A distributed passive heterogeneous sensor situation generation method

Abstract

This invention discloses a distributed passive heterogeneous sensor situational awareness generation method, belonging to the field of distributed situational awareness technology. The method includes: deploying passive heterogeneous sensors to collect multi-dimensional data; employing an adaptive edge computing network to dynamically select the optimal computing node and preprocessing the target situational data through the optimal computing node; dynamically calculating the weight of each passive heterogeneous sensor in data fusion through an intelligent weight adjustment mechanism; fusing the preprocessed target situational data using a multi-source data fusion algorithm based on the weight of each passive heterogeneous sensor in data fusion to construct a local situational awareness map; using a self-organizing network to share and coordinate the local situational awareness map; and fusing the local situational awareness map through a distributed consensus algorithm to generate a global situational awareness map. This invention effectively improves the real-time performance, reliability, and accuracy of situational awareness in complex environments by generating a global situational awareness map through multi-source data fusion and distributed consensus algorithms.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed situation awareness, and in particular to a distributed passive heterogeneous sensor situation generation method. Background Art

[0002] With the development of sensor technology, distributed situational awareness has been widely used in many application fields, such as intelligent transportation, border protection, machine monitoring and other scenarios, using various types of sensors to collect information about the environment and targets to build a real-time situational awareness map. In particular, the application of passive heterogeneous sensors (such as optical, acoustic, infrared and microwave sensors) can detect targets without actively emitting signals, and has the advantages of strong concealment and low energy consumption. These passive heterogeneous sensors can capture multi-dimensional information of the target, thereby providing comprehensive data support for situational awareness. In recent years, with the advancement of edge computing and Internet of Things technologies, passive heterogeneous sensors based on distributed architecture have gradually become a research hotspot for situational awareness. Through a distributed architecture, passive heterogeneous sensor nodes in different regions can work together, which not only improves the coverage and accuracy of data, but also enhances the response speed and real-time performance.

[0003] However, existing distributed passive heterogeneous sensors still face some technical bottlenecks. First, for the fusion problem of multi-source sensor data, most existing technologies adopt a fixed weight fusion method, which fails to fully consider the dynamic factors such as signal quality, perception range, and delay of each passive heterogeneous sensor in different environments, which makes it difficult to ensure the accuracy and reliability of the fusion results. Secondly, in the process of generating local situation maps and sharing and fusion of global situation maps, existing technologies lack an effective conflict resolution mechanism, making it difficult to evaluate and screen the credibility of data in overlapping areas between multiple nodes, resulting in poor accuracy and consistency of the global situation map. These problems not only limit the scalability and flexibility, but also affect the intelligence level of situation awareness. Especially in complex environments, the accuracy and real-time performance of data fusion are difficult to meet actual needs. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a distributed passive heterogeneous sensor situation generation method to solve the problems in the prior art that the data fusion weight cannot be dynamically adjusted and the credibility assessment of the overlapping area data is insufficient.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a distributed passive heterogeneous sensor situation generation method, comprising:

[0008] Deploy passive heterogeneous sensors to collect multi-dimensional data; use an adaptive edge computing network to dynamically select the optimal computing node, and pre-process the target situation data through the optimal computing node; dynamically calculate the weight of each passive heterogeneous sensor in data fusion through an intelligent weight adjustment mechanism; use a multi-source data fusion algorithm to fuse the pre-processed target situation data according to the weight of each passive heterogeneous sensor in data fusion to construct a local situation map; use a self-organizing network to share and collaborate on the local situation map, and fuse the local situation map through a distributed consistency algorithm to generate a global situation map.

[0009] As a preferred solution of the distributed passive heterogeneous sensor situation generation method of the present invention, the passive heterogeneous sensor includes an optical sensor, an acoustic sensor, an infrared sensor and a microwave sensor;

[0010] The multi-dimensional data includes passive heterogeneous sensor parameters, target situation data and environmental data.

