CN112396803A - Vehicle safety alarm method, device, storage medium and device - Google Patents
Vehicle safety alarm method, device, storage medium and device Download PDFInfo
- Publication number
- CN112396803A CN112396803A CN202011425742.0A CN202011425742A CN112396803A CN 112396803 A CN112396803 A CN 112396803A CN 202011425742 A CN202011425742 A CN 202011425742A CN 112396803 A CN112396803 A CN 112396803A
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- audio
- current
- abnormal
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0205—Specific application combined with child monitoring using a transmitter-receiver system
- G08B21/0208—Combination with audio or video communication, e.g. combination with "baby phone" function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
-
- 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
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Abstract
The invention discloses an alarming method, equipment, a storage medium and a device for vehicle safety, wherein the method comprises the steps of firstly obtaining current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information; secondly, when the current vehicle state is an abnormal state, obtaining current image information of the vehicle, judging the abnormal state according to the current image information, and obtaining an abnormal judgment result; and finally, when the abnormity judgment result is that abnormity exists, generating alarm information and sending the alarm information to the mobile terminal. The invention determines the current vehicle state through the current audio information, then judges the abnormal state according to the current image information and generates and sends the alarm information when the abnormal state exists, thereby accurately realizing the alarm of the safety state of the vehicle of the static vehicle.
Description
Technical Field
The invention relates to the technical field of vehicle safety, in particular to an alarming method, equipment, a storage medium and a device for vehicle safety.
Background
From the daily vehicle use scene, most of the time the vehicle is in a parking state, and the external and internal states of the vehicle during parking are expected to be monitored by a user. The problem of difficult parking troubles all car owners, even after parking, the car owners can also worry that the car can not be knocked by others, the event that the car is knocked when parking often happens, the car which causes the accident is difficult to track after leaving, and the parking monitoring system is just needed by users. Sometimes, a user temporarily leaves a vehicle, and may leave children, pets and the like on the vehicle, or leave the children and the pets on the vehicle when leaving, and the children and the pets may be injured or even died in a closed environment in the vehicle, and similar accidents occur in summer every year. Such an occurrence can be avoided if an abnormal state in the vehicle can be monitored.
In the prior art, a single mode is usually adopted to detect the state of a vehicle when the vehicle is parked in real time, for example, an infrared sensing mode needs to arrange an infrared sensor in the vehicle and an ultrasonic monitoring mode waits, and the single mode is adopted to detect the state of the vehicle in real time, so that false alarm is easily generated.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide an alarming method, equipment, a storage medium and a device for vehicle safety, and aims to solve the technical problem that false alarm is easily generated when a static vehicle is detected in real time in a single mode in the prior art.
In order to achieve the above object, the present invention provides a vehicle safety warning method, including the steps of:
acquiring current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information;
when the current vehicle state is an abnormal state, acquiring current image information of the vehicle, and confirming the abnormal state according to the current image information to obtain an abnormal confirmation result;
and when the abnormity judgment result is that abnormity exists, generating alarm information, and sending the alarm information to the mobile terminal.
Preferably, the step of obtaining current audio information generated by the vehicle and determining the current vehicle state according to the current audio information comprises:
acquiring current audio information generated by a vehicle, and denoising the current audio information through a soundproof door denoising technology to acquire denoised audio information;
extracting abnormal audio information from a preset audio library according to the audio feature identification of the noise reduction audio information;
and comparing the noise reduction audio information with the abnormal audio information to determine the current vehicle state.
Preferably, the step of extracting abnormal audio information from a preset audio library according to the audio feature identifier of the noise reduction audio information includes:
inputting the noise reduction audio information into a preset audio feature identification model, and taking a model output result as an audio feature identification;
and extracting abnormal audio information from a preset audio library according to the audio characteristic identifier.
Preferably, before the step of inputting the noise reduction audio information into a preset audio feature identifier model and taking a model output result as an audio feature identifier, the method further includes:
acquiring an initial audio characteristic identification model;
and training the initial audio feature identification model according to the preset audio library to obtain a preset audio feature identification model.
Preferably, when the current vehicle state is an abnormal state, the step of obtaining current image information of the vehicle and confirming the abnormal state according to the current image information includes:
when the current vehicle state is an abnormal state, acquiring current image information of the vehicle;
extracting abnormal image information from a preset image library according to the current image information;
comparing the current image information with the abnormal image information to obtain image similarity;
and judging the abnormal state according to the image similarity and a preset similarity threshold to obtain an abnormal judgment result.
