Dynamic rendering engine implementation method and system based on multi-source data fusion

Abstract

The invention relates to the technical field of ship intelligent navigation, and provides a dynamic rendering engine implementation method and system based on multi-source data fusion, and the method comprises the steps: collecting multi-source data in real time, carrying out the preprocessing, and obtaining multi-modal data; performing time alignment and coordinate transformation on the multi-modal data through space-time registration, performing prediction through adaptive Kalman filtering, calculating a residual error according to prediction data, and performing sensor anomaly detection according to the residual error; carrying out weighted fusion according to the state of the sensor, carrying out Mercator projection transformation on fused data to obtain rendering coordinates, and carrying out detail level marking according to the rendering coordinates; performing alarm judgment according to the detail level marks, and performing rendering sorting according to the alarm judgment; and carrying out load detection and rendering parameter adjustment through a frame rate control module according to the rendering sequence. According to the invention, the whole process optimization from data acquisition and processing to visual display is realized, the navigation precision and reliability are improved, and the ship navigation safety is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent navigation of ships, and in particular to a dynamic rendering engine implementation method and system based on multi-source data fusion. BACKGROUND

[0002] The ship integrated navigation system has important application value due to its multi-source data fusion capability, high real-time information processing and strong safety. Accurate acquisition and efficient management of shipboard navigation information is a key prerequisite for improving ship efficiency. Especially in complex electromagnetic environments and without external reference support, reliable processing and safe sharing of navigation data face severe challenges. With the development of shipboard sensor technology, modern navigation systems can achieve high-precision autonomous navigation through multi-source information fusion and intelligent display and control technology. In existing shipboard navigation solutions, each type of sensor data is usually processed by independent subsystems, such as a satellite navigation system and an inertial navigation system, which are simply superimposed and displayed after separate operation. However, this decentralized architecture has problems such as poor data timeliness and difficulty in system collaboration, and the traditional coarse-grained design of permission management cannot meet the information security requirements in special environments. On the other hand, although commercial navigation devices have high interface standardization, their open communication protocols are at risk of being interfered with and stolen. Therefore, it is urgent to break through the construction of an autonomous and controllable shipboard navigation information management system in a strong confrontation environment. SUMMARY

[0003] The present application aims to at least solve one of the technical problems in the related art. To this end, the present application provides a dynamic rendering engine implementation method and system based on multi-source data fusion, which realizes the optimization of the whole process from data acquisition, processing to visualization display.

[0004] The present application provides a dynamic rendering engine implementation method based on multi-source data fusion, comprising: S1: real-time acquisition of multi-source data, and pre-processing of the multi-source data to obtain multi-modal data; S2: time alignment and coordinate conversion of the multi-modal data through space-time registration, and prediction of the converted multi-modal data through adaptive Kalman filtering to obtain current prediction data; S3: calculation of residuals according to the current prediction data and the converted multi-modal data, sensor anomaly detection according to the residuals, and obtaining of sensor states; S4: weighted fusion of sensor data according to the sensor states to obtain fusion data; S5: Mercator projection transformation of the fusion data to obtain rendering coordinates, detail level marking according to the rendering coordinates, alarm judgment according to the detail level marking, and rendering sorting according to the alarm judgment; S6: Perform load detection and rendering parameter adjustment based on rendering order through the frame rate control module.

[0005] Furthermore, step S1 includes: S11: Perform physical constraint checks on multi-source data; If the physical constraint check is passed, statistical testing is performed; If the physical constraint check fails, an exception is flagged; S12: Pass 3 Statistical testing of the rules; If the statistical test is passed, multimodal data are obtained; If the statistical test fails, it is marked as abnormal; S13: Compensate and correct the data with abnormal markings to obtain multimodal data.

[0006] Furthermore, in step S2, the state equation of the adaptive Kalman filter is: in, for The state vector at time t, is the state transition matrix, for The state vector at time t, is the control input matrix, for The control input vector at time , for The process noise at the moment, for The observation vector at time t, is the observation matrix, for The observation noise at the moment; Prediction step: in, for The prior state estimate at time t, for The posterior state estimate at time t, for The prior covariance matrix at time , for The posterior covariance matrix at time , is the process noise covariance matrix; Update step: in, for The Kalman gain at time t, for The posterior state estimate at time t, is the inverse matrix of the matrix, is the observation noise covariance matrix, is the Huber loss function, is the transpose of the matrix.

