CN111077335B

CN111077335B - Vehicle speed detection method, vehicle speed detection device and readable storage medium

Info

Publication number: CN111077335B
Application number: CN202010074362.0A
Authority: CN
Inventors: 赵世华
Original assignee: Ditu Beijing Technology Co Ltd
Current assignee: Ditu Beijing Technology Co Ltd
Priority date: 2020-01-22
Filing date: 2020-01-22
Publication date: 2021-03-02
Anticipated expiration: 2040-01-22
Also published as: CN111077335A

Abstract

The application provides a vehicle speed detection method, a vehicle speed detection device and a readable storage medium, which are used for acquiring light signal data received when a vehicle runs in a tunnel in a time period to be detected; determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data; and determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained running speed prediction model. Therefore, the driving speed of the vehicle in the tunnel can be detected by receiving the light signal data in the tunnel and obtaining the characteristic information of the light signal, and the driving speed of the vehicle in the special road section with poor signals can be detected, so that the timeliness and the accuracy are high.

Description

Vehicle speed detection method, vehicle speed detection device and readable storage medium

Technical Field

The application relates to the technical field of information transmission, in particular to a vehicle speed detection method, a vehicle speed detection device and a readable storage medium.

Background

With the development of science and technology, automobiles gradually enter the lives of people and become indispensable vehicles for people to go out, and with the development of internet technology and the requirement of people for convenience in going out, the navigation system is greatly developed and advanced, and the vehicle-mounted navigation system and the mobile navigation system play an important role in the driving and going out of people. The navigation system generally utilizes a Global Positioning System (GPS) to cooperate with an electronic map to navigate by detecting the running speed of a vehicle, can conveniently and accurately tell a driver the shortest or fastest path to a destination, and is a good helper of the driver.

However, in some specific road sections, such as in a tunnel, due to poor GPS signals and other reasons, the navigation system cannot detect the driving speed of the vehicle in time, and thus, the navigation system is prone to delay or disconnect, cannot provide real-time and effective navigation for the driver, and is prone to problems such as causing the driving direction of the driver to be wrong or selecting a wrong driving road.

Disclosure of Invention

In view of the above, an object of the present invention is to provide a vehicle speed detecting method, a vehicle speed detecting device and a readable storage medium, which can detect the driving speed of a vehicle in a tunnel through received light signal data in the tunnel and through light signal characteristic information therein, and can detect the driving speed of the vehicle in a special road section with poor signal, and the timeliness and the accuracy are high.

According to one aspect of the present application, an electronic device may include a storage medium and a processor in communication with the storage medium. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is in operation, the processor communicates with the storage medium via the bus, and when the processor executes the machine-readable instructions, one or more of the following operations may be performed:

acquiring light signal data received when a vehicle runs in a tunnel in a time period to be detected;

determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data;

and determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained running speed prediction model.

In some embodiments of the application, the machine readable instructions, when executed by a processor, may perform one or more of the following:

generating a light signal characteristic vector sequence of the vehicle based on the light signal characteristic information of the vehicle at each detection moment, wherein the light signal characteristic vector sequence comprises light signal characteristic vectors respectively corresponding to the detection moments;

and inputting the light signal characteristic vector sequence into a trained running speed prediction model to obtain the running speed of the vehicle in the tunnel.

determining a characteristic value of the vehicle under a plurality of light signal characteristics at each detection moment according to the light signal characteristic information corresponding to each detection moment;

constructing a light signal characteristic vector at each detection moment according to the characteristic values of the vehicle under the characteristics of the plurality of light signals;

and generating the light signal feature vector sequence according to the light signal feature vector at each detection moment.

In the above embodiment, the light signal characteristic includes at least one of the following characteristics:

the system comprises a light signal variation characteristic, a light signal variance characteristic, a light signal energy spectrum characteristic and a light signal power spectrum characteristic.

sequentially taking each light signal feature vector in the light signal feature vector sequence as a light signal feature vector at the current detection moment, and acquiring a middle feature vector at the previous moment, which is output after the light signal feature vector at the previous detection moment passes through a hidden layer in the driving speed prediction model;

inputting the current-time light signal feature vector and the previous-time intermediate feature vector into a trained running speed prediction model to obtain a current-time running speed corresponding to the current-time light signal feature vector;

and determining the average running speed of the vehicle in the time period to be detected based on the acquired multiple running speeds at the current moment.

acquiring the driving direction of the vehicle;

determining navigation information of the vehicle based on the driving direction and the driving speed.

