A highway construction personnel management method and system based on trajectory positioning

Abstract

The present invention discloses a method and system for managing highway construction personnel based on trajectory positioning, which relates to the field of data processing technology. The method collects the distance measurement data of the construction personnel through a positioning device, collects the image data of the construction personnel through a camera device, and the local monitoring device constructs an overdetermined set of equations based on the distance measurement data of the first cycle, and solves and generates the first coordinate. The local monitoring device generates the second coordinate based on the image data of the second cycle. The trajectory prediction model generates the trajectory path of the construction personnel based on the first coordinate and the second coordinate, and outputs an early warning signal based on the trajectory path. Furthermore, the first cycle is reversely adjusted according to the image data, the second cycle is reversely adjusted according to the distance measurement data, the third cycle is adjusted according to the error between the first coordinate and the second coordinate, and the signal processing model and the image processing model are updated based on the third cycle, which can effectively improve the supervision accuracy and response efficiency in complex construction environments.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for managing highway construction personnel based on trajectory positioning. Background Art

[0002] Safety protection work at the construction site has been paid more and more attention. Chinese patent application with publication number CN118506265A discloses a method for identifying and alarming the edge operation trajectory of engineering construction personnel based on machine vision. This method obtains the image information of the field area, uses the AI virtual electronic fence technology to divide the construction operation area, detects and locates the construction personnel in the image information, and uses the ReInspect algorithm to construct a multi-target tracking model for the edge operation of construction personnel in the image information, tracks and collects the movement trajectories of construction personnel. A trajectory prediction module for the edge operation of construction personnel based on Social-STGCNN is established to predict the movement trajectories of construction personnel, and analyze the trajectory information where construction personnel may be in danger, so as to realize the identification and alarm of edge operation. This method requires the terminal device to continuously upload the image information of the field area, requires the deployment of limited broadband to improve the network rate, and requires hardware facilities with relatively high processing capabilities to train the deep learning model. This method is not applicable to the highway construction environment where the construction area is constantly changing. Therefore, it is necessary to propose a method for supervising construction personnel with lower requirements for network rate and hardware facilities to meet the needs of highway construction. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method and system for managing highway construction personnel based on trajectory positioning, which combines ranging data and image data to realize the trajectory positioning of construction personnel. By optimizing the signal period and model update period of ranging data and image data, while ensuring the accuracy of trajectory warning, the data transmission volume and processing difficulty are reduced, and the network rate and hardware requirements for terminal devices are lowered.

[0004] The invention object of the present application can be achieved by the following technical means:

[0005] A method for managing highway construction personnel based on trajectory positioning, comprising the following steps:

[0006] Step 1: Generate an electronic fence for the construction highway, set a buffer area and a passing area on the construction highway based on the electronic fence, set monitoring devices in the passing area, and set throttling devices in the buffer area;

[0007] Step 2: The monitoring device predicts the traffic flow in the buffer area, the throttling device adjusts the traffic flow in the buffer area, the positioning device periodically collects the ranging data of construction personnel, and the imaging device periodically collects the image data of construction personnel;

[0008] Step 3: The positioning device reports ranging data at intervals of a first period, the imaging device reports image data at intervals of a second period, and the local monitoring device predicts the first coordinates of the construction worker based on a signal processing model and predicts the second coordinates of the construction worker based on an image processing model;

[0009] Step 4: The warning device adjusts the trajectory prediction model based on the first period and the second period, inputs multiple groups of first coordinates and second coordinates into the trajectory prediction model to obtain the trajectory path of the construction worker, and outputs a warning signal if at least one trajectory coordinate point of the trajectory path is outside the electronic fence;

[0010] Step 5: Extract the extreme distance between the trajectory path and the electronic fence, and update the signal period of the throttling device according to the traffic flow and multiple groups of extreme distances;

[0011] Step 6: Adjust the first period according to the image data of different imaging devices at the same moment, adjust the second period according to the ranging data of different positioning devices at the same moment, and adjust the third period according to the first coordinates and the second coordinates at the same moment;

[0012] Step 7: The local monitoring device reports ranging data and image data at intervals of a third period, the remote monitoring device updates the signal processing model and the image processing model, and returns to Step 2.

[0013] In the present invention, in Step 3, extract I groups of positioning devices that collect the ranging data of the construction worker, substitute the ranging data into the signal processing model to calculate the signal propagation duration of each positioning device, extract a reference positioning device from the I groups of positioning devices, and create a reference coordinate (x0, y0, z0) and a signal propagation duration t0 of the reference positioning device and the coordinates (x i , y i , z i ) and the signal propagation duration t i of the overdetermined equations, and then calculate the first coordinates of the construction worker, where i = 1, 2,..., I - 1.

