynamic vision sensors is urgently needed. Summary of the Invention

[0004] In view of this, this application provides a space debris positioning method and apparatus to achieve accurate positioning of space debris.

[0005] The objective of this application can be achieved through the following technical solutions:

[0006] The first aspect of this application is to provide a method for locating space debris, including:

[0007] Raw data of sparse event streams from spatial debris are acquired using dynamic visual sensors;

[0008] Obtain the spatiotemporal density of the raw data of the sparse event stream;

[0009] Based on the spatiotemporal density of the original sparse event stream data, the original sparse event stream data is filtered to obtain the target sparse event stream data.

[0010] The time window is determined based on the temporal length of the sparse event stream target data, and the sparse event stream target data is sliced ​​based on the time window to obtain sparse event stream target data segments.

[0011] Construct an objective function based on the spatiotemporal density of the original sparse event stream data;

[0012] Based on the objective function and the target data segment of the sparse event stream, the target coordinate point and the corresponding objective function value are calculated using a metaheuristic optimization algorithm.

[0013] Establish a uniform point target motion model;

[0014] The model parameters of the uniform point target motion model are determined based on the target coordinate point and the corresponding objective function value;

[0015] The trajectory of space debris is determined based on model parameters.

[0016] In one optional embodiment, obtaining the spatiotemporal density of the original sparse event stream data includes:

[0017] Define an initial time surface matrix, where each element represents the time interval between the most recent brightness change at the corresponding location and the current time.

[0018] Calculate the time interval between the two most recent brightness changes to obtain the first time interval;

[0019] The initial time surface matrix is ​​updated based on the first time interval to obtain the target time surface matrix;

[0020] The spatiotemporal density of the original data of the sparse event stream is calculated based on the target time surface matrix.

[0021] In one optional embodiment, updating the initial time surface matrix based on a first time interval to obtain the target time surface matrix includes:

[0022] Based on the first time interval, the initial time surface matrix is ​​updated using the following formula to obtain the target time surface matrix:

[0023] ;

[0024] in, Represents the target time surface matrix. Indicates the exponential decay factor. Indicates the first time interval. Indicates the time coefficient. This indicates the position coordinates of the pixel currently being processed. This represents the position coordinates of the pixel whose brightness changes for the i-th time.

[0025] In one optional embodiment, calculating the spatiotemporal density of the original sparse event stream data based on the target temporal surface matrix includes:

[0026] Based on the target temporal surface matrix, the spatiotemporal density of the original sparse event stream data is calculated using the following formula:

[0027] ;

[0028] in, This represents the spatiotemporal density corresponding to the i-th brightness change. This represents the x-coordinate corresponding to the i-th change in brightness. This represents the ordinate corresponding to the i-th change in brightness. This indicates the offset in the horizontal direction. This indicates the offset in the vertical direction. and Both represent the neighborhood radius, and T() represents the target time surface matrix.

[0029] In one alternative embodiment, the objective function is expressed as:

[0030] ;

[0031] in, Describe the objective function. This represents the x-coordinate of the target, the y-coordinate of the target, and the time to be solved. This represents the x-axis, y-axis, and time corresponding to the i-th brightness change. The value represents the scaling factor, N represents the total number of times the brightness changes, and exp() refers to the power operation with base e.

[0032] In one optional embodiment, the model parameters of the uniform point target motion model are determined based on the target coordinate point and the corresponding objective function value, including:

[0033] Based on the target coordinates and the corresponding objective function values, the model parameters of the uniform point motion model are solved using the weighted least squares method.

[0034] In one optional embodiment, the original sparse event stream data is filtered based on its spatiotemporal density to obtain target sparse event stream data, including:

[0035] If the spatiotemporal density of the original sparse event stream data is not less than the preset spatiotemporal density threshold, then the original sparse event stream data is determined as the target data of the sparse event stream; if the spatiotemporal density of the original sparse event stream data is less than the preset spatiotemporal density threshold, then the original sparse event stream data is discarded.

[0036] A second aspect of this application is to provide a space debris locating device, comprising:

[0037] The acquisition module is used to acquire raw data of sparse event streams of spatial debris through a dynamic visual sensor;

[0038] The acquisition module is used to acquire the spatiotemporal density of the raw data of the sparse event stream;

[0039] The filtering module is used to filter the original sparse event stream data based on the spatiotemporal density of the original sparse event stream data to obtain the target sparse event stream data.

