Data fusion method and device based on confidence coefficient, storage medium and program product

Abstract

The invention provides a confidence-based data fusion method and device, a storage medium and a program product, relates to the field of track data processing, and is used for reducing the calculation complexity of a data fusion process and improving the real-time performance and accuracy of data processing. The method comprises the following steps: acquiring monitoring data of at least one monitoring device on a target aircraft; for each piece of monitoring equipment in the at least one piece of monitoring equipment, calculating the confidence of each piece of monitoring equipment based on the equipment type of each piece of monitoring equipment and the monitoring data of each piece of monitoring equipment; and performing data fusion on the monitoring data of each monitoring device based on the confidence of each monitoring device.

Description

Technical Field

[0001] This application relates to the field of track data processing, and in particular to a confidence-based data fusion method, device, storage medium, and program product. Background Technology

[0002] Establishing an effective regulatory system for low-altitude flight safety is the primary prerequisite and core foundation for the low-altitude economy to move from proof-of-concept and pilot demonstrations to large-scale and commercial development. With the widespread application of aircraft such as drones and electric vertical take-off and landing (eVTOL) aircraft in logistics, surveying, agriculture, and passenger transportation, the low-altitude environment is becoming increasingly complex and dense. Against this backdrop, achieving continuous monitoring and rapid intervention of target aircraft has become crucial for ensuring airspace safety.

[0003] Currently, target aircraft are monitored by surveillance equipment, and the surveillance data is collected and reported to the low-altitude flight safety supervision enabling cloud platform for data fusion. Alternatively, the surveillance equipment can be connected to the network, and algorithm processing and data fusion can be performed at the network element level. Then, intervention can be carried out on the target aircraft based on the results of data fusion.

[0004] However, the monitoring data from various monitoring devices differ, increasing the complexity and computational load of data fusion, resulting in insufficient real-time performance and accuracy of data processing. Summary of the Invention

[0005] This application provides a confidence-based data fusion method, device, storage medium, and program product to reduce the computational complexity of the data fusion process and improve the real-time performance and accuracy of data processing.

[0006] In a first aspect, this application provides a confidence-based data fusion method, comprising: acquiring surveillance data of a target aircraft from at least one surveillance device; calculating the confidence level of each surveillance device based on its device type and the surveillance data; and performing data fusion on the surveillance data of each surveillance device based on the confidence level of each surveillance device.

[0007] The technical solution provided in this application offers at least the following beneficial effects: First, it acquires the raw surveillance data of the target aircraft from each surveillance device; then, it calculates the confidence level of each surveillance device based on its equipment type and surveillance data, reflecting the reliability of each surveillance data point; finally, it performs weighted fusion of the heterogeneous surveillance data based on the confidence levels of each surveillance device. This process reduces the overall computational load, effectively filters out interference from unreliable information by assigning greater weight to high-confidence data, and obtains more accurate flight information of the target aircraft, thereby achieving effective surveillance of the target aircraft.

[0008] One possible implementation is that the monitoring data includes at least one of the following: the target aircraft's altitude, the target aircraft's speed, the target aircraft's heading angle, and the target aircraft's attitude.

[0009] Another possible implementation involves calculating the confidence level of each monitoring device based on its device type and monitoring data. This includes: when the monitoring device is a visual observation device, the confidence level is a pre-set confidence level; when the monitoring device is a radar sensing device, the observation noise covariance matrix of the monitoring device is determined based on its monitoring data; and the confidence level of the monitoring device is determined based on its observation noise covariance matrix.

[0010] Another possible implementation involves calculating the confidence level of each surveillance device based on its device type and surveillance data. This includes calculating the confidence level of each surveillance device based on the order in which at least one surveillance device detected the target aircraft, the device type of each surveillance device, and the surveillance data of each surveillance device.

[0011] Another possible implementation involves calculating the confidence level of each monitoring device based on the order in which at least one monitoring device detects the target aircraft, the device type of each monitoring device, and the monitoring data of each monitoring device. This includes: if only the first monitoring device among the at least one monitoring device detects the target aircraft, the confidence level of the first monitoring device is a preset confidence level; if both the first and second monitoring devices among the at least one monitoring device detect the target aircraft, the confidence level of the second monitoring device is determined based on the type of the second monitoring device and the monitoring data of the second monitoring device, and the confidence level of the first monitoring device is updated based on the confidence level of the second monitoring device; if the first, second, and third monitoring devices among the at least one monitoring device detect the target aircraft, the confidence level of the third monitoring device is determined based on the type of the third monitoring device or the monitoring data of the third monitoring device, and the confidence levels of the second and first monitoring devices are updated based on the confidence level of the third monitoring device, the monitoring data of the second and third monitoring devices.