acquiring a plurality of groups of light signal sample data received when a vehicle runs in a tunnel in a historical time period;

determining light signal sample characteristic information of the vehicle at each historical detection moment in the historical time period based on each set of light signal sample data;

and training a driving speed prediction model based on the characteristic information of the plurality of light signal samples and the actual driving speed of the vehicle corresponding to each group of light signal sample data.

for each group of light signal sample data, generating a light signal sample feature vector sequence of the vehicle based on light signal sample feature information of the vehicle at each historical detection time, wherein the light signal sample feature vector sequence comprises light signal feature vectors corresponding to the historical detection times respectively;

and training a constructed running speed prediction model based on the plurality of light signal sample feature vector sequences and the actual running speed of the vehicle corresponding to each light signal sample feature vector sequence.

for each group of light signal sample data, determining a sample characteristic value under the light signal sample characteristic of the vehicle at each historical detection time according to the light signal sample characteristic information corresponding to each historical detection time;

according to sample characteristic values of the vehicle under the characteristics of a plurality of light signal samples at each historical detection moment, constructing a light signal sample characteristic vector of the vehicle at each historical detection moment;

and generating a light signal characteristic vector sequence of the vehicle in the historical time period according to the light signal sample characteristic vector at each historical detection moment.

In the above embodiment, the light signal sample characteristic includes at least one of the following characteristics:

the method comprises the following steps of light signal sample variation characteristic, light signal sample variance characteristic, light signal sample energy spectrum characteristic and light signal sample power spectrum characteristic.

for each light signal sample feature vector sequence, sequentially taking each light signal sample feature vector in the light signal sample feature vector sequence as a light signal sample feature vector at the current moment of the current sample detection time, and obtaining a light signal sample feature vector at the previous moment of the previous sample detection time, and outputting a middle feature vector of the previous moment sample after the light signal sample feature vector at the previous moment passes through a hidden layer in a driving speed prediction model;

inputting the characteristic vector of the light signal sample at the current moment and the intermediate characteristic vector of the sample at the previous moment into a constructed running speed prediction model to obtain the running speed at the current moment corresponding to the characteristic vector of the light signal sample at the current moment;

the travel speed prediction model is trained based on a plurality of current-time travel speeds and an actual travel speed at each of the historical detection times.

and adjusting model parameters of the running speed prediction model based on each current running speed and the actual running speed corresponding to each current running speed until the difference value between the current running speed output by the running speed prediction model and the corresponding actual running speed is within a preset range, and determining that the running speed prediction model is trained completely.

According to another aspect of the present application, there is provided a vehicle speed detection method including:

In some embodiments of the present application, the determining the traveling speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and a trained traveling speed prediction model includes:

In some embodiments of the present application, the generating a sequence of light signal feature vectors of the vehicle based on the light signal feature information of the vehicle at each of the detection times includes:

In the above embodiments, the light signal characteristic comprises at least one of the following characteristics:

In some embodiments of the present application, the inputting the light signal feature vector sequence into a trained driving speed prediction model to obtain a driving speed of the vehicle in the tunnel includes:

In some embodiments of the present application, after determining the traveling speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained traveling speed prediction model, the method further includes:

acquiring the driving direction of the vehicle;

In some embodiments of the present application, the travel speed prediction model is trained by:

In some embodiments of the present application, the training a driving speed prediction model based on a plurality of characteristic information of the light signal samples and an actual driving speed of the vehicle corresponding to each group of light signal samples includes:

In some embodiments of the application, the generating, for each set of light signal sample data, a sequence of light signal sample feature vectors of the vehicle based on light signal sample feature information of the vehicle at each of the historical detection times includes:

In some embodiments of the present application, the training the constructed driving speed prediction model based on a plurality of light signal sample feature vector sequences and the actual driving speed of the vehicle corresponding to each light signal sample feature vector sequence includes:

In some embodiments of the present application, training a travel speed prediction model based on a plurality of current-time travel speeds and the actual travel speed at each historical detection time includes:

According to another aspect of the present application, there is provided a vehicle speed detection device including:

the first acquisition module is used for acquiring light signal data received when the vehicle runs in the tunnel in a time period to be detected;

the first determining module is used for determining the light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data acquired by the first acquiring module;

and the second determination module is used for determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle determined by the first determination module and the trained running speed prediction model.

