High-stability vehicle-mounted safety prevention and control equipment and method based on Beidou communication

Abstract

The invention discloses a high-stability vehicle-mounted safety prevention and control device and method based on Beidou communication, relates to the technical field of vehicle-mounted safety, and solves the problems of positioning drift and early warning lag in the prior art. The system comprises a main control processor, and a multi-source positioning module, a driver behavior monitoring module, an environment sensing module and a multi-mode communication module which are connected with the main control processor, and a data processing module and a power management module which are connected with the driver behavior monitoring module and the environment sensing module; the multi-source positioning module is integrated with a Beidou / GNSS dual-mode positioning chip and an inertial navigation unit, and is used for realizing positioning compensation in a signal shielding area through a Kalman filtering algorithm; the driver behavior monitoring module is connected with the main control processor, and the driver behavior monitoring module is used for detecting facial features and limb actions of a driver in real time; the main control processor is configured to execute multi-source data fusion processing and generate an early warning signal. The method has the effect of remarkably reducing the accident risk.

Description

Technical Field

[0001] This application relates to the field of vehicle safety technology, and in particular to a highly stable vehicle safety control device and method based on Beidou communication. Background Technology

[0002] With the rapid development of ride-hailing, taxi, and commercial vehicle fleets, vehicle operation safety and management efficiency have become core industry demands. However, traditional in-vehicle equipment has limited functionality, mostly confined to basic GPS positioning or simple video recording, making it difficult to meet the needs of high-precision positioning, real-time monitoring, proactive early warning, and intelligent management. Furthermore, existing technologies primarily rely on GPS for vehicle positioning, but its signal is easily blocked in complex environments such as urban canyons and tunnels, resulting in insufficient positioning accuracy and stability. This leads to vehicle trajectory drift or loss, severely impacting the reliability of dispatching and safety monitoring.

[0003] Furthermore, in terms of driver behavior monitoring, existing technologies mostly rely on offline analysis or periodic reporting, lacking real-time capabilities and making it difficult to promptly correct dangerous behaviors such as fatigued driving and distracted driving. At the same time, data transmission from in-vehicle devices depends on 4G / 5G networks, which are prone to communication interruptions in remote areas or when network coverage is poor, leading to the loss of critical data and impacting safety management efficiency.

[0004] Therefore, there is an urgent need for a highly stable vehicle safety control solution that integrates multi-source data. This solution should combine high-precision BeiDou positioning, real-time video analysis, driver behavior monitoring, and multi-mode communication technology to improve the safety and management efficiency of vehicle operations and solve problems such as positioning drift and delayed early warning in existing technologies. Summary of the Invention

[0005] To improve the problems of vehicle positioning drift and early warning lag in the existing technology, this application provides a highly stable vehicle-mounted safety control device and method based on Beidou communication.

[0006] This application provides a highly stable vehicle-mounted safety control device and method based on BeiDou communication, adopting the following technical solution:

[0007] A highly stable vehicle-mounted safety control device based on Beidou communication includes a main control processor, a multi-source positioning module connected to the main control processor, a driver behavior monitoring module, an environmental perception module, a multi-mode communication module, a data processing module connected to the driver behavior monitoring module and the environmental perception module, and a power management module.

[0008] The multi-source positioning module integrates a BeiDou / GNSS dual-mode positioning chip and an inertial navigation unit, which is used to achieve positioning compensation in signal-blocked areas through a Kalman filter algorithm.

[0009] The driver behavior monitoring module is connected to the main control processor. The driver behavior monitoring module includes an infrared camera and a millimeter-wave radar, which are used to detect the driver's facial features and body movements in real time.

[0010] The environmental perception module includes a forward-facing ADAS camera and a surround-view fisheye lens for collecting data on the vehicle's surrounding environment; the multi-mode communication module supports BeiDou short message service, 4G / 5G and V2X communication, and automatically switches transmission links according to network conditions; the main control processor is configured to perform multi-source data fusion processing and generate early warning signals.

[0011] Preferably, the multi-source positioning module further includes a high-precision differential positioning unit and a motion state detection unit. The high-precision differential positioning unit achieves sub-meter positioning accuracy by receiving differential correction data broadcast by the BeiDou ground-based augmentation system. The motion state detection unit includes a three-axis accelerometer and a gyroscope, which are used to maintain dead reckoning for at least 30 seconds in a tunnel environment.

[0012] Preferably, the driver behavior monitoring module employs a convolutional neural network. The driver behavior monitoring module includes an eye state recognition submodule, a head posture analysis submodule, and a head posture analysis submodule. The eye state recognition submodule is used to detect blinking frequency and eye closure duration. The head posture analysis submodule determines the level of attention distraction through feature point tracking. The handheld object detection submodule identifies smoking and mobile phone use behaviors.

