CN116486583A - Automobile parallel line early warning method, system, equipment and storage medium - Google Patents
Automobile parallel line early warning method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN116486583A CN116486583A CN202310378612.3A CN202310378612A CN116486583A CN 116486583 A CN116486583 A CN 116486583A CN 202310378612 A CN202310378612 A CN 202310378612A CN 116486583 A CN116486583 A CN 116486583A
- Authority
- CN
- China
- Prior art keywords
- parallel
- vehicle
- risk prediction
- early warning
- cnn
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000006399 behavior Effects 0.000 claims abstract description 46
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000004590 computer program Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 22
- 230000015654 memory Effects 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 11
- 230000009471 action Effects 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000009432 framing Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 14
- 238000004422 calculation algorithm Methods 0.000 abstract description 8
- 238000010801 machine learning Methods 0.000 abstract description 7
- 238000013527 convolutional neural network Methods 0.000 description 58
- 230000006872 improvement Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000013501 data transformation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automobile parallel line early warning method, an automobile parallel line early warning system, automobile parallel line early warning equipment and a storage medium, wherein the method comprises the following steps: collecting driving behavior data of a driver and surrounding environment information of a vehicle, and preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed; then inputting the vehicle data into a pre-trained CNN and LSTM mixed model for parallel risk prediction, and obtaining a parallel risk prediction result; carrying out doubling early warning on the vehicle according to the doubling risk prediction result; according to the embodiment of the invention, the CNN and LSTM mixed model is adopted for parallel risk prediction, so that the problems of insufficient data volume and nonlinearity in the traditional automobile parallel early warning technology adopting a machine learning algorithm can be effectively solved, and the accuracy and the practicability of the automobile parallel early warning are improved.
Description
Technical Field
The invention relates to the technical field of automobile safety, in particular to an automobile parallel line early warning method, an automobile parallel line early warning system, automobile parallel line early warning equipment and an automobile parallel line early warning storage medium.
Background
Automotive safety technology is one of the important directions of current automotive industry development. With the increasing attention of people to automobile safety, automobile safety technology is continuously developed and innovated. The automobile parallel line early warning technology is one of important automobile safety technologies. The automobile parallel connection early warning technology is based on inter-vehicle communication and vehicle perception technology, and monitors the surrounding environment of a vehicle and the motion states of other vehicles in real time through equipment such as a sensor, a camera and the like so as to remind a driver of paying attention to safety. The technology can effectively avoid collision and accidents when the automobiles are connected in parallel, and improves driving safety.
At present, the automobile parallel line early warning technology has been widely applied in the automobile industry, and a plurality of automobile manufacturers have introduced corresponding parallel line early warning systems. These systems typically employ sensors such as radar, cameras, etc. to alert the driver to safety by identifying the environment surrounding the vehicle and the state of motion of other vehicles. For example, an automobile parallel line early warning technology based on a machine learning algorithm adopts a machine learning algorithm such as a support vector machine (Support Vector Machine, SVM) and the like to model and predict the behavior and environment information of a driver so as to remind the driver of paying attention to safety.
However, the existing car parallel line early warning technology based on the machine learning algorithm needs a large amount of data to train, and the data volume of the car parallel line early warning system is often limited, and a plurality of nonlinear relations exist, so that the accuracy and stability of the algorithm cannot be ensured.
Disclosure of Invention
The embodiment of the invention provides an automobile parallel line early warning method, an automobile parallel line early warning system, an automobile parallel line early warning device and a storage medium, which can effectively solve the problems of insufficient data quantity and nonlinearity in the traditional automobile parallel line early warning technology adopting a machine learning algorithm, and improve the accuracy of automobile parallel line early warning.
In a first aspect, an embodiment of the present invention provides an automotive parallel line early warning method, including:
collecting driving behavior data of a driver and surrounding environment information of a vehicle;
preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed;
according to the vehicle data, carrying out parallel risk prediction on the vehicle through a pre-trained CNN and LSTM mixed model to obtain a parallel risk prediction result;
and carrying out parallel warning on the vehicle according to the parallel risk prediction result.