[0012] Another possible implementation involves updating the confidence levels of the second and first monitoring devices based on the confidence level of the third monitoring device and the monitoring data of the second and third monitoring devices. This includes: updating the confidence level of the second monitoring device based on the confidence level of the third monitoring device and the ratio of the observation noise covariance matrices of the second and third monitoring devices; wherein the observation noise covariance matrix of the second monitoring device is determined based on the monitoring data of the second monitoring device, and the observation noise covariance matrix of the third monitoring device is determined based on the monitoring data of the third monitoring device; and updating the confidence level of the first monitoring device based on the confidence level of the third monitoring device and the updated confidence level of the second monitoring device.

[0013] Another possible implementation involves fusing the monitoring data of each monitoring device based on the confidence level of each monitoring device, including: using the confidence level of each monitoring device as the weight of the monitoring data of each monitoring device, and fusing the monitoring data of at least one monitoring device.

[0014] Secondly, this application provides a confidence-based data fusion apparatus, comprising: an acquisition module and a processing module; the acquisition module is used to acquire surveillance data of a target aircraft from at least one surveillance device; the processing module is used to calculate the confidence level of each surveillance device based on the device type of each surveillance device and the surveillance data of each surveillance device for each of the at least one surveillance device; the processing module is further used to perform data fusion on the surveillance data of each surveillance device based on the confidence level of each surveillance device.

[0015] One possible implementation is a processing module, specifically used to: when the monitoring device is a visual observation device, set the confidence level of the monitoring device to a preset confidence level; when the monitoring device is a radar sensing device, determine the observation noise covariance matrix of the monitoring device based on the monitoring data of the monitoring device; and determine the confidence level of the monitoring device based on the observation noise covariance matrix of the monitoring device.

[0016] Another possible implementation is a processing module, specifically used to calculate the confidence level of each monitoring device based on the order in which the target aircraft is detected by at least one monitoring device, the device type of each monitoring device, and the monitoring data of each monitoring device.

[0017] Another possible implementation involves a processing module specifically configured to: when only the first monitoring device detects the target aircraft among at least one monitoring device, the confidence level of the first monitoring device is a preset confidence level; when both the first and second monitoring devices detect the target aircraft, the confidence level of the second monitoring device is determined based on the type of the second monitoring device and the monitoring data of the second monitoring device, and the confidence level of the first monitoring device is updated based on the confidence level of the second monitoring device; when the first, second, and third monitoring devices detect the target aircraft, the confidence level of the third monitoring device is determined based on the type of the third monitoring device or the monitoring data of the third monitoring device, and the confidence levels of the second and first monitoring devices are updated based on the confidence level of the third monitoring device, the monitoring data of the second monitoring device, and the monitoring data of the third monitoring device.

[0018] Another possible implementation involves a processing module that updates the confidence level of the second monitoring device based on the confidence level of the third monitoring device and the ratio of the observation noise covariance matrix of the second monitoring device to that of the third monitoring device. The observation noise covariance matrix of the second monitoring device is determined based on the monitoring data of the second monitoring device, and the observation noise covariance matrix of the third monitoring device is determined based on the monitoring data of the third monitoring device. The confidence level of the first monitoring device is then updated based on the confidence level of the third monitoring device and the updated confidence level of the second monitoring device.

[0019] Another possible implementation is a processing module, which is specifically used to perform data fusion on the monitoring data of at least one monitoring device by using the confidence level of each monitoring device as the weight of the monitoring data of each monitoring device.

[0020] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory storing processor-executable instructions; when the processor is configured to execute the instructions, causing the electronic device to implement the method of the first aspect described above.

[0021] Fourthly, this application provides a computer-readable storage medium comprising: computer software instructions; which, when executed in an electronic device, cause the electronic device to implement the method described in the first aspect.

[0022] Fifthly, this application provides a computer program product comprising a computer program; when the computer program is run in an electronic device, the electronic device performs the method described in the first aspect.

