A motorcycle multi-sensor fusion crash for help system, medium and product

Abstract

This invention discloses a motorcycle crash distress signaling system, medium, and product based on multi-sensor fusion, relating to the field of sensors. In this method, the motorcycle's posture is detected by an IMU module as an initial judgment criterion. This is combined with multi-dimensional data such as rider posture detected by a camera, handlebar grip status detected by handlebar detection, and speed changes to confirm the crash. When an abnormal posture is detected, the system cross-validates rider position, handlebar grip status, and speed changes to improve accuracy. Simultaneously, the system employs a redundant power supply system consisting of a supercapacitor and a DC-DC converter. During normal riding, power is drawn from the motorcycle battery to charge the supercapacitor. When the battery is disconnected, the supercapacitor supplies power through the converter, ensuring that distress signals can still be sent during an accident. This invention improves adaptability to complex riding scenarios and power supply reliability during accidents, while ensuring timely transmission of rescue information.

Description

Technical Field

[0001] This application belongs to the field of sensors, and in particular relates to a motorcycle multi-sensor fusion crash rescue system, medium and product. Background Technology

[0002] As motorcycles become increasingly popular as an economical and efficient mode of transportation worldwide, motorcycle safety issues are also becoming more prominent. Motorcycle riders have a significantly higher fatality rate in road accidents than other motor vehicle drivers. However, existing motorcycle safety systems primarily focus on passive safety equipment, such as helmets and protective clothing, and their emergency response mechanisms after accidents remain inadequate.

[0003] Currently available motorcycle crash detection products generally rely on an IMU (6-axis gyroscope) to determine the motorcycle's posture, thereby identifying whether a crash has occurred and enabling subsequent rescue efforts.

[0004] However, this single-sensor detection method lacks confirmation of the rider's actual state, leading to serious false alarms and missed alarms in certain scenarios. For example, when the rider is reversing or performing aggressive driving maneuvers, the system may misinterpret normal operation as a crash; conversely, some low-speed crashes may be ignored by the system due to subtle changes in posture. Furthermore, existing products generally use the motorcycle battery as the sole power source, meaning that in the event of a serious accident causing the battery to disconnect or be damaged, the entire emergency assistance system will be inoperable, losing its critical emergency response capability. This situation requires further improvement. Summary of the Invention

[0005] This application provides a motorcycle crash emergency response system, medium, and product based on multi-sensor fusion, used to accurately detect motorcycle crashes and automatically send emergency signals. By fusing data from multiple sensors and combining it with intelligent algorithm analysis, this system reduces the probability of false alarms and missed alarms caused by relying on a single sensor in existing technologies. Furthermore, the use of a supercapacitor design ensures reliable operation even in extreme accident scenarios.

[0006] In a first aspect, this application provides a motorcycle multi-sensor fusion crash assistance system, including: processor; The camera component is used to detect whether the rider is in a normal riding posture; Handlebar detection component, used to detect whether the rider is holding the handlebars; The IMU module is used to detect changes in the motorcycle's attitude. The vehicle speed detection module is used to connect to the motorcycle's speed sensor or to the motorcycle's CAN bus network. The communication module is used to connect to the backend server; The processor determines whether a crash is possible based on the changes in the motorcycle's posture detected by the IMU module, and confirms this by combining the detection results of the camera component, the handlebar detection component, and the vehicle speed detection module. When a crash is confirmed, a distress signal is sent through the communication module. The power module includes a supercapacitor and a DC-DC converter. The power module draws power from the motorcycle battery to supply power to the system and charges the supercapacitor. When the motorcycle battery is disconnected, the supercapacitor supplies power to the system through the DC-DC converter.

[0007] In the above implementation, the system uses the IMU module to detect the motorcycle's posture as an initial judgment basis, and combines it with multi-dimensional data such as the rider's posture, handlebar detection for grip status, and speed changes to confirm the crash. When the posture is judged to be abnormal, the system will cross-verify the rider's position, grip status, and speed changes to improve the accuracy of the judgment. At the same time, the system uses a supercapacitor and a DC-DC converter to form a redundant power supply system. During normal riding, it draws power from the motorcycle battery to charge the supercapacitor. When the battery is disconnected, the supercapacitor takes over the power supply through the converter, ensuring that it can still send distress signals in the event of an accident. This improves the adaptability to complex riding scenarios and the reliability of power supply in the event of an accident, while ensuring the timely transmission of rescue information.