[0014] In the present invention, in Step 3, the image processing model includes a monocular sub-model and a multi-view sub-model. Extract J groups of imaging devices that collect the image data of the construction worker, extract the image contour of the construction worker from the image data, the monocular sub-model predicts the observation coordinates of the image contour according to the internal parameter matrix of the imaging device, the multi-view sub-model predicts the perspective weight of the image contour according to the external parameter matrix of the imaging device, and then calculates the second coordinates of the construction worker according to multiple observation coordinates and the corresponding perspective weights.

[0015] In the present invention, in step 4, the noise covariance matrix of the ranging data is adjusted according to the first period, the noise covariance matrix of the image data is adjusted according to the second period, and based on the adjusted noise covariance matrices, the weights w1 of the ranging data and the weights w2 of the image data in the trajectory prediction model are calculated respectively.

[0016] In the present invention, in step 4, multiple groups of first coordinates and second coordinates are input into the trajectory prediction model. If the current moment is an integer multiple of the second period, trajectory coordinate points are generated according to the first coordinates and the second coordinates; otherwise, the first coordinates are directly used as the trajectory coordinate points.

[0017] In the present invention, in step 6, image data of J different camera devices at the same moment are acquired, and then J groups of observation coordinates are calculated according to the image data. The difference value Δ1 between the J groups of observation coordinates is calculated, and the first period is adjusted according to the difference value Δ1.

[0018] In the present invention, in step 6, ranging data of I positioning devices at the same moment are acquired. Three positioning devices in the ranging data are selected to generate a positioning device combination. Candidate coordinates are calculated according to the trilateration method and the positioning device combination, multiple groups of candidate coordinates are generated, the difference value Δ2 between the multiple groups of candidate coordinates is calculated, and the second period is adjusted according to the difference value Δ2.

[0019] In the present invention, in step 6, the first coordinates and the second coordinates at the same moment are acquired, the difference value Δ3 between the first coordinates and the second coordinates is calculated, and the third period is adjusted according to the difference value Δ3.

[0020] In the present invention, in step 7, the remote monitoring device calculates the theoretical signal propagation duration between any non-reference positioning device and the reference positioning device based on the ranging data, calculates the time difference between the actual signal propagation duration and the theoretical signal propagation duration, takes the average value of the time difference as the time difference error coefficient δ, performs reprojection on the image data, calculates the perspective deviation between the reprojected pixel coordinates and the pixel coordinates of the image contours of each camera device, takes the average value of the perspective deviation as the perspective error coefficient γ, and the local detection device updates the signal processing model and the image processing model according to δ and γ respectively.

[0021] A system for implementing the above-mentioned method for managing highway construction personnel based on trajectory positioning, comprising:

[0022] A monitoring device configured to predict the traffic flow in the buffer area;

[0023] A throttling device configured to adjust the traffic flow in the buffer area;

[0024] A positioning device configured to collect the ranging data of construction personnel;

[0025] A camera device configured to collect image data of construction workers;

[0026] A local monitoring device configured to predict the first coordinate and the second coordinate of a construction worker;

[0027] An early warning device configured to predict the trajectory path of a construction worker and output an early warning signal;

[0028] A remote monitoring device configured to update a signal processing model and an image processing model, wherein

[0029] The positioning device reports ranging data every first period, the camera device reports image data every second period, and the local monitoring device reports ranging data and image data every third period.

[0030] The local monitoring device adjusts the first period according to the image data of different camera devices at the same moment, adjusts the second period according to the ranging data of different positioning devices at the same moment, and adjusts the third period according to the first coordinate and the second coordinate at the same moment.

