A positioning system for cross-scenario multi-mode communication

CN122525490APending Publication Date: 2026-08-07GUIZHOU INST OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
GUIZHOU INST OF TECH
Filing Date
2026-07-09
Publication Date
2026-08-07

AI Technical Summary

Technical Problem

[0003]然而,在实际应用场景中,用户往往需要在不同的场景之间频繁切换,当用户从室外进入室内或从室内走向室外时,由于环境变化导致单一信号失效或精度骤降,定位结果容易出现误差,无法在跨场景切换时保持稳定

Benefits of technology

[0014]与现有技术相比,本发明的有益效果是:通过获取信号、声音和图像多模数据并提取特征,判别终端当前所处场景类型,由室外权重对视觉定位坐标与信号及声音融合得到的室内融合坐标进行加权计算,使定位结果在室内外场景切换时平滑过渡,避免了传统定位系统因单一信号失效导致的定位中断或精度下降,提高了跨场景下定位的稳定性与准确性。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122525490A_ABST
    Figure CN122525490A_ABST
Patent Text Reader

Abstract

The application discloses a positioning system for cross-scene multi-mode communication and relates to the technical field of spatial positioning. The positioning system comprises a network construction module, a data acquisition module, a data analysis module, a multi-mode communication module, a data storage module and a positioning and navigation module. The network construction module deploys sensors and communication nodes to form a fusion sensing and communication network and establishes a three-dimensional coordinate system. The data acquisition module acquires multi-mode data of signals, sound and images and extracts features. The data analysis module identifies scene types and fuses and calculates three-dimensional coordinates of a terminal. The multi-mode communication module establishes a communication link to transmit coordinates. The positioning and navigation module calculates an optimal path and outputs navigation guidance. The application weights and fuses multi-mode positioning coordinates by identifying scene types, realizes cross-scene positioning, and improves positioning stability and accuracy during scene switching.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of spatial positioning technology, specifically a positioning system with cross-scenario multi-mode communication. Background Technology

[0002] With the increasing demand for location services in smart campuses and smart parks, location technology plays an important role in daily navigation, personnel management, and emergency dispatch. Traditional location technology usually relies on single data for positioning.

[0003] However, in real-world applications, users often need to switch frequently between different scenarios. When a user moves from outdoors to indoors or from indoors to outdoors, the location results are prone to errors due to the failure of a single signal or a sharp drop in accuracy caused by environmental changes. The location results cannot remain stable when switching between scenarios.

[0004] How to jointly determine the scene type through multi-mode data and maintain the continuity and stability of positioning when switching between indoor and outdoor scenes is a problem we need to solve. To this end, we now provide a positioning system with cross-scene multi-mode communication. Summary of the Invention

[0005] The purpose of this invention is to provide a positioning system with cross-scenario multi-mode communication.

[0006] The objective of this invention can be achieved through the following technical solution: a positioning system with cross-scenario multi-mode communication, comprising: The network construction module is used to deploy sensors and communication nodes to form a fusion sensing and communication network, establish a three-dimensional coordinate system, and perform position calibration and obtain three-dimensional coordinates for sensors and communication nodes. The data acquisition module is used to connect the terminal to the fusion sensing and communication network, acquire multi-modal data around the terminal, preprocess the multi-modal data and extract features to obtain a multi-modal dataset and upload it. The data analysis module is used to receive multi-modal datasets, determine the current scene type of the terminal, and calculate the current three-dimensional coordinates of the terminal based on the scene type; The multi-mode communication module is used to establish a communication link by utilizing the fusion sensing and communication network, and send the current three-dimensional coordinates of the terminal to the data storage module; The data storage module is used to store the three-dimensional coordinates of the terminal and the three-dimensional coordinates of the destination; The positioning and navigation module is used to retrieve the three-dimensional coordinates of the terminal and the three-dimensional coordinates of the destination, calculate the optimal path, and output navigation guidance.