[0011] As a preferred solution of the distributed passive heterogeneous sensor situation generation method of the present invention, wherein the adaptive edge computing network is used to dynamically select the optimal computing node, and the target situation data is preprocessed by the optimal computing node. The specific steps are as follows:

[0012] Passive heterogeneous sensors transmit the collected passive heterogeneous sensor parameters to the nearest edge computing node through a low-latency wireless communication protocol;

[0013] When the edge computing node receives the passive heterogeneous sensor parameters, the priority scores of all currently available edge computing nodes are evaluated in real time through the adaptive edge computing network. The expression is:

[0014] ;

[0015] in, represents the computing power of edge computing node i, represents the bandwidth of edge computing node i, represents the network delay of edge computing node i, represents the priority score of edge computing node i;

[0016] Based on the calculated priority score of each edge computing node , select the edge computing node with the highest priority as the optimal computing node;

[0017] On the optimal computing node, the target situation data is denoised by frequency domain filters and standardized by unified data format and time synchronization.

[0018] As a preferred solution of the distributed passive heterogeneous sensor situation generation method of the present invention, the weight of each passive heterogeneous sensor in data fusion is dynamically calculated through an intelligent weight adjustment mechanism, and the specific steps are as follows:

[0019] Based on the signal quality, sensing range, accuracy, delay and environmental interference of each passive heterogeneous sensor, the logarithmic function and the smoothing function are combined to form an intelligent weight adjustment mechanism to dynamically calculate the weight of each passive heterogeneous sensor in data fusion. The expression is:

[0020] ;

[0021] in, is the weight of the jth passive heterogeneous sensor in data fusion, is the signal quality of the jth passive heterogeneous sensor, is the sensing range of the jth passive heterogeneous sensor, is the measurement accuracy of the jth passive heterogeneous sensor, is the delay of the jth passive heterogeneous sensor, is the degree to which the jth passive heterogeneous sensor is affected by the environmental data.

[0022] As a preferred solution of the distributed passive heterogeneous sensor situation generation method of the present invention, the pre-processed target situation data is fused using a multi-source data fusion algorithm according to the weight of each passive heterogeneous sensor in data fusion to construct a local situation map. The specific steps are as follows:

[0023] The weighted average method is used to perform preliminary data fusion on the preprocessed target situation data according to its weight, and the preliminary fused data is recursively updated through Kalman filtering to generate fused data. The expression is:

[0024] ;

[0025] in, is the fused data after the k+1th iteration update, represents the fused data at time t, represents the target situation data collected by the jth passive heterogeneous sensor at time t, n is the total number of passive heterogeneous sensors, represents the credibility of the target situation data of the i-th edge computing node, is the observation matrix, k represents the current iteration number, is the fused data after the k-th iteration update;

[0026] Based on fusion data , the location information of the target is mapped to the map through GIS, and the current real-time location of the target is drawn. At the same time, the historical location information of the target is recorded through time series data, and the movement trajectory of the target is constructed in the form of connecting lines. The environmental data is presented in the final local situation map through ArcGIS.

[0027] As a preferred solution of the distributed passive heterogeneous sensor situation generation method of the present invention, the self-organizing network is used to share and collaborate on the local situation map, and the local situation map is fused through a distributed consistency algorithm to generate a global situation map. The specific steps are as follows:

[0028] Initialize the edge computing nodes. Each edge computing node discovers neighbor nodes through the broadcast mechanism. After discovering the neighbor nodes, it establishes a communication link through a low-latency wireless communication protocol and automatically generates a network topology.

[0029] When the edge computing node updates the local situation map, the self-organizing network shares the updated local situation map with neighboring nodes based on the broadcast mechanism;

[0030] When the local situation map of the edge computing node is shared and coordinated through the self-organizing network, when it receives the local situation map of the neighboring node, it compares the received local situation map with its own local situation map through the regional coverage detection method to analyze the overlapping area;

[0031] A conflict resolution mechanism is used to filter out the trusted target situation data in the overlapping area, and a distributed consistency algorithm is used to coordinate and update all local situation maps. The local situation maps of multiple neighboring nodes are fused to generate a global situation map covering the entire self-organizing network.