[0031] Implementing the method and system for managing highway construction workers based on trajectory positioning of the present invention, the beneficial effects are as follows: The present invention collects the ranging data of construction workers through a positioning device, collects image data through a camera device, and realizes the trajectory positioning of construction workers by combining the ranging data and the image data, ensuring the accuracy of trajectory positioning. When the image data captured by different camera devices has a large difference, the present invention adjusts the first period, and when the ranging data collected by different positioning devices has a large difference, the present invention adjusts the second period, reducing the data transmission volume and processing difficulty on the basis of ensuring the accuracy of trajectory positioning. Further, the present invention adjusts the third period according to the error between the first coordinate and the second coordinate, and updates the signal processing model and the image processing model in a timely manner when the working environment changes and affects data collection, improving the supervision efficiency. Description of the Drawings

[0032] Figure 1 Is a flowchart of the method for managing highway construction workers based on trajectory positioning of the present invention;

[0033] Figure 2 Is a schematic diagram of the construction highway of the present invention;

[0034] Figure 3 Is a schematic diagram of multiple groups of positioning devices collecting ranging data of the present invention;

[0035] Figure 4 Is a schematic diagram of the image contour in an image data of the present invention;

[0036] Figure 5 Is a schematic diagram of predicting the observation coordinates of the image contour of the present invention;

[0037] Figure 6 Schematic diagrams of the first cycle, the second cycle, and the trajectory generation cycle of the present invention;

[0038] Figure 7 Schematic diagram of the trajectory path of the construction personnel of the present invention;

[0039] Figure 8 Block diagram of the system for implementing the method for managing highway construction personnel based on trajectory positioning of the present invention;

[0040] Figure 9 Block diagram of the wireless transceiver device of the construction personnel of the present invention;

[0041] Figure 10 Structural diagram of the intelligent safety helmet with a wireless transceiver device of the present invention.

[0042] Explanation of some reference numerals: helmet body 10, brim 20, waterproof box body 30, warning module 31, charging interface 32. Detailed implementation manners

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0044] The highway construction environment has significant complexity and dynamic characteristics, specifically manifested as high-risk working conditions such as high-frequency movement of construction machinery, real-time change of the boundary of the operation area, and intensive human-machine interaction operations. Traditional personnel management means mainly rely on the following two technical paths: one is a static monitoring system based on fixed cameras, and the other is a positioning device relying on radio frequency signals. However, both of the above single technical solutions have inherent limitations: although the static monitoring system can achieve visual coverage, the image data processing is complex, and there are problems such as low monitoring efficiency and response lag. The signal positioning device is easily blocked by the metal structure of large construction equipment, resulting in deterioration of the positioning accuracy. In view of this technical bottleneck, the present invention innovatively proposes a solution of multi-source data fusion, combines the advantages of ranging data and image data to complementarily position construction personnel, and this dual-modal data cooperation mechanism not only overcomes the technical shortcomings of a single signal source, but also improves the robustness of the system through data complementarity. Embodiment 1

[0045] Referring to Figure 1 , the method for managing highway construction personnel based on trajectory positioning of the present invention described in detail in this embodiment includes the following steps:

[0046] Step 1: Generate an electronic fence for the construction highway, set a buffer area and a passing area on the construction highway based on the electronic fence, set monitoring devices in the passing area, and set throttling devices in the buffer area. Referring to Figure 2, the electronic fence is a virtual boundary generated based on the geographical information of the construction road, which is used to define the construction area of the construction personnel, and the construction area is the current operation range. The buffer area is a triangular area, one side of which is connected to the electronic fence, and the vertex points to the direction of traffic. The area of the buffer area is determined by the construction specifications. The monitoring device is usually an infrared counter or a camera, and the throttling device is, for example, a traffic light.

[0047] Step 2: The monitoring device predicts the traffic flow in the buffer area, the throttling device adjusts the traffic flow in the buffer area, the positioning device periodically collects the ranging data of the construction personnel, and the imaging device periodically collects the image data of the construction personnel. The monitoring device predicts the traffic flow in the buffer area in the next minute or one traffic light cycle based on the vehicle information in the passing area. Refer to Figure 3 , the positioning device is, for example, a UWB base station arranged around the electronic fence. The construction personnel wear intelligent safety helmets, and the wireless transceiver device in the intelligent safety helmet can receive the ranging signals sent by the UWB base station. Multiple UWB base stations send ranging signals to the construction personnel simultaneously using different codes. The wireless transceiver device responds to the signals quickly, and the UWB base station records the signal propagation duration to generate ranging data. Since the construction equipment will block the propagation of some ranging signals, it is necessary to combine the image data for auxiliary positioning. The imaging device is, for example, multiple industrial cameras installed on a bracket with a height of 3 - 6 meters. The multiple industrial cameras synchronously capture the images on the construction road to generate image data.