[0007] Preferably, the process of deploying sensors and communication nodes in the network building module to form a converged sensing and communication network includes: Sensors and communication nodes are deployed within the target area to establish communication connections and form a fusion sensing and communication network. A three-dimensional coordinate system is established with the geometric center of the target area as the origin, and the positions of each node are calibrated and the three-dimensional coordinates are obtained.

[0008] Preferably, the process by which the data acquisition module acquires multi-modal data and performs preprocessing and feature extraction includes: The terminal is connected to a fusion sensing and communication network, and signal data, sound data, and image data of the terminal's location are acquired through sensors and communication nodes. After the sound data is framed and windowed, Mel-frequency cepstral coefficients are extracted to obtain the sound feature vector. The image data is grayscaled and Gaussian filtered to extract ORB feature points and match feature points of images at adjacent time points to obtain the feature matching number. The contrast of the gray-level co-occurrence matrix is ​​extracted as the image feature vector. The signal data is combined into a signal intensity vector. The signal intensity vector, sound feature vector, image feature vector, and feature matching number are combined into a multi-mode dataset and uploaded.

[0009] Preferably, the process by which the data analysis module determines the current scenario type of the terminal includes: The contrast and feature matching number in the signal strength vector, sound feature vector, and image feature vector are extracted. The outdoor weight is obtained by combining the outdoor reference maximum value of the feature matching number and the outdoor reference maximum value of the contrast. The outdoor weight is compared with a threshold to determine the current scene type of the terminal.

[0010] Preferably, the process by which the data analysis module calculates the current 3D coordinates of the terminal based on the scene type includes: Translation vectors are obtained by matching image feature points at adjacent time points, and visual positioning coordinates are calculated by combining them with the terminal coordinates at the previous time point. The distance between the terminal and each communication node is estimated based on the attenuation relationship between signal strength and distance, and signal-estimated coordinates are calculated through triangulation. The sound feature vectors at the current time point and the previous time point are compared, and sound-estimated coordinates are estimated based on the trend of similarity changes. Indoor fusion coordinates are obtained by weighted fusion of signal-estimated coordinates and sound-estimated coordinates. Finally, the current three-dimensional coordinates of the terminal are obtained by combining outdoor weights, visual positioning coordinates, and indoor fusion coordinates.

[0011] Preferably, the process by which the multi-mode communication module selectively establishes a communication link and transmits coordinates includes: Scan the communication channels in the fusion sensing and communication network to obtain the signal strength, bandwidth, latency and bit error rate of each channel; calculate the comprehensive score of each channel and select the channel with the highest score as the communication link, encapsulate the coordinates and send them to the data storage module; continuously monitor the quality of the current link, and reselect the best channel when it exceeds the preset threshold.

[0012] Preferably, the process of storing coordinates in the data storage module includes: The system receives the current 3D coordinates of the receiving terminal and associates them with the terminal number and timestamp for storage; it receives the destination description information input by the user, matches the destination description information with the locations that have been marked in the fusion sensing and communication network, obtains the 3D coordinates of the successfully matched locations as the destination 3D coordinates, and stores them.

[0013] Preferably, the process by which the positioning and navigation module retrieves coordinates, calculates the optimal path, and outputs navigation guidance includes: Retrieve the current 3D coordinates of the terminal and the 3D coordinates of the destination; run a path search algorithm on the passable road network, with the current 3D coordinates as the starting point and the destination 3D coordinates as the ending point. The evaluation function is composed of the sum of the actual travel distance and the Euclidean distance to the destination. Expand the node with the smallest evaluation function in turn to obtain the optimal path; break down the optimal path into road segments, generate navigation guidance containing travel direction, distance and turning action and output it.