Preferably, the step of extracting abnormal image information from a preset image library according to the current image information comprises:
performing local feature recognition on the current image information through a wavelet recognition algorithm to obtain local feature information;
sharpening the local feature information to obtain local feature sharpening information;
and extracting abnormal image information from a preset image library according to the local feature sharpening information.
Preferably, after the step of generating alarm information and sending the alarm information to the mobile terminal when the abnormality confirmation result is that an abnormality is confirmed, the method further includes:
updating the preset audio library according to the current audio information to obtain an updated preset audio library;
and updating the preset image library according to the current image information to obtain the updated preset image library.
In addition, in order to achieve the above object, the present invention further provides a vehicle safety warning device, which includes a memory, a processor, and a vehicle safety warning program stored in the memory and operable on the processor, wherein the vehicle safety warning program is configured to implement the steps of the vehicle safety warning method as described above.
In addition, in order to achieve the above object, the present invention further provides a storage medium, on which a vehicle safety warning program is stored, which when executed by a processor implements the steps of the vehicle safety warning method as described above.
In addition, in order to achieve the above object, the present invention also provides a vehicle safety warning device, including: the device comprises an audio information acquisition module, an image information acquisition module and an alarm information generation module;
the audio information acquisition module is used for acquiring current audio information generated by the vehicle and determining the current vehicle state according to the current audio information;
the image information acquisition module is used for acquiring current image information of the vehicle when the current vehicle state is an abnormal state, and confirming the abnormal state according to the current image information to obtain an abnormal confirmation result;
and the alarm information generation module is used for generating alarm information and sending the alarm information to the mobile terminal when the abnormity judgment result is abnormal.
The invention provides an alarm method, equipment, a storage medium and a device for vehicle safety, wherein the method comprises the steps of firstly obtaining current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information; secondly, when the current vehicle state is an abnormal state, obtaining current image information of the vehicle, judging the abnormal state according to the current image information, and obtaining an abnormal judgment result; and finally, when the abnormity judgment result is that abnormity exists, generating alarm information and sending the alarm information to the mobile terminal. The invention determines the current vehicle state through the current audio information, then judges the abnormal state according to the current image information and generates and sends the alarm information when the abnormal state exists, thereby accurately realizing the alarm of the safety state of the vehicle of the static vehicle.
Drawings
FIG. 1 is a schematic diagram of a vehicle safety warning device for a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram of a first embodiment of a warning method for vehicle safety according to the present invention;
FIG. 3 is a schematic flow chart diagram of a second embodiment of the warning method for vehicle safety of the present invention;
FIG. 4 is a schematic flow chart diagram illustrating a third embodiment of a warning method for vehicle safety according to the present invention;
fig. 5 is a block diagram showing the construction of a first embodiment of the warning device for vehicle safety of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a vehicle safety warning device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the vehicle safety warning apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), and the optional user interface 1003 may further include a standard wired interface and a wireless interface, and the wired interface for the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory or a Non-volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the warning device for vehicle safety and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in FIG. 1, a memory 1005, identified as one type of computer storage medium, may include an operating system, a network communication module, a user interface module, and a vehicle safety alert program.
In the alarm device for vehicle security shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting user equipment; the vehicle safety warning device calls a vehicle safety warning program stored in the memory 1005 through the processor 1001 and executes the vehicle safety warning method provided by the embodiment of the invention.
Based on the hardware structure, the embodiment of the alarm method for vehicle safety is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the vehicle safety warning method, and provides the first embodiment of the vehicle safety warning method.
In a first embodiment, the warning method for vehicle safety includes the steps of:
step S10: the method comprises the steps of obtaining current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information.
It should be understood that the execution main body of the present embodiment may be an onboard controller. The vehicle-mounted controller comprises an information acquisition module and an information processing module. The information acquisition module is used for acquiring current audio information and current image information of the vehicle; the information processing module is used for processing the acquired current audio information and image information of the vehicle, determining whether the vehicle is abnormal or not and giving an alarm when the vehicle is abnormal.
It should be noted that the current audio information refers to sound information generated from the inside or outside of the vehicle in a stationary state. The current audio information can be information generated by the modes of collision, scratch and the like outside the vehicle, and can also be information generated by living objects inside the vehicle. For example, when the current vehicle is in a stationary state, there are other vehicles colliding with the current vehicle, and the sound generated due to the collision is the current audio information. Similarly, when the vehicle is in a stationary state, because children still exist in the vehicle, sound is inevitably generated in the vehicle in a closed state, and the sound is also current audio information. The current vehicle state includes a normal state and an abnormal state of the current vehicle. The normal state refers to a state where no abnormal sound is generated between the inside and the outside of the vehicle, the outside of the vehicle is not collided to generate sound, and no living object is generated inside the vehicle, and the current state of the vehicle is in the normal state by default. Similarly, the abnormal state refers to a state where abnormal sounds are generated inside and outside the vehicle, sounds generated outside the vehicle due to a collision or sounds generated inside a living object, and may also be sounds generated outside the vehicle due to a collision and sounds generated inside the vehicle due to a living object, when it is assumed that the current state of the vehicle is in the abnormal state.