[0032] As a preferred solution of the distributed passive heterogeneous sensor situation generation method of the present invention, a conflict resolution mechanism is used to filter out the credible target situation data in the overlapping area. The specific steps are as follows:

[0033] After the overlapping area is detected, the target situation data of each edge computing node is analyzed for differences, and the credibility of the target situation data of each edge computing node is calculated by combining the priority score, timestamp and transmission delay of each edge computing node. The expression is:

[0034] ;

[0035] in, represents the credibility of the target situation data of the i-th edge computing node, is a constant. is the timestamp of the data of the i-th edge computing node, is the earliest timestamp among all edge computing nodes. is the latest timestamp among all edge computing nodes. represents the priority score of edge computing node i;

[0036] Credibility scoring of edge computing nodes based on historical data , define the credibility standard threshold θ;

[0037] when ≥θ, the target situation data of the current edge computing node is considered to be credible;

[0038] when <θ, the target situation data of the current edge computing node is considered unreliable.

[0039] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, any step of the distributed passive heterogeneous sensor situation generation method as described in the first aspect of the present invention is implemented.

[0040] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the distributed passive heterogeneous sensor situation generation method as described in the first aspect of the present invention.

[0041] The beneficial effects of the present invention are as follows: by adopting an adaptive edge computing network to dynamically select the optimal computing node and an intelligent weight adjustment mechanism to dynamically calculate the weights of passive heterogeneous sensors, efficient processing and precise fusion of a large amount of passive heterogeneous sensor data is achieved. The adaptive edge computing network dynamically selects the optimal computing node for data preprocessing, ensuring the high efficiency and low latency of data processing. The intelligent weight adjustment mechanism dynamically adjusts the weight of each passive heterogeneous sensor in data fusion to ensure the accuracy and robustness of the fusion result. Finally, a global situation map is generated through a multi-source data fusion algorithm and a distributed consistency algorithm, which effectively improves the real-time, reliability and situational awareness accuracy of distributed passive heterogeneous sensors in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0043] Figure 1 This is a flow chart of the distributed passive heterogeneous sensor situation generation method in Example 1;

[0044] Figure 2 This is a flow chart for generating a global situation map in Example 1. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0048] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a distributed passive heterogeneous sensor situation generation method, comprising the following steps:

[0049] S1: Deploy passive heterogeneous sensors to collect multi-dimensional data.

[0050] Passive heterogeneous sensors include optical sensors, acoustic sensors, infrared sensors, and microwave sensors.

[0051] Multidimensional data includes passive heterogeneous sensor parameters, target situation data and environmental data.

[0052] Furthermore, the passive heterogeneous sensor parameters include the operating frequency range, detection angle, signal gain and response time of the passive heterogeneous sensor.

[0053] Target situation data includes the target's direction, distance, speed, and movement mode.

[0054] Environmental data includes terrain information, temperature, humidity, and background noise intensity.

[0055] S2: Adopt an adaptive edge computing network, dynamically select the optimal computing node, and pre-process the target situation data through the optimal computing node.

[0056] Passive heterogeneous sensors transmit the collected passive heterogeneous sensor parameters to the nearest edge computing node through a low-latency wireless communication protocol.

[0057] When the edge computing node receives the passive heterogeneous sensor parameters, the priority scores of all currently available edge computing nodes are evaluated in real time through the adaptive edge computing network. The expression is:

[0058] ;

[0059] in, represents the computing power of edge computing node i, represents the bandwidth of edge computing node i, represents the network delay of edge computing node i, Represents the priority score of edge computing node i.

[0060] It should be noted that the adaptive edge computing network is a network architecture that dynamically optimizes the allocation of computing resources. It evaluates the computing power, bandwidth, network latency and other parameters of edge computing nodes in real time, calculates the priority score of each edge computing node, and selects the edge computing node with the highest priority score for data processing. The network can flexibly adjust the allocation of computing tasks according to the changes in the status of edge computing nodes to ensure the efficiency, low latency and reliability of data processing. It is particularly suitable for real-time data processing tasks of distributed, passive heterogeneous sensors.