[0014] Compared with the prior art, the beneficial effects of the present invention are: by acquiring multi-modal data of signals, sound and images and extracting features, the current scene type of the terminal is determined, and the visual positioning coordinates and the indoor fused coordinates obtained by fusing signals and sound are weighted by outdoor weights, so that the positioning results can be smoothly transitioned when switching between indoor and outdoor scenes. This avoids the positioning interruption or accuracy reduction caused by the failure of a single signal in the traditional positioning system, and improves the stability and accuracy of positioning across scenes. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0016] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0017] like Figure 1 As shown, a positioning system with cross-scenario multi-mode communication includes: The network construction module is used to deploy sensors and communication nodes to form a fusion sensing and communication network, establish a three-dimensional coordinate system, and perform position calibration and obtain three-dimensional coordinates for sensors and communication nodes. The data acquisition module is used to connect the terminal to the fusion sensing and communication network, acquire multi-modal data around the terminal, preprocess the multi-modal data and extract features to obtain a multi-modal dataset and upload it. The data analysis module is used to receive multi-modal datasets, determine the current scene type of the terminal, and calculate the current three-dimensional coordinates of the terminal based on the scene type; The multi-mode communication module is used to establish a communication link by utilizing the fusion sensing and communication network, and send the current three-dimensional coordinates of the terminal to the data storage module; The data storage module is used to store the three-dimensional coordinates of the terminal and the three-dimensional coordinates of the destination; The positioning and navigation module is used to retrieve the three-dimensional coordinates of the terminal and the three-dimensional coordinates of the destination, calculate the optimal path, and output navigation guidance.

[0018] Furthermore, the process of deploying sensors and communication nodes in the network building modules to form a converged sensing and communication network includes: Sensors and communication nodes are deployed within the target area, and each sensor and communication node is numbered, denoted as i. Once deployed, communication connections are established between each sensor and communication node, forming a fused sensing and communication network. Furthermore, the network construction module establishes a three-dimensional coordinate system, and the process of calibrating the positions of sensors and communication nodes and obtaining their three-dimensional coordinates includes: Select the geometric center of the target region as the origin O of the coordinate system. A three-dimensional coordinate system is established with due east as the positive X-axis, due north as the positive Y-axis, and vertically upward as the positive Z-axis. The position of sensor i and communication node i are calibrated, and their three-dimensional coordinates in the three-dimensional coordinate system are obtained, denoted as [i, y]. Record the three-dimensional coordinates of the sensor and communication node to establish a three-dimensional coordinate system; It should be further explained that, in the sensor and communication node, the sensor is used to collect sound data and image data, and the communication node is used to send and receive signal data, together supporting the acquisition and transmission of multi-mode data.

[0019] Furthermore, the data acquisition module connects the terminal to the converged sensing and communication network to acquire multi-modal data from the surrounding environment, including: The terminal sends an access request to the converged sensing and communication network. After the access is completed, the sensors and communication nodes near the terminal collect data on the surrounding environment of the terminal. Multi-mode data around the terminal is acquired, including signal data, sound data and image data. The signal data includes the signal strength values ​​of each communication node received by the terminal and the corresponding communication node number. The sound data includes the environmental audio stream acquired by the terminal through the sound acquisition function. The image data includes the continuous image frames acquired by the terminal through the image acquisition function. Furthermore, the data acquisition module preprocesses the multi-modal data and extracts features, including: The audio data is subjected to frame segmentation, windowing, and pre-emphasis processing to obtain a preprocessed audio frame sequence; Mel-frequency cepstral coefficients are extracted from the preprocessed audio frame sequence to obtain the audio feature vector. , Where k is the feature dimension of MFCC; Image data is converted to grayscale and Gaussian filtered to obtain preprocessed image frames. ORB feature points are extracted from the preprocessed image frames to obtain a feature point descriptor set for each frame. Feature point matching is performed on the feature point descriptor sets of adjacent frames, and the number of successfully matched feature point pairs is counted, denoted as the feature match number F. The grayscale co-occurrence matrix is ​​extracted from the preprocessed image frames to obtain contrast texture features, forming an image feature vector. , Signal data is represented as a signal intensity vector, which is described as follows: , Where n is the total number of communication nodes; Furthermore, the process of the data acquisition module obtaining and uploading the multi-model dataset includes: The signal strength vector S, sound feature vector A, image feature vector G, and feature matching number F are combined, and the terminal number and timestamp are appended to obtain the multi-mode dataset; the multi-mode dataset is then uploaded to the data analysis module. It should be further explained that the combination refers to encapsulating the signal strength vector S, sound feature vector A, image feature vector G, and feature matching number F into a multi-mode data record. Each multi-mode data record corresponds to a collection time, and after attaching the terminal number and timestamp, a multi-mode dataset is formed.