[0008] In one embodiment, the system further includes: The positioning module is used to obtain the current location information of the motorcycle; Bluetooth module, used to connect to the rider's mobile phone; When a crash is confirmed, the processor controls the rider's mobile phone to dial an emergency contact number via the Bluetooth module, and sends the location information obtained by the positioning module to the emergency contact and the backend server.

[0009] In the above implementation, the system obtains the precise location information of the motorcycle in real time through the positioning module, and establishes a connection with the rider's mobile phone through the Bluetooth module. When the system confirms that a crash has occurred, the processor not only sends a distress signal to the backend server through the communication module, but also directly controls the rider's mobile phone to automatically dial the preset emergency contact number through the Bluetooth module, and sends the accurate location information obtained by the positioning module to the emergency contact and the backend server at the same time, thereby improving the reliability and timeliness of the rescue response.

[0010] In one embodiment, the system further includes: The alarm module is used to issue an audible alert when an abnormal riding condition is detected but it is uncertain whether it is a crash. The user input interface is used to receive confirmation or cancellation signals from the rider. Specifically, when the processor determines an abnormal riding state based on changes in motorcycle posture detected by the IMU module, but has not yet confirmed a crash, the processor controls the alarm module to enter a warning state and issue an audible alert. If a cancellation signal from the rider is received through the user input interface within a preset time, the alarm process is terminated. If no cancellation signal from the rider is received within the preset time, the processor further confirms whether a crash has occurred by combining the detection results from the camera component, the handlebar detection component, and the vehicle speed detection module. When a crash is confirmed, a distress signal is sent through the communication module.

[0011] In the above implementation, when the processor detects an abnormal change in the motorcycle's posture based on the IMU module, but the threshold for determining a crash has not yet been reached, the system will issue an audible warning through the alarm module to alert the rider of a potential risk. At this time, the rider can send a cancellation signal through the user input interface to terminate the false alarm process and avoid unnecessary calls for help. If the rider does not respond within a preset time, the system will automatically activate a more comprehensive detection process, combining multi-dimensional data such as rider posture from the camera, handlebar grip status detection, and changes in vehicle speed for in-depth analysis to further confirm whether a crash has actually occurred. This solution can reduce the system's false alarm rate, improve the user experience, and ensure that the system can quickly and accurately make a judgment and send a call for help when a real crash occurs, achieving an effective balance between system intelligence and practicality.

[0012] In one embodiment, the processor further includes a sensor data quality assessment module and a weight dynamic allocation module; The sensor data quality assessment module analyzes the consistency, stability and noise level of each sensor data in real time, and assigns a confidence score to the camera component, the handle detection component, the IMU module and the vehicle speed detection module. The weight dynamic allocation module calculates the optimal weight allocation scheme based on the credibility score and the current environmental conditions, which include lighting conditions, weather conditions, and road surface type.

[0013] In the above implementation, the sensor data quality assessment module can monitor and analyze the consistency, stability, and noise level of each sensor data in real time, assigning objective reliability scores to the camera component, handlebar detection component, IMU module, and vehicle speed detection module to reflect the current reliability of each sensor data. Based on these scores, the weight dynamic allocation module further combines environmental factors such as lighting conditions, weather conditions, and road surface type to calculate the optimal sensor data weight allocation scheme. For example, at night or in strong light, the system will automatically reduce the weight of camera data and increase the weight of IMU and handlebar detection. When riding on rough roads, the system will appropriately reduce the weight of IMU data to avoid road vibration interference. This adaptive weight adjustment mechanism significantly improves the detection accuracy of the system under various complex environments and conditions, effectively reduces misjudgments caused by environmental factors, and enables the system to maintain stable and reliable performance in different riding scenarios.

[0014] In one implementation, the processor further performs the following steps: Based on the confidence score assigned by the sensor data quality assessment module, the sensor data with the highest confidence level is selected as the main judgment criterion. When the reliability score of the IMU module is lower than a preset threshold, the weight of the camera component is increased, and an image deep learning algorithm is enabled to enhance the accuracy of rider posture recognition. When the confidence score of the camera component is lower than a preset threshold, the weights of the handle detection component and the IMU module are increased, and a multi-frame data analysis algorithm is enabled to reduce ambient light interference.