In a specific implementation, the vehicle-mounted controller may acquire current audio information generated by the vehicle through the sound sensor to acquire the current audio information inside and outside the vehicle. And after the current audio information is acquired, analyzing the acquired current audio information, and determining the current vehicle state according to an analysis result.
Step S20: and when the current vehicle state is an abnormal state, acquiring current image information of the vehicle, and confirming the abnormal state according to the current image information to obtain an abnormal confirmation result.
The current vehicle state is an abnormal state, which means a state in which abnormal sounds are generated between the inside and the outside of the vehicle of the current vehicle, and at least one of sounds generated by a collision outside the vehicle or sounds generated by living objects inside the vehicle exists in the abnormal state. The current image information refers to image information of the current vehicle at the current time. The current image information includes image information of the inside of the vehicle and image information of the outside of the vehicle. The abnormality confirmation result is a result of confirming whether or not the vehicle is in an abnormal state. The exception confirmation result includes the presence and absence of an exception. When acquiring the current image information of the vehicle, the current image information may be acquired by an image acquisition device, such as an on-board camera.
In a specific implementation, when the current vehicle state is an abnormal state, the vehicle-mounted controller can acquire current image information outside and inside the vehicle through the image acquisition device, analyze the current image information when acquiring the current image information, and confirm the abnormal state according to an analysis result to obtain an abnormal confirmation result. For example, the current image information may be compared with the feature information in the abnormal image information to check the abnormal state of the vehicle. The characteristic information is information that reflects the state of the vehicle, such as information on the living things inside the vehicle,
step S30: and when the abnormity judgment result is that abnormity exists, generating alarm information, and sending the alarm information to the mobile terminal.
It should be noted that the alarm information is information for reminding the owner of the vehicle that the vehicle is abnormal. The alarm information may be information including at least one of current audio information or current image information, or may be pure alarm information including no current audio information or current image information. The mobile terminal is a mobile terminal bound with the current vehicle, and may be a mobile terminal carried by a vehicle owner, such as a mobile phone. The alarm information of the vehicle safety can be used for actively detecting the state of the current vehicle by the vehicle in a static state, and can also be used for detecting the state of the current vehicle by a vehicle owner through remote starting of a mobile client.
In specific implementation, when the abnormality judgment result is that the abnormality exists, the vehicle-mounted controller generates alarm information of the vehicle abnormality, and sends the alarm information to the mobile terminal through the wireless network, so that a vehicle owner knows the current state of the vehicle and takes corresponding measures.
The embodiment provides an alarming method, equipment, a storage medium and a device for vehicle safety, wherein the method comprises the steps of firstly obtaining current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information; secondly, when the current vehicle state is an abnormal state, obtaining current image information of the vehicle, judging the abnormal state according to the current image information, and obtaining an abnormal judgment result; and finally, when the abnormity judgment result is that abnormity exists, generating alarm information and sending the alarm information to the mobile terminal. The embodiment determines the current vehicle state through the current audio information, then judges the abnormal state according to the current image information, generates and sends the alarm information when the abnormal state exists, and accurately realizes the alarm of the safety state of the vehicle of the static vehicle.
Referring to fig. 3, fig. 3 is a flowchart illustrating a second embodiment of the warning method for vehicle safety according to the present invention, and the second embodiment of the warning method for vehicle safety according to the present invention is proposed based on the first embodiment illustrated in fig. 2.
In the second embodiment, the step S10 includes:
step S101: the method comprises the steps of obtaining current audio information generated by a vehicle, and denoising the current audio information through a soundproof door denoising technology to obtain denoising audio information.
It should be noted that the noise removal technique of the sound-proof gate is a noise removal technique in which a threshold value of a level is determined, all signal levels lower than the threshold value are filtered, and all signal levels higher than the threshold value pass through. The sound-proof door noise removal technology can effectively remove background noise and does not damage original sound. Background noise refers generally to any disturbance in a generating, examining, measuring or recording system that is not related to the presence or absence of a signal. Noise reduction refers to reducing noise information in the current audio information. The noise reduction audio information refers to audio information with low noise obtained after noise reduction is performed on current audio information.