[0020] Furthermore, the process by which the data analysis module receives the multi-modal dataset and determines the current scenario type of the terminal includes: Receive a multi-mode dataset, extract the signal intensity vector S, sound feature vector A, contrast C from the image feature vector G, and the number of feature matches F; calculate the outdoor weights. : , in, This represents the maximum reference value for the number of feature matches in outdoor scenes. This represents the maximum reference contrast ratio for outdoor scenes. The value range is from 0 to 1; when ≥0.5 indicates an outdoor scene; when When the value is less than 0.5, the scene is classified as indoors. Furthermore, the data analysis module calculates the terminal's current 3D coordinates based on the scene type, including: Calculate visual positioning coordinates from image data Extract ORB feature point matching pairs from images at two adjacent time points, obtain the translation vector, and calculate the visual positioning coordinates based on the terminal coordinates at the previous time point. The calculation method is as follows: , in, Let t be the terminal coordinates at the previous moment, and t be the translation vector; Calculating coordinates by calculating signal attenuation Based on the signal strength values ​​of each communication node in the current signal strength vector, and utilizing the attenuation relationship between signal strength and distance, the distance between the terminal and the communication node numbered i is calculated. The calculation method is as follows: , Where A is the reference signal strength value at a distance of 1 meter from the communication node, and n is the path loss exponent; based on the distance between the terminal and at least three communication nodes. Given the known coordinates of each communication node, coordinates are calculated from the signals using triangulation. ; Sound coordinates are calculated by comparing sound features. : The sound feature vector at the current moment Compared with the sound feature vector of the previous moment The two are compared and their cosine similarity is calculated. The direction and distance of the terminal's movement are inferred based on the trend of the similarity. The coordinates of the sound are inferred by combining the terminal coordinates of the previous moment. Calculate indoor fusion coordinates: , in, The signal positioning weighting coefficient has a value range of 0.5-0.8. The visual positioning coordinates and indoor fusion coordinates are weighted and fused to obtain the current three-dimensional coordinates of the terminal: , It needs to be further explained that, and It is determined by collecting the number of feature matches and the contrast in typical outdoor scenes and taking the maximum value; for example, the value of the number of feature matches F collected in outdoor scenes ranges from 150 to 300, corresponding to... The value is 300; the contrast ratio C ranges from 50 to 100, corresponding to... The value is 100.

[0021] Furthermore, the multi-mode communication module utilizes fused sensing and communication networks to selectively establish communication links, and the process of sending the terminal's current three-dimensional coordinates to the data storage module includes: The communication channels in the fusion sensing and communication network are scanned to obtain the signal strength, bandwidth, delay, and bit error rate of each channel; a comprehensive score is calculated for each channel, and the comprehensive score of the channel numbered j is recorded as follows: The calculation method is as follows: , in, For signal strength, For bandwidth, For time delay, For bit error rate, These are the weighting coefficients for signal strength, bandwidth, delay, and bit error rate, respectively. The communication channel with the highest overall score is selected as the current communication link, and the terminal's current three-dimensional coordinates are transmitted through this link. The location data packet, along with the terminal number and timestamp, is encapsulated into a location data packet and sent to the data storage module. During terminal movement, the signal strength and bit error rate of the current communication link are monitored. When the signal strength is lower than the preset signal threshold or the bit error rate is higher than the preset bit error rate threshold, the communication channel is rescanned and the communication link is switched preferentially.