[0040] The first determining module is used to determine the time window based on the temporal length of the sparse event stream target data, and to slice the sparse event stream target data based on the time window to obtain sparse event stream target data segments.

[0041] The building module is used to construct the objective function based on the spatiotemporal density of the original sparse event stream data;

[0042] The calculation module is used to calculate the target coordinate point and the corresponding objective function value based on the objective function and the target data segment of the sparse event stream using a metaheuristic optimization algorithm.

[0043] A module is created to build a model of a uniform point target motion.

[0044] The second determining module is used to determine the model parameters of the uniform point target motion model based on the target coordinate point and the target function value corresponding to the target coordinate point;

[0045] The third determination module is used to determine the trajectory of space debris based on model parameters.

[0046] A third aspect of this application is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the method as described in the first aspect.

[0047] A fourth aspect of this application is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the method as described in the first aspect.

[0048] Compared with existing technologies, the space debris localization method provided in this application acquires raw data of sparse event streams of space debris using a dynamic visual sensor; based on the spatiotemporal density of the acquired raw data, the raw data is filtered to obtain target data; a time window is determined according to the temporal length of the target data, and the target data is sliced ​​based on the time window to obtain target data segments; an objective function is constructed based on the spatiotemporal density of the raw data; based on the objective function and the target data segments, a metaheuristic optimization algorithm is used to calculate the target coordinates and the corresponding objective function values; and the trajectory of the space debris is determined based on the target coordinates and the corresponding objective function values. This allows for precise localization of space debris. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 A schematic flowchart of a spatial debris location method provided in an embodiment of this application;

[0051] Figure 2 A schematic diagram of the raw data of the sparse event stream provided in the embodiments of this application;

[0052] Figure 3 A schematic diagram of an iterative curve obtained by using a particle swarm optimization algorithm for search optimization, provided in an embodiment of this application;

[0053] Figure 4 A schematic diagram of the motion trajectory of a fitted space debris provided in an embodiment of this application;

[0054] Figure 5 A schematic diagram of the fitted motion trajectory (algorithm positioning result) of space debris and the actual motion trajectory (actual position of target) of space debris provided in the embodiments of this application;

[0055] Figure 6 A structural block diagram of a space debris positioning device provided in an embodiment of this application;

[0056] Figure 7 This is a structural block diagram of an electronic device for implementing a space debris location method, provided in an embodiment of this application. Detailed Implementation

[0057] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0058] It should be noted that the terms "first," "second," etc., appearing in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0059] It should be understood that in the embodiments of this application, "at least one" means one or more, and "more than one" means two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the related objects before and after it are in an "or" relationship. "Contains A, B and / or C" means containing any one, two, or three of A, B, and C.

[0060] It should be understood that in the embodiments of this application, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0061] To address the technical problems existing in related technologies, this application provides a method and apparatus for locating space debris.

[0062] The spatial fragment location method provided in this application can be executed by an electronic device, such as a terminal or a server. The terminal can be a smartphone, tablet, laptop, or other similar device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. It is understood that this application does not limit the specific entity executing the spatial fragment location method.

[0063] The technical solution of this application will be described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments described below are used to explain the technical solution of this application and are not intended to limit actual use.

[0064] To address the technical problems existing in related technologies, embodiments of this application provide a method for locating space debris, such as... Figure 1 As shown, Figure 1 This is a flowchart illustrating a space debris localization method provided in an embodiment of this application. It should be noted that the steps shown may be executed in a different logical order than those shown in the flowchart. The method may include the following steps S101 to S109.

[0065] Step S101: Acquire raw data of sparse event streams of space debris using a dynamic visual sensor.

[0066] It's important to note that the dynamic vision sensor outputs a series of asynchronous events. Each event records when (timestamp), where (pixel coordinates), and how the brightness changed. The brightness change is represented by polarity. Furthermore, because spatial debris is typically dark and moves quickly, it only causes localized, weak light variations in the field of view. Therefore, the resulting events are very sparse, forming a spatiotemporal point cloud. That is, the raw data of the sparse event stream is a set of (x, y, t, p) points with timestamps, where x and y represent the pixel coordinates of the event, t represents the timestamp of the event, and p represents the polarity.