[0061] Based on the calculated priority score of each edge computing node , select the edge computing node with the highest priority as the optimal computing node.

[0062] It should be noted that the reason for selecting the edge computing node with the highest priority score as the optimal computing node is that the priority score The computing power, bandwidth and network latency of edge computing nodes are comprehensively considered, which directly affect the efficiency and response speed of edge computing nodes in processing tasks. By selecting the edge computing node with the highest priority score, it can ensure that the computing task is executed on the most advantageous edge computing node at the moment, thereby maximizing computing efficiency, reducing data processing latency, and improving the real-time performance and resource utilization of the entire network.

[0063] On the optimal computing node, the target situation data is denoised by frequency domain filters and standardized by unified data format and time synchronization.

[0064] Specifically, the target situation data is denoised through a frequency domain filter, which converts the collected target situation data into the frequency domain, identifies and removes high-frequency noise or low-frequency interference, and extracts a purer effective signal. Then, the denoised target situation data is standardized, including unifying the target situation data from different passive heterogeneous sensors into the same format (such as a unified unit or data structure), and aligning the timestamps of different passive heterogeneous sensors through time synchronization to ensure that the target situation data is processed and fused on the same time basis to ensure the accuracy and consistency of multi-dimensional data.

[0065] The target situation data generated by different passive heterogeneous sensors are converted into a unified format, and the timestamps of each passive heterogeneous sensor are aligned through time synchronization to ensure that the multi-dimensional data are fused on the same time basis.

[0066] S3: Dynamically calculate the weight of each passive heterogeneous sensor in data fusion through an intelligent weight adjustment mechanism.

[0067] Based on the signal quality, sensing range, accuracy, delay and environmental interference of each passive heterogeneous sensor, the logarithmic function and the smoothing function are combined to form an intelligent weight adjustment mechanism to dynamically calculate the weight of each passive heterogeneous sensor in data fusion. The expression is:

[0068] ;

[0069] in, is the weight of the jth passive heterogeneous sensor in data fusion, is the signal quality of the jth passive heterogeneous sensor, is the sensing range of the jth passive heterogeneous sensor, is the measurement accuracy of the jth passive heterogeneous sensor, is the delay of the jth passive heterogeneous sensor, is the degree to which the jth passive heterogeneous sensor is affected by the environmental data.

[0070] It should be noted that the jth passive heterogeneous sensor is affected by the environmental data , the expression is:

[0071] ;

[0072] in, represents the impact of meteorological data on the jth passive heterogeneous sensor, represents the impact of optical interference on the jth passive heterogeneous sensor, represents the impact of electromagnetic interference on the jth passive heterogeneous sensor, represents the impact of acoustic interference on the jth passive heterogeneous sensor.

[0073] It should also be noted that through the intelligent weight adjustment mechanism, the weight of each passive heterogeneous sensor in data fusion is dynamically calculated based on multiple factors such as signal quality, perception range, measurement accuracy, delay and environmental interference, ensuring that in the data fusion process, passive heterogeneous sensors with higher weights can affect the final result to a greater extent, thereby improving the accuracy and reliability of the fused data and achieving more accurate situational awareness and decision support.

[0074] S4: According to the weight of each passive heterogeneous sensor in data fusion, the pre-processed target situation data is fused using a multi-source data fusion algorithm to construct a local situation map.

[0075] The weighted average method is used to perform preliminary data fusion on the preprocessed target situation data according to its weight, and the preliminary fused data is recursively updated through Kalman filtering to generate fused data. The expression is:

[0076] ;

[0077] in, is the fused data after the k+1th iteration update, represents the fused data at time t, represents the target situation data collected by the jth passive heterogeneous sensor at time t, n is the total number of passive heterogeneous sensors, represents the credibility of the target situation data of the i-th edge computing node, is the observation matrix, k represents the current iteration number, is the fused data after the k-th iteration update.

[0078] It should be noted that the observation matrix H is a key matrix in Kalman filtering, which is used to map the state space to the observation space of passive heterogeneous sensors. It describes how the state variables affect the observation values ​​of passive heterogeneous sensors and defines the linear relationship between the state and the observation values.