[0013] Preferably, the environment sensing module includes:

[0014] The system includes a forward-facing 120° wide-angle camera, a 77GHz millimeter-wave radar for distance detection, and a data processing unit. The forward-facing 120° wide-angle camera supports HDR imaging and nighttime infrared illumination. The data processing unit uses the YOLOv5 algorithm to identify pedestrians, vehicles, and obstacles in real time.

[0015] Preferably, the multi-mode communication module includes a network quality detection unit, an intelligent switching unit, and a data compression unit. The network quality detection unit monitors the quality indicators of each communication channel in real time, and the intelligent switching unit uses H.265 encoding to compress the video stream.

[0016] Preferably, the main control processor is configured as follows:

[0017] Establish a driving risk prediction model based on deep reinforcement learning;

[0018] When signs of fatigued driving are detected, a warning mechanism is triggered.

[0019] Generate structured alarm messages containing location data, behavior analysis results, and environmental information;

[0020] Meanwhile, the main control processor is equipped with an emergency event discrimination model, which triggers an immediate warning when the following conditions are met simultaneously:

[0021] The location data showed a position jump greater than 2σ after 5 consecutive updates.

[0022] Millimeter-wave radar detected a sudden obstacle within 50 meters ahead;

[0023] The driver's eyelid closure is >80% for more than 1.5 seconds.

[0024] A highly stable vehicle-mounted safety control method based on BeiDou communication includes the following steps:

[0025] S1. Simultaneously collect vehicle positioning data, driver biometrics, and surrounding environment information through multi-source sensors;

[0026] S2. The federated filtering algorithm is used to fuse BeiDou positioning data and inertial navigation data;

[0027] S3. Real-time analysis of driver's facial features; triggers fatigue warning when closed eyes are detected three times in a row.

[0028] S4. Dynamically select the communication method based on network conditions, and prioritize the transmission of emergency alarm information via BeiDou short message service;

[0029] S5. When the electronic fence is triggered, automatically upload an encrypted data packet containing latitude and longitude, vehicle speed, and driving status.

[0030] Preferably, step S2 includes weighted fusion of BeiDou pseudorange measurements and inertial navigation-calculated positions in an urban canyon environment; and when the satellite loses lock for more than a threshold time, a trajectory prediction algorithm based on a motion model is activated.

[0031] Preferably, the communication method selection strategy in step S4 includes establishing a communication quality assessment matrix, which includes parameters such as signal strength, transmission delay, and bit error rate; emergency event data is preferentially transmitted using BeiDou RDSS service; and routine monitoring data is transmitted in segments using 4G / 5G networks.

[0032] In summary, this application includes at least one of the following beneficial effects:

[0033] 1. This application achieves sub-meter positioning accuracy in complex environments such as urban canyons and tunnels by integrating BeiDou / GNSS dual-mode positioning with an inertial navigation unit (including a three-axis accelerometer / gyroscope), combined with Kalman filtering algorithm and differential positioning technology, thus improving the trajectory drift problem caused by traditional GPS signal blockage.

[0034] 2. Employing multimodal perception with infrared cameras and millimeter-wave radar, and using CNN algorithms to achieve real-time analysis of blink frequency, head posture, and handheld objects (such as mobile phones), the fatigue driving detection response time is less than 0.5 seconds, and the three-level early warning mechanism (voice → vibration → cloud alarm) significantly reduces the risk of accidents;

[0035] 3. It adopts integrated BeiDou short message service (RDSS), 4G / 5G, and V2X communication, and dynamically selects the optimal link through intelligent switching unit. When the network is interrupted, BeiDou emergency transmission is automatically activated to ensure the reliability of communication in remote areas. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the working process of the vehicle positioning device in this embodiment of the application. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0040] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in certain circumstances to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.

[0041] In addition, the term "multiple" should mean two or more.

[0042] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0043] This application discloses a highly stable vehicle-mounted safety control device based on BeiDou communication, configured on a vehicle. The device includes a main control processor, a multi-source positioning module connected to the main control processor, a driver behavior monitoring module, an environmental perception module, a multi-mode communication module, a data processing module connected to the driver behavior monitoring module and the environmental perception module, and a power management module. The main control processor can use a Rockchip RK3588 chip, with a built-in dual-core NPU, responsible for running multi-source data fusion algorithms (federated filtering + Kalman filtering) and driving risk prediction models (based on PPO reinforcement learning algorithm).