In specific implementation, the vehicle controller may collect current audio information through the audio collecting device, and perform noise reduction processing on the collected current audio information through a noise reduction technology of the soundproof door to obtain noise reduction audio information. For example, a vehicle-mounted audio collector is adopted to collect current audio information inside and outside a vehicle, the collected audio information passes through a sound insulation door, and background noises below a threshold value are all filtered to obtain noise reduction audio information with low noise.
Step S102: and extracting abnormal audio information from a preset audio library according to the audio feature identification of the noise reduction audio information.
It should be noted that the audio feature identifier refers to an identifier having a distinctive feature in the noise reduction audio information. Such as crying by a child, rubbing by a vehicle collision, etc. The preset audio library refers to a preset audio library comprising a large amount of abnormal audio information. The abnormal audio information refers to audio information in which the current vehicle state is in an abnormal state.
In specific implementation, the vehicle-mounted controller obtains the audio feature identifier from the noise reduction audio information, and extracts corresponding abnormal audio information from a preset audio library according to the obtained audio feature identifier, for example, when a library needs a specific book, a corresponding book storage cabinet needs to be searched from the library according to the type of the book, so as to find the book.
Wherein, step S102 includes:
step S1021: and inputting the noise reduction audio information into a preset audio feature identification model, and taking a model output result as an audio feature identification.
It should be noted that the preset audio feature identifier model refers to a preset model for outputting an audio feature identifier according to noise reduction audio information. The preset audio feature identification model may use noise-reduced audio information as an input, and use audio feature identification as an output, and certainly may also use non-noise-reduced audio information as an input, which is not specifically limited herein. The model output result is the output result of the preset audio feature identification model, namely the audio feature identification.
In specific implementation, the vehicle-mounted controller may input the obtained noise reduction audio information to a preset audio feature identifier model in an instruction manner and obtain a model output result, where the model output result is the audio feature identifier.
Step S1022: and extracting abnormal audio information from a preset audio library according to the audio characteristic identifier.
It should be noted that, after obtaining the audio feature identifier, the vehicle-mounted controller extracts corresponding abnormal audio information from a preset audio library according to the obtained audio feature identifier.
Before the step S1021, the method further includes:
step S1021': an initial audio feature identification model is obtained.
It should be noted that the initial audio feature identification model is a trained feature identification recognition model. The initial audio feature identification model can identify the audio feature identification in the noise reduction audio information, but the accuracy of the identification result cannot be ensured. In a specific implementation process, the vehicle-mounted controller may generate the initial audio feature identification model in a command generation manner, may extract the initial audio feature identification model from the storage device in a command extraction manner, and may also obtain the initial audio feature identification model in other manners, which is not specifically limited herein.
Step S1022': and training the initial audio feature identification model according to the preset audio library to obtain a preset audio feature identification model.
It should be noted that training is a process for improving the accuracy of the initial audio feature identification model for identifying the audio feature identification. In a specific implementation process, the vehicle-mounted controller can divide audio files in a preset audio library into training audio and testing audio, wherein the training audio is used for training the initial audio feature identification model, the testing audio is used for testing the trained initial audio feature identification model, and the qualified initial audio feature identification model is used as the preset audio feature identification model. For example, seventy percent of the audio files in the preset audio library are used as training audio, and thirty percent are used as test audio. After the initial audio feature identification model is trained by training audio, the trained initial audio feature identification model needs to be tested by using test audio, and when the accuracy of a test result exceeds a preset threshold value, the trained initial audio feature identification model is used as a preset audio feature identification model.
Step S103: and comparing the noise reduction audio information with the abnormal audio information to determine the current vehicle state.
It should be noted that the current vehicle state is determined by the similarity between the noise reduction audio information and the abnormal audio information. And when the similarity between the noise reduction audio information and the abnormal audio information exceeds the preset similarity, the current vehicle state is determined to be the abnormal state by default, otherwise, the current vehicle state is determined to be the normal state. The preset similarity is a preset similarity threshold. The preset similarity is used for comparing with the similarity of the noise reduction audio information and the abnormal audio information.
In a specific implementation, the on-board controller may compare the digital encoded signal of the audio signal of the noise reduction audio information with the digital encoded signal of the abnormal audio signal to determine a similarity between the noise reduction audio information and the abnormal audio information. And comparing the current similarity with the preset similarity, and if the current similarity is greater than or equal to the preset similarity, determining that the current vehicle state is an abnormal state, otherwise, determining that the current vehicle state is a normal state. The digital coding signal refers to a digital signal obtained by performing analog-to-digital conversion on an audio signal.