[0015] In the above implementation, the processor intelligently selects the sensor data with the highest confidence level as the main judgment basis based on the confidence score assigned by the sensor data quality assessment module, ensuring that the system always makes decisions based on the most reliable data source. When the confidence score of the IMU module drops below a preset threshold due to severe vibration or special road conditions, the system automatically increases the weight of the camera component and activates the image deep learning algorithm to enhance the recognition accuracy of rider posture, thereby compensating for the impact of the decline in IMU data quality. When the confidence of the camera component decreases due to insufficient light, strong light interference, or foggy and rainy weather, the system increases the weight of the handlebar detection component and the IMU module and uses a multi-frame data analysis algorithm to process the image, effectively reducing interference caused by changes in ambient light.

[0016] In one embodiment, the processor further includes a crash probability prediction module and a graded response module; The crash probability prediction module receives motorcycle posture change data detected by the IMU module and data from the vehicle speed detection module, and calculates the probability value of a crash occurring within a preset time period. The graded response module executes different levels of response measures based on the probability value: when the probability value is below the first threshold, the system maintains normal monitoring status; when the probability value is between the first threshold and the second threshold, the sampling frequency of all sensors is increased and a warning signal is sent to the rider through the alarm module; when the probability value exceeds the second threshold, the data buffer recording function is activated and the communication module is pre-activated, while a warning is issued through the alarm module. When a crash is confirmed, the processor extracts the pre-crash data and the instantaneous crash data from the data buffer and sends them as part of the crash report through the communication module.

[0017] In the above implementation, the crash probability prediction module receives motorcycle posture change data detected by the IMU module and speed information from the vehicle speed detection module. It calculates the probability value of a crash occurring within a preset time period through a data analysis algorithm. Based on this probability value, the graded response module can execute different levels of response measures. The graded response strategy saves system resources and can adjust the system state in a timely manner when the risk increases. In addition, when a crash is confirmed, the system can extract the data before the crash and the data at the moment of the crash from the data buffer and send them through the communication module as part of the crash report, thereby improving rescue efficiency and the accuracy of accident cause analysis.

[0018] In one embodiment, the system further includes an intelligent power management module; The intelligent power management module monitors the energy consumption status of each component of the system and configures power resources according to the current riding scenario. Under normal riding conditions, the IMU module and the handlebar detection component maintain a high-frequency sampling mode, while the camera component and the communication module operate intermittently. When the IMU module detects an abnormal riding state, the intelligent power management module controls the camera component and the communication module to switch to a high-frequency sampling mode; The intelligent power management module also monitors the voltage status of the motorcycle battery. When abnormal voltage fluctuations are detected, it pre-activates the discharge preparation program of the supercapacitor.

[0019] In the above implementation, the intelligent power management module monitors the energy consumption of each component and dynamically configures power resources according to the riding scenario, thereby achieving efficient use of system energy. During normal riding, the IMU module and handlebar detection component maintain high-frequency sampling to ensure basic safety monitoring, while the high-energy-consuming camera and communication module adopt intermittent operation to save energy. When an abnormal riding state is detected, the system immediately increases the sampling frequency of the camera and communication module to ensure comprehensive data acquisition and prepare communication resources. At the same time, the module also monitors the battery voltage status and pre-activates the supercapacitor discharge preparation program when abnormal fluctuations are detected, ensuring seamless switching to backup power when the main power fails, thereby improving the system's reliability and continuous working capability in emergency situations.

[0020] Secondly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a system, cause the system to perform the functions of the system as described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product that, when run on a system, causes the system to perform the functions of the system as described in any possible implementation of the first aspect.