[0044] Furthermore, the multi-source positioning module integrates a BeiDou / GNSS dual-mode positioning chip and an inertial navigation unit, used to achieve positioning compensation in signal-blocked areas through a Kalman filter algorithm. The Kalman filter algorithm employs an adaptive noise covariance adjustment strategy, automatically increasing the process noise weight when satellite signal lock is lost. Its positioning compensation error in tunnel environments does not exceed 0.3% of the total positioning mileage. Additionally, when the warning signal generation delay is less than 200ms, obstacle recognition can be accelerated by pre-loading an environmental feature library.

[0045] The inertial navigation unit includes an MPU-9250 nine-axis sensor, which achieves positioning compensation within the tunnel using an extended Kalman filter (EKF), with a positioning error of less than 1.5m / 30s. The multi-source positioning module also includes a high-precision differential positioning unit and a motion state detection unit. The high-precision differential positioning unit receives differential correction data broadcast by the BeiDou ground-based augmentation system to achieve sub-meter-level positioning results; the motion state detection unit includes a three-axis accelerometer and a gyroscope, used to maintain dead reckoning for at least 30 seconds in the tunnel environment.

[0046] Furthermore, the driver behavior monitoring module is connected to the main control processor. This module includes an infrared camera and millimeter-wave radar for real-time detection of the driver's facial features and body movements. The driver behavior monitoring module also employs a convolutional neural network and includes an eye state recognition submodule and a head posture analysis submodule. The eye state recognition submodule detects blink frequency and eye closure duration, the head posture analysis submodule determines the level of attention distraction through feature point tracking, and a handheld object detection submodule identifies behaviors such as smoking and mobile phone use.

[0047] The environmental perception module includes a forward-facing ADAS camera and a surround-view fisheye lens for collecting data on the vehicle's surrounding environment. The multi-mode communication module supports BeiDou short message service, 4G / 5G, and V2X communication, and automatically switches transmission links based on network conditions. The main control processor is configured to perform multi-source data fusion processing and generate warning signals. The environmental perception module also includes a forward-facing 120° wide-angle camera, a 77GHz millimeter-wave radar for distance detection, and a data processing unit. The forward-facing 120° wide-angle camera supports HDR imaging and nighttime infrared illumination. The data processing unit uses the YOLOv5 algorithm to identify pedestrians, vehicles, and obstacles in real time.

[0048] Furthermore, the multi-mode communication module includes a network quality detection unit, an intelligent switching unit, and a data compression unit. The network quality detection unit monitors the quality indicators of each communication channel in real time, and the intelligent switching unit uses H.265 encoding to compress the video stream.

[0049] Furthermore, the main control processor is configured to establish a driving risk prediction model based on deep reinforcement learning. Simultaneously, the in-vehicle safety control device in this application uses machine vision technology based on video analytics to automatically identify road risks and unsafe driving behaviors of the driver. Any detected event will trigger an audible alarm to remind the driver in real time; these events will also be synchronized to the platform, such as: forward collision warning, lane departure warning, driver fatigue warning, distracted driving warning, smoking warning, and phone call alarm.

[0050] Specific alarm methods include: when fatigue driving characteristics (such as closed eyes or yawning) are detected, an early warning mechanism is triggered; a structured alarm message containing location data, behavioral analysis results, and environmental information is generated. Simultaneously, the main control processor has a built-in emergency event discrimination model, which triggers an immediate warning when the following conditions are met:

[0051] The location data showed a position jump greater than 2σ after 5 consecutive updates.

[0052] Millimeter-wave radar detected a sudden obstacle within 50 meters ahead;

[0053] The driver's eyelid closure is >80% for more than 1.5 seconds.

[0054] A highly stable vehicle-mounted safety control method based on BeiDou communication includes the following steps:

[0055] S1. Simultaneously collect vehicle positioning data, driver biometrics, and surrounding environment information through multi-source sensors;

[0056] S2. The federated filtering algorithm is used to fuse BeiDou positioning data and inertial navigation data;

[0057] S3. Real-time analysis of driver's facial features; when eye closure is detected for more than 2 seconds three times in a row, a fatigue warning is triggered.

[0058] S4. Dynamically select the communication method based on network conditions, and prioritize the transmission of emergency alarm information via BeiDou short message service;

[0059] S5. When the electronic fence is triggered, automatically upload an encrypted data packet containing latitude and longitude, vehicle speed, and driving status.

[0060] Furthermore, step S2 includes weighted fusion of BeiDou pseudorange measurements and inertial navigation-calculated positions in an urban canyon environment; when the satellite loses lock for more than a threshold time, a trajectory prediction algorithm based on a motion model is activated.

[0061] Furthermore, the communication method selection strategy in step S4 includes establishing a communication quality assessment matrix, which includes parameters such as signal strength, transmission delay, and bit error rate; emergency event data is preferentially transmitted using BeiDou RDSS service; and routine monitoring data is transmitted in segments using 4G / 5G networks.