[0007] Furthermore, step S3 includes: S31: Calculate the statistical significance of the residual vector through a chi-square test, and determine the sensor state based on the statistical significance of the residual vector; S32: If the sensor is normal, perform Kalman update; If the sensor is abnormal, determine whether the sensor has been reset. If the sensor has been reset, re-collect sensor data and execute step S1. If the sensor has not been reset, set the sensor isolation time and reset the sensor within the sensor isolation time.

[0008] Furthermore, in step S31, Anomaly detection is performed through the chi-square test, like , the sensor is normal; like , then the sensor is abnormal; in, for The residual vector at time , is the critical value of the chi-square distribution, for The prior covariance matrix at time , is the observation noise covariance matrix, is the transpose of the matrix, is the inverse matrix of the matrix.

[0009] Furthermore, in step S4, The calculation expression of sensor weight is: in, For the The fusion weight of each sensor, For the Real-time variance of each sensor; is the sensor weight attenuation coefficient, M is the number of sensors involved in the fusion, For the Real-time variance of each sensor; No. The calculation expression of the real-time variance of each sensor is: in, is the observation vector of the first sensor, is the observation matrix of the first sensor, is the observation vector of the first sensor, is the observation matrix of the first sensor, is the current state estimation of the system, is the length of the sliding time window, is the Euclidean norm, is the current time.

[0010] Further, in the S5 step, S51: performing a Mercator projection transformation on the fusion data to obtain rendering coordinates; S52: calculating a detail level switching condition according to the rendering coordinates, selecting a rendering detail level according to the detail level switching condition, and performing detail level marking; S53: performing alarm judgment according to the detail level marking, and performing rendering sorting according to the alarm judgment; If there is an alarm, a dynamic transparency is calculated, which is used for visual differentiation of alarms of the same level; a level priority is defined, which is used for covering of alarms across levels; If there is no alarm, the default rendering is maintained.

[0011] Further, in the S6 step, S61: calculating the rendering load of the current frame by a frame rate control module, and if the system is overloaded, reducing the detail level and adjusting the rendering parameters; If the system is not overloaded, the current rendering parameters are maintained; S62: repeating the S61 step to sequentially complete the load detection and rendering parameter adjustment of all frames according to the rendering sorting.

[0012] The application also provides a dynamic rendering engine implementation system based on multi-source data fusion, which is used to execute the above-mentioned dynamic rendering engine implementation method based on multi-source data fusion, comprising: A data acquisition unit, which acquires multi-source data in real time, and pre-processes the multi-source data to obtain multi-modal data; A prediction unit, which performs time alignment and coordinate conversion on the multi-modal data through space-time registration, and predicts the converted multi-modal data through adaptive Kalman filtering to obtain current prediction data; A detection unit, which calculates a residual error according to the current prediction data and the converted multi-modal data, and performs sensor anomaly detection according to the residual error to obtain a sensor state; A fusion unit, which weights and fuses the sensor data according to the sensor state to obtain fusion data; The rendering unit carries out Mercator projection transformation on the fused data, obtains rendering coordinates, and carries out detail level marking according to the rendering coordinates; alarm judgment is carried out according to the detail level marking, and rendering sequencing is carried out according to the alarm judgment; The adjusting unit carries out load detection and rendering parameter adjustment according to the rendering sequencing through a frame rate control module.

[0013] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects: In multi-source data fusion processing, the problem of time and space reference difference of sensor data is solved by a time and space registration technology, and a Huber robust kernel function is introduced into a Kalman filter algorithm for data fusion. Based on the real-time measurement variance of each sensor, the fusion weight is dynamically calculated to realize optimal estimation. Fault sensors are identified through chi-square test, and a dynamic isolation strategy is implemented. The multi-source data after fusion is converted into a unified Mercator projection coordinate system, the rendering precision level is automatically adjusted according to the target distance, the high-precision model is used for close distance, the medium-precision model is switched for medium distance, and the simplified model is used for long distance. The periodic transparency adjustment algorithm is used for alarm information, and hierarchical rendering is implemented according to the three-level priority of collision alarm, boundary alarm and general target. Through the adaptive frame rate control technology, the rendering period is dynamically adjusted according to the system load while ensuring the reference performance. The present application supports dynamic rendering of the sea chart, route planning, equipment state monitoring and other core navigation functions, can be directly integrated into the existing shipborne navigation system, has low modification cost and strong compatibility, and has important application value for improving the safety and autonomy of ship navigation, and is especially suitable for high-precision and high-reliability scenes such as ocean transportation and special ships.