[0048] Step 3: The positioning device reports the ranging data every first period, and the imaging device reports the image data every second period. The local monitoring device predicts the first coordinate of the construction personnel based on a signal processing model and predicts the second coordinate of the construction personnel based on an image processing model. Extract I groups of positioning devices that have collected the ranging data of the construction personnel. Calculate the signal propagation duration of each positioning device through the signal processing model, select a reference positioning device and establish an overdetermined equation system, and solve the overdetermined equation system to obtain the first coordinate of the construction personnel. The image processing model includes a monocular sub - model and a multi - camera sub - model. Refer to Figure 4 , and extract the image contour of the construction personnel in combination with the contour size characteristics of the construction personnel. Refer to Figure 5 , the monocular sub - model predicts the observation coordinates of the image contour based on the internal parameter matrix of the imaging device. The multi - camera sub - model predicts the perspective weights of the image contour based on the external parameter matrix of the imaging device, and then calculates the second coordinate of the construction personnel based on multiple observation coordinates and the corresponding perspective weights. The specific calculation methods of the first coordinate and the second coordinate refer to Embodiment 2.

[0049] Step 4: The warning device adjusts the trajectory prediction model based on the first period and the second period, inputs multiple groups of first coordinates and second coordinates into the trajectory prediction model to obtain the trajectory path of the construction worker. If at least one trajectory coordinate point of the trajectory path is outside the electronic fence, a warning signal is output. Adjust the noise covariance matrix of the ranging data according to the first period, adjust the noise covariance matrix of the image data according to the second period, and calculate the weight w1 of the ranging data and the weight w2 of the image data in the trajectory prediction model based on the adjusted noise covariance matrices. Input multiple groups of first coordinates and second coordinates into the trajectory prediction model. If the current moment is an integer multiple of the second period, generate trajectory coordinate points according to the first coordinates and the second coordinates; otherwise, directly use the first coordinates as the trajectory coordinate points. For the specific generation method of the trajectory route, refer to Embodiment 2.

[0050] Step 5: Extract the extreme distance between the trajectory path and the electronic fence, and update the signal period of the throttling device according to the traffic flow and multiple groups of extreme distances. The smaller the extreme distance between the trajectory path of the construction worker and the electronic fence, the closer the construction worker is to the passing area, and the corresponding safety risk increases. At the same time, the increase in traffic flow will increase the probability that vehicles in the passing area will accidentally intrude into the electronic fence due to factors such as congestion or lane change, further exacerbating the safety hazards of construction workers. Therefore, it is necessary to adjust the signal period of the throttling device in real time based on the extreme distance and traffic flow to effectively reduce the operation risk of construction workers.

[0051] Calculate the instantaneous distance from each trajectory coordinate point in the trajectory path to the electronic fence, and store the minimum distance within a preset time as the extreme distance D, or generate an instantaneous distance function. The extreme distance D is when the derivative of the instantaneous distance function changes from a negative value to a positive value (the derivative is zero). The passing time T = T0[1 + σ(Q / Q0) + ξ(D0 / D)], where Q is the traffic flow, Q0 is the maximum allowable flow (usually taken as 10 vehicles / minute), D0 is the safety distance threshold (usually taken as 0.5 meters), T0 is the basic passing time, σ is the traffic flow weight coefficient, ξ is the extreme distance weight coefficient, σ is usually 0.2 - 0.5, and ξ is usually 0.1 - 0.3. The signal period of the throttling device (traffic light) consists of the passing time and the prohibited time.

[0052] Step 6: Adjust the first period according to the image data of different imaging devices at the same moment, adjust the second period according to the ranging data of different positioning devices at the same moment, and adjust the third period according to the first coordinate and the second coordinate at the same moment. Obtain the image data of J groups of different imaging devices at the same moment, and then calculate J groups of observed coordinates according to the image data. Calculate the difference value Δ1 between the J groups of observed coordinates. Adjust the first period according to the difference value Δ1. The larger the difference value Δ1, the greater the error of the imaging device, and it is necessary to reduce the first period and increase the acquisition frequency of the ranging data. Obtain the ranging data of I groups of positioning devices at the same moment. Select three groups of positioning devices to generate a positioning device combination. Calculate the candidate coordinates of the construction worker according to the trilateration method and the positioning device combination, generate multiple groups of candidate coordinates, calculate the difference value Δ2 between the multiple groups of candidate coordinates, and adjust the second period according to the difference value Δ2. The larger the difference value Δ2, the greater the error of the positioning device, and it is necessary to reduce the second period and increase the acquisition frequency of the image data. Obtain the first coordinate and the second coordinate at the same moment, calculate the difference value Δ3 between the first coordinate and the second coordinate, and adjust the third period according to the difference value Δ3. The specific adjustment methods of the first period, the second period, and the third period refer to Embodiment 3.