In some embodiments of the present application, the second determining module is specifically configured to:

In some embodiments of the present application, the second determining module is specifically further configured to:

In some embodiments of the present application, the vehicle speed detection device further includes:

the second acquisition module is used for acquiring the driving direction of the vehicle;

and a third determination module configured to determine navigation information of the vehicle based on the driving direction acquired by the second acquisition module and the driving speed determined by the second determination module.

In some embodiments of the present application, the vehicle speed detection apparatus further includes a model training module for training the traveling speed prediction model by:

In some embodiments of the present application, the model training module is specifically configured to:

In some embodiments of the present application, the light signal sample characteristic comprises at least one of:

In some embodiments of the present application, the model training module is further specifically configured to:

According to another aspect of the present application, a computer-readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, performs the steps of the vehicle speed detection method described above.

According to the vehicle speed detection method, the vehicle speed detection device and the readable storage medium, light signal data received when a vehicle runs in a tunnel in a time period to be detected are obtained; determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data; and determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained running speed prediction model.

Therefore, the driving speed of the vehicle in the tunnel can be detected by receiving the light signal data in the tunnel and obtaining the characteristic information of the light signal, and the driving speed of the vehicle in the special road section with poor signals can be detected, so that the timeliness and the accuracy are high.

Furthermore, the running speed of the vehicle is detected, the running speed and the running direction can be combined, the vehicle can be helped to realize navigation in a special road section, the navigation error caused by poor signals can be effectively reduced, and the real-time performance and the accuracy rate of navigation are improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a system diagram in one possible application scenario;

FIG. 2 is a schematic flow chart illustrating a vehicle speed detection method according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of another vehicle speed detection method provided by the present application, according to an exemplary embodiment;

fig. 4 is one of structural diagrams of a vehicle speed detection device according to an embodiment of the present application;

fig. 5 is a second structural diagram of a vehicle speed detection device according to an embodiment of the present application;

fig. 6 is a third structural diagram of a vehicle speed detecting device according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

In order to enable those skilled in the art to use the present disclosure, the following embodiments are given in conjunction with a specific application scenario "detecting a traveling speed of a vehicle while traveling in a tunnel". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of detecting a travel speed of a vehicle while traveling in a tunnel, it should be understood that this is merely one exemplary embodiment.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

One aspect of the present application relates to a vehicle speed detection system. The system can collect light signal data of the lighting device arranged in the tunnel when the vehicle runs in special road sections such as the tunnel, and then determine light signal characteristic information from the received light signal data, so that the running speed of the vehicle in the tunnel can be detected through the light signal characteristic information and a trained running speed prediction model, and the vehicle can be helped to perform better navigation in the tunnel. Referring to fig. 1, fig. 1 is a system diagram in a possible application scenario. As shown in fig. 1, the vehicle speed detecting system includes a vehicle, a light signal detecting device and a vehicle speed detecting device, wherein the light signal detecting device and the vehicle speed detecting device may be built in the vehicle or only mounted on the vehicle, but are independent from the vehicle, when the vehicle runs in a special road section, such as a tunnel, the light signal detecting device may detect a lighting device in the tunnel, so as to receive light signal data of the lighting device, and the vehicle speed detecting device may acquire the light signal data, detect a running speed of the vehicle by extracting relevant light signal characteristic information in the light signal data, and through a trained running speed prediction model.

Before the application, in a specific road section such as a tunnel, the GPS signal is not good due to poor network signals, the navigation system cannot detect the driving speed of the vehicle in time, the navigation is prone to be delayed or disconnected, real-time effective navigation cannot be provided for a driver, and the problems that the driving direction of the driver is wrong or a wrong driving road is selected and the like are prone to occur. However, the vehicle speed detection system provided by the application can detect the running speed of the vehicle according to the light signal characteristic information in the light signal data and the trained running speed prediction model by detecting the light signal data in the tunnel when the vehicle runs in the tunnel, and the timeliness and the accuracy of vehicle speed detection are high. Furthermore, the navigation of the vehicle in a special road section can be realized, the navigation error caused by poor signals can be effectively reduced, and the real-time performance and the accuracy rate of the navigation are improved.

The following describes the vehicle speed detection method provided by the embodiment of the present application in detail with reference to the content described in the vehicle speed detection system shown in fig. 1.

Referring to fig. 2, fig. 2 is a flowchart illustrating a vehicle speed detection method according to an embodiment of the present application, where the vehicle speed detection method can be applied to the vehicle speed detection system and is specifically executed by one or more processors in a vehicle speed detection device in the vehicle speed detection system, as shown in fig. 2, the specific execution process is as follows:

s201: and acquiring light signal data received when the vehicle runs in the tunnel in a time period to be detected.