[0079] Based on fusion data , the location information of the target is mapped to the map through GIS, and the current real-time location of the target is drawn. At the same time, the historical location information of the target is recorded through time series data, and the movement trajectory of the target is constructed in the form of connecting lines. The environmental data is presented in the final local situation map through ArcGIS.

[0080] It should be noted that by mapping the target location information through GIS, the location information of the target (such as longitude and latitude coordinates) is mapped to the actual map using the Geographic Information System (GIS). In this process, the coordinate data of the target is converted into a specific location point on the map, and is visualized on the map through a marking tool, thereby intuitively displaying the real-time location of the target, which is convenient for users to monitor and track the situation.

[0081] Environmental data is presented through ArcGIS. Using ArcGIS software, the collected environmental data (such as temperature, humidity, wind speed, etc.) is associated with the corresponding geographical area, and the information is intuitively presented on the final local situation map through data layer overlay technology. Each type of environmental data can be visualized through different colors, symbols or heat maps, so that users can intuitively understand the environmental conditions of each area, assist in decision-making and situation analysis.

[0082] S5: Use a self-organizing network to share and collaborate on local situation maps, and use a distributed consistency algorithm to fuse local situation maps to generate a global situation map.

[0083] The edge computing nodes are initialized. Each edge computing node discovers neighbor nodes through the broadcast mechanism. After discovering the neighbor nodes, a communication link is established through a low-latency wireless communication protocol to automatically generate a network topology.

[0084] When the edge computing node updates the local situation map, the self-organizing network shares the updated local situation map with neighboring nodes based on the broadcast mechanism.

[0085] When the local situation map of the edge computing node is shared and coordinated through the self-organizing network, when it receives the local situation map of the neighboring node, it compares the received local situation map with its own local situation map through the regional coverage detection method to analyze the overlapping area.

[0086] Furthermore, through the regional coverage detection method, the received local situation map is compared with its own local situation map to analyze the overlapping area. The specific steps are as follows: First, based on the regional division in the geographic space, the local situation maps of both parties are divided into several corresponding grids or regional units. Then, the situation information (such as target location, threat level, environmental data, etc.) in each corresponding area is compared one by one to detect differences or conflicts in the overlapping area. These differences may include target location deviation, inconsistent environmental data, etc. Finally, the comparison results are analyzed according to preset rules (such as data credibility, timestamp priority, etc.) to identify target situation data with higher accuracy.

[0087] A conflict resolution mechanism is used to filter out the trusted target situation data in the overlapping area, and a distributed consistency algorithm is used to coordinate and update all local situation maps. The local situation maps of multiple neighboring nodes are fused to generate a global situation map covering the entire self-organizing network.

[0088] It should be noted that the global situation map is a comprehensive and unified situation display map generated by integrating local situation maps collected by multiple edge computing nodes or passive heterogeneous sensors through data fusion and conflict resolution mechanisms. It covers information such as target location, movement trajectory, environmental conditions, threat level, etc. in the entire monitoring area, reflecting the current overall situation from a macro perspective. The global situation map can be updated in real time and ensure the consistency and accuracy of information between various regions. It is an important tool for decision support and situation awareness, helping users make global judgments and responses in complex environments.

[0089] The conflict resolution mechanism is used to filter out the credible target situation data in the overlapping area. The specific steps are as follows:

[0090] After the overlapping area is detected, the target situation data of each edge computing node is analyzed for differences, and the credibility of the target situation data of each edge computing node is calculated by combining the priority score, timestamp and transmission delay of each edge computing node. The expression is:

[0091] ;

[0092] in, represents the credibility of the target situation data of the i-th edge computing node, is a constant. is the timestamp of the data of the i-th edge computing node, is the earliest timestamp among all edge computing nodes. is the latest timestamp among all edge computing nodes. Represents the priority score of edge computing node i.

