A method for predicting and fusion of space target coordinates
By preprocessing and feature extraction of multiple sets of sensor data, combined with filtering algorithms and data fusion technology, the fusion difficulties caused by sensor data differences are solved, and high-precision positioning and tracking of spatial goals are achieved.
Patent Information
- Application Number
- CN202411834557.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-13
- Publication Date
- 2025-04-04
AI Technical Summary
In the existing spatial target coordinate prediction and fusion technology, the difference in format, accuracy and time synchronization of multiple sets of sensor data leads to difficulty in data fusion, affecting positioning accuracy and tracking effect.
By collecting multiple sets of data for preprocessing, extracting key features, performing data fusion, using filtering algorithms to perform state prediction, and fusing measurement data from multiple sensors to obtain the best estimated trajectory of the target.
High-precision positioning and tracking of spatial targets is achieved, and the accuracy and reliability of data fusion are improved.
Smart Images
Figure CN119760398A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of space coordinate management technology, and more specifically, to a space target coordinate prediction and fusion method. Background Art
[0002] Space target coordinate prediction and fusion refers to the process of locating, tracking and identifying targets in space by using information from multiple sensors or data sources through algorithms and technical means. This process is extremely important for improving positioning accuracy, achieving real-time dynamic tracking, enhancing situational awareness, optimizing resource allocation, supporting scientific research, improving defense capabilities and promoting international cooperation. In the existing space target coordinate prediction and fusion, target parameters are mainly collected through multiple sets of sensor data, but data from different sensors may have differences in format, accuracy and time synchronization, which brings challenges to data fusion. Summary of the invention
[0003] In order to overcome the deficiencies of the prior art, the present invention provides a method for predicting and fusing space target coordinates.
[0004] To achieve the above object, the present invention provides the following technical solution: a method for predicting and fusing space target coordinates, comprising the following steps: Step 1: Collect data from different spacecraft or sensors and perform data preprocessing; Step 2: Extract key features from the preprocessed data; Step 3: Fuse data from different sensors or at different time points; Step 4: Use filtering algorithm to estimate the state of the target; Step 5: Fuse the measurement data from multiple sensors to obtain the best estimated trajectory of the target; Step 6: Convert the sensor data from its original coordinate system to a unified coordinate system; Step 7: Output the fused target trajectory or coordinate information.
[0005] As a preferred technical solution of the present invention, in step 1, the source of data includes but is not limited to radar, optical telescope, infrared sensor, and the data includes but is not limited to position information, speed information, and attitude information.
[0006] As a preferred technical solution of the present invention, in step one, the process of data preprocessing is to check and process outliers and errors in the data, such as noise points, missing values or inconsistent data points, to ensure that data from different sources are synchronized in time.
[0007] As a preferred technical solution of the present invention, the step 2 comprises the following steps: A1. Identify spatial targets in sensor data through threshold processing, edge detection or pattern recognition; A2. Classify the target into different types according to its characteristics and convert the target's attributes into numerical form; A3. Select discriminative and representative features from the candidate features and standardize or normalize the features; A4. Check the extracted features and store them.
[0008] As a preferred technical solution of the present invention, in the step three, control points are selected in the data to be fused, and a mapping relationship between images is established based on the control points. According to the mapping relationship, the non-reference image is resampled to obtain an image registered with the reference image, and the remote sensing image data that has undergone spatial registration is organically synthesized.
[0009] As a preferred technical solution of the present invention, the step 4 includes the following steps: B1. Determine the initial state vector and covariance matrix, and predict the state of the target at the next moment based on the target's motion model; B2. When new observation data arrives, use this data to update the state estimate of the target. In the prediction and update steps, the error covariance matrix needs to be calculated and propagated; B3, associate new observation data with existing target trajectories and fuse data from different sensors; B4. Check whether the estimated results meet the expected quality requirements and store the estimated results.