In this step, when the vehicle speed detection device needs to detect the running speed of the vehicle, the light signal data received in the time period to be detected when the vehicle runs in the tunnel can be acquired according to the time period to be detected in which the running speed needs to be detected.

The vehicle speed detection device may determine that the driving speed of the vehicle needs to be detected when the vehicle speed detection device detects that the vehicle is about to enter the tunnel to drive or detects that the vehicle has entered the tunnel to drive through the position of the vehicle.

In some embodiments, for better detecting the running speed of the vehicle in real time, the vehicle speed detecting device may periodically detect the running speed of the vehicle, and when the running speed of the vehicle in one period is detected, the light signal data in one period needs to be acquired, so that the time period to be detected may correspond to a detection period of the vehicle speed detecting device for the running speed of the vehicle, for example, if the vehicle speed detecting device needs to detect the running speed of the vehicle once for 30 seconds, the time period to be detected may also be a time period of 30 seconds.

The light signal data received when the vehicle travels in the tunnel may be light signal data received by detecting the illumination light and the like of the illumination device in the tunnel by the light signal detecting device in the vehicle speed detecting system shown in fig. 1. In a specific embodiment, the light signal detection device may be a light detection device or a simple light sensor disposed on a vehicle, and may also collect light signal data by using a light detection function of a mobile terminal of a driver or a passenger.

S202: and determining the light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data.

In this step, after the vehicle speed detection device acquires the light signal data, the light signal characteristic information of the vehicle at each detection time in the time period to be detected can be determined from the light signal data.

The light signal characteristic information may be information representing various dimensional characteristics of the collected light signal, such as variation information, variance information, energy spectrum information, and power spectrum information of the light signal.

In some embodiments, the collected light signal when the vehicle travels in the tunnel may reflect a light intensity change of the vehicle in the tunnel during the traveling, and specifically, the collected light with the light intensity change may be represented by a periodic waveform map, and the light signal characteristic information may be further extracted from the waveform map.

S203: and determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained running speed prediction model.

In this step, after the characteristic information of the light signal is determined, the vehicle speed detection device may obtain the driving speed of the vehicle through a trained driving speed prediction model and the characteristic information of the light signal, so as to achieve the purpose of detecting the driving speed of the vehicle.

The travel speed prediction model may be a model using various neural networks, a deep learning model, or the like, and may be, for example, an LSTM regression model.

Further, because the characteristics of different tunnels and other special road sections are different, for example, the lengths of different tunnels, the distances between illuminating lamps, linear tunnels, tunnels with curves or tunnels with branches and the like, different tunnels can be generally classified into several types, then the same or same type of driving speed prediction models are used for the same type of tunnels, no limitation is made on the specific type of the used models, a large amount of data is needed as a basis compared with the mode that each tunnel needs to use the respective model, the calculation amount of a service end is large, the calculation speed is influenced, the same model is used for the same type of tunnels, the requirement of the data amount and the calculation space can be reduced, and the calculation speed is improved.

According to the vehicle speed detection method provided by the embodiment of the application, light signal data received when a vehicle runs in a tunnel in a time period to be detected is obtained; determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data; and determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained running speed prediction model.

Therefore, the driving speed of the vehicle in the tunnel is detected by receiving the light signal data in the tunnel, obtaining the light signal characteristic information and the trained driving speed prediction model, the driving speed of the vehicle in the special road section with poor signals can be detected, and timeliness and accuracy are high.

Referring to fig. 3, fig. 3 is a flowchart illustrating another vehicle speed detection method according to an embodiment of the present application, where the vehicle speed detection method can be applied to the vehicle speed detection system and is specifically executed by one or more processors in a vehicle speed detection device in the vehicle speed detection system, and as shown in fig. 3, the specific execution process is as follows:

s301: and acquiring light signal data received when the vehicle runs in the tunnel in a time period to be detected.

S302: and determining the light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data.

S303: and determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained running speed prediction model.

S304: the driving direction of the vehicle is acquired.

The driving direction of the vehicle may be obtained by identifying through an accelerometer, a gyroscope, or other devices or sensors mounted on the vehicle, or may be detected through a third-party device independent of the vehicle, such as a mobile terminal with a direction detection function of a driver or a passenger.

S305: determining navigation information of the vehicle based on the driving direction and the driving speed.