The embodiment provides an alarming method, equipment, a storage medium and a device for vehicle safety, wherein the method comprises the steps of firstly obtaining current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information; secondly, when the current vehicle state is an abnormal state, obtaining current image information of the vehicle, judging the abnormal state according to the current image information, and obtaining an abnormal judgment result; and finally, when the abnormity judgment result is that abnormity exists, generating alarm information and sending the alarm information to the mobile terminal. The embodiment determines the current vehicle state through the optimization of the current audio information, then judges the abnormal state according to the current image information, generates and sends the alarm information when the abnormal state exists, and more accurately realizes the alarm of the safety state of the vehicle of the static vehicle.
Referring to fig. 4, fig. 4 is a flowchart illustrating a third embodiment of the warning method for vehicle safety according to the present invention, and the third embodiment of the warning method for vehicle safety according to the present invention is proposed based on the first embodiment illustrated in fig. 2.
In the third embodiment, the step S20 includes:
step S201: and when the current vehicle state is an abnormal state, acquiring the current image information of the vehicle.
The current image information is image information of the current vehicle at the current time. The current image information includes image information of the inside of the vehicle and image information of the outside of the vehicle. In a specific implementation process, when the current vehicle state is an abnormal state, the vehicle-mounted controller can acquire current image information outside and inside the vehicle through the image acquisition device, analyze the current image information when acquiring the current image information, and confirm the abnormal state according to an analysis result to obtain an abnormal confirmation result.
Step S202: and extracting abnormal image information from a preset image library according to the current image information.
The preset image library is an image library that is preset and includes a large amount of abnormal image information. The abnormal image information refers to image information in which the current vehicle state is in an abnormal state. In a specific implementation process, the vehicle-mounted controller may extract corresponding abnormal image information from a preset image library according to the obtained current image information by sending an instruction for obtaining the abnormal image information, and certainly, the vehicle-mounted controller may also use other modes, which is not specifically limited herein.
The step S202 includes:
step S2021: and carrying out local feature identification on the current image information through a wavelet identification algorithm to obtain local feature information.
It should be noted that the wavelet recognition algorithm is an efficient algorithm for image compression and recognition, and is applied to various fields requiring data compression and recognition. In addition, the wavelet recognition algorithm may also perform denoising processing on the image information, which is not described in detail herein. The local feature recognition is a process of recognizing local feature information in image information. For example, the image feature information of the vehicle outside the vehicle colliding with the vehicle or the feature information of the living things inside the vehicle in the current image information is identified. In a specific implementation, the vehicle-mounted controller can identify local features in the current image information through a wavelet identification algorithm, and record the identified local feature information.
Step S2022: and sharpening the local feature information to obtain local feature sharpening information.
In this embodiment, the sharpening refers to image sharpening. Image sharpening (image sharpening) is to compensate the outline of an image, enhance the edge of the image and the part with jump gray level, make the image become clear, and is divided into two types, namely spatial domain processing and frequency domain processing. Image sharpening is to highlight edges, contours, or features of some linear target elements of a terrain on an image. This filtering method improves the contrast between the feature edges and the surrounding picture elements and is therefore also referred to as edge enhancement. The local feature sharpening information refers to current image information obtained by sharpening the local feature information.
In specific implementation, when the local feature information of the current image is acquired, the vehicle-mounted controller may perform sharpening processing on the local feature information of the current image by using sharpening software in an instruction manner, so as to obtain local feature sharpening information.
Step S2023: and extracting abnormal image information from a preset image library according to the local feature sharpening information.
In this embodiment, the on-board controller may extract corresponding abnormal image information from a preset image library according to the obtained local feature sharpening information by sending an instruction to obtain the abnormal image information, which may be of course, the on-board controller may also use other manners, and is not limited herein.
Step S203: and comparing the current image information with the abnormal image information to obtain the image similarity.
The image similarity refers to a degree of similarity between the current image information and the abnormal image information. When the image similarity degree exceeds a certain threshold value, the current image information and the abnormal image information can be determined to be the same. In particular implementations, the on-board controller may compare image pixels of the current image information with image pixels of the abnormal image information to determine an image similarity between the previous image information and the abnormal image information.
Step S204: and judging the abnormal state according to the image similarity and a preset similarity threshold to obtain an abnormal judgment result.
It should be noted that the preset similarity threshold is a threshold for determining whether images are classified as the same type. The same type of image is worth of images with the same local area feature information. In the specific implementation process, the image similarity is compared with a preset similarity threshold, when the image similarity is greater than or equal to the preset similarity threshold, the abnormal judgment result is determined to be abnormal, otherwise, the abnormal judgment result is determined to be abnormal.