[0010] As a preferred technical solution of the present invention, in the step five, corresponding feature points are found between the observation data of different sensors, and the data of different sensors are spatially aligned according to the result of feature matching; the multi-source data after spatial registration are organically synthesized to obtain a comprehensive representation or estimation of the target; in a multi-target environment, the new observation data is associated with the existing target trajectory; and the state estimation of the target is updated according to the fused information.
[0011] As a preferred technical solution of the present invention, in step six, the coordinate system type of the target before and after the coordinate conversion is clearly defined, and the corresponding conversion method is selected according to the type of coordinate system and the conversion requirements; the selected conversion method and the calculated parameters are used to perform actual conversion operations on the target coordinates, and verification is performed after the conversion.
[0012] As a preferred technical solution of the present invention, in the step seven, the fused target trajectory or coordinate information is sorted, and the sorted data is converted into a corresponding storage format as needed; the fused target trajectory or coordinate information is displayed in a graphical manner, a detailed report is generated based on the fused results, and the fused results are stored.
[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: the prediction and fusion method provided by the present invention processes the data after collecting multiple sets of data, and fuses multiple sets of sensor data after pre-processing the data. In this way, the target trajectory is obtained, and high-precision positioning and tracking of space targets can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION
[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0016] like Figure 1 As shown, the present invention provides a space target coordinate prediction and fusion method, comprising the following steps: Step 1: Collect data from different spacecraft or sensors and perform data preprocessing; The sources of data include but are not limited to radar, optical telescope, infrared sensor, and the data include but are not limited to position information, velocity information, and attitude information. The process of data preprocessing is to check and process outliers and errors in the data, such as noise points, missing values, or inconsistent data points, to ensure that data from different sources are synchronized in time. It provides a clean, consistent, and high-quality data foundation for subsequent feature extraction, state estimation, and track fusion, which can greatly improve the accuracy and reliability of the final results.
[0017] Step 2: Extract key features from the preprocessed data; Step 2 includes the following steps: A1. Identify spatial targets in sensor data through threshold processing, edge detection or pattern recognition; A2. Classify the target into different types according to its characteristics and convert the target's attributes into numerical form; A3. Select discriminative and representative features from the candidate features and standardize or normalize the features; A4. Check the extracted features and store them.
[0018] Feature extraction is the process of extracting key information from preprocessed data. This information is crucial for identifying and tracking spatial targets. It ensures that the extracted features are accurate, reliable and useful, providing a solid foundation for subsequent state estimation and track fusion.
[0019] Step 3: Fuse data from different sensors or at different time points; Select control points in the data to be fused, establish the mapping relationship between images based on the control points, resample the non-reference image based on the mapping relationship, obtain the image registered with the reference image, and organically synthesize the remote sensing image data that has undergone spatial registration. Through reasonable design and implementation, high-precision positioning and tracking of space targets can be achieved.
[0020] Step 4: Use filtering algorithm to estimate the state of the target; Step 4 includes the following steps: B1. Determine the initial state vector and covariance matrix, and predict the state of the target at the next moment based on the target's motion model; B2. When new observation data arrives, use this data to update the state estimate of the target. In the prediction and update steps, the error covariance matrix needs to be calculated and propagated; B3, associate new observation data with existing target trajectories and fuse data from different sensors; B4. Check whether the estimated results meet the expected quality requirements and store the estimated results.
[0021] State estimation is an iterative process that continuously uses new observation data to update the state estimate of the target, which can achieve high-precision positioning and tracking of space targets.