[0053] Step 7: The local monitoring device reports the ranging data and the image data at intervals of the third period. The remote monitoring device updates the signal processing model and the image processing model, and returns to Step 2. Calculate the theoretical signal propagation duration between each positioning device and the reference positioning device in the ranging data. The actual signal propagation duration is the signal propagation duration recorded in the ranging data, and the theoretical signal propagation duration is calculated based on the installation distance between each positioning device and the reference positioning device. Calculate the time difference between the actual signal propagation duration and the theoretical signal propagation duration, and use the average value of the time difference as the time difference error coefficient δ. According to the image data, the internal parameter matrix K j and the external parameter matrix M ext,j of each imaging device, reproject the image contour of the construction worker. The reprojection formula is: , where (u' j , v' j ) is the reprojected pixel coordinate of the image contour, and P2 is the second coordinate of the construction worker corresponding to the image contour. Calculate the perspective deviation (Euclidean distance) between the reprojected pixel coordinate and the pixel coordinate of the image contour of each imaging device, normalize the perspective deviation, and calculate the average value of the processed perspective deviation to obtain the perspective error coefficient γ. The remote monitoring device issues the time difference error coefficient δ and the perspective error coefficient γ. The local monitoring device updates the time difference error coefficient δ of the signal processing model, and updates the perspective weight (w xj , w yj , w zj ) of the corresponding image contour in the image processing model according to the perspective error coefficient γ of the image contour, that is, w xj = wxj / (γ + 1), w yj = w yj / (γ + 1), w zj = w zj / (γ + 1). Example Two

[0054] This example discloses a preferred method for generating the first coordinate, the second coordinate, and the trajectory path.

[0055] Predict the first coordinate of the construction worker based on a signal processing model. The positioning device sends a ranging signal to the construction worker. After receiving the ranging signal, the intelligent safety helmet terminal of the construction worker will have a fixed time delay due to the signal processing process. At the same time, factors such as the occlusion of construction equipment may cause an increase in the signal propagation path loss, thereby affecting the signal propagation speed. These factors together result in a systematic deviation in the signal propagation duration recorded in the ranging data, which needs to be compensated and corrected through the signal processing model. Extract the I groups of positioning devices that collect the ranging data of this construction worker, and substitute the ranging data into the signal processing model to calculate the signal propagation duration t of each positioning device, that is, t = (t - δ) / 2, where δ is the time difference error coefficient. Extract a reference positioning device from the I groups of positioning devices, and create the reference coordinates (x0, y0, z0) and the signal propagation duration t0 of the reference positioning device and the coordinates (x i , y i , z i ) and the signal propagation duration t i of the overdetermined equations, i = 1, 2,..., I - 1.

[0056] The overdetermined equations are: , i = 1, 2,..., I - 1. Solve the overdetermined equations by, for example, the least squares method or the minimum value method. The solution of the overdetermined equations is the first coordinate of this construction worker, where c is the speed of light.

[0057] Predict the second coordinate of the construction worker based on an image processing model. The image processing model includes a monocular sub-model and a multi-view sub-model. Extract the J groups of camera devices that collect the image data of this construction worker, and extract the image contour of the construction worker by combining the contour size characteristics of the construction worker. The monocular sub-model converts the image contour from pixel coordinates to normalized camera coordinates according to the internal parameter matrix K j (including focal length and principal point offset), and the conversion formula is: , where, (x j , y j ) is the normalized camera coordinate of the image contour, and (u j , v j ) is the pixel coordinate of the image contour. Estimate the depth z by combining the contour size characteristics of the construction worker.j , and then obtain the observed coordinates (x j , y j , z j ) of the image contour. The multi-camera sub-model calculates the angles of the construction worker relative to the optical axis of the camera device in three directions (horizontal, vertical, and depth directions) according to the external parameter matrix of the camera device (including the position coordinates and the optical axis orientation of the camera device). The smaller the angle, the higher the reliability of the corresponding direction, and the higher the perspective weight of the corresponding viewing angle. According to the angles, predict the perspective weights (w xj , w yj , w zj ) of the image contour, and substitute the observed coordinates and perspective weights into the bundle adjustment equation. The bundle adjustment equation is simplified as: , solve the bundle adjustment equation, and the solution of the bundle adjustment equation is the second coordinate of the construction worker, j = 1, 2,..., J.