In this step, after the driving speed is determined and the driving direction is acquired, the vehicle speed detection device may determine the navigation information of the vehicle according to the driving direction and the driving speed, so as to assist the navigation device of the vehicle in navigating the vehicle in real time.

The descriptions of step S301 to step S303 may refer to the descriptions of step S201 to step S203, and the same technical effects may be achieved, which are not described herein again.

In some embodiments of the present application, S303 comprises:

generating a light signal characteristic vector sequence of the vehicle based on the light signal characteristic information of the vehicle at each detection moment, wherein the light signal characteristic vector sequence comprises light signal characteristic vectors respectively corresponding to the detection moments; and inputting the light signal characteristic vector sequence into a trained running speed prediction model to obtain the running speed of the vehicle in the tunnel.

In this step, after the light signal characteristic information at each detection time is determined, the vehicle speed detection device may perform characteristic extraction from the light signal characteristic information corresponding to each detection time, so as to extract light signal characteristics corresponding to the vehicle at each detection time, so as to generate a light signal characteristic vector sequence of the vehicle according to the extracted light information characteristics, and then the vehicle speed detection device may input the light signal characteristic vector sequence into a trained traveling speed prediction model to process the light signal characteristic vector sequence, so as to detect the speed of the vehicle, and finally, the traveling speed of the vehicle in the tunnel may be obtained according to an output result of the traveling speed prediction model.

The light signal feature vector sequence comprises light signal feature vectors respectively corresponding to the detection moments, and each light signal feature vector comprises a feature value of a light signal feature corresponding to the corresponding detection moment.

Specifically, the light signal feature vector sequence of the vehicle is generated based on the light signal feature information of the vehicle at each detection time, and the processing such as feature screening and extraction may be performed from the light signal feature information corresponding to each detection time, so that a plurality of light signal features of the vehicle at each detection time are obtained according to the light signal feature information corresponding to each detection time, and further, a feature value under each light signal feature may be determined according to the light signal feature information, then, the light signal feature vector at each detection time is constructed according to the feature value under the plurality of light signal features of the vehicle, and then, the light signal feature vector sequence may be generated according to the light signal feature vector at each detection time.

Further, the light signal feature vector sequence is input into a trained traveling speed prediction model to obtain the traveling speed of the vehicle in the tunnel, and may be that each light signal feature vector in the light signal feature vector sequence is sequentially used as a light signal feature vector at the current detection time, and a previous-time intermediate feature vector output after the light signal feature vector at the previous detection time passes through a hidden layer in the traveling speed prediction model is obtained.

The light signal characteristic vector at the previous moment is a characteristic vector at a previous detection moment of the light signal characteristic vector at the current moment, and the previous detection moment is a moment before the current detection moment.

And then inputting the current-time light signal characteristic vector and the previous-time intermediate characteristic vector into a trained running speed prediction model to obtain the current-time running speed corresponding to the current-time light signal characteristic vector.

And finally, determining the average running speed of the vehicle in the time period to be detected based on the obtained running speeds at the current moment.

Illustratively, the travel speed prediction model may be an LSTM model, and when the travel speed of the vehicle is determined by the light signal feature vector sequence and the travel speed prediction model, in view of characteristics of the LSTM model, each light signal feature vector may be sequentially used as a light signal feature vector at a current time at which speed detection is required in an acquisition order of light signals, that is, a time-series order of each light signal feature vector in the light signal feature vector sequence, and a previous-time intermediate feature vector corresponding to a light signal feature vector at a previous detection time to the current detection time may be acquired, where, when the light signal feature vector as the light signal feature vector at the current time is a first feature vector, the obtained light signal characteristic vector at the current moment and the obtained corresponding intermediate characteristic vector at the previous moment are input into a neural network of a driving speed prediction model to be processed, if the light signal characteristic vector at the current moment and the obtained corresponding intermediate characteristic vector at the previous moment are input into the neural network of an LSTM model, the driving speed of the vehicle at the current detection moment corresponding to the light signal characteristic vector at the current moment output by the neural network can be obtained, and after the driving speed at the current moment corresponding to each detection moment in the time period to be detected is obtained, the average driving speed of the vehicle in the time period to be detected can be calculated.

The intermediate characteristic vector of the previous time corresponding to the characteristic vector of the light signal of the previous time may be an intermediate characteristic vector that is output by a hidden layer and needs to be used when the characteristic vector is processed next time when the characteristic vector of the light signal of the previous time is processed in a neural network in a driving speed prediction model.