[0023] The beneficial effects of the second to fifth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description

[0024] Figure 1 This application provides an illustration of an application environment for a confidence-based data fusion method. Figure 2 A flowchart illustrating a confidence-based data fusion method provided in this application embodiment; Figure 3 A flowchart illustrating another confidence-based data fusion method provided in this application embodiment; Figure 4 A flowchart illustrating yet another confidence-based data fusion method provided in this application embodiment; Figure 5 This is a schematic diagram of the composition of a data fusion device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] The following section will describe in detail, with reference to the accompanying drawings, a confidence-based data fusion method provided in this application.

[0026] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0027] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0028] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0029] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0030] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0031] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0032] With the rapid development of the low-altitude economy, building an efficient low-altitude flight safety supervision system has become crucial for ensuring airspace safety and promoting the industry's large-scale development. The core requirement of a low-altitude flight safety supervision system is the ability to detect target aircraft promptly and accurately, and to achieve continuous and stable monitoring and tracking. Based on this, when necessary, precise and controllable measures can be taken against specific targets using integrated intervention and countermeasure equipment. At the technical level, surveillance methods encompass traditional methods such as radar, Time Difference of Arrival (TDOA), Angle of Arrival (AOA), electro-optical observation, sonar detection, and spectrum scanning, as well as emerging technologies such as 5G-A integrated sensing. Countermeasures include GPS decoys, flight control signal suppression, and physical strike methods such as net capture and laser attacks. In actual system construction, different technologies need to be organically selected and integrated based on the functional requirements, environmental characteristics, and economic costs of specific scenarios. Taking civil airport scenarios as an example, the regulatory system needs to achieve tiered coverage from remote routes to near-field headquarters, and strictly ensure the safety of civil flights and ground facilities during the countermeasure process. This highlights the extremely high requirements for the accuracy and reliability of surveillance and countermeasure capabilities. Countermeasures need to be based on surveillance, and establishing effective surveillance is even more important.

[0033] To address these needs, two main approaches to integrating surveillance technologies have emerged. One approach is a centralized integration scheme centered on a low-altitude flight safety supervision enabling cloud platform. Each surveillance device acts as a data acquisition node, uploading its surveillance data to the platform, which then performs multi-source data fusion processing and intelligently schedules countermeasures resources based on the fusion results. The other approach is an edge integration scheme. After connecting to the network, surveillance devices perform data processing and fusion at network edge nodes (network elements) close to the data source. The low-altitude flight safety supervision enabling cloud platform then intelligently schedules countermeasures to deal with target aircraft based on the fusion results.

[0034] However, in the first type of solution, the fusion of surveillance data is handled by the low-altitude flight safety supervision enabling cloud platform. The entire process requires surveillance equipment to first upload its respective surveillance results data, and then the platform runs an algorithm to fuse the data. Precise clock synchronization of the surveillance equipment is difficult to achieve, resulting in data misalignment in the time domain, severely impacting the accuracy and reliability of the fusion algorithm. In the second type of solution, surveillance equipment sends surveillance process data to network elements in real time for unified real-time processing. However, due to the significant differences in data structure, dimensions, and characteristics between different types of surveillance equipment (such as radar point clouds and video images), effective processing using a single fusion algorithm is difficult. Often, dedicated fusion algorithms need to be deployed for different types of equipment, requiring the system to run multiple fusion processes simultaneously. This results in a substantial increase in computing resource requirements, significantly raising computational complexity and maintenance costs, posing a significant challenge to implementation and maintenance.

[0035] To address the aforementioned technical issues, this application provides a confidence-based data fusion method. The method involves: first, acquiring the raw surveillance data of the target aircraft from each surveillance device; then, calculating the confidence level of each surveillance device based on its equipment type and the amount of surveillance data, thus obtaining the reliability of each surveillance data point; finally, weighted fusion of the heterogeneous surveillance data based on the confidence levels of each surveillance device. This process reduces the overall computational load, effectively filters out interference from unreliable information by assigning greater weight to high-confidence data, and obtains more accurate flight information of the target aircraft, thereby achieving effective surveillance of the target aircraft.

[0036] The embodiments provided in this application will now be described in detail with reference to the accompanying drawings.