[0022] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. This application provides a motorcycle crash rescue system based on multi-sensor fusion. It uses an IMU module to detect the motorcycle's posture as an initial assessment, combined with multi-dimensional data such as rider posture detected by a camera, handlebar grip status detected by the camera, and speed changes to confirm the crash. When an abnormal posture is detected, the system cross-verifies the rider's position, handlebar grip status, and speed changes to improve accuracy. Simultaneously, the system employs a redundant power supply system consisting of a supercapacitor and a DC-DC converter. During normal riding, power is drawn from the motorcycle battery to charge the supercapacitor. When the battery is disconnected, the supercapacitor takes over power supply via the converter, ensuring that a rescue signal can still be sent during an accident. This improves adaptability to complex riding scenarios and power supply reliability during accidents, while also ensuring timely transmission of rescue information.

[0023] 2. This application provides a motorcycle multi-sensor fusion crash assistance system. When the processor detects an abnormal change in the motorcycle's posture based on the IMU module, but the change has not yet reached the threshold for determining a crash, the system will issue an audible warning through the alarm module to alert the rider of a potential risk. At this time, the rider can send a cancellation signal through the user input interface to terminate the false alarm process and avoid unnecessary requests for assistance. If the rider does not respond within a preset time, the system will automatically activate a more comprehensive detection process, combining multi-dimensional data such as rider posture from the camera, handlebar grip status from the sensor, and changes in vehicle speed for in-depth analysis to further confirm whether a crash has actually occurred. This system can reduce the false alarm rate and improve the user experience, while ensuring that the system can quickly and accurately make a judgment and send an assistance signal when a real crash occurs, achieving an effective balance between system intelligence and practicality.

[0024] 3. This application provides a motorcycle multi-sensor fusion crash rescue system. The sensor data quality assessment module can monitor and analyze the consistency, stability and noise level of each sensor data in real time, and assign objective credibility scores to the camera component, handlebar detection component, IMU module and vehicle speed detection module to reflect the reliability of each sensor data at present. Based on these scores, the weight dynamic allocation module further combines environmental factors such as lighting conditions, weather conditions and road surface type to calculate the optimal sensor data weight allocation scheme, so that the system can maintain stable and reliable performance in different riding scenarios. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of the structure of a motorcycle multi-sensor fusion crash rescue system according to an embodiment of this application. Figure 1 .

[0026] Figure 2 This is a schematic diagram of the physical device structure of a motorcycle multi-sensor fusion crash rescue system provided in an embodiment of this application. Detailed Implementation

[0027] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0029] In the field of motorcycle safety monitoring and rescue, accurate and timely crash detection and emergency assistance functions are crucial for improving rider survival rates after accidents.

[0030] In related technologies, most motorcycle crash detection systems rely on a single IMU sensor to determine changes in the vehicle's posture, which cannot cope with diverse crash scenarios and generally suffers from power supply reliability issues. These systems are prone to false alarms during normal operations such as reversing or sharp turns, while they may miss alarms in situations such as low-speed crashes, and they completely lose their functionality when the battery is disconnected.

[0031] This application is primarily applied to diverse riding scenarios such as daily commuting, long-distance travel, and track riding on motorcycles, aiming to provide comprehensive rider safety protection. In these application scenarios, the system needs to accurately identify various crash accidents, while eliminating interference factors during normal riding, and ensuring reliable transmission of distress signals in the event of an accident. To address the aforementioned technical problems, this application provides a motorcycle multi-sensor fusion crash distress signaling system, medium, and product. An embodiment is described below in conjunction with… Figure 1 This application describes a motorcycle crash rescue system based on multi-sensor fusion in an embodiment: Please see Figure 1 This is a schematic diagram of the structure of a motorcycle multi-sensor fusion crash rescue system according to an embodiment of this application. Figure 1 .

[0032] like Figure 1 As shown, this embodiment provides a motorcycle multi-sensor fusion crash rescue system. The system mainly includes a processor, a camera component, a handlebar detection component, an IMU module, a vehicle speed detection module, a communication module, a power supply module, a positioning module, and a Bluetooth module.

[0033] The processor, as the core control unit of the system, is responsible for receiving and processing data from various sensors and making decisions. The camera assembly, mounted on the front of the motorcycle or on the dashboard, can capture real-time images of the rider's riding posture and use image processing algorithms to determine if the rider is in a normal riding posture. The handlebar detection assembly, mounted on the motorcycle handlebars, can be a pressure sensor or a capacitive sensor, used to detect whether the rider is gripping the handlebars. The IMU module, containing an accelerometer and a gyroscope, is mounted in a stable position on the motorcycle to monitor real-time changes in the motorcycle's attitude, including parameters such as tilt angle and acceleration changes. The speed detection module obtains real-time speed information by connecting to the motorcycle's original speed sensor or directly connecting to the motorcycle's CAN bus network. The communication module integrates 4G communication functionality to transmit the data and alarm information collected by the system to the backend server.