[0058] Adjust the trajectory prediction model based on the first period and the second period. Obtain the noise covariance matrix R1 of the ranging data and the noise covariance matrix R2 of the image data. The noise covariance matrices R1 and R2 are obtained through the statistical analysis of the historical errors of the ranging data and the image data respectively. R1 reflects the ranging fluctuation characteristics of the positioning device, and R2 characterizes the imaging error distribution of the camera device. Adjust R1 according to the first period T1, R1 = αT1, adjust R2 according to the second period T2, R2 = βT2. Calculate the weight w1 of the ranging data and the weight w2 of the image data based on the adjusted noise covariance matrices, w1 = 1 / (|R1| + ε), w2 = 1 / (|R2| + ε). Where ε is a regularization constant term, and α and β are adjustment coefficients. The first period is shorter than the second period, and its real-time performance is more valuable in the trajectory prediction model. Therefore, the weight of the ranging data is higher, and usually α < β is set.

[0059] Refer to Figures 6 to 7 , input multiple groups of first coordinates and second coordinates into the trajectory prediction model to obtain the trajectory path of the construction worker. The trajectory path generates trajectory coordinate points according to the trajectory generation period, and the trajectory generation period is the same as the first period. If the current time t' is an integer multiple of the second period, then generate a temporary coordinate point p according to the first coordinate P1 and the second coordinate P2, that is, p = (w1P1 + w2P2) / (w1 + w2). Otherwise, directly use the first coordinate P1 as the temporary coordinate point p, that is, p = P1. In this embodiment, the temporary coordinate point is used as the trajectory coordinate point.

[0060] In a more preferred embodiment, the Kalman filter generates a predicted value g2 at the current moment based on the state vector of the construction worker at the previous moment (including the trajectory coordinate points and the moving speed at the previous moment), takes the temporary coordinate point p as the observed value g1, and then fuses the result of mapping the observed value g1 and the predicted value g2 through the observation matrix H, that is, g3 = g2 + K(g1 - Hg2), and obtains the trajectory coordinate points at the current moment according to g3. Among them, the observation matrix H is usually , indicating that only the trajectory coordinate points are observed and the moving speed is not observed. The Kalman gain F automatically adjusts the weight ratio of the observed value and the predicted value. When the observed value g1 has a deviation due to occlusion, the Kalman gain automatically reduces its weight to ensure the continuity of the trajectory coordinate points. Embodiment III

[0061] This embodiment discloses a preferred method for adjusting the first period, the second period, and the third period.

[0062] Adjust the first period according to the image data of different imaging devices at the same moment. Obtain the image data of J groups of different imaging devices at the same moment, and then calculate J groups of observed coordinates (x j , y j , z j ) according to the image data, and calculate the difference value between the J groups of observed coordinates , where is the centroid of the J groups of observed coordinates, and the centroid is the arithmetic mean of the J groups of observed coordinates. If the difference value Δ1 exceeds the first difference threshold, it indicates that the image data is inconsistent in the observed coordinates of multiple groups of imaging devices due to noise interference or occlusion effects at this time, and the credibility of the image data is low, then reduce the first period and increase the acquisition frequency of the ranging data. The first difference threshold is usually 0.3 - 0.5 meters.

[0063] Adjust the second period according to the ranging data of different positioning devices at the same moment. Obtain the ranging data of I groups of positioning devices at the same moment, select three groups of positioning devices to form a positioning device combination, calculate the candidate coordinates of the construction worker according to the trilateration method and the positioning device combination, and generate multiple groups of candidate coordinates. Refer to the calculation method of the difference value Δ1 to calculate the difference value Δ2 between the multiple groups of candidate coordinates. If the difference value Δ2 exceeds the second difference threshold, it indicates that the positioning noise of the ranging data is large or there is occlusion at this time, and high-frequency image data is needed to assist in positioning, then reduce the second period. The difference value Δ2 between the candidate coordinates is usually less than 0.4 meters. If it exceeds 1.0 meter, there may be serious occlusion, then the second difference threshold is usually 0.4 - 1 meter. Preferably, if I > 5, randomly select 15 groups of positioning device combinations to calculate the difference value Δ2 to reduce the calculation amount.