After the corresponding step S30, the method further includes:
step S301: and updating the preset audio library according to the current audio information to obtain the updated preset audio library.
It should be noted that the updated preset audio library is an audio library after the current audio information is added to the preset audio library. In a specific implementation process, after the alarm information is generated, the preset audio library needs to be updated according to the current audio information, which may be that the current audio information is added to the preset audio library to update the preset audio library, so as to obtain the updated preset audio library. And taking the updated preset audio library as a preset audio library for the next vehicle abnormity detection.
Step S302: and updating the preset image library according to the current image information to obtain the updated preset image library.
It should be noted that the updated preset image library is an image library after the current image information is added to the preset image library. In a specific implementation process, after the alarm information is generated, the preset image library needs to be updated according to the current image information, which may be that the current image information is added to the preset image library to update the preset image library, so as to obtain the updated preset image library. And taking the updated preset image library as a preset image library for the next vehicle abnormity detection.
The embodiment provides an alarming method, equipment, a storage medium and a device for vehicle safety, wherein the method comprises the steps of firstly obtaining current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information; secondly, when the current vehicle state is an abnormal state, obtaining current image information of the vehicle, judging the abnormal state according to the current image information, and obtaining an abnormal judgment result; and finally, when the abnormity judgment result is that abnormity exists, generating alarm information and sending the alarm information to the mobile terminal. The embodiment determines the current vehicle state through the current audio information, then judges the abnormal state according to the optimized current image information, generates and sends the alarm information when the abnormal state exists, and more accurately realizes the alarm of the safety state of the vehicle of the static vehicle.
In addition, an embodiment of the present invention further provides a storage medium, where a vehicle safety warning program is stored, and the vehicle safety warning program, when executed by a processor, implements the steps of the vehicle safety warning method as described above.
In addition, referring to fig. 5, an embodiment of the present invention further provides a warning device for vehicle safety, where the device includes: the audio information acquisition module 10, the image information acquisition module 20 and the alarm information generation module 30;
the audio information acquiring module 10 is configured to acquire current audio information generated by a vehicle, and determine a current vehicle state according to the current audio information;
the image information obtaining module 20 is configured to obtain current image information of a vehicle when the current vehicle state is an abnormal state, and confirm the abnormal state according to the current image information to obtain an abnormal confirmation result;
and the alarm information generating module 30 is configured to generate alarm information and send the alarm information to the mobile terminal when the abnormality determination result indicates that there is an abnormality.
The embodiment provides a vehicle safety alarm device, wherein an audio information acquisition module 10 acquires current audio information generated by a vehicle, and determines a current vehicle state according to the current audio information; the image information obtaining module 20 obtains current image information of the vehicle when the current vehicle state is an abnormal state, and judges the abnormal state according to the current image information to obtain an abnormal judgment result; the alarm information generation module 30 generates alarm information when the abnormality determination result indicates that there is an abnormality, and sends the alarm information to the mobile terminal. The invention determines the current vehicle state through the current audio information, then judges the abnormal state according to the current image information and generates and sends the alarm information when the abnormal state exists, thereby accurately realizing the alarm of the safety state of the vehicle of the static vehicle.
In an embodiment, the audio information obtaining module 10 is further configured to obtain current audio information generated by a vehicle, and perform noise reduction on the current audio information through a noise isolation door noise removal technology to obtain noise-reduced audio information; extracting abnormal audio information from a preset audio library according to the audio feature identification of the noise reduction audio information; and comparing the noise reduction audio information with the abnormal audio information to determine the current vehicle state.
In an embodiment, the audio information obtaining module 10 is further configured to input the noise reduction audio information to a preset audio feature identifier model, and use a model output result as an audio feature identifier; and extracting abnormal audio information from a preset audio library according to the audio characteristic identifier.
In an embodiment, the audio information obtaining module 10 is further configured to obtain an initial audio feature identification model; and training the initial audio feature identification model according to the preset audio library to obtain a preset audio feature identification model.
In an embodiment, the image information obtaining module 20 is further configured to obtain current image information of the vehicle when the current vehicle state is an abnormal state; extracting abnormal image information from a preset image library according to the current image information; comparing the current image information with the abnormal image information to obtain image similarity; and judging the abnormal state according to the image similarity and a preset similarity threshold to obtain an abnormal judgment result.
In an embodiment, the image information obtaining module 20 is further configured to perform local feature recognition on the current image information through a wavelet recognition algorithm to obtain local feature information; sharpening the local feature information to obtain local feature sharpening information; and extracting abnormal image information from a preset image library according to the local feature sharpening information.