[0034] The power module is crucial for the stable operation of the system. The power module in this application comprises a supercapacitor and a DC-DC converter. Under normal circumstances, the power module draws power from the motorcycle battery to supply power to the entire system and simultaneously charges the supercapacitor. In the event of a serious accident that causes the motorcycle battery to disconnect or be damaged, the supercapacitor will take over the power supply via the DC-DC converter, ensuring that the system can still operate normally and send distress signals in critical moments.

[0035] Furthermore, the positioning module incorporates a GPS or BeiDou positioning chip to obtain the motorcycle's precise location information, providing accurate rescue positioning in emergencies. The Bluetooth module establishes a wireless connection with the rider's mobile phone. Upon confirmation of a crash, the system can control the rider's phone via Bluetooth to automatically dial a pre-set emergency contact number and simultaneously send the location information obtained by the positioning module to the emergency contact and the backend server.

[0036] In one embodiment, the system also includes an alarm module and a user input interface. When the processor determines an abnormal riding state based on data detected by the IMU module but has not yet confirmed a crash, it controls the alarm module to enter a warning state and emit an audible alert to remind the rider. At this time, the rider can send a cancellation signal through the user input interface to terminate the false alarm process. If no response is received from the rider within a preset time, the system will combine data from other sensors to further confirm whether a crash has occurred, avoiding potential misjudgments from a single sensor.

[0037] In one embodiment, the processor further includes a sensor data quality assessment module and a weight dynamic allocation module; wherein, the sensor data quality assessment module analyzes the consistency, stability and noise level of each sensor data in real time, and assigns a confidence score to the camera component, the handlebar detection component, the IMU module and the vehicle speed detection module; the weight dynamic allocation module calculates the optimal weight allocation scheme based on the confidence score and the current environmental conditions, including lighting conditions, weather conditions and road surface type.

[0038] The sensor data quality assessment module continuously evaluates the quality characteristics of data from various sensors using computer algorithms. "Consistency" refers to the degree of agreement between multiple samples from the same sensor within a short period; high consistency indicates stable and reliable sensor readings. "Stability" measures the fluctuation of sensor data under static or uniform conditions, reflecting the sensor's baseline performance. "Noise level" quantifies the strength of interference signals in the sensor data. The dynamic weight allocation module is an adaptive algorithm system that analyzes the combination of current reliability scores and environmental factors to calculate the most suitable sensor data fusion scheme for the current situation, enabling the system to maintain high accuracy in crash detection under various complex environments.

[0039] Specifically, for the IMU module, the system calculates the standard deviation and spectral analysis results of triaxial acceleration and angular velocity data; for the camera component, the system evaluates image sharpness, illumination uniformity, and target detection confidence; for the handlebar detection component, the system monitors the fluctuation range and frequency of pressure values; for the vehicle speed detection module, the system analyzes the smoothness of speed data and its consistency with expected changes. The weight dynamic allocation module uses a weighted average algorithm, with the basic formula W=(α·S+β·E) / (α+β), where W is the final weight, S is the confidence score, E is the environmental adaptability coefficient, and α and β are adjustable parameters. Environmental conditions are obtained through camera image analysis, weather API data matched with time and geographic location, and IMU vibration characteristic analysis. Optionally, a deep learning-based sensor fusion method can be used, employing recurrent neural networks or long short-term memory networks to process time-series sensor data. The system collects normal riding data from the rider during the initial use phase of the motorcycle to establish a personalized baseline, and then continuously optimizes the model through incremental learning.