Accordingly, in some embodiments of the present application, there is also provided a method for training a traveling speed prediction model, which may train the traveling speed prediction model by:

(1) and acquiring a plurality of groups of light signal sample data received when the vehicle runs in the tunnel in a historical time period.

The light signal data received when the vehicle runs in the tunnel can be acquired through light detection equipment or a simple light sensor arranged on the vehicle, and can also be acquired by using a light detection function on a mobile terminal of a driver or a passenger.

The multiple groups of light signal sample data received when the vehicle runs in the tunnel can be different groups of light signal sample data detected by different light signal detection devices in the same historical time period; because the lighting equipment in the tunnel is normally on for 24 hours, multiple sets of light signal sample data received when the vehicle runs in the tunnel can be acquired in each historical time period through the same light signal detection device aiming at multiple historical time periods with the same time length.

(2) And determining the characteristic information of the light signal sample of the vehicle at each historical detection moment in the historical time period based on each group of light signal sample data.

After a plurality of groups of light signal sample data are collected, preprocessing such as denoising processing can be performed on the collected plurality of groups of light signal sample data, so that interference data in each group of light signal sample data are removed, for example, if local construction and other conditions occur in a tunnel, construction illumination for construction may exist, the construction illumination may be different from the brightness and the like of tunnel illumination, and certain interference can be performed on the collected data, so that the heterogeneous light signal data can be removed through preprocessing.

(3) And training a driving speed prediction model based on the characteristic information of the plurality of light signal samples and the actual driving speed of the vehicle corresponding to each group of light signal sample data.

In the above embodiment, (3) specifically includes:

for each group of light signal sample data, generating a light signal sample feature vector sequence of the vehicle based on light signal sample feature information of the vehicle at each historical detection time, wherein the light signal sample feature vector sequence comprises light signal feature vectors corresponding to the historical detection times respectively; and training a constructed running speed prediction model based on the plurality of light signal sample feature vector sequences and the actual running speed of the vehicle corresponding to each light signal sample feature vector sequence.

In this step, for each set of light signal sample data, feature extraction may be performed from the light signal feature information corresponding to each historical detection time to generate a light signal sample feature vector sequence of the vehicle according to the extracted light information sample features, and then the vehicle speed detection apparatus may input the light signal sample feature vector sequence into a constructed travel speed prediction model, and train the constructed travel speed prediction model through a plurality of light signal sample feature vector sequences and an actual travel speed of the vehicle corresponding to each light signal sample feature vector sequence.

The light signal sample feature vector sequence comprises light signal feature vectors corresponding to the historical detection moments respectively, and each light signal sample feature vector comprises a sample feature value of a light signal sample feature corresponding to the corresponding historical detection moment.

Specifically, for each set of light signal sample data, a light signal sample feature vector sequence of the vehicle is generated based on light signal sample feature information of the vehicle at each historical detection time, which may be obtained by performing sample feature screening, extraction and other processing on the light signal sample feature information corresponding to each historical detection time, so as to obtain a plurality of light signal sample features of the vehicle at each historical detection time according to the light signal sample feature information corresponding to each historical detection time, and further determine a sample feature value under each light signal sample feature according to the light signal sample feature information, then construct a light signal sample feature vector at each historical detection time according to the sample feature value under the plurality of light signal sample features of the vehicle, and then construct a light signal sample feature vector at each historical detection time according to the light signal sample feature vector at each historical detection time, and generating a light signal characteristic vector sequence of the vehicle in the historical time period.

Further, the driving speed prediction model is trained based on the plurality of light signal sample feature vector sequences and the actual driving speed of the vehicle corresponding to each light signal sample feature vector sequence, and may be that, for each light signal sample feature vector sequence, each light signal sample feature vector in the light signal sample feature vector sequence is sequentially used as a light signal sample feature vector at the current moment of the current sample detection moment, and a feature vector in the middle of a previous moment sample output after the light signal sample feature vector at the previous moment of the previous sample detection moment passes through a hidden layer in the driving speed prediction model is obtained.

The characteristic vector of the light signal sample at the previous moment is a characteristic vector of the light signal characteristic vector at the previous sample detection moment at the current moment, and the previous sample detection moment is a moment before the current sample detection moment.

And then inputting the characteristic vector of the light signal sample at the current moment and the intermediate characteristic vector of the sample at the previous moment into a constructed running speed prediction model to obtain the running speed at the current moment corresponding to the characteristic vector of the light signal sample at the current moment.