[0067] In one specific embodiment, Figure 2 This is a schematic diagram of the raw data of the sparse event stream provided in an embodiment of this application. Figure 2 This includes a pixel domain -X, a pixel domain -Y, and a time domain -t. The pixel domain -X represents the horizontal pixel coordinates, in pixels, ranging from 1 to 240. The pixel domain -Y represents the vertical pixel coordinates, in pixels, ranging from 1 to 180. The time domain -t is the timestamp, in nanoseconds, ranging from... - .

[0068] In a dynamic vision sensor, each pixel has its own light intensity comparison circuit, eliminating the need for a global shutter or synchronized exposure. Furthermore, the pixel only triggers output when it detects a change in illumination (such as a brightness change exceeding a threshold), without relying on a fixed frame rate. It responds only to relative changes in light intensity, rather than absolute brightness values.

[0069] Step S102: Obtain the spatiotemporal density of the original sparse event stream data.

[0070] In one optional embodiment, obtaining the spatiotemporal density of the original sparse event stream data specifically includes the following steps:

[0071] Define an initial time surface matrix, where each element represents the time interval between the most recent brightness change at the corresponding location and the current time.

[0072] Calculate the time interval between the two most recent brightness changes to obtain the first time interval;

[0073] The initial time surface matrix is ​​updated based on the first time interval to obtain the target time surface matrix;

[0074] The spatiotemporal density of the original data of the sparse event stream is calculated based on the target time surface matrix.

[0075] In one specific embodiment, the initial time surface matrix has the same dimension as the resolution of the dynamic vision sensor, and the initial value of the elements in the time surface matrix is ​​0.

[0076] In another specific embodiment, the first time interval is calculated using the following formula:

[0077]

[0078] in, Indicates the first time interval. This represents the timestamp corresponding to the i-th brightness change. This represents the timestamp corresponding to the (i-1)th brightness change.

[0079] In another specific embodiment, the initial time surface matrix is ​​updated based on the first time interval to obtain the target time surface matrix, including:

[0080] Based on the first time interval, the initial time surface matrix is ​​updated using the following formula to obtain the target time surface matrix:

[0081] ;

[0082] in, Represents the target time surface matrix. Indicates the exponential decay factor. Indicates the first time interval. Indicates the time coefficient. This indicates the position coordinates of the pixel currently being processed. This represents the position coordinates of the pixel whose brightness changes for the i-th time.

[0083] It should be noted that the time coefficient can be set based on actual experience or can be adaptively adjusted; this application does not limit this.

[0084] In another specific embodiment, calculating the spatiotemporal density of the original sparse event stream data based on the target temporal surface matrix includes:

[0085] Based on the target temporal surface matrix, the spatiotemporal density of the original sparse event stream data is calculated using the following formula:

[0086] ;

[0087] in, This represents the spatiotemporal density corresponding to the i-th brightness change. This represents the x-coordinate corresponding to the i-th change in brightness. This represents the ordinate corresponding to the i-th change in brightness. This indicates the offset in the horizontal direction. This indicates the offset in the vertical direction. and Both represent the neighborhood radius, and T() represents the target time surface matrix.

[0088] Step S103: Based on the spatiotemporal density of the original sparse event stream data, filter the original sparse event stream data to obtain the target sparse event stream data.

[0089] In one optional embodiment, the original sparse event stream data is filtered based on its spatiotemporal density to obtain target sparse event stream data, including:

[0090] If the spatiotemporal density of the original sparse event stream data is not less than the preset spatiotemporal density threshold, then the original sparse event stream data is determined as the target data of the sparse event stream; if the spatiotemporal density of the original sparse event stream data is less than the preset spatiotemporal density threshold, then the original sparse event stream data is discarded.

[0091] It should be noted that the preset spatiotemporal density threshold can be set based on actual experience or can be adaptively adjusted; this application does not limit this.

[0092] Step S104: Determine the time window based on the time domain length of the sparse event stream target data, and slice the sparse event stream target data based on the time window to obtain sparse event stream target data segments.

[0093] In one specific embodiment, assume the time window is set to Stamp all times and The sparse event stream target data within is constructed as the firsti A sparse event stream target data segment, which can be represented as:

[0094]

[0095] in, This represents the first segment of the target data in the sparse event stream. k An event that changes in brightness, For the first k The pixel coordinates corresponding to each brightness change event. For the first k The timestamps corresponding to the brightness change events. For the first k The polarity corresponding to each brightness change event. The polarity can be represented by +1 and -1, where +1 represents an increase in brightness and -1 represents a decrease in brightness.

