Intelligent driving recording system, method, medium and equipment
Through the design of the intelligent driving record system, the use of neural network models to identify and record vehicle driving data, solving the problem that traditional driving recorders cannot provide early warning and in-depth data analysis in real time, and significantly improving driving safety and accident handling efficiency.
Patent Information
- Application Number
- CN202411008079.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-26
AI Technical Summary
Traditional dash recorders cannot provide real-time early warning or in-depth data analysis services, resulting in the prominent road traffic safety problems and the inability to automatically and accurately identify and record key events during driving.
Design an intelligent driving recording system, including a vehicle data acquisition unit, an event recognition unit and an early warning unit, use a trained neural network model to identify vehicle driving data, and automatically recognize and record driving through voice warning and data storage modules. key event.
It realizes automatic and accurate identification and recording of key events in driving, such as sudden braking and collisions, improves driving safety and accident handling efficiency, and maximizes data utilization value through cloud data analysis platforms.
Smart Images

Figure CN119028043A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent transportation technology, and in particular to an intelligent driving recorder system, method, medium and equipment. Background Art
[0002] As the number of cars increases, road traffic safety issues are becoming increasingly prominent. Although traditional dashcams can record driving videos, they often rely on manual judgment or post-analysis to determine key events and cannot provide real-time warnings or in-depth data analysis services.
[0003] In view of the deficiencies in the prior art, the present invention aims to provide an intelligent driving recorder system that can automatically and accurately identify and record key events during driving, such as sudden braking, collisions, etc., so as to improve driving safety and accident handling efficiency. Summary of the invention
[0004] The purpose of the present invention is to overcome the deficiencies of the above-mentioned background technology and to provide an intelligent driving recorder system, method, medium and device that can automatically and accurately identify and record key events during driving to improve driving safety and accident handling efficiency.
[0005] In a first aspect, an intelligent driving recorder system is provided, comprising:
[0006] On-vehicle data collection unit, used to collect vehicle driving data;
[0007] an event recognition unit, which is in communication with the vehicle-mounted data acquisition unit and is used to use the trained neural network model to perform driving event recognition on the vehicle driving data to obtain a target driving event result; and
[0008] The early warning unit is connected to the vehicle data collection unit and the event recognition unit for displaying the vehicle driving data and the target driving event result and providing a voice early warning for the target driving event result.
[0009] In some embodiments, the step of obtaining the trained neural network model is: constructing an event recognition network model based on a machine learning algorithm and a deep learning algorithm, and training the event recognition network model using data samples with labeled event types to obtain a trained neural network model.
[0010] In some embodiments, the step of using the trained neural network model to identify the vehicle driving data and obtain the target driving event result specifically includes the following steps:
[0011] Dividing the vehicle driving data into continuous data blocks, extracting features of each data block, and obtaining corresponding feature vectors;
[0012] Performing driving event recognition on each of the feature vectors to obtain the driving event type and the probability corresponding to the driving event type;
[0013] If the probability corresponding to the driving event type is greater than a preset threshold, it is determined that the vehicle has experienced the identified driving event type.
[0014] In some embodiments, the vehicle-mounted data acquisition module includes:
[0015] A camera is used to collect vehicle driving scene videos;
[0016] An acceleration sensor, used to detect vehicle acceleration data;
[0017] Gyroscope, used to detect the vehicle's driving posture and direction changes;
[0018] GPS locator, used to collect vehicle location information and driving speed data.
[0019] In some embodiments, the early warning unit includes:
[0020] A display screen, used to display the vehicle driving data and the target driving event result;
[0021] The voice warning system is used to provide voice warning for the target driving event result.
[0022] In some embodiments, it also includes a data storage module that is communicatively connected to the vehicle-mounted data acquisition unit and the event recognition unit, and the data storage module is used to store the vehicle driving data and the target driving event results.
[0023] In a second aspect, a smart driving record recognition method is provided, comprising the following steps:
[0024] Control the vehicle-mounted data acquisition module to collect vehicle driving data;
[0025] The control event recognition unit uses the trained neural network model to perform driving event recognition on the vehicle driving data to obtain a target driving event result;
[0026] The warning unit is controlled to display the vehicle driving data and the target driving event result, and to issue a voice warning for the target driving event result.