In an embodiment, the alarm information generating module 30 is further configured to update the preset audio library according to the current audio information, so as to obtain an updated preset audio library;
and updating the preset image library according to the current image information to obtain the updated preset image library.
Other embodiments or specific implementation manners of the alarm device for vehicle safety of the invention can refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order, but rather the words first, second, third, etc. are to be interpreted as names.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g., a Read Only Memory (ROM)/Random Access Memory (RAM), a magnetic disk, an optical disk), and includes several instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A warning method for vehicle safety, the method comprising:
acquiring current audio information generated by a vehicle, and determining the current vehicle state according to the current audio information;
when the current vehicle state is an abnormal state, acquiring current image information of the vehicle, and confirming the abnormal state according to the current image information to obtain an abnormal confirmation result;
and when the abnormity judgment result is that abnormity exists, generating alarm information, and sending the alarm information to the mobile terminal.
2. The method of claim 1, wherein the step of obtaining current audio information generated by the vehicle, and determining the current vehicle state based on the current audio information comprises:
acquiring current audio information generated by a vehicle, and denoising the current audio information through a soundproof door denoising technology to acquire denoised audio information;
extracting abnormal audio information from a preset audio library according to the audio feature identification of the noise reduction audio information;
and comparing the noise reduction audio information with the abnormal audio information to determine the current vehicle state.
3. The method of claim 2, wherein the step of extracting abnormal audio information from a preset audio library according to the audio feature identifier of the noise reduction audio information comprises:
inputting the noise reduction audio information into a preset audio feature identification model, and taking a model output result as an audio feature identification;
and extracting abnormal audio information from a preset audio library according to the audio characteristic identifier.
4. The method of claim 3, wherein before the step of inputting the noise reduction audio information into a preset audio feature identification model and outputting the model output result as an audio feature identification, the method further comprises:
acquiring an initial audio characteristic identification model;
and training the initial audio feature identification model according to the preset audio library to obtain a preset audio feature identification model.
5. The method according to claim 1, wherein the step of acquiring current image information of the vehicle when the current vehicle state is an abnormal state, and confirming the abnormal state according to the current image information, and obtaining an abnormal confirmation result comprises:
when the current vehicle state is an abnormal state, acquiring current image information of the vehicle;
extracting abnormal image information from a preset image library according to the current image information;
comparing the current image information with the abnormal image information to obtain image similarity;
and judging the abnormal state according to the image similarity and a preset similarity threshold to obtain an abnormal judgment result.
6. The method as claimed in claim 5, wherein the step of extracting the abnormal image information from the preset image library based on the current image information comprises:
performing local feature recognition on the current image information through a wavelet recognition algorithm to obtain local feature information;
sharpening the local feature information to obtain local feature sharpening information;
and extracting abnormal image information from a preset image library according to the local feature sharpening information.
7. The method according to any one of claims 1 to 6, wherein after the step of generating alarm information and sending the alarm information to a mobile terminal when the abnormality determination result is that there is an abnormality, the method further comprises:
updating the preset audio library according to the current audio information to obtain an updated preset audio library;
and updating the preset image library according to the current image information to obtain the updated preset image library.
8. A vehicle safety warning device, comprising: memory, processor and vehicle safety warning program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the vehicle safety warning method according to one of claims 1 to 7.
9. A storage medium, characterized in that the storage medium has stored thereon a vehicle safety warning program which, when executed by a processor, implements the steps of the vehicle safety warning method according to any one of claims 1 to 7.