[0096] Step S105: Construct an objective function based on the spatiotemporal density of the original sparse event stream data.

[0097] In one alternative embodiment, the objective function is expressed as:

[0098] ;

[0099] in, Describe the objective function. This represents the x-coordinate of the target, the y-coordinate of the target, and the time to be solved. This represents the x-axis, y-axis, and time corresponding to the i-th brightness change. The value represents the scaling factor, N represents the total number of times the brightness changes, and exp() refers to the power operation with base e.

[0100] It should be noted that the proportional coefficient can be set based on practical experience, and this application does not impose any restrictions on it.

[0101] In one specific embodiment, and The Euler distance between them is less than a preset Euler distance threshold. The preset Euler distance threshold can be set based on actual experience, and this application does not impose any restrictions on it.

[0102] Step S106: Based on the objective function and the target data segment of the sparse event stream, the target coordinate point and the corresponding objective function value are calculated using a metaheuristic optimization algorithm.

[0103] In one alternative embodiment, the metaheuristic optimization algorithm includes, but is not limited to, evolution-based algorithms (such as genetic algorithms), population-based algorithms (such as particle swarm optimization algorithms), and algorithms based on physical / chemical phenomena (such as simulated annealing algorithms). In addition, the metaheuristic optimization algorithm may also include other algorithms, which are not limited herein.

[0104] In one specific embodiment, 10 sparse event stream target data segments are set, and the particle swarm optimization algorithm is selected to perform 10 search optimizations to obtain the target coordinate points and the target function values ​​corresponding to the target coordinate points. Figure 3 This is a schematic diagram of an iterative curve obtained by searching and optimizing using the particle swarm optimization algorithm, provided in an embodiment of this application. The diagram includes the trend of data from 10 different slices (sparse event flow target data segments) with the number of iterations. The horizontal axis represents the number of iterations, and the vertical axis represents the objective function value. The horizontal axis ranges from 0 to 100, and the vertical axis ranges from -25 to 0.

[0105] Step S107: Establish a uniform point target motion model.

[0106] In one optional embodiment, the expression for the uniform point target motion model is:

[0107] ;

[0108] in, Represents the position function in the x-direction. Let t represent the position function in the y-direction, t represent the time variable, and a, b, c, and d represent the model parameters.

[0109] Step S108: Determine the model parameters of the uniform point target motion model based on the target coordinate point and the corresponding objective function value.

[0110] In one optional embodiment, the model parameters of the uniform point target motion model are determined based on the target coordinate point and the corresponding objective function value, specifically including the following steps:

[0111] Based on the target coordinates and the corresponding objective function values, the model parameters of the uniform point motion model are solved using the weighted least squares method.

[0112] In one specific embodiment, based on the target coordinate point and the corresponding objective function value, the weighted least squares method is used to solve for the model parameters of the uniform point target motion model, including:

[0113] Solve for the intermediate variables used in weighted least squares fitting; solve for the model parameters of the uniform point target motion model based on the intermediate variables.

[0114] In one specific embodiment, the intermediate variables used for weighted least squares fitting are solved using the following formula:

[0115] ;

[0116] ;

[0117] ;

[0118] ;

[0119] ;

[0120] ;

[0121] ;

[0122] Where m represents the number of target coordinate points. This represents the objective function value corresponding to the j-th target coordinate point. This represents the timestamp corresponding to the j-th target coordinate point. This represents the x-coordinate of the j-th target point. This represents the ordinate of the j-th target point.

[0123] Calculate the parameters to be solved a and b for:

[0124]

[0125] Calculate the parameters to be solved c and d for:

[0126]

[0127] Step S109: Determine the trajectory of space debris based on model parameters.