Then, the travel speed prediction model may be trained based on a plurality of current-time travel speeds and the actual travel speed at each of the historical detection times. Specifically, the model parameters of the travel speed prediction model may be adjusted based on each current travel speed and an actual travel speed corresponding to each current travel speed until a difference between the current travel speed output by the travel speed prediction model and the corresponding actual travel speed is within a preset range, and it is determined that the travel speed prediction model is trained.

Wherein, because light signal detection device probably receives other interferences at the tunnel in-process of traveling, for example, along with the increase of street lamp duration of use in the tunnel, the street lamp has wearing and tearing, and the luminance of light can change, and the signal that leads to gathering also can follow the change. Therefore, the parameters of the traveling speed prediction model can be updated regularly, and the accuracy of the traveling speed prediction model can be improved.

Moreover, the same driving speed prediction model can be used for similar or same tunnels of the same type, so that the required quantity of training data can be reduced, the data processing quantity can be reduced, the training efficiency of the driving speed prediction model can be improved, and the corresponding overall training time can be shortened in the process of training the model.

According to the vehicle speed detection method provided by the embodiment of the application, light signal data received when a vehicle runs in a tunnel in a time period to be detected is obtained; determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data; determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and a trained running speed prediction model; acquiring the driving direction of the vehicle; determining navigation information of the vehicle based on the driving direction and the driving speed.

Therefore, the light signal data in the tunnel are collected, the driving speed of the vehicle in the tunnel is detected through the light signal characteristic information, the obtained driving speed and the obtained driving direction of the vehicle are combined to determine the navigation information of the vehicle, the driving speed of the vehicle in a special road section with poor signals can be detected, the timeliness and the accuracy are high, the vehicle can be further helped to realize navigation in the special road section, the navigation error caused by poor signals is effectively reduced, and the navigation instantaneity and the accuracy are improved.

Based on the same inventive concept, the embodiment of the present application further provides a vehicle speed detection device corresponding to the vehicle speed detection method, and as the principle of solving the problem of the device in the embodiment of the present application is similar to that of the vehicle speed detection method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and repeated details are not repeated.

Referring to fig. 4 to 6, fig. 4 is a first structural diagram of a vehicle speed detecting device according to an embodiment of the present application, fig. 5 is a second structural diagram of a vehicle speed detecting device according to an embodiment of the present application, and fig. 6 is a third structural diagram of a vehicle speed detecting device according to an embodiment of the present application. As shown in fig. 4, the vehicle speed detection device 400 includes:

the first obtaining module 410 is configured to obtain light signal data received when the vehicle travels in the tunnel in the time period to be detected.

A first determining module 420, configured to determine light signal characteristic information of the vehicle at each detection time in the time period to be detected based on the light signal data acquired by the first acquiring module 410.

And a second determining module 430, configured to determine a traveling speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle determined by the first determining module 420 and the trained traveling speed prediction model.

In some embodiments of the present application, the second determining module 430 is specifically configured to:

In some embodiments of the present application, the second determining module 430 is further specifically configured to:

In some embodiments of the present application, as shown in fig. 5, the vehicle speed detection device 400 further includes:

a second obtaining module 440, configured to obtain a driving direction of the vehicle;

a third determining module 450, configured to determine navigation information of the vehicle based on the driving direction acquired by the second acquiring module 440 and the driving speed determined by the second determining module 430.

In some embodiments of the present application, as shown in fig. 6, the vehicle speed detection apparatus 400 further includes a model training module 460 for training the travel speed prediction model by:

In some embodiments of the present application, the model training module 460 is specifically configured to:

In some embodiments of the present application, the model training module 460 is further specifically configured to:

The vehicle speed detection device provided by the embodiment of the application obtains the light signal data received by the vehicle when the vehicle runs in the tunnel in the time period to be detected; determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data; and determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained running speed prediction model.

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 700 provided by the embodiment of the present application includes a processor 710, a memory 720 and a bus 730.