As an improvement of the scheme, the CNN and LSTM hybrid model comprises a CNN network layer, an LSTM network layer and a fusion layer;
and carrying out parallel risk prediction on the vehicle according to the vehicle data through a pre-trained CNN and LSTM mixed model to obtain a parallel risk prediction result, wherein the parallel risk prediction result comprises the following steps:
extracting spatial features of input vehicle data through the CNN network layer;
performing time sequence modeling on the spatial characteristics output by the CNN network layer through the LSTM network layer to obtain time sequence characteristics;
and fusing the spatial features and the time sequence features through the fusion layer to obtain the parallel line risk prediction result.
As an improvement of the above-described aspect, the driving behavior data includes: steering wheel rotation information, throttle signals, brake signals, acceleration information and steering angle information; the surrounding environment information includes: position information, speed information and traveling direction of other vehicles around the vehicle, width of a road and marking information.
As an improvement of the scheme, the automobile parallel line early warning method further comprises the following training steps of the CNN and LSTM mixed model:
preprocessing a pre-collected driving behavior data sample and a pre-collected surrounding environment information sample of the vehicle;
carrying out framing treatment on the driving behavior data sample and the surrounding environment information sample obtained after pretreatment to obtain a vehicle data sample; wherein each frame of vehicle data samples comprises a plurality of driving behavior data samples and a plurality of surrounding environment information samples;
labeling each frame of vehicle data sample;
training the CNN and LSTM hybrid model by using the labeled vehicle data sample to obtain a corresponding parallel risk prediction result;
calculating a cross entropy loss function value of the CNN and LSTM hybrid model according to the labels of the vehicle data samples and the corresponding parallel risk prediction results;
and when the cross entropy loss function value meets a preset condition, obtaining a trained CNN and LSTM mixed model.
As an improvement of the above scheme, the method for pre-warning the parallel wires of the automobile further comprises:
and controlling the vehicle to execute corresponding evading actions according to the parallel risk prediction result.
As an improvement of the above solution, the controlling the vehicle to execute the corresponding avoidance action according to the parallel risk prediction result includes:
when the parallel line risk prediction result is that the speed is too high, controlling the vehicle to reduce the speed;
and when the parallel line risk prediction result is that the distance between the parallel line risk prediction result and other vehicles is too close, controlling the vehicles to keep a preset safety distance with the other vehicles.
As an improvement of the above solution, the calculating the cross entropy loss function value of the CNN and LSTM hybrid model according to the label of the vehicle data sample and the corresponding parallel line risk prediction result thereof includes:
according to the formula (1), calculating a cross entropy loss function value of the CNN and LSTM mixed model;
wherein y is i A tag representing a sample of the vehicle data of the i-th frame,and (5) representing a parallel line risk prediction result corresponding to the vehicle data sample of the ith frame, and n representing the number of the vehicle data samples.
In a second aspect, an embodiment of the present invention provides an automotive parallel line early warning system, including:
the data acquisition module is used for acquiring driving behavior data of a driver and surrounding environment information of the vehicle;
the data preprocessing module is used for preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed;
the parallel risk prediction module is used for predicting the parallel risk of the vehicle through a pre-trained CNN and LSTM mixed model according to the vehicle data to obtain a parallel risk prediction result;
and the doubling early warning module is used for carrying out doubling early warning on the vehicle according to the doubling risk prediction result.
In a third aspect, an embodiment of the present invention provides an automotive parallel line early warning device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the car merging pre-warning method according to any one of the first aspects when the computer program is executed.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, where a computer program is stored, where when the computer program runs, a device where the computer readable storage medium is controlled to execute the method for parallel line early warning of an automobile according to any one of the first aspects.