[0062] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A highly stable vehicle-mounted safety control device based on BeiDou communication, characterized in that: It includes a main control processor, a multi-source positioning module connected to the main control processor, a driver behavior monitoring module, an environmental perception module, a multi-mode communication module, a data processing module connected to the driver behavior monitoring module and the environmental perception module, and a power management module; The multi-source positioning module integrates a BeiDou / GNSS dual-mode positioning chip and an inertial navigation unit, which is used to achieve positioning compensation in signal-blocked areas through a Kalman filter algorithm. The driver behavior monitoring module is connected to the main control processor. The driver behavior monitoring module includes an infrared camera and a millimeter-wave radar, which are used to detect the driver's facial features and body movements in real time. The environmental perception module includes a forward-facing ADAS camera and a surround-view fisheye lens for collecting data on the vehicle's surrounding environment; the multi-mode communication module supports BeiDou short message service, 4G / 5G and V2X communication, and automatically switches transmission links according to network conditions; the main control processor is configured to perform multi-source data fusion processing and generate early warning signals.

2. The highly stable vehicle-mounted safety control device based on BeiDou communication according to claim 1, characterized in that: The multi-source positioning module also includes a high-precision differential positioning unit and a motion state detection unit. The high-precision differential positioning unit achieves sub-meter positioning accuracy by receiving differential correction data broadcast by the BeiDou ground-based augmentation system. The motion state detection unit includes a three-axis accelerometer and a gyroscope, which are used to maintain dead reckoning for at least 30 seconds in a tunnel environment.

3. The highly stable vehicle-mounted safety control device based on BeiDou communication according to claim 1, characterized in that: The driver behavior monitoring module employs a convolutional neural network and includes an eye state recognition submodule, a head posture analysis submodule, and a head posture analysis submodule. The eye state recognition submodule is used to detect blinking frequency and eye closure duration. The head posture analysis submodule determines the level of attention distraction through feature point tracking. The handheld object detection submodule identifies smoking and mobile phone use behaviors.

4. The highly stable vehicle-mounted safety control device based on BeiDou communication according to claim 1, characterized in that: The environment sensing module includes: The system includes a forward-facing 120° wide-angle camera, a 77GHz millimeter-wave radar for distance detection, and a data processing unit. The forward-facing 120° wide-angle camera supports HDR imaging and nighttime infrared illumination. The data processing unit uses the YOLOv5 algorithm to identify pedestrians, vehicles, and obstacles in real time.

5. A highly stable vehicle-mounted safety control device based on BeiDou communication according to claim 1, characterized in that: The multi-mode communication module includes a network quality detection unit, an intelligent switching unit, and a data compression unit. The network quality detection unit monitors the quality indicators of each communication channel in real time, and the intelligent switching unit uses H.265 encoding to compress the video stream.

6. A highly stable vehicle-mounted safety control device based on BeiDou communication according to claim 1, characterized in that: The main control processor is configured as follows: Establish a driving risk prediction model based on deep reinforcement learning; When signs of fatigued driving are detected, a warning mechanism is triggered. Generate structured alarm messages containing location data, behavior analysis results, and environmental information; Meanwhile, the main control processor is equipped with an emergency event discrimination model, which triggers an immediate warning when the following conditions are met simultaneously: The location data showed a position jump greater than 2σ after 5 consecutive updates. Millimeter-wave radar detected a sudden obstacle within 50 meters ahead; The driver's eyelid closure is greater than 80% for more than 1.5 seconds.

7. A method based on the device according to any one of claims 1-6, characterized in that: Includes the following steps: S1. Simultaneously collect vehicle positioning data, driver biometrics, and surrounding environment information through multi-source sensors; S2. The federated filtering algorithm is used to fuse BeiDou positioning data and inertial navigation data; S3. Real-time analysis of driver's facial features; triggers fatigue warning when closed eyes are detected three times in a row. S4. Dynamically select the communication method based on network conditions, and prioritize the transmission of emergency alarm information via BeiDou short message service; S5. When the electronic fence is triggered, automatically upload an encrypted data packet containing latitude and longitude, vehicle speed, and driving status.

8. The method according to claim 7, characterized in that Step S2 includes: In urban canyon environments, BeiDou pseudorange measurements are weighted and fused with inertial navigation-derived positions; when a satellite loses lock for more than a threshold time, a trajectory prediction algorithm based on a motion model is activated.

9. The method according to claim 7, characterized in that: The communication method selection strategy in step S4 includes: Establish a communication quality assessment matrix, including parameters such as signal strength, transmission delay, and bit error rate; Emergency event data will be transmitted using BeiDou RDSS service as a priority. Regular monitoring data is transmitted in segments using 4G / 5G networks.

Images