[0064] Adjust the third period according to the first coordinates and the second coordinates at the same moment. Obtain the first coordinates (x1, y1, z1) and the second coordinates (x2, y2, z2) at the same moment, and calculate the difference value , the difference value Δ3 reflects the consistency between the ranging data and the image data. If Δ3 exceeds the third difference threshold, it is necessary to reduce the third period and report frequently at a high frequency to remotely correct the signal processing model and the image processing model. The construction road belongs to a general construction area, and the third difference threshold is usually 0.5 - 1 meter. In this embodiment, the third difference threshold is, for example, 0.5 meter. Embodiment 4

[0065] Refer to Figure 8 , this embodiment discloses a system for implementing the method for managing highway construction personnel based on trajectory positioning, including: a monitoring device, a throttling device, a camera device, a positioning device, a local monitoring device, an early warning device, a remote monitoring device, a wireless transceiver device, and a database.

[0066] The monitoring device is configured to predict the traffic flow in the buffer area. The throttling device is configured to adjust the traffic flow in the buffer area. The positioning device is configured to collect the ranging data of the construction personnel. The camera device is configured to collect the image data of the construction personnel. The local monitoring device is configured to predict the first coordinates and the second coordinates of the construction personnel. The early warning device is configured to predict the trajectory path of the construction personnel and output an early warning signal. The remote monitoring device is configured to update the signal processing model and the image processing model. The positioning device reports the ranging data at intervals of the first period, the camera device reports the image data at intervals of the second period, and the local monitoring device reports the ranging data and the image data at intervals of the third period. The local monitoring device adjusts the first period according to the image data of different camera devices at the same moment, adjusts the second period according to the ranging data of different positioning devices at the same moment, and adjusts the third period according to the first coordinates and the second coordinates at the same moment. The wireless transceiver device is used to communicate with the positioning device and feedback the ranging signal to the positioning device. The wireless transceiver device can be installed in the intelligent safety helmet of the construction personnel. The database is used to store the signal processing model and the image processing model.

[0067] Refer to Figure 9, the wireless transceiver device may include a mobile positioning module, a wireless communication module, a warning module, a clock module, a power supply, an environmental perception module, and a microprocessor. The mobile positioning module is the core component and is used to feedback ranging signals to the positioning device. The wireless communication module is used to receive clock calibration instructions from the local monitoring device or instructions for adjusting the first period. The warning module is, for example, a warning light or a buzzer. After receiving a warning signal, the warning module turns on the warning light or the buzzer. The clock module is used to record the moment when the mobile positioning module receives the ranging signal. The power supply is used to supply power to the mobile positioning module, the warning module, etc. The environmental perception module can increase auxiliary energy consumption and can be used to measure environmental PM2.5 or noise. The microprocessor is used to coordinate the work of the mobile positioning module, the wireless communication module, the clock module, etc. Refer to Figure 10 , the intelligent safety helmet includes a helmet body 10 and a visor 20. A waterproof box body 30 is provided on the outer side of the helmet body. The mobile positioning module, the wireless communication module, the clock module, the microprocessor, the power supply, and the environmental perception module of the wireless transceiver device are fixed in the box body. The warning module 31 is located on the surface of the box body, and a charging interface 32 for the power supply is also provided on the surface of the box body.

[0068] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A highway construction personnel management method based on trajectory positioning, characterized in that, It includes the following steps: Step 1: Generate an electronic fence for the construction road, set a buffer area and a passing area on the construction road based on the electronic fence, set monitoring devices in the passing area, and set throttling devices in the buffer area; Step 2: The monitoring device predicts the traffic flow in the buffer area, the throttling device adjusts the traffic flow in the buffer area, the positioning device periodically collects the ranging data of construction workers, and the camera device periodically collects the image data of construction workers; Step 3: The positioning device reports the ranging data every first period, the camera device reports the image data every second period, extract a reference positioning device from the I group of positioning devices, and the local monitoring device predicts the first coordinate of the construction worker based on a signal processing model and predicts the second coordinate of the construction worker based on an image processing model; Step 4: The warning device adjusts the trajectory prediction model based on the first period and the second period, inputs multiple groups of first coordinates and second coordinates into the trajectory prediction model to obtain the trajectory path of the construction worker. If at least one trajectory coordinate point of the trajectory path is outside the electronic fence, an alarm signal is output; Step 5: Extract the extreme distance between the trajectory path and the electronic fence, and update the signal period of the throttling device according to the traffic flow and multiple groups of extreme distances; Step 6: Adjust the first period according to the image data of different camera devices at the same moment, adjust the second period according to the ranging data of different positioning devices at the same moment, and adjust the third period according to the first coordinate and the second coordinate at the same moment; Step 7: The local monitoring device reports the ranging data and the image data every third period, the remote monitoring device updates the signal processing model and the image processing model, and returns to Step 2, where in Step 4, adjust the noise covariance matrix of the ranging data according to the first period, adjust the noise covariance matrix of the image data according to the second period, and calculate the weight w1 of the ranging data and the weight w2 of the image data in the trajectory prediction model based on the adjusted noise covariance matrix, if the current time t' is an integer multiple of the second period, then generate a temporary coordinate point p according to the first coordinate P1 and the second coordinate P2, p = (w1P1 + w2P2) / (w1 + w2), otherwise, p = P1, and use the temporary coordinate point as the trajectory coordinate point, in Step 7, the remote monitoring device calculates the theoretical signal propagation duration between any positioning device and the reference positioning device based on the ranging data, calculates the time difference between the actual signal propagation duration and the theoretical signal propagation duration, takes the mean value of the time difference as the time difference error coefficient δ, performs reprojection on the image data, calculates the perspective deviation between the reprojected pixel coordinates and the pixel coordinates of the image contour of each camera device, and takes the mean value of the perspective deviation as the perspective error coefficient γ, the local monitoring device updates the time difference error coefficient δ of the signal processing model and updates the perspective weight corresponding to the image contour in the image processing model according to the perspective error coefficient γ of the image contour.