[0093] Credibility scoring of edge computing nodes based on historical data , define the credibility standard threshold θ;

[0094] when ≥θ, the target situation data of the current edge computing node is considered to be credible.

[0095] when <θ, the target situation data of the current edge computing node is considered unreliable.

[0096] It should be noted that through the self-organizing network and distributed consistency algorithm, efficient sharing and fusion of local situation maps are achieved to generate a global situation map. The target situation data in the overlapping area are analyzed and screened by using the regional coverage detection method and conflict resolution mechanism to ensure that the fused data is improved in terms of accuracy, consistency and reliability. The credibility is calculated based on the priority score, timestamp and transmission delay of each edge computing node, and the credibility threshold is used to filter out the credible data, which effectively avoids the participation of inaccurate information caused by noise or delay of passive heterogeneous sensors in fusion. This method not only enhances the situation awareness capability in complex environments, but also improves the timeliness and decision support capability of the global situation map, ensuring the stability and robustness of the information fusion process.

[0097] This embodiment also provides a computer device, which is applicable to the distributed passive heterogeneous sensor situation generation method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the distributed passive heterogeneous sensor situation generation method proposed in the above embodiment.

[0098] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0099] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the distributed passive heterogeneous sensor situation generation method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0100] In summary, the present invention realizes efficient processing and precise fusion of a large amount of passive heterogeneous sensor data by adopting an adaptive edge computing network to dynamically select the optimal computing node and an intelligent weight adjustment mechanism to dynamically calculate the weight of passive heterogeneous sensors. The adaptive edge computing network dynamically selects the optimal computing node for data preprocessing, ensuring the high efficiency and low latency of data processing. The intelligent weight adjustment mechanism dynamically adjusts the weight of each passive heterogeneous sensor in data fusion to ensure the accuracy and robustness of the fusion result. Finally, a global situation map is generated through a multi-source data fusion algorithm and a distributed consistency algorithm, which effectively improves the real-time, reliability and situational awareness accuracy of distributed passive heterogeneous sensors in complex environments.

[0101] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a distributed passive heterogeneous sensor situation generation method is provided.

[0102] In this embodiment, a group of passive heterogeneous sensor networks are deployed, including optical sensors, acoustic sensors, infrared sensors and microwave sensors, which are used to collect multi-dimensional data of the target (such as the precise position of the target, movement speed, environmental parameters, signal strength and noise, etc.). The purpose of the experiment is to evaluate the performance of the distributed passive heterogeneous sensor situation generation method of the present invention and compare it with the prior art.

[0103] First, a group of passive heterogeneous sensors, including optical, acoustic, infrared and microwave sensors, were deployed in a designated area to collect multi-dimensional data of targets and environments. Passive heterogeneous sensors transmit data to the nearest edge computing node through a low-latency wireless communication protocol. The system relies on the adaptive edge computing network to dynamically select the optimal computing node and pre-process the target situation data in the multi-dimensional data, including denoising, time synchronization and standardization operations.

[0104] Secondly, the intelligent weight adjustment mechanism is used to dynamically calculate the weight of each passive heterogeneous sensor in data fusion according to factors such as signal quality, sensing range, accuracy, delay and environmental interference of passive heterogeneous sensors, ensuring that the data of high-quality passive heterogeneous sensors has a greater weight in fusion. Subsequently, a multi-source data fusion algorithm is used to fuse the pre-processed data through weighted averaging and Kalman filtering to generate a local situation map of each edge computing node.

[0105] Then, the local situation map is shared and coordinated through the self-organizing network. After each edge computing node receives the situation map of the neighboring node, it uses the regional coverage detection method to compare the overlapping areas and analyze the differences in the target situation data. Through the conflict resolution mechanism, based on parameters such as timestamp, priority and transmission delay, the reliable target situation data is screened out, and the local situation map is fused using the distributed consistency algorithm.

[0106] Finally, the experiment verifies the advantages of the present invention by comparing the key indicators of the generation time, accuracy and network delay of the global situation map of the prior art and the present invention. The experimental results show that the present invention is significantly better than the prior art in terms of shortening the generation time of the global situation map, improving the situation accuracy and reducing the network delay, which proves the effectiveness of the method of the present invention in practical applications.