[0037] This application provides a confidence-based data fusion method that can be applied to, for example... Figure 1 The application environment shown. For example... Figure 1 As shown, the application environment includes a monitoring device 10 and a processing device 20. The monitoring device 10 and the processing device 20 are communicatively connected.

[0038] In some embodiments, the monitoring device 10 is used to monitor the target aircraft and collect various forms of input data information. In this application, the monitoring device 10 is used to monitor the flight trajectory of the target aircraft (such as a drone, eVTOL, etc.), acquire the monitoring data information of the target aircraft, and transmit the monitoring data information to the processing device 20.

[0039] In some embodiments, the monitoring device 10 can be a device with wireless transceiver capabilities, such as radar, infrared camera, camera, surveillance equipment, mobile phone with camera function, tablet computer, wearable device, in-vehicle device, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), etc. This application does not limit the specific device form of the monitoring device 10.

[0040] In some embodiments, the processing device 20 is used to receive data information transmitted by the monitoring device 10 and to analyze and process the data information. In this application, the processing device 20 is used to receive raw monitoring data collected by the monitoring device 10, then calculate the confidence level of each monitoring data to evaluate its reliability, and finally, perform fusion processing on the multi-source monitoring data based on the confidence level to generate accurate target aircraft trajectory information.

[0041] In some embodiments, the processing device 20 may be a server cluster consisting of multiple servers, a single server, a computer, or a processor or processing chip in a server or computer. This application does not limit the specific device form of the processing device 20.

[0042] It should be noted that the system architecture described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of system architecture, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0043] See Figure 2 The above is a flowchart illustrating a confidence-based data fusion method provided in an embodiment of this application. Figure 2 As shown, the confidence-based data fusion method provided in this application specifically includes the following steps S201~S203.

[0044] S201. Acquire surveillance data of the target aircraft from at least one surveillance device.

[0045] The surveillance data includes at least one of the following: the target aircraft's altitude, speed, heading angle, and attitude.

[0046] S202. For each of the at least one monitoring devices, calculate the confidence level of each monitoring device based on the device type and monitoring data of each monitoring device.

[0047] The surveillance equipment includes visual observation equipment and radar sensing equipment. Confidence level is used to reflect the reliability and accuracy of the surveillance data from the surveillance equipment.

[0048] In some embodiments, visual observation devices refer to devices that use optical imaging principles (visible light or infrared light) to acquire visual information such as the appearance and texture of a target aircraft, such as high-definition cameras, infrared thermal imagers, and photoelectric tracking systems. Visual observation devices acquire intuitive visual information such as the appearance and texture features of a target aircraft by receiving optical signals in the visible light or infrared bands, and output surveillance data containing images, video streams, and derived feature information of the target aircraft.

[0049] In some embodiments, radar sensing devices detect and track target aircraft by transmitting radio waves (radar waves) into space and receiving the echoes reflected from the target. Radar sensing devices can achieve all-weather, all-time, long-range detection of target aircraft and output surveillance data including the target aircraft's range, azimuth, pitch angle, speed, and radar cross-section characteristics.

[0050] As one possible approach, when the monitoring device is a visual observation device, the confidence level of the monitoring device is a preset confidence level.

[0051] Among them, visual observation devices (such as cameras) can generate surveillance data such as videos and images, providing intuitive information that can be directly interpreted by the human eye and providing reliable surveillance data.

[0052] For example, under ideal conditions of clear images and unobstructed field of view, a high preset confidence level (such as 100%) can be assigned to visual observation devices. The preset confidence level can be dynamically adjusted in combination with factors such as real-time image quality and ambient lighting.

[0053] As another possible approach, when the monitoring device is a radar sensing device, the observation noise covariance matrix of the monitoring device is determined based on the monitoring data of the monitoring device; and the confidence level of the monitoring device is determined based on the observation noise covariance matrix of the monitoring device.

[0054] For example, the observation noise covariance matrix R is calculated by analyzing surveillance data from radar sensing devices over multiple consecutive periods. The diagonal elements of the observation noise covariance matrix R represent the variance of each observation, while the off-diagonal elements reflect the degree of error correlation between different observations. Taking the TDOA (Total Distance Aspect Ratio) of a target aircraft detected by a radar sensing device as an example, its observation noise covariance matrix R can be expressed as: R=[Dτ12,σ(12,13);σ(12,13),Dτ13] Where Dτ12 represents the variance of the time difference between the arrival of the signal at ground reference station 1 and ground reference station 2, Dτ13 represents the variance of the time difference between the arrival of the signal at ground reference station 1 and ground reference station 3, and σ(12,13) ​​represents the covariance of the two sets of observation data.