[0014] Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following and / or can be learned by practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0016] Fig. 1 It is a flowchart of the implementation method of the dynamic rendering engine based on multi-source data fusion provided by the present application.

[0017] Fig. 2 It is a structural schematic diagram of the dynamic rendering engine implementation system based on multi-source data fusion provided by the present application.

[0018] Reference signs: 101, data acquisition unit; 102, prediction unit; 103, detection unit; 104, fusion unit; 105, rendering unit; 106, adjustment unit. DETAILED DESCRIPTION

[0019] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the protection scope of the present application. The following embodiments are used to illustrate the present application, but cannot be used to limit the scope of the present application.

[0020] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in combination with the embodiment or example are contained in at least one embodiment or example of the embodiments of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0021] The following will be described in combination with Figs. 1-2 The present application describes a dynamic rendering engine implementation method and system based on multi-source data fusion.

[0022] The navigation system faces the shipborne navigation system composed of a display control terminal, a data processing server and multiple sensors. In addition to containing the basic control and communication module, the display control terminal needs to carry the AngularJS framework to realize information visualization, the data processing server needs to configure the background service developed by Python+Qt, and the Conn and History double-structure databases are established. Among them, the high-precision navigation equipment (such as optical fiber inertial navigation) is directly connected to the data processing server, and the ordinary navigation equipment is connected through the RS-422 or Ethernet interface. The original data collected by the navigation equipment is standardized and analyzed, and then the front-end and back-end data interaction is realized through the intermediate database. The inertial measurement unit provides attitude and motion information, the satellite navigation equipment provides absolute position reference, and the radar / AIS equipment provides surrounding situation information.

[0023] The navigation information processing method provided by the application is based on a distributed system architecture, first, through multi-thread concurrent collection, synchronous acquisition of 11 types of sensor data is realized, and data checking mechanism is used to filter abnormal data packets; second, a transaction management strategy of "emptying-inserting-overwriting" is adopted to ensure the atomicity of database operation, sensitive data protection is realized through three-level permission control; finally, comprehensive display of navigation situation is realized on the front-end display and control interface, functions such as dynamic rendering of the chart, route planning, equipment state monitoring and the like are supported, intelligent identification and processing of abnormal conditions are realized through four-level alarm classification, and finally a complete closed-loop system from data acquisition, processing to display is formed.

[0024] The system is initialized and a hardware self-check is performed, and the communication state of the equipment is detected in turn, specifically, the satellite navigation device: verifying the $GPGGA statement of NMEA-0183 protocol received; The inertial navigation device: checking the FOG-148 state register (0xAA55 indicates normal); The radar: sending PING to test network delay (threshold ≤ 50 ms).

[0025] Software initialization: configuration file loading, reading database connection parameters in SlaveConf.ini, setting sensor sampling rate.

[0026] Database initialization: creating Conn / History library table structure; establishing a database connection pool.

[0027] Real-time acquisition of multi-source data, and preprocessing of the multi-source data, obtaining multi-modal data; Time synchronization enhancement, exponential weight dynamic compensation clock bias, Time synchronization formula: Among them, is the system unified time reference, is the UTC time provided by the satellite navigation device, is the dynamic clock bias compensation amount; The calculation expression of the dynamic clock bias compensation amount is: Among them, is the satellite navigation clock weight, is the deviation of the satellite navigation clock and the system master clock, is the inertial navigation clock weight, is the deviation of the inertial navigation clock and the system master clock.

[0028] The calculation expression of the weight is: Among them, is the first The weight of the clock, is the clock weight attenuation coefficient, For the The variance of a clock source is an indicator of sensor stability.