Compared with the prior art, the embodiment of the invention has the beneficial effects that: acquiring driving behavior data of a driver and surrounding environment information of a vehicle, and preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed; then inputting the vehicle data into a pre-trained CNN and LSTM mixed model for parallel risk prediction, and obtaining a parallel risk prediction result; carrying out doubling early warning on the vehicle according to the doubling risk prediction result; according to the embodiment of the invention, the CNN and LSTM mixed model is adopted for parallel risk prediction, so that the problems of insufficient data volume and nonlinearity in the traditional automobile parallel early warning technology adopting a machine learning algorithm can be effectively solved, and the accuracy and the practicability of the automobile parallel early warning are improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that will be used in the embodiments will be briefly described below, and it will be apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an automobile parallel line early warning method provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of an automotive parallel line early warning system according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an automotive parallel line early warning device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Fig. 1 is a flowchart of an automotive parallel line early warning method according to an embodiment of the present invention. The automobile parallel line early warning method comprises the following steps:
s1: collecting driving behavior data of a driver and surrounding environment information of a vehicle;
for example, driving behavior data and surrounding environment information of the driver may be collected by sensors and cameras mounted on the vehicle. Wherein the driving behavior data includes: steering wheel rotation information, throttle signals, brake signals, acceleration information and steering angle information; the surrounding environment information includes: position information, speed information and traveling direction of other vehicles around the vehicle, width of a road and marking information.
S2: preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed;
the preprocessing comprises one or more of data cleaning, data integration, data transformation, data reduction, data screening and feature extraction, and the quality and reliability of the data can be improved by preprocessing the driving behavior data and the surrounding environment information, so that the subsequent model can be conveniently processed and analyzed.
Furthermore, the driving behavior data and the surrounding environment information can be time aligned according to the time stamp of the driving behavior data and the time stamp of the surrounding environment information, at least one driving behavior data and at least one surrounding environment information in the vehicle data input into the CNN and LSTM hybrid model are time aligned, and the accuracy of the parallel risk prediction is further improved.
S3: according to the vehicle data, carrying out parallel risk prediction on the vehicle through a pre-trained CNN and LSTM mixed model to obtain a parallel risk prediction result;
s4: and carrying out parallel warning on the vehicle according to the parallel risk prediction result.
According to the embodiment of the invention, the vehicle data comprising the current driving behavior data and the surrounding environment information is input into a pre-trained CNN (convolutional neural network ) and LSTM (Long Short Term Memory) mixed model, so that the learning capacity of the CNN on the space characteristics and the LSTM on the time sequence characteristics is utilized to conduct the parallel line risk prediction, and the parallel line early warning is conducted on the vehicle according to the parallel line risk prediction result, so that the problems of insufficient data quantity and nonlinearity existing in the traditional vehicle parallel line early warning technology adopting a machine learning algorithm can be effectively solved, and the accuracy and the practicability of the vehicle parallel line early warning are improved. Meanwhile, the embodiment of the invention can better predict the behavior of the driver and judge the potential danger by monitoring the behavior of the driver and the surrounding environment in real time, improves the sensitivity and the response speed of the system, can better help the driver to improve the driving safety, can adapt to different driving scenes and different driving behaviors, and can improve the adaptability and the intelligence of the early warning system.
Furthermore, the parallel line early warning function of the automobile can be realized only by installing a corresponding sensor and a camera on the automobile and carrying out data acquisition and pretreatment, and the implementation is simple.
In an alternative embodiment, the CNN and LSTM hybrid model includes a CNN network layer, an LSTM network layer, and a fusion layer;
and carrying out parallel risk prediction on the vehicle according to the vehicle data through a pre-trained CNN and LSTM mixed model to obtain a parallel risk prediction result, wherein the parallel risk prediction result comprises the following steps:
extracting spatial features of input vehicle data through the CNN network layer;
illustratively, the network structure of the CNN network layer may be expressed as:
y CNN ＝Conv 3 (Conv 3 (x))；
wherein x represents the input vehicle data, conv 3 Representing a convolution layer with a convolution kernel size of 3 x 3, y CNN Representing the spatial features extracted by CNN.
Performing time sequence modeling on the spatial characteristics output by the CNN network layer through the LSTM network layer to obtain time sequence characteristics;
illustratively, the spatial features extracted by the CNN network layer are input into the LSTM network layer for time sequence modeling, and specifically, the network structure of the LSTM network layer may be expressed as:
y LSTM ＝LSTM(y cnn )；
wherein y is CNN Representing spatial features of the input, LSTM represents an LSTM layer, y LSTM Representing the timing characteristics of LSTM modeling.
And fusing the spatial features and the time sequence features through the fusion layer to obtain the parallel line risk prediction result.