[0055] As one feasible approach, the observation noise covariance matrix of radar sensing devices can be converted into confidence scores based on matrix norm mapping.

[0056] For example, the norm of the observation noise covariance matrix R (such as the Frobenius norm) is calculated, and the norm value is mapped to a confidence level in the range of 0 to 1 using a nonlinear function.

[0057] As another possible approach, the observation noise covariance matrix of radar sensing devices can be converted into confidence levels, which can be evaluated based on information entropy.

[0058] For example, the inverse of the observation noise covariance matrix can be regarded as the information matrix. The observation quality can be evaluated by calculating the entropy of the information matrix. The smaller the information entropy, the lower the uncertainty of the observation data and the higher the corresponding confidence level.

[0059] If the norm of the observation noise covariance matrix is ​​small, it indicates that the radar measurement accuracy is high and the data is stable, and the confidence level of radar sensing equipment is high; if the norm of the observation noise covariance matrix increases, it indicates that the radar is affected by the environment (such as meteorological clutter and electromagnetic interference), resulting in a larger measurement error, and the confidence level of radar sensing equipment is low.

[0060] S203. Perform data fusion on the monitoring data of each monitoring device based on the confidence level of each monitoring device.

[0061] In some embodiments, the confidence level of each monitoring device is used as the weight of the monitoring data of each monitoring device, and the monitoring data of at least one monitoring device are fused.

[0062] For example, monitoring equipment A and monitoring equipment B observe the position data of the same target aircraft. Monitoring equipment A reports the position (105.2, 201.5) with a current confidence level of 60%; monitoring equipment B reports the position (107.8, 199.2) with a current confidence level of 40%. After normalizing the confidence levels, the weight of radar A is 0.6, and the weight of electro-optical equipment B is 0.4. Where longitude = 105.2 × 0.6 + 107.8 × 0.4 = 106.24; latitude = 201.5 × 0.6 + 199.2 × 0.4 = 200.58, the position of the target aircraft is obtained as (106.24, 200.58).

[0063] Based on the above embodiments, firstly, the raw surveillance data of the target aircraft from each surveillance device is acquired; then, the confidence level of each surveillance device is calculated according to its device type and the surveillance data, thus obtaining the reliability of each surveillance data; finally, the heterogeneous surveillance data is weighted and fused based on the confidence levels of each surveillance device. This process reduces the overall computational load, effectively filters out interference from unreliable information by assigning greater weight to high-confidence data, and obtains more accurate flight information of the target aircraft, thereby completing effective surveillance of the target aircraft.

[0064] In some embodiments, step S202 above calculates the confidence level of each monitoring device based on the device type of each monitoring device and the monitoring data of each monitoring device, including: calculating the confidence level of each monitoring device based on the order in which at least one monitoring device detects the target aircraft, the device type of each monitoring device, and the monitoring data of each monitoring device.

[0065] like Figure 3 As shown, the calculation of the confidence level of each monitoring device can be specifically implemented as follows: S301~S303: S301. If, among at least one monitoring device, only the first monitoring device detects the target aircraft, the confidence level of the first monitoring device is a preset confidence level.

[0066] For example, the first monitoring device is the first monitoring device to discover the target aircraft. Other monitoring devices have not yet discovered the target due to distance limitations. At this time, the confidence level of the monitoring data reported by the first monitoring device is 100%.

[0067] S302. When both the first and second monitoring devices in at least one monitoring device detect the target aircraft, the confidence level of the second monitoring device is determined based on the type of the second monitoring device and the monitoring data of the second monitoring device, and the confidence level of the first monitoring device is updated based on the confidence level of the second monitoring device.

[0068] For example, the second surveillance device is the second surveillance device to detect the target aircraft. When the target aircraft enters the effective detection range of the second surveillance device, based on the surveillance data reported by the second surveillance device, if the second surveillance device is a radar sensing device, the confidence level of the second surveillance device is determined to be X by calculating the observation noise covariance matrix of the second surveillance device. At this time, the confidence level of the first surveillance device is adjusted to 100%-X.