[0029] In some specific embodiments of the present invention, .

[0030] like Fig. 1 As shown, a method for implementing a dynamic rendering engine based on multi-source data fusion includes: S1: Real-time collection of multi-source data, and pre-processing of multi-source data to obtain multimodal data; Multi-source data includes satellite navigation data, inertial navigation data, radar data and AIS data.

[0031] S11: Perform physical constraint checks on multi-source data; If the physical constraint check is passed, statistical testing is performed; If the physical constraint check fails, an exception is flagged; The calculation expression for physical constraint checking is: in, For physical constraints, Speed ​​data provided by AIS, is the attitude change rate, For height.

[0032] S12: Pass 3 Statistical testing of the rules; If the statistical test is passed, multimodal data are obtained; If the statistical test fails, it is marked as abnormal; The calculation expression is: in, For statistical verification, is the active window mean, For multi-source data, , For the Data source data, is the number of data sources; In some specific embodiments of the present invention, .

[0033] S13: Compensate and correct the data with abnormal markings to obtain multimodal data; The calculation expression of the standard deviation of the time is: wherein, is the standard deviation of the time, is a weighting coefficient, is the standard deviation of the time, is the time data.

[0034] A single verification failure is a transient anomaly, which is compensated by linear interpolation: the calculation expression is: wherein, is the compensated data, is the data of the time, is the data of the time; Three consecutive failures are persistent anomalies, and the data source is switched; Device state anomaly is a hardware failure, triggering the first alarm and isolating the device.

[0035] S2: time alignment and coordinate conversion of multi-modal data through space-time registration, and prediction of the converted multi-modal data through adaptive Kalman filtering to obtain current prediction data; Space-time registration includes time alignment and coordinate conversion, The calculation expression of time alignment is: wherein, is the aligned time, is the sensor local timestamp, is the sensor fixed delay, is the current time, is the initial capture time of the sensor data packet, is the delay time of data from generation to processing, is the first dynamic compensation coefficient, is the second dynamic compensation coefficient.

[0036] In some specific embodiments of the present application, , .

[0037] Convert the sensor coordinate system to the world coordinate system, and the calculation expression is: wherein, is the converted world coordinate system, is the fixed displacement vector between the sensor installation position and the origin of the carrier coordinate system, is the yaw angle, is the pitch angle, The first intermediate matrix, is the second intermediate matrix, is the sensor coordinate system, The calculation expression is: The calculation expression is: The state equation of the adaptive Kalman filter is: in, for The state vector at time t, is the state transition matrix, for The state vector at time t, is the control input matrix, for The control input vector at time , for The process noise at the moment, , is the process noise covariance matrix, for The observation vector at time t, is the observation matrix, for The observation noise at time , is the observation noise covariance matrix, Include Variables at time , are three-dimensional coordinates, is the three-dimensional velocity, is the roll angle, is the pitch angle, is the yaw angle; Prediction step: in, for The prior state estimate at time t, for The posterior state estimate at time t, for The prior covariance matrix at time , for The posterior covariance matrix at time , is the transpose of the matrix, is the process noise covariance matrix; Update step: wherein, is Kalman gain at time t, is posterior state estimate at time t, is observation noise covariance matrix, is Huber loss function, is the inverse matrix of matrix; The calculation expression of Huber loss function is: wherein, is robust kernel threshold, is the input variable of function.

[0038] In some specific embodiments of the present application, .

[0039] S3: calculating residual according to current predicted data and converted multi-modal data, performing sensor anomaly detection according to residual, and obtaining sensor state; S31: calculating statistical significance of residual vector through chi-square test, and judging sensor state according to statistical significance of residual vector; performing anomaly detection through chi-square test, if , the sensor is normal; if , the sensor is abnormal; wherein, is residual vector at time t, is chi-square distribution critical value, is prior covariance matrix at time t, is observation matrix, is observation noise covariance matrix; S32: if the sensor is normal, performing Kalman update; if the sensor is abnormal, judging whether the sensor has been reset, if the sensor has been reset, re-collecting sensor data, and performing S1 step, if the sensor has not been reset, setting sensor isolation duration, and resetting the sensor within the sensor isolation duration; The calculation expression of sensor isolation duration is: wherein, is sensor isolation duration, is minimum value function, is the i-th Real-time variance of each sensor; When a sensor is frequently marked as faulty due to residual errors, setting an isolation duration can temporarily exclude it from data fusion, such as reducing its weight or directly isolating it, to prevent continued interference from abnormal observations and ensure the accuracy of system state estimation.