[0128] By substituting the solved parameters a, b, c, and d into the uniform point target motion model, the motion trajectory of the space debris can be obtained. Figure 4 This is a schematic diagram of the motion trajectory of a fitted space debris provided in an embodiment of this application. Figure 4 It includes pixel domain-X, pixel domain-Y, and time domain-t. Pixel domain-X is the horizontal pixel coordinate in pixels, ranging from 0 to 1. Pixel domain-Y is the vertical pixel coordinate in pixels, ranging from 0 to 1. Time domain-t is the timestamp in nanoseconds, ranging from 0 to 1. Figure 5This is a schematic diagram illustrating the fitted motion trajectory (algorithm positioning result) of a space debris and its actual motion trajectory (actual target position) provided in an embodiment of this application. Figure 5 The domain includes pixel-X, pixel-Y, and time-t. Pixel-X represents the horizontal pixel coordinates in pixels, ranging from 0 to 1; pixel-Y represents the vertical pixel coordinates in pixels, also ranging from 0 to 1; and time-t represents the timestamp in nanoseconds, ranging from 0 to 1. It can be seen that the fitted trajectory of the space debris (algorithm positioning result) almost perfectly matches the actual trajectory of the space debris (actual target position), indicating that the space debris positioning method provided in this application can achieve accurate positioning of space debris.

[0129] In this embodiment, a dynamic visual sensor based on illumination change events is used for the detection, localization, and tracking of uniformly moving point targets in space. The dynamic visual sensor employs a biomimetic asynchronous sensing principle, with each pixel independently responding to illumination changes. The output sparse event stream has a time resolution down to the microsecond level, making it particularly suitable for observing space debris targets. The pure space background means that only moving space debris targets and stars generate event signals, resulting in naturally sparse data. Compared to traditional cameras that continuously transmit complete image frames, the communication bandwidth required by the dynamic visual sensor is significantly reduced. Combined with its high dynamic range and low power consumption, it is especially suitable for continuous all-day monitoring of space debris on resource-constrained space-based platforms. A detection strategy of partitioned continuous search localization and target trajectory weighted fitting tracking is adopted. First, the original event stream data is reasonably sliced ​​to match the characteristics of the metaheuristic optimization search algorithm, balancing search accuracy and algorithm efficiency. Then, the coordinates output by the algorithm are combined with their corresponding fitness values ​​to perform least-squares fitting with weighted terms. This solves for the target fitting parameters while offsetting the adverse effects of probabilistic convergence in the metaheuristic optimization algorithm, and also achieves overall method simplicity.

[0130] Corresponding to the space debris location method provided in the embodiments of this application, the embodiments of this application also provide a space debris location device, such as... Figure 6 As shown, the space debris locating device includes:

[0131] Acquisition module 601 is used to acquire raw data of sparse event streams of spatial debris through a dynamic visual sensor;

[0132] The acquisition module 602 is used to acquire the spatiotemporal density of the original data of the sparse event stream;

[0133] The filtering module 603 is used to filter the original sparse event stream data based on the spatiotemporal density of the original sparse event stream data to obtain the target sparse event stream data.

[0134] The first determining module 604 is used to determine a time window based on the temporal length of the sparse event stream target data, and to slice the sparse event stream target data based on the time window to obtain sparse event stream target data segments.

[0135] Module 605 is used to construct an objective function based on the spatiotemporal density of the original sparse event stream data;

[0136] The calculation module 606 is used to calculate the target coordinate point and the target function value corresponding to the target coordinate point based on the objective function and the target data segment of the sparse event stream using a metaheuristic optimization algorithm.

[0137] Module 607 is established to create a uniform point target motion model;

[0138] The second determining module 608 is used to determine the model parameters of the uniform point target motion model based on the target coordinate point and the target function value corresponding to the target coordinate point;

[0139] The third determining module 609 is used to determine the trajectory of space debris based on model parameters.

[0140] Corresponding to the space debris location method provided in the embodiments of this application, the embodiments of this application also provide an electronic device for performing the space debris location method, such as... Figure 7 As shown, the electronic device includes: a processor 701; and a memory 702 for storing a program for a space debris location method. After the device is powered on and the program for the space debris location method is run by the processor, the following steps are performed:

[0141] Raw data of sparse event streams from spatial debris are acquired using dynamic visual sensors;

[0142] Obtain the spatiotemporal density of the raw data of the sparse event stream;

[0143] Based on the spatiotemporal density of the original sparse event stream data, the original sparse event stream data is filtered to obtain the target sparse event stream data.

[0144] The time window is determined based on the temporal length of the sparse event stream target data, and the sparse event stream target data is sliced ​​based on the time window to obtain sparse event stream target data segments.

[0145] Construct an objective function based on the spatiotemporal density of the original sparse event stream data;

[0146] Based on the objective function and the target data segment of the sparse event stream, the target coordinate point and the corresponding objective function value are calculated using a metaheuristic optimization algorithm.