[0069] For example, the second monitoring device is the second monitoring device to detect the target aircraft. When the target aircraft enters the effective detection range of the second monitoring device, according to the monitoring data reported by the second monitoring device, if the second monitoring device is a visual observation device, the preset confidence level of the second monitoring device is X. At this time, the confidence level of the first monitoring device is adjusted to 100%-X.

[0070] S303. When the target aircraft is detected by all of the first, second, and third monitoring devices among at least one monitoring device, the confidence level of the third monitoring device is determined based on the type of the third monitoring device or the monitoring data of the third monitoring device, and the confidence level of the second monitoring device and the confidence level of the first monitoring device are updated based on the confidence level of the third monitoring device, the monitoring data of the second and third monitoring devices.

[0071] In some embodiments, updating the confidence levels of the second and first monitoring devices based on the confidence level of the third monitoring device, the monitoring data of the second and third monitoring devices, includes: updating the confidence level of the second monitoring device based on the confidence level of the third monitoring device and the ratio of the observation noise covariance matrix of the second and third monitoring devices; and further, updating the confidence level of the first monitoring device based on the confidence level of the third monitoring device and the updated confidence level of the second monitoring device.

[0072] The observation noise covariance matrix of the second monitoring device is determined based on the monitoring data of the second monitoring device, and the observation noise covariance matrix of the third monitoring device is determined based on the monitoring data of the third monitoring device.

[0073] For example, the third surveillance device is the third surveillance device to detect the target aircraft. When the target aircraft enters the effective detection range of the third surveillance device, the observation noise covariance matrix is ​​calculated based on the surveillance data of the third surveillance device, and the confidence level of the third surveillance device is determined to be C3. Subsequently, the confidence level is dynamically updated through the following steps: If based on the confidence level C3 of the third surveillance device and the norm ratio k of the observation noise covariance matrix of the third surveillance device and the second surveillance device, the confidence level of the second surveillance device is updated: C2 = C3 * k. Afterwards, based on the confidence level C3 of the third surveillance device and the updated confidence level of the second surveillance device, the confidence level of the first surveillance device is calculated: C1 = 100% - C2 - C3.

[0074] In some embodiments, if the confidence level of a certain monitoring device is determined to be 100%, the monitoring data reported by that monitoring device is directly used as the final fusion result, without the need for weighted fusion calculation of the monitoring data.

[0075] Based on the above embodiments, the confidence level of each monitoring device is calculated according to its type, based on the order in which the monitoring devices detect the target aircraft and the monitoring data of each device. When only one monitoring device detects the target aircraft, it is directly assigned the highest confidence level, allowing for rapid establishment of an initial trajectory from a single reliable data source, significantly shortening the initialization time for target acquisition and tracking. As more monitoring devices subsequently detect the target aircraft, the confidence levels of subsequent monitoring devices are used to correct the confidence levels of previous devices, establishing a collaborative verification mechanism for the monitoring devices. Then, based on the confidence levels of each monitoring device, the monitoring data of each device is fused, resulting in more accurate detection of the target aircraft.

[0076] The following describes a specific embodiment of the confidence-based data fusion method of this application. The specific implementation process of this method is as follows: Figure 4 As shown.

[0077] S401. Acquire surveillance data of the target aircraft from at least one surveillance device.

[0078] S402. If, among at least one monitoring device, only the first monitoring device detects the target aircraft, the confidence level of the first monitoring device is a preset confidence level.

[0079] S403. When both the first and second monitoring devices in at least one monitoring device detect the target aircraft, the confidence level of the second monitoring device is determined based on the type of the second monitoring device and the monitoring data of the second monitoring device, and the confidence level of the first monitoring device is updated based on the confidence level of the second monitoring device.

[0080] S404. When the target aircraft is detected by all of the first, second, and third monitoring devices among at least one monitoring device, the confidence level of the third monitoring device is determined based on the type of the third monitoring device or the monitoring data of the third monitoring device, and the confidence level of the second monitoring device and the confidence level of the first monitoring device are updated based on the confidence level of the third monitoring device, the monitoring data of the second and third monitoring devices.

[0081] S405. Use the confidence level of each monitoring device as the weight of the monitoring data of each monitoring device, and perform data fusion on the monitoring data of at least one monitoring device.