[0107] The existing technical method in this experiment is a data fusion method based on a centralized server and fixed weights, that is, all passive heterogeneous sensors (such as optical, acoustic, infrared and microwave sensors) collect multi-dimensional data of the target respectively, and transmit it to the centralized server through a wireless communication protocol. The server uses pre-set fixed weights to perform weighted average fusion on the data of various passive heterogeneous sensors to generate a situation map. These weights are fixed throughout the process and cannot be adjusted according to the real-time signal quality of the passive heterogeneous sensors or environmental changes. Finally, the server uniformly generates a situation map of the target.

[0108] The details are shown in Table 1 below:

[0109] Table 1 Performance comparison of distributed passive heterogeneous sensor situation generation methods

[0110]

[0111] Through the data analysis of the above table, it can be clearly seen that the present invention has significant advantages over the prior art in terms of situation map generation time, accuracy and network delay. The present invention can process passive heterogeneous sensor data faster through an adaptive edge computing network and an intelligent weight adjustment mechanism, and dynamically adjust the edge computing nodes and the weights of passive heterogeneous sensors, thereby improving system performance. For example, in node 1, the situation map generation time of the present invention is 2.21 seconds, which is 38% less than 3.57 seconds in the prior art. At the same time, the accuracy of the situation map of the present invention is 92.3%, which is 6.9% higher than 85.4% in the prior art. In terms of network delay, the delay of the present invention in node 1 is 83 milliseconds, which is significantly lower than 137 milliseconds in the prior art, a decrease of 39.4%. These data show that the present invention significantly improves the efficiency and accuracy of situation generation by optimizing edge computing node selection and intelligently adjusting the weights of passive heterogeneous sensors, effectively overcoming the problems of high delay and low accuracy in the prior art.

[0112] The distributed passive heterogeneous sensor situation generation method of the present invention can not only significantly improve the speed of situation map generation and reduce processing delays, but also dynamically adjust the weights of passive heterogeneous sensors to enhance the accuracy of data fusion. This reflects the adaptability and efficiency of the present invention in complex environments, and can quickly and accurately integrate multi-dimensional data from multi-source heterogeneous sensors to generate a real-time global situation map, thereby effectively improving overall perception and real-time response capabilities.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A distributed passive heterogeneous sensor situation generation method, characterized in that: include: Deploy passive heterogeneous sensors to collect multi-dimensional data; Adopting adaptive edge computing network, dynamically selecting optimal computing nodes, and preprocessing target situation data through the optimal computing nodes; Through the intelligent weight adjustment mechanism, the weight of each passive heterogeneous sensor in data fusion is dynamically calculated; According to the weight of each passive heterogeneous sensor in data fusion, a multi-source data fusion algorithm is used to fuse the pre-processed target situation data to construct a local situation map; Adopt self-organizing network to share and coordinate local situation maps, and integrate local situation maps through distributed consistency algorithm to generate global situation maps; The passive heterogeneous sensors include optical sensors, acoustic sensors, infrared sensors and microwave sensors; The multi-dimensional data includes passive heterogeneous sensor parameters, target situation data and environmental data; The weight of each passive heterogeneous sensor in data fusion is dynamically calculated through the intelligent weight adjustment mechanism. The specific steps are as follows: Based on the signal quality, sensing range, accuracy, delay and environmental interference of each passive heterogeneous sensor, the logarithmic function and the smoothing function are combined to form an intelligent weight adjustment mechanism to dynamically calculate the weight of each passive heterogeneous sensor in data fusion. The expression is: ； in, is the weight of the jth passive heterogeneous sensor in data fusion, is the signal quality of the jth passive heterogeneous sensor, is the sensing range of the jth passive heterogeneous sensor, is the measurement accuracy of the jth passive heterogeneous sensor, is the delay of the jth passive heterogeneous sensor, is the degree to which the jth passive heterogeneous sensor is affected by the environmental data.