[0022] It should be further explained that the preset signal threshold refers to the minimum signal strength value that triggers channel reselection; the preset bit error rate threshold refers to the maximum bit error rate value that triggers channel reselection.

[0023] Furthermore, the process of storing the terminal's three-dimensional coordinates and the destination's three-dimensional coordinates in the data storage module includes: Current three-dimensional coordinates of the receiving terminal The terminal number and timestamp are attached for storage; the destination description information input by the user through the terminal is received and matched to obtain the three-dimensional coordinates of the destination. And store; It should be further explained that the destination description information includes the destination name or a description of the destination's environmental features; matching to obtain the destination's three-dimensional coordinates refers to matching the destination description information with the features of various locations that have been calibrated in the fusion sensing and communication network, and obtaining the three-dimensional coordinates of the successfully matched locations as the destination's three-dimensional coordinates.

[0024] Furthermore, the process by which the positioning and navigation module retrieves the terminal's three-dimensional coordinates and the destination's three-dimensional coordinates, calculates the optimal path, and outputs navigation guidance includes: Retrieve the current three-dimensional coordinates of the terminal and destination 3D coordinates ; Run the path search algorithm on the traversable road network, to Starting point The endpoint is [the path to the destination]. The evaluation function of the path search algorithm is: , in, This represents the actual travel distance from the starting point to the current node n. This is the estimated Euclidean distance from the current node n to the endpoint; during the search process, neighboring nodes are expanded sequentially from the starting point, and the distance to each candidate node is calculated. Select The smallest node is used as the next node on the path, ensuring that the search direction always leads to the destination and the total travel distance is minimized, until the path extends to the destination, thus obtaining the optimal path composed of the node sequence. The optimal path's node sequence is divided into several segments based on adjacency. A navigation guide is generated for each segment, including the starting node name, direction of travel, distance traveled, and turning actions upon reaching the next node. The navigation guides for all segments are arranged sequentially and output to the terminal interface.

[0025] It is necessary to further explain the construction process of the passable road network: After establishing a three-dimensional coordinate system in the network construction module, the road intersections, entrances and exits, and stairwells in the target area are marked as nodes. Each node is assigned three-dimensional coordinates and a node name. The actual passable path between two adjacent nodes is marked as an edge. The actual passable distance between two nodes is measured as the edge weight, and the passable road network is constructed.

[0026] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications or equivalent substitutions made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A positioning system with cross-scenario multi-mode communication, characterized in that, include: The network construction module is used to deploy sensors and communication nodes to form a fusion sensing and communication network, establish a three-dimensional coordinate system, and perform position calibration and obtain three-dimensional coordinates for sensors and communication nodes. The data acquisition module is used to connect the terminal to the fusion sensing and communication network, acquire multi-modal data around the terminal, preprocess the multi-modal data and extract features to obtain a multi-modal dataset and upload it. The data analysis module is used to receive multi-modal datasets, determine the current scene type of the terminal, and calculate the current three-dimensional coordinates of the terminal based on the scene type; The multi-mode communication module is used to establish a communication link by utilizing the fusion sensing and communication network, and send the current three-dimensional coordinates of the terminal to the data storage module; The data storage module is used to store the three-dimensional coordinates of the terminal and the three-dimensional coordinates of the destination; The positioning and navigation module is used to retrieve the three-dimensional coordinates of the terminal and the three-dimensional coordinates of the destination, calculate the optimal path, and output navigation guidance.

2. The positioning system for cross-scenario multi-mode communication according to claim 1, characterized in that, The process of deploying sensors and communication nodes to form a converged sensing and communication network includes: Sensors and communication nodes are deployed within the target area to establish communication connections and form a fusion sensing and communication network. A three-dimensional coordinate system is established with the geometric center of the target area as the origin, and the positions of each node are calibrated and the three-dimensional coordinates are obtained.