[0027] In some embodiments, the step of using the trained neural network model to identify the vehicle driving data and obtain the target driving event result specifically includes the following steps:
[0028] Dividing the vehicle driving data into continuous data blocks, extracting features of each data block, and obtaining corresponding feature vectors;
[0029] Performing driving event recognition on each of the feature vectors to obtain the driving event type and the probability corresponding to the driving event type;
[0030] If the probability corresponding to the driving event type is greater than a preset threshold, it is determined that the vehicle has experienced the identified driving event type.
[0031] In a third aspect, a storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the intelligent driving record recognition method as described above is implemented.
[0032] In a fourth aspect, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein the processor implements the intelligent driving record identification method as described above when executing the computer program.
[0033] Compared with the prior art, the event recognition unit of the present invention uses a trained neural network model to identify driving events on vehicle driving data to obtain target driving event results. It can automatically and accurately identify and record key events in driving, such as sudden braking, collision, etc., to improve driving safety and accident handling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 It is a structural schematic diagram of an intelligent driving record recognition system of the present invention. DETAILED DESCRIPTION
[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0036] See also Figure 1As shown, an embodiment of the present invention provides an intelligent driving record recognition system, including: an on-board data acquisition unit, an event recognition unit and an early warning unit. The on-board data acquisition unit is used to collect vehicle driving data; the event recognition unit is connected in communication with the on-board data acquisition unit, and is used to use the trained neural network model to perform driving event recognition on the vehicle driving data to obtain the target driving event result; the early warning unit is connected in communication with the on-board data acquisition unit and the event recognition unit, and is used to display the vehicle driving data and the target driving event result, and to issue a voice warning for the target driving event result.
[0037] Specifically, in this embodiment, the event recognition unit of the present invention uses a trained neural network model to perform driving event recognition on vehicle driving data to obtain target driving event results. It can therefore automatically and accurately identify and record key events in driving, such as sudden braking, collisions, etc., to improve driving safety and accident handling efficiency.
[0038] Optionally, the vehicle-mounted data acquisition module includes:
[0039] A camera is used to collect vehicle driving scene videos;
[0040] An acceleration sensor, used to detect vehicle acceleration data;
[0041] Gyroscope, used to detect the vehicle's driving posture and direction changes;
[0042] GPS locator, used to collect vehicle location information and driving speed data.
[0043] Specifically, in this embodiment, the high-definition camera: a high-resolution, wide-angle camera is selected and installed at the front and / or rear of the vehicle to capture driving video in real time. The camera should have night vision function and good anti-shake performance to ensure clear video images in various light and road conditions.
[0044] Sensor integration: Accelerometers and gyroscopes are installed at key locations of the vehicle (such as near the chassis or suspension system) to monitor changes in acceleration and posture of the vehicle. The GPS positioning module is used to obtain the vehicle's geographic location information in real time. All sensors are connected to the data processing unit through the vehicle CAN bus or a dedicated interface.
[0045] Data processing unit: Integrates high-performance processors and embedded operating systems, is responsible for receiving raw data from sensors, performing preliminary processing and pre-analysis, and providing necessary data support for the event recognition module.
[0046] Optionally, the step of obtaining the trained neural network model is: constructing an event recognition network model based on a machine learning algorithm and a deep learning algorithm, and training the event recognition network model using data samples with labeled event types to obtain a trained neural network model.
[0047] Specifically, in this embodiment, data samples need to be cleaned and feature extracted before training.
[0048] Data cleaning: Clean the raw data received from the vehicle-mounted data acquisition unit to remove noise and outliers to ensure the accuracy and reliability of the data.
[0049] Feature extraction: Extract features useful for event recognition from the cleaned data, such as the peak value and rate of change of acceleration, the angular velocity change of the gyroscope, the speed change of the GPS, and the key frames and feature points in the video image.
[0050] The event recognition network model based on machine learning algorithms and deep learning algorithms is as follows:
[0051] Machine Learning Algorithm: Select a suitable machine learning algorithm, such as Support Vector Machine (SVM), Random Forest, or Gradient Boosting Trees.