[0147] Establish a uniform point target motion model;

[0148] The model parameters of the uniform point target motion model are determined based on the target coordinate point and the corresponding objective function value;

[0149] The trajectory of space debris is determined based on model parameters.

[0150] Corresponding to the space debris location method provided in the embodiments of this application, the embodiments of this application also provide a computer-readable storage medium storing a program for the space debris location method, which is executed by a processor to perform the following steps:

[0151] Raw data of sparse event streams from spatial debris are acquired using dynamic visual sensors;

[0152] Obtain the spatiotemporal density of the raw data of the sparse event stream;

[0153] Based on the spatiotemporal density of the original sparse event stream data, the original sparse event stream data is filtered to obtain the target sparse event stream data.

[0154] The time window is determined based on the temporal length of the sparse event stream target data, and the sparse event stream target data is sliced ​​based on the time window to obtain sparse event stream target data segments.

[0155] Construct an objective function based on the spatiotemporal density of the original sparse event stream data;

[0156] Based on the objective function and the target data segment of the sparse event stream, the target coordinate point and the corresponding objective function value are calculated using a metaheuristic optimization algorithm.

[0157] Establish a uniform point target motion model;

[0158] The model parameters of the uniform point target motion model are determined based on the target coordinate point and the corresponding objective function value;

[0159] The trajectory of space debris is determined based on model parameters.

[0160] Corresponding to the space debris location method provided in the embodiments of this application, the embodiments of this application also provide a computer program containing instructions, which, when executed by a computer, cause the computer to perform the following steps:

[0161] Raw data of sparse event streams from spatial debris are acquired using dynamic visual sensors;

[0162] Obtain the spatiotemporal density of the raw data of the sparse event stream;

[0163] Based on the spatiotemporal density of the original sparse event stream data, the original sparse event stream data is filtered to obtain the target sparse event stream data.

[0164] The time window is determined based on the temporal length of the sparse event stream target data, and the sparse event stream target data is sliced ​​based on the time window to obtain sparse event stream target data segments.

[0165] Construct an objective function based on the spatiotemporal density of the original sparse event stream data;

[0166] Based on the objective function and the target data segment of the sparse event stream, the target coordinate point and the corresponding objective function value are calculated using a metaheuristic optimization algorithm.

[0167] Establish a uniform point target motion model;

[0168] The model parameters of the uniform point target motion model are determined based on the target coordinate point and the corresponding objective function value;

[0169] The trajectory of space debris is determined based on model parameters.

[0170] It should be noted that for a detailed description of the space debris positioning device, electronic device, computer-readable storage medium and computer program product provided in the embodiments of this application, please refer to the relevant description of the space debris positioning method embodiments provided in the embodiments of this application, which will not be repeated here.

[0171] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.

[0172] In a typical configuration, an electronic device includes one or more processors (Central Processing Units), input / output interfaces, network interfaces, and memory.

[0173] Memory may include non-persistent storage in computer-readable media, such as random access memory and / or non-volatile memory, like read-only memory or flash memory. Memory is an example of computer-readable media.

[0174] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable operations, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory, static random access memory, dynamic random access memory, other types of random access memory, read-only memory, electrically erasable programmable read-only memory, flash memory or other memory technologies, compact disc read-only memory, digital video disc or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0175] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, compact disc read-only memory, optical storage, etc.) containing computer-usable program code.

[0176] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.

Claims

1. A method for locating space debris, characterized in that, include: Raw data of sparse event streams from spatial debris are acquired using dynamic visual sensors; Define an initial time surface matrix, where each element represents the time interval between the most recent brightness change at the corresponding location and the current time. Calculate the time interval between the two most recent brightness changes to obtain the first time interval; The initial time surface matrix is ​​updated based on the first time interval to obtain the target time surface matrix; Calculate the spatiotemporal density of the original data of the sparse event stream based on the target temporal surface matrix; Based on the spatiotemporal density of the original sparse event stream data, the original sparse event stream data is filtered to obtain the target sparse event stream data. A time window is determined based on the temporal length of the sparse event stream target data, and the sparse event stream target data is sliced ​​based on the time window to obtain sparse event stream target data segments. An objective function is constructed based on the spatiotemporal density of the original sparse event stream data, wherein the expression of the objective function is: ； in, Describe the objective function. This represents the x-coordinate of the target, the y-coordinate of the target, and the time to be solved. This represents the x-axis, y-axis, and time corresponding to the i-th brightness change. The value represents the scaling factor, N represents the total number of times the brightness changes, and exp() refers to the power operation with base e. Based on the objective function and the sparse event stream target data segment, the target coordinate point and the objective function value corresponding to the target coordinate point are calculated using a metaheuristic optimization algorithm. Establish a uniform point target motion model; The model parameters of the uniform point target motion model are determined based on the target coordinate point and the target function value corresponding to the target coordinate point; The trajectory of the space debris is determined based on the model parameters.