[0082] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0083] This application embodiment can divide the confidence-based data fusion device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0084] In some embodiments, this application also provides a confidence-based data fusion apparatus. This confidence-based data fusion apparatus may include one or more functional modules for implementing the confidence-based data fusion method described in the above method embodiments.

[0085] For example, Figure 5 This is a schematic diagram illustrating the composition of a data fusion apparatus provided in an embodiment of this application. Figure 5 As shown, the data fusion device 500 includes an acquisition module 501 and a processing module 502.

[0086] The acquisition module 501 is used to acquire surveillance data of the target aircraft from at least one surveillance device; the processing module 502 is used to calculate the confidence level of each surveillance device based on the device type and the surveillance data of each surveillance device for each of the at least one surveillance devices; the processing module 502 is also used to perform data fusion on the surveillance data of each surveillance device based on the confidence level of each surveillance device.

[0087] In some embodiments, the processing module 502 is specifically configured to: when the monitoring device is a visual observation device, set the confidence level of the monitoring device to a preset confidence level; when the monitoring device is a radar sensing device, determine the observation noise covariance matrix of the monitoring device based on the monitoring data of the monitoring device; and determine the confidence level of the monitoring device based on the observation noise covariance matrix of the monitoring device.

[0088] In other embodiments, the processing module 502 is specifically configured to calculate the confidence level of each monitoring device based on the order in which the target aircraft is detected by at least one monitoring device, the device type of each monitoring device, and the monitoring data of each monitoring device.

[0089] In some other embodiments, the processing module 502 is specifically configured to: when only the first monitoring device among at least one monitoring device detects the target aircraft, set the confidence level of the first monitoring device to a preset confidence level; when both the first and second monitoring devices among at least one monitoring device detect the target aircraft, determine the confidence level of the second monitoring device based on the type of the second monitoring device and the monitoring data of the second monitoring device, and update the confidence level of the first monitoring device based on the confidence level of the second monitoring device; when the first, second, and third monitoring devices among at least one monitoring device detect the target aircraft, determine the confidence level of the third monitoring device based on the type of the third monitoring device or the monitoring data of the third monitoring device, and update the confidence level of the second monitoring device and the confidence level of the first monitoring device based on the confidence level of the third monitoring device, the monitoring data of the second monitoring device, and the monitoring data of the third monitoring device.

[0090] In some other embodiments, the processing module 502 is specifically used to update the confidence level of the second monitoring device based on the confidence level of the third monitoring device and the ratio of the observation noise covariance matrix of the second monitoring device to that of the third monitoring device; wherein the observation noise covariance matrix of the second monitoring device is determined based on the monitoring data of the second monitoring device, and the observation noise covariance matrix of the third monitoring device is determined based on the monitoring data of the third monitoring device; and to update the confidence level of the first monitoring device based on the confidence level of the third monitoring device and the updated confidence level of the second monitoring device.

[0091] In some other embodiments, the processing module 502 is specifically used to perform data fusion on the monitoring data of at least one monitoring device by using the confidence level of each monitoring device as the weight of the monitoring data of each monitoring device.

[0092] In the case of implementing the functions of the integrated modules described above in hardware, this embodiment of the invention provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 6 As shown, the electronic device 600 includes: a processor 602, a communication interface 603, and a bus 604. Optionally, the electronic device 600 may also include a memory 601.

[0093] Processor 602 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 602 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 602 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0094] Communication interface 603 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0095] The memory 601 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0096] In one possible implementation, the memory 601 can exist independently of the processor 602. The memory 601 can be connected to the processor 602 via a bus 604 and is used to store instructions or program code. When the processor 602 calls and executes the instructions or program code stored in the memory 601, it can implement the confidence-based data fusion method provided in this embodiment of the invention.

[0097] In another possible implementation, the memory 601 can also be integrated with the processor 602.

[0098] Bus 604 can be an extended industry standard architecture (EISA) bus, etc. Bus 604 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0099] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0100] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware. The program can be stored in the aforementioned computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be any of the foregoing embodiments or memory. The aforementioned computer-readable storage medium can also be an external storage device of the aforementioned service invocation device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the aforementioned service invocation device. Further, the aforementioned computer-readable storage medium can include both internal storage units of the aforementioned service invocation device and external storage devices. The aforementioned computer-readable storage medium is used to store the aforementioned computer program and other programs and data required by the aforementioned service invocation device. The aforementioned computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0101] This application also provides a computer program product comprising a computer program that, when run on a computer, causes the computer to execute any of the confidence-based data fusion methods provided in the above embodiments.