[0040] S4: Perform weighted fusion on the sensor data according to the sensor state to obtain fused data; The calculation expression of sensor weight is: in, For the The fusion weight of each sensor, For the Real-time variance of each sensor; is the sensor weight attenuation coefficient, M is the number of sensors involved in the fusion, For the Real-time variance of each sensor; No. The calculation expression of the real-time variance of each sensor is: in, For the The observation vector of each sensor, For the The observation matrix of sensors, is the current state estimate of the system, is the length of the sliding time window; is the Euclidean norm.

[0041] In some specific embodiments of the present invention, .

[0042] S5: Perform Mercator projection transformation on the fused data to obtain sea rendering coordinates, and mark the detail level according to the chart coordinates and system performance parameters; make alarm judgments based on the detail level markings, and perform rendering sorting based on the alarm judgments; S51: Perform Mercator projection transformation on the fused data to obtain rendering coordinates; The calculation expression of Mercator projection transformation is: in, is the horizontal coordinate of the target point, is the longitudinal coordinate of the target point; is the target longitude of the target point, is the target latitude of the target point, is the longitude of the projection center; R is the radius of the earth; S52: Calculate the detail level switching condition according to the rendering coordinates, select the rendering detail level according to the detail level switching condition, and mark the detail level; According to the distance between the target and the observer, the rendering details are dynamically adjusted to optimize performance while ensuring visual effects. In close range, high-precision models are used, such as more triangles and high-definition textures; in long distance, low-precision models are used, such as simplified geometry and compressed textures; aiming to balance rendering quality and computational load; Detail level switching condition: Wherein, is the first level of detail level; is the projection coordinate of the target in the view coordinate system; is the distance threshold; is the high-precision mode; is the medium-precision mode; is the low-precision mode; Performance optimization index: Wherein, is the rendering cost, which is a quantitative performance evaluation index, used to measure the computational resource consumption required for rendering a specific object, is the number of model triangles, used to measure the geometric complexity of the model, is the number of texture pixels, used to measure the texture memory and sampling pressure, is the geometric weight coefficient, used to measure the influence weight of the number of triangles, typical value 0.7; is the texture weight coefficient, used to measure the influence weight of the texture resolution, typical value 0.3; S53: Alarm judgment according to the detail level mark, rendering sorting according to the alarm judgment; If there is an alarm, calculate the dynamic transparency, which is used for visual differentiation of alarms in the same level; define the level priority, which is used for coverage of cross-level alarms; The calculation expression of dynamic transparency is: Wherein, is the alarm state transparency; is the flicker frequency, typical value 1Hz.

[0043] The calculation expression of level priority is: Wherein, is the level priority, the system is arranged from =3 to 1 sequential rendering, i.e. regular target → boundary alert → collision alert, even if the dynamic transparency is the same, the high-level content will cover the low-level content; If there is no alert, the default rendering is maintained.

[0044] S6: Load detection and rendering parameter adjustment are performed by the frame rate control module according to the rendering order; S61: The rendering load of the current frame is calculated by the frame rate control module, and if the system is overloaded, the detail level is reduced and the rendering parameter is adjusted.

[0045] The calculation expression of the target frame period is: wherein, is the target frame period, is the reference period, is the actual time consumption of the last frame, is the load buffer coefficient, is the maximum value function; The calculation expression of the system load rate is: wherein, is the system load rate, which is used to measure the resource occupation rate of the current frame; is the rendering cost of the i-th model, which comprehensively considers the geometry and texture complexity; is the number of rendered objects in the current frame; is the target frame period. If the system is not overloaded, the current rendering parameter is maintained.

[0046] If the system is overloaded, the detail level is reduced and the rendering parameter is adjusted, and the adjustment of the rendering parameter includes the adjustment of the target frame period.