[0040] Furthermore, when the IMU module detects that the motorcycle's lean angle exceeds a preset cornering threshold, the system does not immediately classify it as a crash. Instead, it calls upon data from the handlebar detection component. If the system detects that the rider is still maintaining an effective grip on the handlebars, and the camera component identifies the rider's skeletal key points as actively controlling their posture, it is classified as "active cornering." The system maintains monitoring and reduces the IMU's crash detection weight. If the IMU detects a sudden change in posture, and the handlebar detection component detects a sudden disappearance of grip (indicating that the rider has separated from the vehicle), combined with the abnormal displacement of the rider's skeletal key points and vehicle key points identified by the camera, it is classified as "passive crashing," and the system immediately triggers a distress signal. In addition, the system establishes a personalized riding baseline for the rider through incremental learning during the initialization phase. For example, for high-frequency cornering data from track riders, the system automatically increases the weight of the handlebar detection component in the dynamic weight allocation, thereby suppressing false alarms in non-crash scenarios.

[0041] In some embodiments, sensors may suddenly fail. To address this, the system is designed with a "degraded operation" mechanism. When a sensor's reliability score falls below 20 points for 10 consecutive times, the system determines that it has failed, automatically reallocates the weights of the remaining sensors, and sends a maintenance reminder to the rider.

[0042] In one embodiment, the processor further performs the following steps: based on the confidence score assigned by the sensor data quality assessment module, selects the sensor data with the highest confidence as the main judgment criterion; when the confidence score of the IMU module is lower than a preset threshold, increases the weight of the camera component and enables an image deep learning algorithm to enhance the accuracy of rider posture recognition; when the confidence score of the camera component is lower than a preset threshold, increases the weight of the handlebar detection component and the IMU module and enables a multi-frame data analysis algorithm to reduce ambient light interference.

[0043] The system first obtains real-time reliability scores for each sensor through a sensor data quality assessment module. When a sensor's score is significantly higher than others, the system automatically increases that sensor's weight in the final judgment by at least 50%, prioritizing high-reliability data to ensure the system's decisions are based on the most reliable data. For example, when the IMU module's reliability score falls below a preset threshold of 65 due to external interference or internal malfunction, the system increases the weight coefficient of the camera component in data fusion calculation from the standard weight of 0.25 to 0.40. Simultaneously, it activates image deep learning algorithms that are normally in standby mode. For instance, a pre-trained convolutional neural network model can accurately identify key postural features from images acquired by the camera, such as the rider's upper body tilt angle, head position, and torso twisting degree, thereby determining whether the rider is in a normal riding posture. At this time, the sampling frequency of the camera component is also increased to obtain more detailed data on rider posture changes.

[0044] In the above embodiments, this application provides a motorcycle crash distress signaling system based on multi-sensor fusion, achieving high-precision crash detection through multi-sensor data fusion technology. The system employs multiple sensors, including a camera module, handlebar detection module, IMU module, and vehicle speed detection module, working collaboratively. It intelligently adjusts the weights of each sensor's data through a sensor data quality evaluation module and a dynamic weight allocation module, ensuring high accuracy in crash detection under various complex environments. Furthermore, the system is equipped with a specially designed power module, including a redundant power supply system consisting of a supercapacitor and a DC-DC converter, ensuring that the system can still function normally and send distress signals even when the motorcycle battery is disconnected due to a serious accident.

[0045] In one embodiment, the system further includes a crash probability prediction module, a graded response module, and an intelligent power management module.

[0046] The crash probability prediction module receives and analyzes real-time data on motorcycle posture changes detected by the IMU module and speed data from the speed detection module to calculate the probability of a crash occurring within a preset timeframe, such as 3 seconds. This module employs a sliding time window technique, combining historical data patterns and current data trends, and uses a statistical learning algorithm to generate crash risk probabilities ranging from 0% to 100%. For example, the system detects the rate of change of the motorcycle's tilt angle, acceleration fluctuation patterns, and their correlation with the current speed to identify abnormal riding conditions that could lead to a crash.

[0047] The graded response module implements a three-level response strategy based on the probability value output by the crash probability prediction module: When the probability value is below the first threshold, the system maintains normal monitoring and collects data at the standard sampling frequency; when the probability value is between the first and second thresholds, the system increases the sampling frequency of all sensors to obtain more refined data, and at the same time, it sends an audible or vibration warning signal to the rider through the alarm module to remind them of potential risks; when the probability value exceeds the second threshold, the system activates the data buffer recording function, begins to cyclically store all raw sensor data from the last 30 seconds, and pre-activates the communication module to put it into a ready state to shorten the possible emergency communication initiation time, while simultaneously issuing a stronger warning through the alarm module, such as a high-frequency audible alarm or a strong vibration alert.