2. The space debris location method according to claim 1, characterized in that, The step of updating the initial time surface matrix based on the first time interval to obtain the target time surface matrix includes: Based on the first time interval, the initial time surface matrix is ​​updated using the following formula to obtain the target time surface matrix: ； in, Represents the target time surface matrix. Indicates the exponential decay factor. Indicates the first time interval. Indicates the time coefficient. This indicates the position coordinates of the pixel currently being processed. This represents the position coordinates of the pixel whose brightness changes for the i-th time.

3. The space debris location method according to claim 1, characterized in that, The calculation of the spatiotemporal density of the original sparse event stream data based on the target temporal surface matrix includes: Based on the target time surface matrix, the spatiotemporal density of the original data of the sparse event stream is calculated using the following formula: ； in, This represents the spatiotemporal density corresponding to the i-th brightness change. This represents the x-coordinate corresponding to the i-th change in brightness. This represents the ordinate corresponding to the i-th change in brightness. This indicates the offset in the horizontal direction. This indicates the offset in the vertical direction. and Both represent the neighborhood radius, and T() represents the target time surface matrix.

4. The space debris location method according to claim 1, characterized in that, The process of determining the model parameters of the uniform point target motion model based on the target coordinate point and the corresponding objective function value includes: Based on the target coordinate point and the corresponding objective function value, the model parameters of the uniform point target motion model are solved using the weighted least squares method.

5. The space debris location method according to claim 1, characterized in that, The process of filtering the original sparse event stream data based on its spatiotemporal density to obtain target sparse event stream data includes: If the spatiotemporal density of the original sparse event stream data is not less than a preset spatiotemporal density threshold, then the original sparse event stream data is determined as the target data of the sparse event stream; if the spatiotemporal density of the original sparse event stream data is less than the preset spatiotemporal density threshold, then the original sparse event stream data is discarded.

6. A space debris positioning device, characterized in that, include: The acquisition module is used to acquire raw data of sparse event streams of spatial debris through a dynamic visual sensor; The acquisition module is used to acquire the spatiotemporal density of the original data of the sparse event stream; The filtering module is used to filter the original sparse event stream data based on the spatiotemporal density of the original sparse event stream data to obtain the target sparse event stream data. The first determining module is used to determine a time window based on the temporal length of the sparse event stream target data, and to slice the sparse event stream target data based on the time window to obtain sparse event stream target data segments. The construction module is used to construct an objective function based on the spatiotemporal density of the original sparse event stream data, wherein the expression of the objective function is: ； in, Describe the objective function. This represents the x-coordinate of the target, the y-coordinate of the target, and the time to be solved. This represents the x-axis, y-axis, and time corresponding to the i-th brightness change. The value represents the scaling factor, N represents the total number of times the brightness changes, and exp() refers to the power operation with base e. The calculation module is used to calculate the target coordinate point and the target function value corresponding to the target coordinate point using a metaheuristic optimization algorithm based on the objective function and the target data segment of the sparse event stream. A module is created to build a model of a uniform point target motion. The second determining module is used to determine the model parameters of the uniform point target motion model based on the target coordinate point and the target function value corresponding to the target coordinate point; The third determining module is used to determine the motion trajectory of the space debris based on the model parameters; The acquisition module is specifically used to define an initial time surface matrix, where each element represents the time interval between the most recent brightness change at the corresponding location and the current time; calculate the time interval between the two most recent brightness changes to obtain a first time interval; update the initial time surface matrix based on the first time interval to obtain a target time surface matrix; and calculate the spatiotemporal density of the original sparse event stream data based on the target time surface matrix.

7. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the space debris location method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the space debris location method according to any one of claims 1-5.

Images