The memory 720 stores machine-readable instructions executable by the processor 710, the processor 710 and the memory 720 communicate via the bus 730 when the electronic device 700 is operating, and the processor 710 executes the machine-readable instructions to perform one or more of the following:

In some embodiments of the application, the machine readable instructions, when executed by the processor 710, may perform one or more of the following operations:

acquiring the driving direction of the vehicle;

The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the vehicle speed detection method in the method embodiments shown in fig. 2 and fig. 3 may be executed.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A vehicle speed detection method, characterized by comprising:

acquiring light signal data of lighting equipment arranged in a tunnel, which is received when a vehicle runs in the tunnel in a time period to be detected;

determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data, wherein the light signal characteristic information is characteristic information used for reflecting light brightness change of the vehicle in a tunnel in the driving process;

determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and a trained running speed prediction model;

the driving speed prediction model is obtained by training based on the light signal sample characteristic information corresponding to each group of light signal sample data acquired in a historical time period and the actual driving speed of the vehicle corresponding to each group of light signal sample data, wherein the light signal sample data is received when the vehicle drives in the tunnel in the historical time period and is light signal data of lighting equipment arranged in the tunnel.

2. The vehicle speed detection method according to claim 1, wherein the determining the traveling speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and a trained traveling speed prediction model comprises:

3. The vehicle speed detection method according to claim 2, wherein the generating of the light signal feature vector sequence of the vehicle based on the light signal feature information of the vehicle at each of the detection times includes:

4. A vehicle speed detection method as claimed in claim 3, wherein the light signal characteristic includes at least one of:

5. The vehicle speed detection method according to claim 2, wherein the inputting the light signal feature vector sequence into a trained running speed prediction model to obtain the running speed of the vehicle in the tunnel comprises:

6. The vehicle speed detection method according to claim 1, wherein after determining the traveling speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle and the trained traveling speed prediction model, the method further comprises:

acquiring the driving direction of the vehicle;

7. The vehicle speed detection method according to claim 1, characterized in that the running speed prediction model is trained by:

acquiring a plurality of groups of light signal sample data of lighting equipment arranged in a tunnel, which are received when a vehicle runs in the tunnel in a historical time period;

8. The vehicle speed detecting method according to claim 7, wherein the training of the driving speed prediction model based on the plurality of characteristic information of the light signal samples and the actual driving speed of the vehicle corresponding to each group of light signal samples comprises:

9. The vehicle speed detection method according to claim 8, wherein the generating a light signal sample feature vector sequence of the vehicle based on light signal sample feature information of the vehicle at each of the historical detection times for each set of light signal sample data includes:

10. The vehicle speed detection method according to claim 9, wherein the light signal sample characteristic includes at least one of:

11. The vehicle speed detection method according to claim 8, wherein the training of the constructed travel speed prediction model based on the plurality of light signal sample feature vector sequences and the actual travel speed of the vehicle corresponding to each light signal sample feature vector sequence comprises:

12. The vehicle speed detection method according to claim 11, wherein training a travel speed prediction model based on a plurality of current-time travel speeds and the actual travel speed at each of the historical detection times includes:

13. A vehicle speed detection device, characterized by comprising:

the first acquisition module is used for acquiring light signal data of the lighting equipment arranged in the tunnel, which is received when the vehicle runs in the tunnel in a time period to be detected;

the first determining module is used for determining light signal characteristic information of the vehicle at each detection moment in the time period to be detected based on the light signal data acquired by the first acquiring module, wherein the light signal characteristic information comprises collected characteristic information of various dimensional characteristics of light signals used for reflecting light and shade changes of the vehicle in a tunnel in the driving process;

the second determination module is used for determining the running speed of the vehicle in the tunnel based on the light signal characteristic information of the vehicle determined by the first determination module and the trained running speed prediction model;

14. The vehicle speed detection device according to claim 13, characterized in that the second determination module is specifically configured to:

15. The vehicle speed detection device according to claim 14, wherein the second determination module is further specifically configured to:

16. The vehicle speed detection device of claim 15, wherein the light signal characteristic includes at least one of:

17. The vehicle speed detection device according to claim 14, wherein the second determination module is further specifically configured to:

18. The vehicle speed detection device according to claim 13, characterized by further comprising:

19. The vehicle speed detection apparatus according to claim 13, characterized by further comprising a model training module for training the running speed prediction model by:

20. The vehicle speed detection device of claim 19, wherein the model training module is specifically configured to:

21. The vehicle speed detection device of claim 20, wherein the model training module is specifically configured to:

22. The vehicle speed detection device of claim 21, wherein the light signal sample characteristics include at least one of:

23. The vehicle speed detection device of claim 20, wherein the model training module is further configured to:

24. The vehicle speed detection device of claim 23, wherein the model training module is further configured to:

25. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the vehicle speed detection method according to any one of claims 1 to 12.

26. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, is adapted to carry out the steps of the vehicle speed detection method according to any one of claims 1 to 12.