[0048] Once the system confirms a crash, the processor retrieves pre-crash and instantaneous crash data from the data buffer and sends it as part of the crash report to the backend server and emergency contacts via the communication module. This data includes not only IMU data and speed change curves but may also contain crucial footage captured by cameras.

[0049] The intelligent power management module is responsible for monitoring the energy consumption status of each component in the system and dynamically configuring power resources according to the current riding scenario to extend the system's operating time and ensure power supply during critical moments. Under normal riding conditions, the IMU module and handlebar detection components, due to their relatively low energy consumption and high real-time requirements, maintain a high-frequency sampling mode (e.g., 50Hz); while the higher-energy-consuming camera components and communication module adopt an intermittent working mode. The camera may collect an image every 2 seconds, and the communication module establishes a heartbeat connection with the server once per minute when there is no emergency.

[0050] When the IMU module detects abnormal riding conditions, the intelligent power management module immediately adjusts its operating strategy, controlling the camera components to switch to high-frequency sampling mode, and the communication module also enters standby mode to prepare for possible emergency communication. In addition, the intelligent power management module continuously monitors the motorcycle battery voltage. When abnormal voltage fluctuations are detected, it pre-activates the supercapacitor's discharge preparation program to ensure that the backup power supply can seamlessly take over the system's power supply in the event of a potential main power failure. Optionally, the intelligent power management module can also achieve dynamic power consumption adjustment based on riding scenarios. For example, when riding at low speeds in the city, the system reduces the IMU sampling frequency to save energy; when riding on highways, the system increases the sampling frequency of the IMU and vehicle speed detection module to ensure timely capture of abnormal situations at high speeds; when riding at night, the system increases the camera's exposure time and enables infrared illumination to ensure image quality.

[0051] In the above embodiments, the system analyzes IMU data and vehicle speed data in real time through the crash probability prediction module, which can identify potential dangerous situations in advance; the graded response module intelligently adjusts the system status and resource allocation according to the risk level, realizing a smooth transition from early warning to emergency; and the intelligent power management module dynamically adjusts the working mode and energy allocation of each component according to the riding scenario and system status, which not only extends the daily use time, but also ensures that the system has sufficient power support in emergency situations.

[0052] The system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 2 This is a schematic diagram of the physical device structure of a motorcycle multi-sensor fusion crash rescue system provided in an embodiment of this application.

[0053] It should be noted that, Figure 2 The structure of the system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0054] like Figure 2 As shown, the system includes a CPU, which can perform various appropriate actions and processes based on a program stored in the ROM or a program loaded into the RAM from a storage portion, such as executing the methods described in the above embodiments. The RAM also stores various programs and data required for system operation. The CPU, ROM, and RAM are interconnected via a bus. I / O interfaces are also connected to the bus.

[0055] The following components are connected to the I / O interface: input sections including cameras, infrared sensors, etc.; output sections including liquid crystal displays (LCDs) and speakers, etc.; storage sections including hard drives, etc.; and communication sections including network interface cards such as LAN (Local Area Network) cards and modems, etc. The communication section performs communication processing via a network such as the Internet. Drives are also connected to the I / O interface as needed. Removable media, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as needed.

[0056] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a CPU, it performs the various functions defined in the present invention.

[0057] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. The transmitted data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0058] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0059] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the system described in the above embodiments; or it may exist independently and not assembled into the system. The storage medium carries one or more computer programs that, when executed by a processor of a system, cause the system to implement the methods provided in the above embodiments.

[0060] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0061] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0062] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0063] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A motorcycle crash rescue system based on multi-sensor fusion, characterized in that, include: processor; The camera component is used to detect whether the rider is in a normal riding posture; Handlebar detection component, used to detect whether the rider is holding the handlebars; The IMU module is used to detect changes in the motorcycle's attitude. The vehicle speed detection module is used to connect to the motorcycle's speed sensor or to the motorcycle's CAN bus network. The communication module is used to connect to the backend server; The processor determines whether a crash is possible based on the changes in the motorcycle's posture detected by the IMU module, and confirms this by combining the detection results of the camera component, the handlebar detection component, and the vehicle speed detection module. When a crash is confirmed, a distress signal is sent through the communication module. The power module includes a supercapacitor and a DC-DC converter. The power module draws power from the motorcycle battery to supply power to the system and charges the supercapacitor. When the motorcycle battery is disconnected, the supercapacitor supplies power to the system through the DC-DC converter.