[0047] In some embodiments of the present application,

[0048] , . S62: Repeat the load detection and rendering parameter adjustment of all frames according to the rendering order in step S61.

[0049] The device state, navigation situation and alert information are displayed through a visual interface, interactive operations such as chart zooming and route planning are supported, system parameters can be adjusted by a special configuration tool, such as modifying the sensor weight coefficient and adjusting the alert threshold, the system log records the complete operation trajectory, and supports post-audit analysis.

[0050] For example,

[0051] Fig. 2 ​As shown, a dynamic rendering engine implementation system based on multi-source data fusion is used to execute a dynamic rendering engine implementation method based on multi-source data fusion, comprising: The data acquisition unit 101 collects multi-source data in real time, and pre-processes the multi-source data to obtain multi-modal data; The prediction unit 102 performs time alignment and coordinate conversion on the multi-modal data through space-time registration, and predicts the converted multi-modal data through adaptive Kalman filtering to obtain current prediction data; The detection unit 103 calculates the residual according to the current prediction data and the converted multi-modal data, and performs sensor anomaly detection according to the residual to obtain the sensor state; The fusion unit 104 weights and fuses the sensor data according to the sensor state to obtain fused data; The rendering unit 105 performs Mercator projection transformation on the fused data to obtain chart coordinates, and performs detail level marking according to the chart coordinates and system performance parameters; according to the alarm judgment, the rendering sorting is carried out; The adjustment unit 106 performs load detection and rendering parameter adjustment according to the rendering sorting through the frame rate control module.

[0052] Through the cooperative work of the above-mentioned modules, the space-time reference difference problem of sensor data is solved through space-time registration technology in multi-source data fusion processing, and Huber robust kernel function is introduced in Kalman filtering algorithm for data fusion. Based on the real-time measurement variance of each sensor, the fusion weight is dynamically calculated to realize optimal estimation. Through chi-square test, the faulty sensor is identified, and a dynamic isolation strategy is implemented. The fused multi-source data is converted into a unified Mercator projection coordinate system, the rendering precision level is automatically adjusted according to the target distance, the high-precision model is used for short-distance, the medium-precision model is switched for medium-distance, and the simplified model is used for long-distance. The alarm information adopts periodic transparency adjustment algorithm, and hierarchical rendering is implemented according to the three priority levels of collision alarm, boundary alarm and conventional target. Through adaptive frame rate control technology, the rendering period is dynamically adjusted according to the system load while ensuring the reference performance. The present application supports dynamic rendering of chart, route planning, equipment state monitoring and other core navigation functions, and can be directly integrated into the existing shipborne navigation system. The transformation cost is low, the compatibility is strong, and it has important application value for improving the safety and autonomy of ship navigation, especially suitable for high-precision and high-reliability scenes such as ocean transportation and special ships.

[0053] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for implementing a dynamic rendering engine based on multi-source data fusion, characterized in that: include: S1: Real-time collection of multi-source data, and pre-processing of multi-source data to obtain multimodal data; S2: Time alignment and coordinate conversion of multimodal data are performed through spatiotemporal registration, and adaptive Kalman filtering is used to predict the converted multimodal data to obtain the current predicted data; S3: Calculate the residual based on the current prediction data and the converted multimodal data, perform sensor anomaly detection based on the residual, and obtain the sensor status; S4: Perform weighted fusion on the sensor data according to the sensor state to obtain fused data; S5: Perform Mercator projection transformation on the fused data to obtain rendering coordinates, mark the detail level according to the rendering coordinates; make alarm judgments based on the detail level marks, and perform rendering sorting based on the alarm judgments; S6: Perform load detection and rendering parameter adjustment based on rendering order through the frame rate control module.

2. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 1, characterized in that: The multi-source data includes satellite navigation data, inertial navigation data, radar data and AIS data.

3. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 1, characterized in that: Step S1 includes: S11: Perform physical constraint checks on multi-source data; If the physical constraint check is passed, statistical testing is performed; If the physical constraint check fails, an exception is flagged; S12: Pass 3 Statistical testing of the rules; If the statistical test is passed, multimodal data are obtained; If the statistical test fails, it is marked as abnormal; S13: Compensate and correct the data with abnormal markings to obtain multimodal data.

4. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 1, characterized in that: In step S2, the state equation of the adaptive Kalman filter is: in, for The state vector at time t, is the state transition matrix, for The state vector at time t, is the control input matrix, for The control input vector at time , for The process noise at the moment, for The observation vector at time t, is the observation matrix, for The observation noise at the moment; Prediction step: in, for The prior state estimate at time t, for The posterior state estimate at time t, for The prior covariance matrix at time , for The posterior covariance matrix at time , is the process noise covariance matrix; Update step: in, for The Kalman gain at time t, for The posterior state estimate at time t, is the inverse matrix of the matrix, is the observation noise covariance matrix, is the Huber loss function, is the transpose of the matrix.

5. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 1, characterized in that: The S3 steps include: S31: Calculate the statistical significance of the residual vector through a chi-square test, and determine the sensor state based on the statistical significance of the residual vector; S32: If the sensor is normal, perform Kalman update; If the sensor is abnormal, determine whether the sensor has been reset. If the sensor has been reset, re-collect sensor data and execute step S1. If the sensor has not been reset, set the sensor isolation time and reset the sensor within the sensor isolation time.

6. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 5, characterized in that: In step S31, Anomaly detection is performed through the chi-square test, like , the sensor is normal; like , then the sensor is abnormal; in, for The residual vector at time , is the critical value of the chi-square distribution, for The prior covariance matrix at time , is the observation matrix, is the observation noise covariance matrix, is the transpose of the matrix, is the inverse matrix of the matrix.

7. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 1, characterized in that: In step S4, The calculation expression of sensor weight is: in, For the The fusion weight of each sensor, For the Real-time variance of each sensor; is the sensor weight attenuation coefficient, M is the number of sensors involved in the fusion, For the Real-time variance of each sensor; No. The calculation expression of the real-time variance of each sensor is: in, For the The observation vector of each sensor, For the The observation matrix of sensors, is the current state estimate of the system, is the length of the sliding time window, is the Euclidean norm, For the current moment.

8. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 1, characterized in that: In step S5, S51: Perform Mercator projection transformation on the fused data to obtain rendering coordinates; S52: Calculating a detail level switching condition according to the rendering coordinates, selecting a rendering detail level according to the detail level switching condition, and marking the detail level; S53: Performing an alarm judgment based on the detail level mark, and performing rendering sorting based on the alarm judgment; If an alarm exists, dynamic transparency is calculated. Dynamic transparency is used to visually distinguish alarms at the same level. Define layer priorities, which are used to cover cross-layer alarms; If there is no warning, keep the default rendering.

9. The method for implementing a dynamic rendering engine based on multi-source data fusion according to claim 1, characterized in that: In step S6, S61: Calculate the rendering load of the current frame through the frame rate control module. If the system is overloaded, reduce the detail level and adjust the rendering parameters. If the system is not overloaded, keep the current rendering parameters; S62: Repeat step S61 to complete the load detection and rendering parameter adjustment of all frames in sequence according to the rendering order.

10. A dynamic rendering engine implementation system based on multi-source data fusion, characterized in that: The method for implementing a dynamic rendering engine based on multi-source data fusion as claimed in any one of claims 1 to 9 comprises: A data acquisition unit, which collects multi-source data in real time and pre-processes the multi-source data to obtain multi-modal data; A prediction unit, wherein the prediction unit performs time alignment and coordinate conversion on the multimodal data through spatiotemporal registration, and predicts the converted multimodal data through adaptive Kalman filtering to obtain current prediction data; a detection unit, wherein the detection unit calculates a residual based on the current prediction data and the converted multimodal data, performs sensor anomaly detection based on the residual, and obtains a sensor state; a fusion unit, wherein the fusion unit performs weighted fusion on the sensor data according to the sensor state to obtain fused data; A rendering unit, wherein the rendering unit performs a Mercator projection transformation on the fused data to obtain rendering coordinates, marks the detail level according to the rendering coordinates, makes an alarm judgment according to the detail level marking, and performs rendering sorting according to the alarm judgment; An adjustment unit performs load detection and rendering parameter adjustment according to the rendering sequence through a frame rate control module.

Images