10. A warning device for vehicle safety, the device comprising: the device comprises an audio information acquisition module, an image information acquisition module and an alarm information generation module;
the audio information acquisition module is used for acquiring current audio information generated by the vehicle and determining the current vehicle state according to the current audio information;
the image information acquisition module is used for acquiring current image information of the vehicle when the current vehicle state is an abnormal state, and confirming the abnormal state according to the current image information to obtain an abnormal confirmation result;
and the alarm information generation module is used for generating alarm information and sending the alarm information to the mobile terminal when the abnormity judgment result is abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425742.0A CN112396803A (en) | 2020-12-07 | 2020-12-07 | Vehicle safety alarm method, device, storage medium and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425742.0A CN112396803A (en) | 2020-12-07 | 2020-12-07 | Vehicle safety alarm method, device, storage medium and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112396803A true CN112396803A (en) | 2021-02-23 |
Family
ID=74605814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011425742.0A Pending CN112396803A (en) | 2020-12-07 | 2020-12-07 | Vehicle safety alarm method, device, storage medium and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112396803A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070135978A1 (en) * | 2005-12-08 | 2007-06-14 | Kim Jae M | Vehicle status monitoring apparatus and method |
| CN105459954A (en) * | 2015-12-16 | 2016-04-06 | 方正宽带网络服务有限公司 | Automobile alarming method and device |
| CN109300471A (en) * | 2018-10-23 | 2019-02-01 | 中冶东方工程技术有限公司 | Merge place intelligent video monitoring method, the apparatus and system of sound collection identification |
| CN109514583A (en) * | 2018-12-21 | 2019-03-26 | 深圳科卫机器人服务有限公司 | Abnormal alarm method, night watching robot and storage medium |
| CN110443975A (en) * | 2019-07-31 | 2019-11-12 | 深圳奥尼电子股份有限公司 | Smart security guard and alarm method and system |
| CN111179527A (en) * | 2019-12-26 | 2020-05-19 | 数海信息技术有限公司 | Alarm method, device and system based on dynamic audio information and storage medium |
| CN111200720A (en) * | 2018-11-19 | 2020-05-26 | 上海擎感智能科技有限公司 | Internet of vehicles platform, vehicle remote video monitoring method and system |
-
2020
- 2020-12-07 CN CN202011425742.0A patent/CN112396803A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070135978A1 (en) * | 2005-12-08 | 2007-06-14 | Kim Jae M | Vehicle status monitoring apparatus and method |
| CN105459954A (en) * | 2015-12-16 | 2016-04-06 | 方正宽带网络服务有限公司 | Automobile alarming method and device |
| CN109300471A (en) * | 2018-10-23 | 2019-02-01 | 中冶东方工程技术有限公司 | Merge place intelligent video monitoring method, the apparatus and system of sound collection identification |
| CN111200720A (en) * | 2018-11-19 | 2020-05-26 | 上海擎感智能科技有限公司 | Internet of vehicles platform, vehicle remote video monitoring method and system |
| CN109514583A (en) * | 2018-12-21 | 2019-03-26 | 深圳科卫机器人服务有限公司 | Abnormal alarm method, night watching robot and storage medium |
| CN110443975A (en) * | 2019-07-31 | 2019-11-12 | 深圳奥尼电子股份有限公司 | Smart security guard and alarm method and system |
| CN111179527A (en) * | 2019-12-26 | 2020-05-19 | 数海信息技术有限公司 | Alarm method, device and system based on dynamic audio information and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108860162B (en) | Electronic device, safety early warning method based on user driving behavior and storage medium | |
| US20150006023A1 (en) | System and method for determination of vheicle accident information | |
| CN107884064B (en) | Method and device for detecting vehicle impact based on acoustic sensor and acceleration sensor | |
| CN112744174B (en) | Vehicle collision monitoring method, device, equipment and computer readable storage medium | |
| CN112532941A (en) | Vehicle source intensity monitoring method and device, electronic equipment and storage medium | |
| AU2020286290A1 (en) | Systems and methods for identifying vehicles using wireless device identifiers | |
| CN114373189A (en) | Behavior detection method and apparatus, terminal device and storage medium | |
| CN112507939A (en) | Key vehicle detection method, system, equipment and storage medium | |
| CN110211316B (en) | Monitoring early warning method and system | |
| CN113408364B (en) | Temporary license plate recognition method, system, device and storage medium | |
| Josephinshermila et al. | Accident detection using automotive smart black-box based monitoring system | |
| CN112396803A (en) | Vehicle safety alarm method, device, storage medium and device | |
| CN112380977A (en) | Smoking behavior detection method and device | |
| CN109147338B (en) | Illegal parking identification method and device and server | |
| CN115880632A (en) | Timeout stay detection method, monitoring device, computer-readable storage medium, and chip | |
| CN110765837A (en) | Method and device for identifying vehicle whistling against regulations and terminal equipment | |
| CN113183977A (en) | Vehicle brake control method and device and electronic equipment | |
| Nilsson et al. | Combining physical and digital evidence in vehicle environments | |
| CN111738185B (en) | Target identification method, device and equipment | |
| US11580751B2 (en) | Imaging device, video retrieving method, video retrieving program, and information collecting device | |
| CN115730117A (en) | Information inquiry method, device, storage medium and program product | |
| CN112837326B (en) | Method, device and equipment for detecting carryover | |
| CN115620248B (en) | Camera calling method and system based on traffic monitoring | |
| CN113570872B (en) | Processing method and device for blocking parking space event | |
| CN112731365A (en) | Vehicle environment detection system and method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210223 |