[0102] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A confidence-based data fusion method, characterized in that, include: Acquire surveillance data of the target aircraft from at least one surveillance device; For each of the at least one monitoring device, the confidence level of each monitoring device is calculated based on the device type of each monitoring device and the monitoring data of each monitoring device; Data fusion is performed on the monitoring data of each monitoring device based on the confidence level of each monitoring device.

2. The method according to claim 1, characterized in that, The monitoring data includes at least one of the following: The target aircraft's altitude, speed, heading angle, and attitude.

3. The method according to claim 1, characterized in that, The step of calculating the confidence level of each monitoring device based on the device type and monitoring data of each monitoring device includes: When the monitoring device is a visual observation device, the confidence level of the monitoring device is the preset confidence level; When the monitoring device is a radar sensing device, the observation noise covariance matrix of the monitoring device is determined based on the monitoring data of the monitoring device; The confidence level of the monitoring device is determined based on the observation noise covariance matrix of the monitoring device.

4. The method according to claim 1, characterized in that, The step of calculating the confidence level of each monitoring device based on the device type and monitoring data of each monitoring device includes: The confidence level of each surveillance device is calculated based on the order in which the target aircraft is detected by the at least one surveillance device, the device type of each surveillance device, and the surveillance data of each surveillance device.

5. The method according to claim 4, characterized in that, The step of calculating the confidence level of each monitoring device based on the order in which the target aircraft was detected by the at least one monitoring device, the device type of each monitoring device, and the monitoring data of each monitoring device includes: If only the first monitoring device among the at least one monitoring device detects the target aircraft, the confidence level of the first monitoring device is the preset confidence level. If both the first and second monitoring devices in the at least one monitoring device detect the target aircraft, the confidence level of the second monitoring device is determined based on the type of the second monitoring device and the monitoring data of the second monitoring device, and the confidence level of the first monitoring device is updated based on the confidence level of the second monitoring device. If the first monitoring device, the second monitoring device, and the third monitoring device among the at least one monitoring device all detect the target aircraft, the confidence level of the third monitoring device is determined based on the type of the third monitoring device or the monitoring data of the third monitoring device, and the confidence level of the second monitoring device and the confidence level of the first monitoring device are updated based on the confidence level of the third monitoring device, the monitoring data of the second monitoring device, and the monitoring data of the third monitoring device.

6. The method according to claim 5, characterized in that, The step of updating the confidence levels of the second and first monitoring devices based on the confidence level of the third monitoring device, the monitoring data of the second and third monitoring devices, includes: The confidence level of the second monitoring device is updated based on the confidence level of the third monitoring device and the ratio of the observation noise covariance matrix of the second monitoring device to that of the third monitoring device; wherein, the observation noise covariance matrix of the second monitoring device is determined based on the monitoring data of the second monitoring device, and the observation noise covariance matrix of the third monitoring device is determined based on the monitoring data of the third monitoring device. The confidence level of the first monitoring device is updated based on the confidence level of the third monitoring device and the updated confidence level of the second monitoring device.

7. The method according to claim 1, characterized in that, The data fusion based on the confidence level of each monitoring device includes: The confidence level of each monitoring device is used as the weight of the monitoring data of each monitoring device, and the monitoring data of at least one monitoring device are fused.

8. A confidence-based data fusion device, characterized in that, include: Acquisition module and processing module; The acquisition module is used to acquire surveillance data of the target aircraft from at least one surveillance device; The processing module is configured to calculate the confidence level of each monitoring device based on the device type and monitoring data of each monitoring device for each of the at least one monitoring device. The processing module is used to perform data fusion on the monitoring data of each monitoring device based on the confidence level of each monitoring device.

9. An electronic device, characterized in that, The device includes a processor and a memory, the processor being coupled to the memory; the memory is used to store computer instructions, which are loaded and executed by the processor to enable the computer device to implement the confidence-based data fusion method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer-executable instructions that, when executed on a computer, cause the computer to perform the confidence-based data fusion method as described in any one of claims 1 to 8.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when run on an electronic device, causes the electronic device to perform the confidence-based data fusion method as described in any one of claims 1 to 8.

Images