The time sequence features output by the CNN network layer and the spatial features output by the CNN network layer are fused to obtain a final prediction result, specifically, the following formula may be adopted for fusion:
y＝f fusion (y CNN ,y LSTM )；
wherein y is CNN Representing the spatial features extracted by CNN, y LSTM Representing the timing characteristics of LSTM modeling, f fusion And (3) representing a fusion function, and y representing a final parallel line risk prediction result.
In the embodiment of the invention, the CNN and LSTM mixed model is adopted, so that the learning capability of the CNN on the space characteristics and the LSTM on the time sequence characteristics can be simultaneously utilized to identify the behavior of a driver and judge whether the potential danger exists in the parallel line or not, the problem of nonlinearity and the problem of insufficient data volume can be better solved, and the accuracy and the practicability of the early warning system are improved.
In an optional embodiment, the method for pre-warning the parallel line of the automobile further includes the following steps of training a CNN and LSTM hybrid model:
preprocessing a pre-collected driving behavior data sample and a pre-collected surrounding environment information sample of the vehicle;
the preprocessing comprises one or more of data cleaning, data integration, data transformation, data reduction, data screening and feature extraction, and the quality and reliability of the data can be improved by preprocessing the driving behavior data and the surrounding environment information, so that the subsequent model can be conveniently processed and analyzed.
Carrying out framing treatment on the driving behavior data sample and the surrounding environment information sample obtained after pretreatment to obtain a vehicle data sample; wherein each frame of vehicle data samples comprises a plurality of driving behavior data samples and a plurality of surrounding environment information samples;
further, a plurality of driving behavior data samples and a plurality of surrounding information samples in each frame of vehicle data samples may also be time-aligned.
Labeling each frame of vehicle data sample;
for example, tag data is added to each frame of vehicle data sample according to the corresponding real-scene parallel scene, for example, the distance from other vehicles is too short, the speed is too fast, the steering wheel is unstable, and the like, and the hybrid model of the CNN and the LSTM is trained through the vehicle data sample after the tag data is added, so that the hybrid model of the CNN and the LSTM is helped to better identify the parallel risk behaviors.
Training the CNN and LSTM hybrid model by using the labeled vehicle data sample to obtain a corresponding parallel risk prediction result;
by way of example, the principle of the CNN and LSTM hybrid model parallel risk prediction can be understood as the following three aspects:
judging and predicting the motion state of surrounding vehicles: by analyzing information such as the position, the speed and the like of surrounding vehicles, the motion state of the surrounding vehicles is predicted, so that whether the potential danger exists in the process of merging is judged.
Judging the road width and the position of the marking: by analyzing the information such as the width of the road and the position of the marking, whether the vehicle has enough space to perform the doubling operation is judged, so that whether the potential danger exists during the doubling operation is judged.
Judging the shape and gradient of the road: by analyzing the information such as the shape and gradient of the road, the acceleration and steering angle of the vehicle are predicted, so that whether the potential danger exists in the process of merging is judged.
Calculating a cross entropy loss function value of the CNN and LSTM hybrid model according to the labels of the vehicle data samples and the corresponding parallel risk prediction results;
specifically, according to formula (1), calculating a cross entropy loss function value of the CNN and LSTM hybrid model;
wherein y is i A tag representing a sample of the vehicle data of the i-th frame,and (5) representing a parallel line risk prediction result corresponding to the vehicle data sample of the ith frame, and n representing the number of the vehicle data samples.
And when the cross entropy loss function value meets a preset condition, obtaining a trained CNN and LSTM mixed model.
For example, when the cross entropy loss function value is smaller than a preset threshold, determining that the precision of the CNN and LSTM mixed model meets the requirement, and outputting the trained CNN and LSTM mixed model. The output result of the model is interpreted, so that the interpretation is strong, people can understand the prediction result of the model, and the reliability and the credibility of the parallel line early warning are improved.
In the embodiment of the invention, the potential danger during the parallel line can be more accurately judged by training and predicting the CNN and LSTM mixed model, and the accuracy and the practicability of the parallel line early warning are improved.