[0022] Step 5: Fuse the measurement data from multiple sensors to obtain the best estimated trajectory of the target; Find the corresponding feature points between the observation data of different sensors, and align the data of different sensors in space according to the result of feature matching; synthesize the multi-source data after spatial registration to obtain a comprehensive representation or estimation of the target; in a multi-target environment, associate the new observation data with the existing target trajectory; update the target state estimation based on the fused information. Step 6: Convert the sensor data from its original coordinate system to a unified coordinate system; In step six, the coordinate system type of the target before and after the coordinate conversion is clearly defined, and the corresponding conversion method is selected according to the type of coordinate system and the conversion requirements; the selected conversion method and the calculated parameters are used to perform the actual conversion operation on the target coordinates, and the conversion is verified after the conversion. Coordinate conversion ensures the accuracy and reliability of coordinate conversion through reasonable design and implementation, providing a solid foundation for subsequent spatial analysis and decision-making.
[0023] Step 7: Output the fused target trajectory or coordinate information; In step seven, the fused target trajectory or coordinate information is sorted, and the sorted data is converted into the corresponding storage format as needed; the fused target trajectory or coordinate information is displayed in a graphical way, a detailed report is generated based on the fused results, and the fused results are stored. Result output is a comprehensive process, which not only involves data processing and display, but also includes interaction with other systems and personnel. Through reasonable design and implementation, it can ensure that the final output results are both accurate and easy to understand, providing users with valuable information support.
[0024] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0025] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A method for predicting and fusing spatial target coordinates, characterized in that: The steps include: Step 1: Collect data from different spacecraft or sensors and perform data preprocessing; Step 2: Extract key features from the preprocessed data; Step 3: Fuse data from different sensors or at different time points; Step 4: Use filtering algorithm to estimate the state of the target; Step 5: Fuse the measurement data from multiple sensors to obtain the best estimated trajectory of the target; Step 6: Convert the sensor data from its original coordinate system to a unified coordinate system; Step 7: Output the fused target trajectory or coordinate information.
2. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: In step 1, the source of data includes but is not limited to radar, optical telescope, and infrared sensor, and the data includes but is not limited to position information, speed information, and attitude information.
3. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: In step 1, the process of data preprocessing is to check and process outliers and errors in the data, such as noise points, missing values or inconsistent data points, to ensure that data from different sources are synchronized in time.
4. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: The step 2 comprises the following steps: A1. Identify spatial targets in sensor data through threshold processing, edge detection or pattern recognition; A2. Classify the target into different types according to its characteristics and convert the target's attributes into numerical form; A3. Select discriminative and representative features from the candidate features and standardize or normalize the features; A4. Check the extracted features and store them.
5. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: In the step three, control points are selected from the data to be fused, and a mapping relationship between images is established based on the control points. Based on the mapping relationship, the non-reference image is resampled to obtain an image registered with the reference image, and the remote sensing image data that has undergone spatial registration is organically synthesized.
6. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: The step 4 includes the following steps: B1. Determine the initial state vector and covariance matrix, and predict the state of the target at the next moment based on the target's motion model; B2. When new observation data arrives, use this data to update the state estimate of the target. In the prediction and update steps, the error covariance matrix needs to be calculated and propagated; B3, associate new observation data with existing target trajectories and fuse data from different sensors; B4. Check whether the estimated results meet the expected quality requirements and store the estimated results.
7. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: In the step five, corresponding feature points are found between the observation data of different sensors, and the data of different sensors are spatially aligned according to the result of feature matching; the multi-source data after spatial registration are organically synthesized to obtain a comprehensive representation or estimation of the target; in a multi-target environment, the new observation data is associated with the existing target trajectory; and the state estimation of the target is updated according to the fused information.
8. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: In the step six, the coordinate system type of the target before and after the coordinate conversion is clearly defined, and the corresponding conversion method is selected according to the type of coordinate system and the conversion requirements; the selected conversion method and the calculated parameters are used to perform actual conversion operations on the target coordinates, and verification is performed after the conversion.
9. A method for predicting and fusing space target coordinates according to claim 1, characterized in that: In the step 7, the fused target trajectory or coordinate information is sorted, and the sorted data is converted into a corresponding storage format as needed; The fused target trajectory or coordinate information is displayed in a graphical manner, a detailed report is generated based on the fused results, and the fused results are stored.