2. The method for managing highway construction personnel based on trajectory positioning according to claim 1, wherein, In step 3, extract the I positioning devices that have collected the ranging data of the construction worker, substitute the ranging data into the signal processing model to calculate the signal propagation duration of each positioning device, and create an overdetermined system of equations with the reference coordinates (x0, y0, z0) and signal propagation duration t0 of the reference positioning device and the coordinates (x i , y i , z i ) and signal propagation duration t i of any positioning device, and then calculate the first coordinates of the construction worker, where i = 1, 2,..., I - 1.

3. The method for managing highway construction personnel based on trajectory positioning according to claim 1, wherein In step 3, the image processing model includes a monocular sub - model and a multi -ocular sub - model. J sets of camera devices that collect the image data of the construction worker are extracted, and the image contour of the construction worker in the image data is extracted. The monocular sub - model predicts the observed coordinates of the image contour according to the internal parameter matrix of the camera device, and the multi -ocular sub - model predicts the perspective weight of the image contour according to the external parameter matrix of the camera device. Then, the second coordinates of the construction worker are calculated based on multiple observed coordinates and the corresponding perspective weights.

4. The method for managing highway construction personnel based on trajectory positioning according to claim 3, wherein In step 6, the image data of J sets of different camera devices at the same moment is obtained. Then, J sets of observed coordinates are calculated based on the image data, the difference value Δ1 between the J sets of observed coordinates is calculated, and the first period is adjusted according to the difference value Δ1.

5. The method for managing highway construction personnel based on trajectory positioning according to claim 1, characterized in that, In step 6, the ranging data of I sets of positioning devices at the same moment is obtained. Three sets of positioning devices in the ranging data are selected to generate a positioning device combination. Candidate coordinates are calculated according to the trilateration method and the positioning device combination, multiple sets of candidate coordinates are generated, the difference value Δ2 between the multiple sets of candidate coordinates is calculated, and the second period is adjusted according to the difference value Δ2.

6. The method for managing highway construction personnel based on trajectory positioning according to claim 1, characterized in that In step 6, the first coordinates and the second coordinates at the same moment are obtained, the difference value Δ3 between the first coordinates and the second coordinates is calculated, and the third period is adjusted according to the difference value Δ3.

7. A system for implementing the method for managing highway construction personnel based on trajectory positioning according to claim 1, characterized in that, It includes: A monitoring device configured to predict the traffic flow in the buffer area; A throttling device configured to adjust the traffic flow in the buffer area; A positioning device configured to collect the ranging data of the construction worker; A camera device configured to collect the image data of the construction worker; A local monitoring device configured to predict the first coordinates and the second coordinates of the construction worker; An early warning device configured to predict the trajectory path of the construction worker and output an early warning signal; A remote monitoring device configured to update the signal processing model and the image processing model, where The positioning device reports the ranging data every first period, the camera device reports the image data every second period, and the local monitoring device reports the ranging data and the image data every third period. The local monitoring device adjusts the first period according to the image data of different camera devices at the same moment, adjusts the second period according to the ranging data of different positioning devices at the same moment, and adjusts the third period according to the first coordinates and the second coordinates at the same moment.

Images