In an optional embodiment, the method for pre-warning the parallel wires of the automobile further includes:
and controlling the vehicle to execute corresponding evading actions according to the parallel risk prediction result.
Specifically, when the parallel line risk prediction result is that the speed is too high, controlling the vehicle to reduce the speed;
and when the parallel line risk prediction result is that the distance between the parallel line risk prediction result and other vehicles is too close, controlling the vehicles to keep a preset safety distance with the other vehicles.
In the embodiment of the invention, when the early warning signal is judged and sent, for example, the conditions of too close distance between the vehicle and other vehicles, too high speed, unstable rotation of the steering wheel and the like are identified, and the corresponding early warning signal is further sent in a touch manner, so that the driver is reminded of safety. Meanwhile, the vehicle can also perform corresponding automatic control, such as automatically reducing the speed of the vehicle, keeping the safety distance and the like, so as to avoid potential traffic accidents and improve the driving safety.
Example two
Referring to fig. 2, an embodiment of the present invention provides an automotive parallel line early warning system, including:
the data acquisition module 1 is used for acquiring driving behavior data of a driver and surrounding environment information of a vehicle;
the data preprocessing module 2 is used for preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed;
the parallel risk prediction module 3 is used for predicting the parallel risk of the vehicle through a pre-trained CNN and LSTM mixed model according to the vehicle data to obtain a parallel risk prediction result;
and the doubling early warning module 4 is used for carrying out doubling early warning on the vehicle according to the doubling risk prediction result.
In an alternative embodiment, the CNN and LSTM hybrid model includes a CNN network layer, an LSTM network layer, and a fusion layer;
the CNN network layer is used for extracting spatial characteristics of input vehicle data;
the LSTM network layer is used for carrying out time sequence modeling on the spatial characteristics output by the CNN network layer to obtain time sequence characteristics;
and the fusion layer is used for fusing the spatial features and the time sequence features to obtain the parallel line risk prediction result.
In an alternative embodiment, the driving behavior data includes: steering wheel rotation information, throttle signals, brake signals, acceleration information and steering angle information; the surrounding environment information includes: position information, speed information and traveling direction of other vehicles around the vehicle, width of a road and marking information.
In an alternative embodiment, the car parallel warning system further includes a model training module, the model training module including:
the preprocessing unit is used for preprocessing a pre-acquired driving behavior data sample and a surrounding environment information sample of the vehicle;
the framing processing unit is used for framing the driving behavior data sample and the surrounding environment information sample obtained after the pretreatment to obtain a vehicle data sample; wherein each frame of vehicle data samples comprises a plurality of driving behavior data samples and a plurality of surrounding environment information samples;
the marking unit is used for marking each frame of vehicle data sample;
the training unit is used for training the CNN and LSTM hybrid model by using the labeled vehicle data sample to obtain a corresponding parallel risk prediction result;
the loss calculation unit is used for calculating a cross entropy loss function value of the CNN and LSTM hybrid model according to the label of the vehicle data sample and the corresponding parallel risk prediction result; and when the cross entropy loss function value meets a preset condition, obtaining a trained CNN and LSTM mixed model.
In an alternative embodiment, the car parallel line early warning system further includes:
and the risk avoidance module is used for controlling the vehicle to execute corresponding avoidance actions according to the parallel risk prediction result.
In an alternative embodiment, the risk avoidance module includes:
the vehicle speed control unit is used for controlling the vehicle to reduce the vehicle speed when the parallel line risk prediction result is that the speed is too high;
and the vehicle distance control unit is used for controlling the vehicle to keep a preset safety distance with other vehicles when the parallel line risk prediction result is that the distance between the vehicle and the other vehicles is too close.
In an alternative embodiment, the loss calculation unit is specifically configured to calculate a cross entropy loss function value of the CNN and LSTM hybrid model according to formula (1);
wherein y is i A tag representing a sample of the vehicle data of the i-th frame,and (5) representing a parallel line risk prediction result corresponding to the vehicle data sample of the ith frame, and n representing the number of the vehicle data samples.
It should be noted that the technical principle and technical effect of the embodiment of the present invention are the same as those of the first embodiment, and will not be described in detail here.