2. The system according to claim 1, characterized in that, The system also includes: The positioning module is used to obtain the current location information of the motorcycle; Bluetooth module, used to connect to the rider's mobile phone; When a crash is confirmed, the processor controls the rider's mobile phone to dial an emergency contact number via the Bluetooth module, and sends the location information obtained by the positioning module to the emergency contact and the backend server.

3. The system according to claim 1, characterized in that, The system also includes: The alarm module is used to issue an audible alert when an abnormal riding condition is detected but it is uncertain whether it is a crash. The user input interface is used to receive confirmation or cancellation signals from the rider. Specifically, when the processor determines an abnormal riding state based on changes in motorcycle posture detected by the IMU module, but has not yet confirmed a crash, the processor controls the alarm module to enter a warning state and issue an audible alert. If a cancellation signal from the rider is received through the user input interface within a preset time, the alarm process is terminated. If no cancellation signal from the rider is received within the preset time, the processor further confirms whether a crash has occurred by combining the detection results from the camera component, the handlebar detection component, and the vehicle speed detection module. When a crash is confirmed, a distress signal is sent through the communication module.

4. The system according to claim 1, characterized in that, The processor also includes a sensor data quality assessment module and a weight dynamic allocation module; The sensor data quality assessment module analyzes the consistency, stability and noise level of each sensor data in real time, and assigns a confidence score to the camera component, the handle detection component, the IMU module and the vehicle speed detection module. The weight dynamic allocation module calculates the optimal weight allocation scheme based on the credibility score and the current environmental conditions, which include lighting conditions, weather conditions, and road surface type.

5. The system according to claim 4, characterized in that, The processor also performs the following steps: Based on the confidence score assigned by the sensor data quality assessment module, the sensor data with the highest confidence level is selected as the main judgment criterion. When the reliability score of the IMU module is lower than a preset threshold, the weight of the camera component is increased, and an image deep learning algorithm is enabled to enhance the accuracy of rider posture recognition. When the confidence score of the camera component is lower than a preset threshold, the weights of the handle detection component and the IMU module are increased, and a multi-frame data analysis algorithm is enabled to reduce ambient light interference.

6. The system according to claim 3, characterized in that, The processor also includes a crash probability prediction module and a graded response module; The crash probability prediction module receives motorcycle posture change data detected by the IMU module and data from the vehicle speed detection module, and calculates the probability value of a crash occurring within a preset time period. The graded response module executes different levels of response measures based on the probability value: when the probability value is below the first threshold, the system maintains normal monitoring status; when the probability value is between the first threshold and the second threshold, the sampling frequency of all sensors is increased and a warning signal is sent to the rider through the alarm module; when the probability value exceeds the second threshold, the data buffer recording function is activated and the communication module is pre-activated, while a warning is issued through the alarm module. When a crash is confirmed, the processor extracts the pre-crash data and the instantaneous crash data from the data buffer and sends them as part of the crash report through the communication module.

7. The system according to claim 3, characterized in that, The system also includes an intelligent power management module; The intelligent power management module monitors the energy consumption status of each component of the system and configures power resources according to the current riding scenario. Under normal riding conditions, the IMU module and the handlebar detection component maintain a high-frequency sampling mode, while the camera component and the communication module operate intermittently. When the IMU module detects an abnormal riding state, the intelligent power management module controls the camera component and the communication module to switch to a high-frequency sampling mode; The intelligent power management module also monitors the voltage status of the motorcycle battery. When abnormal voltage fluctuations are detected, it pre-activates the discharge preparation program of the supercapacitor.

8. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on the system, the system performs the functions of the system as described in any one of claims 1-7.

9. A computer program product, characterized in that, When the computer program product is run on the system, it causes the system to perform the functions of the system as described in any one of claims 1-7.

Images