2. The distributed passive heterogeneous sensor situation generation method according to claim 1, characterized in that: The adaptive edge computing network is used to dynamically select the optimal computing node, and the target situation data is preprocessed through the optimal computing node. The specific steps are as follows: Passive heterogeneous sensors transmit the collected passive heterogeneous sensor parameters to the nearest edge computing node through a low-latency wireless communication protocol; When the edge computing node receives the passive heterogeneous sensor parameters, the priority scores of all currently available edge computing nodes are evaluated in real time through the adaptive edge computing network. The expression is: ； in, represents the computing power of edge computing node i, represents the bandwidth of edge computing node i, represents the network delay of edge computing node i, represents the priority score of edge computing node i; Based on the calculated priority score of each edge computing node , select the edge computing node with the highest priority as the optimal computing node; On the optimal computing node, the target situation data is denoised by frequency domain filters and standardized by unified data format and time synchronization.

3. The distributed passive heterogeneous sensor situation generation method according to claim 2, characterized in that: According to the weight of each passive heterogeneous sensor in data fusion, a multi-source data fusion algorithm is used to fuse the pre-processed target situation data to construct a local situation map. The specific steps are as follows: The weighted average method is used to perform preliminary data fusion on the preprocessed target situation data according to its weight, and the preliminary fused data is recursively updated through Kalman filtering to generate fused data. The expression is: ； in, is the fused data after the k+1th iteration update, represents the fused data at time t, represents the target situation data collected by the jth passive heterogeneous sensor at time t, n is the total number of passive heterogeneous sensors, represents the credibility of the target situation data of the i-th edge computing node, is the observation matrix, k represents the current iteration number, is the fused data after the k-th iteration update; Based on fusion data , the location information of the target is mapped to the map through GIS, and the current real-time location of the target is drawn. At the same time, the historical location information of the target is recorded through time series data, and the movement trajectory of the target is constructed in the form of connecting lines. The environmental data is presented in the final local situation map through ArcGIS.

4. The distributed passive heterogeneous sensor situation generation method according to claim 3, characterized in that: The self-organizing network is used to share and coordinate the local situation map, and the local situation map is integrated through the distributed consistency algorithm to generate the global situation map. The specific steps are as follows: Initialize the edge computing nodes. Each edge computing node discovers neighbor nodes through the broadcast mechanism. After discovering the neighbor nodes, it establishes a communication link through a low-latency wireless communication protocol and automatically generates a network topology. When the edge computing node updates the local situation map, the self-organizing network shares the updated local situation map with neighboring nodes based on the broadcast mechanism; When the local situation map of the edge computing node is shared and coordinated through the self-organizing network, when it receives the local situation map of the neighboring node, it compares the received local situation map with its own local situation map through the regional coverage detection method to analyze the overlapping area; A conflict resolution mechanism is used to filter out the trusted target situation data in the overlapping area, and a distributed consistency algorithm is used to coordinate and update all local situation maps. The local situation maps of multiple neighboring nodes are fused to generate a global situation map covering the entire self-organizing network.

5. The distributed passive heterogeneous sensor situation generation method according to claim 4, characterized in that: The conflict resolution mechanism is used to filter out the credible target situation data in the overlapping area. The specific steps are as follows: After the overlapping area is detected, the target situation data of each edge computing node is analyzed for differences, and the credibility of the target situation data of each edge computing node is calculated by combining the priority score, timestamp and transmission delay of each edge computing node. The expression is: ； in, represents the credibility of the target situation data of the i-th edge computing node, is a constant. is the timestamp of the data of the i-th edge computing node, Is the earliest timestamp among all edge computing nodes, is the latest timestamp among all edge computing nodes. represents the priority score of edge computing node i; Credibility scoring of edge computing nodes based on historical data , define the credibility standard threshold θ; when ≥θ, the target situation data of the current edge computing node is considered to be credible; when <θ, the target situation data of the current edge computing node is considered unreliable.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the distributed passive heterogeneous sensor situation generation method described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the distributed passive heterogeneous sensor situation generation method described in any one of claims 1 to 5 are implemented.

Images