3. The positioning system for cross-scenario multi-mode communication according to claim 2, characterized in that, The data acquisition module acquires multi-modal data and performs preprocessing and feature extraction, including the following processes: The terminal is connected to a fusion sensing and communication network, and signal data, sound data, and image data of the terminal's location are acquired through sensors and communication nodes. After the sound data is framed and windowed, Mel-frequency cepstral coefficients are extracted to obtain the sound feature vector. The image data is grayscaled and Gaussian filtered to extract ORB feature points and match feature points of images at adjacent time points to obtain the feature matching number. The contrast of the gray-level co-occurrence matrix is ​​extracted as the image feature vector. The signal data is combined into a signal intensity vector. The signal intensity vector, sound feature vector, image feature vector, and feature matching number are combined into a multi-mode dataset and uploaded.

4. A positioning system for cross-scenario multi-mode communication according to claim 3, characterized in that, The process by which the data analysis module determines the current scenario type of the terminal includes: The contrast and feature matching number in the signal strength vector, sound feature vector, and image feature vector are extracted. The outdoor weight is obtained by combining the outdoor reference maximum value of the feature matching number and the outdoor reference maximum value of the contrast. The outdoor weight is compared with a threshold to determine the current scene type of the terminal.

5. A positioning system for cross-scenario multi-mode communication according to claim 4, characterized in that, The data analysis module calculates the terminal's current 3D coordinates based on the scene type, including: Translation vectors are obtained by matching image feature points at adjacent time points, and visual positioning coordinates are calculated by combining them with the terminal coordinates at the previous time point. The distance between the terminal and each communication node is estimated based on the attenuation relationship between signal strength and distance, and signal-estimated coordinates are calculated through triangulation. The sound feature vectors at the current time point and the previous time point are compared, and sound-estimated coordinates are estimated based on the trend of similarity changes. Indoor fusion coordinates are obtained by weighted fusion of signal-estimated coordinates and sound-estimated coordinates. Finally, the current three-dimensional coordinates of the terminal are obtained by combining outdoor weights, visual positioning coordinates, and indoor fusion coordinates.

6. A positioning system for cross-scenario multi-mode communication according to claim 5, characterized in that, The process by which the multi-mode communication module selectively establishes a communication link and transmits coordinates includes: Scan the communication channels in the fusion sensing and communication network to obtain the signal strength, bandwidth, latency and bit error rate of each channel; calculate the comprehensive score of each channel and select the channel with the highest score as the communication link, encapsulate the coordinates and send them to the data storage module; continuously monitor the quality of the current link, and reselect the best channel when it exceeds the preset threshold.

7. A positioning system for cross-scenario multi-mode communication according to claim 6, characterized in that, The process of storing coordinates in the data storage module includes: The system receives the current 3D coordinates of the receiving terminal and associates them with the terminal number and timestamp for storage; it receives the destination description information input by the user, matches the destination description information with the locations that have been marked in the fusion sensing and communication network, obtains the 3D coordinates of the successfully matched locations as the destination 3D coordinates, and stores them.

8. A positioning system for cross-scenario multi-mode communication according to claim 7, characterized in that, The process by which the positioning and navigation module retrieves coordinates, calculates the optimal path, and outputs navigation guidance includes: Retrieve the current 3D coordinates of the terminal and the 3D coordinates of the destination; run a path search algorithm on the passable road network, with the current 3D coordinates as the starting point and the destination 3D coordinates as the ending point. The evaluation function is composed of the sum of the actual travel distance and the Euclidean distance to the destination. Expand the node with the smallest evaluation function in turn to obtain the optimal path; break down the optimal path into road segments, generate navigation guidance containing travel direction, distance and turning action and output it.