Example III
Referring to fig. 3, a schematic diagram of an automotive parallel line early warning device according to an embodiment of the present invention is shown. The automobile parallel line early warning device of the embodiment comprises: a processor 100, a memory 200 and a computer program stored in the memory 200 and executable on the processor 100, such as an automotive parallel line warning program. The steps of the above-mentioned embodiments of the parallel wire early warning method for automobiles, such as steps S1-S4 shown in fig. 1, are implemented when the processor 100 executes the computer program.
The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present invention, for example. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the automotive parallel line warning device.
The car parallel line early warning device can comprise, but is not limited to, a processor and a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of an automotive parallel line warning device, and does not constitute a limitation of an automotive parallel line warning device, and may include more or fewer components than illustrated, or may combine certain components, or different components, e.g., the automotive parallel line warning device may further include an input-output device, a network access device, a bus, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general processor may be a microprocessor or the processor may be any conventional processor, etc., where the processor is a control center of the automotive parallel line early warning device, and various interfaces and lines are used to connect various parts of the entire automotive parallel line early warning device.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the vehicle parallel line warning device by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The module/unit integrated by the automobile parallel line early warning device can be stored in a computer readable storage medium if the module/unit is realized in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
It should be noted that the above-described apparatus embodiments are merely illustrative, and the units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that many modifications and variations may be made without departing from the spirit of the invention, and it is intended that such modifications and variations be considered as a departure from the scope of the invention.
Claims (10)
1. An automobile parallel line early warning method is characterized by comprising the following steps:
collecting driving behavior data of a driver and surrounding environment information of a vehicle;
preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed;
according to the vehicle data, carrying out parallel risk prediction on the vehicle through a pre-trained CNN and LSTM mixed model to obtain a parallel risk prediction result;
and carrying out parallel warning on the vehicle according to the parallel risk prediction result.
2. The method for early warning of parallel lines of automobiles according to claim 1, wherein the mixed model of CNN and LSTM comprises a CNN network layer, an LSTM network layer and a fusion layer;
and carrying out parallel risk prediction on the vehicle according to the vehicle data through a pre-trained CNN and LSTM mixed model to obtain a parallel risk prediction result, wherein the parallel risk prediction result comprises the following steps:
extracting spatial features of input vehicle data through the CNN network layer;
performing time sequence modeling on the spatial characteristics output by the CNN network layer through the LSTM network layer to obtain time sequence characteristics;
and fusing the spatial features and the time sequence features through the fusion layer to obtain the parallel line risk prediction result.
3. The vehicle parallel line warning method according to claim 1, wherein the driving behavior data includes: steering wheel rotation information, throttle signals, brake signals, acceleration information and steering angle information; the surrounding environment information includes: position information, speed information and traveling direction of other vehicles around the vehicle, width of a road and marking information.
4. The method for warning the parallel line of the automobile according to claim 1, further comprising the following training steps of a CNN and LSTM hybrid model:
preprocessing a pre-collected driving behavior data sample and a pre-collected surrounding environment information sample of the vehicle;
carrying out framing treatment on the driving behavior data sample and the surrounding environment information sample obtained after pretreatment to obtain a vehicle data sample; wherein each frame of vehicle data samples comprises a plurality of driving behavior data samples and a plurality of surrounding environment information samples;
labeling each frame of vehicle data sample;
training the CNN and LSTM hybrid model by using the labeled vehicle data sample to obtain a corresponding parallel risk prediction result;
calculating a cross entropy loss function value of the CNN and LSTM hybrid model according to the labels of the vehicle data samples and the corresponding parallel risk prediction results;
and when the cross entropy loss function value meets a preset condition, obtaining a trained CNN and LSTM mixed model.
5. The method for warning the parallel wires of the automobile according to claim 1, further comprising:
and controlling the vehicle to execute corresponding evading actions according to the parallel risk prediction result.
6. The method for warning the parallel lines of the automobile according to claim 5, wherein the controlling the automobile to execute the corresponding evading action according to the prediction result of the parallel line risk comprises:
when the parallel line risk prediction result is that the speed is too high, controlling the vehicle to reduce the speed;
and when the parallel line risk prediction result is that the distance between the parallel line risk prediction result and other vehicles is too close, controlling the vehicles to keep a preset safety distance with the other vehicles.