[0052] Deep learning algorithms: Consider using deep learning algorithms such as convolutional neural networks (CNN) for video image processing, recurrent neural networks (RNN) or long short-term memory networks (LSTM) for time series data analysis to capture complex spatiotemporal features.
[0053] Model training: Use data samples with labeled event types to train the event recognition network model. These data samples should include instances of various driving events (such as sudden braking, collision, turning, etc.) and corresponding labels (i.e., event types).
[0054] Optionally, the step of using the trained neural network model to identify driving events on the vehicle driving data to obtain a target driving event result specifically includes the following steps:
[0055] Dividing the vehicle driving data into continuous data blocks, extracting features of each data block, and obtaining corresponding feature vectors;
[0056] Performing driving event recognition on each of the feature vectors to obtain the driving event type and the probability corresponding to the driving event type;
[0057] If the probability corresponding to the driving event type is greater than a preset threshold, it is determined that the vehicle has experienced the identified driving event type.
[0058] Specifically, in this embodiment, the trained neural network model receives vehicle driving data (data stream) in real time, and divides these data streams into continuous data blocks or windows, each of which contains data within a certain period of time. Then, the extracted features are calculated for each data block to form a feature vector. Then, the driving event is identified for each of the feature vectors, and the model outputs the driving event type of the data block and the probability corresponding to the driving event type.
[0059] Finally, based on the results of the model output, one or more thresholds are set to determine whether a specific event has occurred. For example, if the probability of a collision event output by the model exceeds the set threshold, it is considered that a collision event has occurred.
[0060] Optionally, the early warning unit includes:
[0061] A display screen, used to display the vehicle driving data and the target driving event result;
[0062] The voice warning system is used to provide voice warning for the target driving event result.
[0063] Specifically, in this embodiment, a high-definition display screen is installed inside the vehicle to display real-time video, event records, driving scores and other information. The display screen supports touch operation, and users can perform operations such as menu selection and video playback by touching the screen. At the same time, the voice warning system can issue a voice warning for the target driving event results.
[0064] Optionally, it also includes a data storage module that is communicatively connected to the vehicle-mounted data acquisition unit and the event recognition unit, and the data storage module is used to store the vehicle driving data and the target driving event results.
[0065] Specifically, in this embodiment, the vehicle system is equipped with a large-capacity storage device (such as an SD card, a solid-state hard disk, etc.) for temporarily storing videos and data of important events. When storing, the event types and timestamps are marked and classified for easy subsequent retrieval and management.
[0066] Data encryption: Before uploading data, advanced encryption algorithms are used to encrypt the data to ensure security and privacy protection during data transmission.
[0067] Network upload: The vehicle system uploads the encrypted data to the cloud server in real time through wireless network technologies such as 4G / 5G and Wi-Fi. During the upload process, the system will perform network status monitoring and error retransmission mechanism to ensure the integrity and reliability of the data.
[0068] At the same time, the implementation of the cloud data analysis platform is as follows:
[0069] Data storage layer: The cloud server adopts a distributed storage architecture to efficiently store and manage the received data. At the same time, it supports data backup and recovery functions to ensure data security and availability.
[0070] Data processing layer: Use big data processing frameworks (such as Hadoop, Spark, etc.) to clean, transform, and aggregate stored data to provide high-quality data sources for data analysis.
[0071] Analysis engine: Integrates multiple data analysis algorithms and models (such as cluster analysis, association rule mining, time series analysis, etc.), conducts in-depth mining and analysis on processed data, and extracts valuable driving behavior characteristics and accident warning information.
[0072] Service layer: Provides users with an intuitive web interface or mobile APP interface, displays analysis results, driving scores, accident warnings and other information, and provides personalized driving suggestions and improvement plans based on user needs.
[0073] The embodiment of the present invention also provides an intelligent driving record recognition method, comprising the following steps:
[0074] Control the vehicle-mounted data acquisition module to collect vehicle driving data;
[0075] The control event recognition unit uses the trained neural network model to perform driving event recognition on the vehicle driving data to obtain a target driving event result;
[0076] The warning unit is controlled to display the vehicle driving data and the target driving event result, and to issue a voice warning for the target driving event result.
[0077] The step of using the trained neural network model to identify the vehicle driving data and obtain the target driving event result specifically includes the following steps:
[0078] Dividing the vehicle driving data into continuous data blocks, extracting features of each data block, and obtaining corresponding feature vectors;
[0079] Performing driving event recognition on each of the feature vectors to obtain the driving event type and the probability corresponding to the driving event type;
[0080] If the probability corresponding to the driving event type is greater than a preset threshold, it is determined that the vehicle has experienced the identified driving event type.
[0081] Therefore, the present invention can significantly improve the level of driving safety, and provide drivers with immediate feedback and improvement suggestions by identifying and recording key events in real time. At the same time, the introduction of the cloud data analysis platform maximizes the value of data utilization, providing strong support for traffic accident prevention, handling and driving behavior research.
[0082] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the method steps of the above method are implemented.
[0083] The present invention implements all or part of the process in the above method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0084] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program running on the processor, and when the processor executes the computer program, all or part of the method steps in the above method are implemented.
[0085] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of a computer device, and uses various interfaces and lines to connect various parts of the entire computer device.
[0086] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0087] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, servers or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.
[0088] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), servers, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0089] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0091] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. An intelligent driving record recognition system, characterized in that: include: On-vehicle data collection unit, used to collect vehicle driving data; An event recognition unit, which is in communication with the vehicle-mounted data acquisition unit and is used to use a trained neural network model to perform driving event recognition on the vehicle driving data to obtain a target driving event result; as well as, The early warning unit is connected to the vehicle data collection unit and the event recognition unit for displaying the vehicle driving data and the target driving event result and providing a voice early warning for the target driving event result.
2. The intelligent driving record recognition system according to claim 1, characterized in that: The steps for obtaining the trained neural network model are: constructing an event recognition network model based on a machine learning algorithm and a deep learning algorithm, and training the event recognition network model using data samples with labeled event types to obtain a trained neural network model.
3. The intelligent driving record recognition system according to claim 1, characterized in that: The step of using the trained neural network model to identify the vehicle driving data and obtain the target driving event result is as follows: The following steps are included: Dividing the vehicle driving data into continuous data blocks, extracting features of each data block, and obtaining corresponding feature vectors; Performing driving event recognition on each of the feature vectors to obtain the driving event type and the probability corresponding to the driving event type; If the probability corresponding to the driving event type is greater than a preset threshold, it is determined that the vehicle has experienced the identified driving event type.
4. The intelligent driving record recognition system according to claim 1, characterized in that: The vehicle-mounted data acquisition module comprises: A camera is used to collect vehicle driving scene videos; An acceleration sensor, used to detect vehicle acceleration data; Gyroscope, used to detect the vehicle's driving posture and direction changes; GPS locator, used to collect vehicle location information and driving speed data.
5. The intelligent driving record recognition system according to claim 1, characterized in that: The early warning unit comprises: A display screen, used to display the vehicle driving data and the target driving event result; The voice warning system is used to provide voice warning for the target driving event result.
6. The intelligent driving record recognition system according to claim 1, characterized in that: It also includes a data storage module that is communicatively connected to the vehicle-mounted data acquisition unit and the event recognition unit, and the data storage module is used to store the vehicle driving data and the target driving event results.
7. An intelligent driving record recognition method, characterized in that: The following steps are involved: Control the vehicle-mounted data acquisition module to collect vehicle driving data; The control event recognition unit uses the trained neural network model to perform driving event recognition on the vehicle driving data to obtain a target driving event result; The warning unit is controlled to display the vehicle driving data and the target driving event result, and to issue a voice warning for the target driving event result.
8. The intelligent driving record recognition method according to claim 7, characterized in that: The step of using the trained neural network model to identify the vehicle driving data and obtain the target driving event result specifically includes the following steps: Dividing the vehicle driving data into continuous data blocks, extracting features of each data block, and obtaining corresponding feature vectors; Performing driving event recognition on each of the feature vectors to obtain the driving event type and the probability corresponding to the driving event type; If the probability corresponding to the driving event type is greater than a preset threshold, it is determined that the vehicle has experienced the identified driving event type.
9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent driving record identification method as described in any one of claims 7-8 is implemented.
10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor runs the computer program, the intelligent driving record identification method as described in any one of claims 7-8 is implemented.