7. The method for early warning of merging of vehicles according to claim 4, wherein the calculating the cross entropy loss function value of the CNN and LSTM hybrid model according to the labels of the vehicle data samples and the corresponding merging risk prediction results thereof comprises:
according to the formula (1), calculating a cross entropy loss function value of the CNN and LSTM mixed model;
wherein y is i A tag representing a sample of the vehicle data of the i-th frame,and (5) representing a parallel line risk prediction result corresponding to the vehicle data sample of the ith frame, and n representing the number of the vehicle data samples.
8. An automotive parallel line early warning system, comprising:
the data acquisition module is used for acquiring driving behavior data of a driver and surrounding environment information of the vehicle;
the data preprocessing module is used for preprocessing the driving behavior data and the surrounding environment information to obtain vehicle data to be processed;
the parallel risk prediction module is used for predicting the parallel risk of the vehicle through a pre-trained CNN and LSTM mixed model according to the vehicle data to obtain a parallel risk prediction result;
and the doubling early warning module is used for carrying out doubling early warning on the vehicle according to the doubling risk prediction result.
9. An automotive parallel line early warning device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the car merging pre-warning method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, wherein the computer readable storage medium stores a computer program, and wherein the computer program when executed controls a device in which the computer readable storage medium is located to perform the auto parallel warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310378612.3A CN116486583A (en) | 2023-04-10 | 2023-04-10 | Automobile parallel line early warning method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310378612.3A CN116486583A (en) | 2023-04-10 | 2023-04-10 | Automobile parallel line early warning method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116486583A true CN116486583A (en) | 2023-07-25 |
Family
ID=87213028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310378612.3A Pending CN116486583A (en) | 2023-04-10 | 2023-04-10 | Automobile parallel line early warning method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116486583A (en) |
-
2023
- 2023-04-10 CN CN202310378612.3A patent/CN116486583A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108388834B (en) | Object detection using recurrent neural networks and cascade feature mapping | |
| CN106980813B (en) | Gaze generation for machine learning | |
| CN107220581B (en) | Pedestrian detection and motion prediction by a rear camera | |
| CN111033510A (en) | Method and device for operating a driver assistance system, driver assistance system and motor vehicle | |
| CN112172835B (en) | Vehicle early warning method, device, equipment and storage medium | |
| JP7042937B2 (en) | System and method for identifying dangerous objects using causal inference | |
| Al Mamun et al. | Lane marking detection using simple encode decode deep learning technique: SegNet | |
| CN111145569A (en) | Road monitoring and vehicle running control method and device and vehicle-road cooperative system | |
| JP5895728B2 (en) | Vehicle group management device | |
| CN114475656B (en) | Travel track prediction method, apparatus, electronic device and storage medium | |
| Alpar | Corona segmentation for nighttime brake light detection | |
| CN111278708B (en) | Method and device for assisting driving | |
| CN111310696B (en) | Parking accident identification method and device based on analysis of abnormal parking behaviors and vehicle | |
| CN116486583A (en) | Automobile parallel line early warning method, system, equipment and storage medium | |
| EP4113377A1 (en) | Use of dbscan for lane detection | |
| CN115631626A (en) | Vehicle data monitoring and analyzing method, device, equipment and medium | |
| CN115188191A (en) | Vehicle safe driving control method and device and vehicle | |
| CN112686136A (en) | Object detection method, device and system | |
| CN114820691B (en) | Method, device and equipment for detecting motion state of vehicle and storage medium | |
| González et al. | Low-Cost Deep Learning-Based Prototype for Automatic Identification of Traffic Signs in Vehicles | |
| CN118042433A (en) | Inter-vehicle communication method, device, electronic equipment and readable storage medium | |
| Kushwaha et al. | Forward vehicle brake light detection for avoiding road accidents using Yolov7 and IR sensor | |
| Bhatlawande et al. | Driver Assistance System for Recognition of Brake and Parking Signal | |
| CN111857108A (en) | Method and device for automatically following vehicle | |
| CN116229430A (en) | Illegal driving image processing method, device, equipment, storage medium and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |