CN111994074A - Vehicle collision early warning method and device - Google Patents
Vehicle collision early warning method and device Download PDFInfo
- Publication number
- CN111994074A CN111994074A CN202010898307.3A CN202010898307A CN111994074A CN 111994074 A CN111994074 A CN 111994074A CN 202010898307 A CN202010898307 A CN 202010898307A CN 111994074 A CN111994074 A CN 111994074A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- current
- collision
- driving
- obstacle
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012015 optical character recognition Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000035484 reaction time Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
A vehicle collision early warning method and a device thereof are provided, the method comprises the following steps: acquiring identity information of a driver, and acquiring the driving mileage of the driver driving the vehicle according to the identity information; inquiring the current driving experience grade of the driver according to the driving mileage, and inquiring the corresponding current safe vehicle distance and current safe collision time according to the current driving experience grade; acquiring and identifying video frame images in front of a vehicle in real time to determine the relative distance between the vehicle and a nearest obstacle vehicle in front of the vehicle, and judging whether the relative distance exceeds the current safe vehicle distance; if so, calculating the relative speed of the obstacle vehicle and the vehicle according to the image change of the characteristic area of the obstacle vehicle in the video frame image, and calculating the collision time according to the relative distance and the relative speed; and when the collision time is less than the current safe collision time, sending a collision early warning prompt.
Description
Technical Field
The invention relates to the field of automobiles, in particular to a vehicle collision early warning method and device.
Background
With the rapid development of the automobile industry, the types of vehicles are diversified, and each type of vehicle has different performances, even if the same type of vehicle has different performances. People are generally required to have a certain break-in period for new vehicles or vehicles unfamiliar with themselves, during which time careful driving is required to become familiar with their performance.
With the increasing proportion of all the people in the automobile and the development of the road transportation industry, the frequency of the traffic accidents is increasing, and according to the data published by the traffic department, the rear-end collision of the automobile caused by the inattention of the driver or the lack of the driving experience is one of the main reasons of the traffic accidents.
The existing vehicle collision early warning mode is single, and an early warning prompt is generally sent out by judging whether the distance between vehicles in front exceeds the safe distance. The mode does not consider the driving experience of the user and the familiarity degree of the vehicle, the degree of the contact with the condition of the user is not high, and the user experience is poor.
Disclosure of Invention
In view of the above, it is necessary to provide a vehicle collision warning method and apparatus for solving the problems in the prior art.
A vehicle collision warning method, comprising:
acquiring identity information of a driver, and acquiring the driving mileage of the driver driving the vehicle according to the identity information;
inquiring the current driving experience grade of the driver according to the driving mileage, and inquiring the corresponding current safe vehicle distance and current safe collision time according to the current driving experience grade;
acquiring and identifying video frame images in front of a vehicle in real time to determine the relative distance between the vehicle and a nearest obstacle vehicle in front of the vehicle, and judging whether the relative distance exceeds the current safe vehicle distance;
if so, calculating the relative speed of the obstacle vehicle and the vehicle according to the image change of the characteristic area of the obstacle vehicle in the video frame image, and calculating the collision time according to the relative distance and the relative speed;
and when the collision time is less than the current safe collision time, sending a collision early warning prompt.
Further, the vehicle collision warning method further includes, before the step of sending the collision warning prompt:
identifying whether preset mark information exists on the obstacle vehicle in the video frame image, wherein the mark information is used for identifying the obstacle vehicle as a vehicle needing special protection;
the step of sending out the collision early warning prompt comprises the following steps:
when the marking information exists on the obstacle vehicle, sending a first-level collision early warning prompt;
and when the obstacle vehicle does not have the marking information, sending a secondary collision early warning prompt.
Further, the vehicle collision warning method may further include the step of identifying whether the obstacle vehicle in the video frame image has preset mark information, including:
extracting the area images of the video frame images to obtain a plurality of area images, and judging the type of each area image;
when the judged current area image is of the pattern type, recognizing the area image by using a trained neural network model, and outputting label information of the area image, wherein the label information comprises two labels of identification mark information and non-mark information;
and when the current area image is of a character type, recognizing the character content in the area image through an OCR technology, and determining whether the character content belongs to the mark information.
Further, in the vehicle collision warning method, the step of querying the current driving experience level of the driver according to the mileage includes:
inquiring a current mileage range to which the driving mileage belongs from a pre-stored first relation table according to the driving mileage, and inquiring a current driving experience grade corresponding to the current mileage range from the first relation table, wherein the first relation table comprises a one-to-one correspondence relationship between a plurality of driving mileage ranges and driving experience grades;
the step of inquiring the corresponding current safe vehicle distance and current safe collision time according to the current driving experience level comprises the following steps:
and inquiring corresponding current safe vehicle distance and current safe collision time from a preset second relation table according to the current driving experience grade, wherein the second relation table comprises the one-to-one correspondence of the driving experience grade, the safe vehicle distance and the collision time.
Further, in the vehicle collision warning method, the step of calculating the relative speed of the obstacle vehicle and the host vehicle according to the image change of the feature area of the obstacle vehicle in the video frame image includes:
and calculating the relative speed of the obstacle vehicle relative to the vehicle according to the size or position change of the characteristic area of the current moment relative to the previous moment in the video frame image.
Further, the vehicle collision early warning method further comprises the following steps:
and recording the current driving mileage, and correspondingly increasing the driving mileage of the driver.
The embodiment of the invention also provides a vehicle collision early warning device, which comprises:
the acquisition module is used for acquiring the identity information of a driver and acquiring the driving mileage of the driver driving the vehicle according to the identity information;
the query module is used for querying the current driving experience level of the driver according to the driving mileage and querying the corresponding current safe vehicle distance and current safe collision time according to the current driving experience level;
the first identification module is used for acquiring and identifying video frame images in front of the vehicle in real time so as to determine the relative distance between the vehicle and a nearest obstacle vehicle in front of the vehicle;
the judging module is used for judging whether the relative distance exceeds the current safe vehicle distance;
the computing module is used for computing the relative speed of the obstacle vehicle and the vehicle according to the image change of the characteristic area of the obstacle vehicle in the video frame image when the relative distance exceeds the current safe vehicle distance, and computing the collision time according to the relative distance and the relative speed;
and the early warning module is used for sending out a collision early warning prompt when the collision time is less than the current safe collision time.
Further, the vehicle collision warning device further comprises:
the second identification module is used for identifying whether preset mark information exists on the obstacle vehicle in the video frame image, and the mark information is used for identifying the obstacle vehicle as a vehicle needing special protection;
the early warning module is specifically configured to:
when the marking information exists on the obstacle vehicle, sending a first-level collision early warning prompt;
and when the obstacle vehicle does not have the marking information, sending a secondary collision early warning prompt.
Further, the vehicle collision warning device, wherein the second identification module includes:
the image extraction module is used for extracting the area images of the video frame images to obtain a plurality of area images and judging the type of each area image;
the first identification submodule is used for identifying the area image by using a trained neural network model and outputting label information of the area image when the judged current area image is of the pattern type, wherein the label information comprises two labels of identification label information and non-label information;
and the second identification submodule identifies the text content in the area image through an OCR technology when the current area image is of a text type, and determines whether the text content belongs to the mark information.
Further, the vehicle collision warning device, wherein the query module includes:
the first query submodule is used for querying a current mileage range to which the driving mileage belongs from a pre-stored first relation table according to the driving mileage and querying a current driving experience grade corresponding to the current mileage range from the first relation table, and the first relation table comprises a one-to-one correspondence relationship between a plurality of driving mileage ranges and driving experience grades;
and the second query submodule is used for querying the corresponding current safe vehicle distance and the current safe collision time from a preset second relation table according to the current driving experience grade, and the second relation table comprises the one-to-one corresponding relation among the driving experience grade, the safe vehicle distance and the collision time.
In the embodiment of the invention, the early warning prompt is carried out according to the driving experience of the driver and the familiarity degree of the vehicle, the safe vehicle distance and the safe collision time corresponding to different driving experience levels are different, and the alarm is carried out when the corresponding safe vehicle distance and the safe collision time are exceeded, so that reasonable reaction time is reserved for the driver, and the user experience is improved.
Drawings
Fig. 1 is a flowchart of a vehicle collision warning method according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a vehicle collision warning method according to a second embodiment of the present invention;
fig. 3 is a block diagram showing a vehicle collision warning apparatus according to a second embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
These and other aspects of embodiments of the invention will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the invention have been disclosed in detail as being indicative of some of the ways in which the principles of the embodiments of the invention may be practiced, but it is understood that the scope of the embodiments of the invention is not limited correspondingly. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Referring to fig. 1, a vehicle collision warning method according to a first embodiment of the present invention includes steps S11-S15.
And step S11, acquiring driver identity information, and acquiring the driving mileage of the driver driving the vehicle according to the identity information.
The driver identity information can be identified and acquired through a biological characteristic identification mode, such as identity identification through a human face identification device, a fingerprint identification device or an iris identification device which are installed in a vehicle. The identity information of at least one driver and the corresponding driving mileage are stored in the vehicle, and the driving mileage is the mileage of the vehicle. The identity information of each driver is pre-recorded into the vehicle, and when a user uses the vehicle, the driving mileage of the vehicle is recorded in real time and the identity information of the driver is correspondingly stored.
When the biological characteristic recognition device in the vehicle collects the biological characteristics of the driver driving currently, the biological characteristics are compared with the driver identity information stored in the system to determine the identity of the driver driving currently. In specific implementation, the vehicle system can pre-establish the corresponding relationship between the identity information of each driver and the driving distance of each driver. After the identity information of the driver on the vehicle is acquired, the driving mileage corresponding to the identity information is inquired.
And step S12, inquiring the current driving experience level of the driver according to the driving mileage, and inquiring the corresponding current safe vehicle distance and current safe collision time according to the current driving experience level.
The driving mileage is related to the driving experience level, and the larger the number of the driving mileage, the more the driving experience is. Based on this, a correspondence relationship between the travel mileage and the driving experience level is established in the present embodiment. The correspondence may be stored in the vehicle system in the form of a first relationship table in which correspondences between a plurality of driving range ranges and driving experience levels are stored. The driving experience levels can be set to be multiple according to actual needs, and in this embodiment, three driving experience levels can be set, wherein the driving mileage range corresponding to the driving experience level one is zero to five kilometers, the driving mileage range corresponding to the driving experience level two is five kilometers to ten thousand kilometers, and the driving mileage range corresponding to the driving experience level three is greater than ten thousand kilometers.
Each driving experience level is provided with a corresponding safe vehicle distance and collision time. In the embodiment, the safe vehicle distance corresponding to each driving experience level is different, and the collision time is also different. The higher the driving experience level is, the more mature the driving technology of the driver is and the more familiar the performance of the vehicle, and the corresponding safe vehicle distance and the collision time can be set to be smaller. And the safe vehicle distance and the collision time corresponding to the driver with low driving experience level are set to be larger, so that the driver reserves enough reaction time to avoid the front obstacle vehicle.
The safe vehicle distance and the collision time can also be obtained by a table look-up. The vehicle system stores a second relation table, and the second relation table stores the corresponding relation between each driving experience level and the safe vehicle distance and the collision time. For example, in this embodiment, the safe vehicle distance corresponding to the driving experience level one is 100m, the corresponding safe collision time is 2.5s, the safe vehicle distance corresponding to the driving experience level two is 70m, the corresponding safe collision time is 2s, the safe vehicle distance corresponding to the driving experience level three is 50m, and the corresponding safe collision time is 1.5 s.
In particular, the first relation table and the second relation table in the vehicle system may be set in the same table, or may be set in different tables.
It is understood that in other embodiments of the present invention, the safe inter-vehicle distance corresponding to each driving experience level may be set to be the same, and the corresponding safe collision time may be set to be different.
Step S13, collecting video frame images in front of the vehicle in real time and identifying the video frame images to determine the relative distance between the vehicle and the nearest obstacle vehicle in front of the vehicle, and judging whether the relative distance exceeds the current safe vehicle distance, if so, executing step S14.
Step S14, calculating the relative speed of the obstacle vehicle and the vehicle according to the image change of the characteristic area of the obstacle vehicle in the video frame image, and calculating the collision time according to the relative distance and the relative speed.
The video frame images in front of the vehicle can be collected by a camera mounted on the vehicle, and the camera is mounted above a front windshield of the vehicle. The vehicle acquires video images in front of the vehicle collected by the camera in real time, and identifies each video frame image to monitor whether an obstacle vehicle exceeding the current safe vehicle distance exists in front of the vehicle.
The distance between the vehicle and the front vehicle can be determined by recognizing the video frame image. In particular, the front vehicle may be determined by extracting vehicle profile information and identifying the extracted profile information. And determining the position of the center position point of the front obstacle vehicle in the video frame image and the distance between the center position point and a preset position point in the video frame image to determine the relative distance between the obstacle vehicle and the vehicle. The preset position point is a preset position point in the video image, the distance between the vehicle center position point and the preset position point is calculated, and the vehicle distance in the real scene can be calculated through proportion conversion.
And when the relative distance is judged to be larger than the safe distance, calculating the speed of the obstacle vehicle relative to the vehicle. The relative speed can be calculated according to the image change of the characteristic area of the obstacle vehicle in the video frame image. The characteristic region of the obstacle vehicle is, for example, a license plate of a vehicle rear, a rear bumper, or the like. The feature region can be identified by a detection algorithm in the prior art, such as an edge detection algorithm, a region extraction method, or a contour identification algorithm.
In this embodiment, the relative speed of the obstacle vehicle with respect to the host vehicle may be calculated based on a change in size or position of the feature area in the video frame image at the current time with respect to the previous time. When the speed of the vehicle at the front obstacle is greater than zero relative to the speed of the vehicle at the host vehicle, the distance between the host vehicle and the obstacle is smaller and smaller, that is, the size of the characteristic area is greater than the size at the previous moment, the position of the characteristic area is higher than the height at the previous moment, or the size of the characteristic area is greater than the size at the previous moment in the video frame image.
The distance between the obstacle vehicle and the vehicle can be calculated according to the variation of the size or the position of the characteristic area. In specific implementation, the corresponding relationship between the variation in the video image and the actual driving distance may be counted in advance. The calculation formula of the relative vehicle speed V is V ═ ds/dt, and the relative vehicle speed can be calculated according to the actual travel distance and the travel time.
The collision time is abbreviated as TTC, TTC is defined as the time required by two vehicles to keep the current vehicle speed to run until collision occurs, and is used as a basis for judging dangerous collision, and the calculation formula is as follows:
where Drel is the relative distance between the vehicle and the obstacle vehicle, vrelIs the relative speed between the vehicle and the obstacle vehicle. The collision time can be calculated according to the relative distance and the calculated relative vehicle speed.
And step S15, when the collision time is less than the current safe collision time, sending out a collision early warning prompt.
And when the calculated collision time is less than the current safe collision time, performing collision early warning prompt. The collision early warning prompt can be realized through a buzzer, a warning lamp or prompt information displayed on a control panel so as to remind a driver of paying attention.
In this embodiment, the vehicle is recorded with the identity information of at least one driver and the driving range of the vehicle corresponding to each driver. And determining the driving experience grade of the driver according to the driving mileage of the driver in the vehicle, and inquiring the corresponding current safe vehicle distance and current safe collision time according to the driving experience grade. The method comprises the steps of acquiring video frame images in front of a vehicle, identifying the images to determine whether a front obstacle vehicle is in a current safe vehicle distance, if so, calculating collision time according to the relative distance and the relative speed between the vehicle and the obstacle vehicle, and sending a collision early warning prompt when the collision time is smaller than the current safe collision time. In the embodiment, the early warning prompt is carried out according to the driving experience of the driver and the familiarity degree of the vehicle, the safe vehicle distance and the safe collision time corresponding to different driving experience levels are different, and when the safe vehicle distance and the safe collision time exceed the corresponding safe vehicle distance and the safe collision time, the alarm is carried out, so that reasonable reaction time is reserved for the driver.
Referring to fig. 2, a vehicle collision warning method according to a second embodiment of the present invention includes steps S21-S27.
And step S21, acquiring driver identity information, and acquiring the driving mileage of the driver driving the vehicle according to the identity information.
And step S22, inquiring the current driving experience level of the driver according to the driving mileage, and inquiring the corresponding current safe vehicle distance and current safe collision time according to the current driving experience level.
Step S23, collecting video frame images in front of the vehicle in real time and identifying the video frame images to determine the relative distance between the vehicle and the nearest obstacle vehicle in front of the vehicle, and judging whether the relative distance exceeds the current safe vehicle distance, if so, executing step S24.
And step S24, calculating the relative speed of the obstacle vehicle and the vehicle according to the image change of the characteristic area of the obstacle vehicle in the video frame image, and calculating the collision time according to the relative distance and the relative speed.
And step S25, when the collision time is less than the current safe collision time, identifying whether preset mark information exists on the obstacle vehicle in the video frame image, wherein the mark information is used for identifying the obstacle vehicle as a vehicle needing special protection.
For a driver with poor driving technique or driving experience, it is common to post a prompt message at the rear of the vehicle to prompt the following vehicle to maintain the vehicle distance. The prompt information can be embodied in a text form, for example, the tail of the vehicle is pasted with prompt information such as 'practice', 'beginner on the road' or 'children in the vehicle'. The prompt message can also be embodied in the form of a picture, such as a picture with a baby to indicate that children are in the car.
The step of identifying whether the obstacle vehicle in the video frame image has preset mark information includes:
extracting the area images of the video frame images to obtain a plurality of area images, and judging the type of each area image;
when the current area image is of a pattern type, recognizing the area image by using a trained neural network model, and outputting label information of the area image, wherein the label information comprises two labels of identification mark information and non-mark information;
and when the current area image is of a character type, recognizing the character content in the area image through an OCR technology, and determining whether the character content belongs to the mark information.
In this embodiment, the video frame image is extracted by an image recognition technology to be recognized, so as to extract each region image in the video frame image. And judging the type of each area image, such as pattern type or character type.
And aiming at the area image of the pattern type, the outline of each object in the video frame image can be identified through an outline identification algorithm to obtain a corresponding area image. And classifying the area image by adopting a trained neural network model so as to output label information of the area image. The neural network model is trained using labeled data sets that employ contour information. And training the neural network through the data set, so that the neural network can fully identify the type of the input contour information and output a corresponding label.
And sequentially inputting the area images extracted from the video frame images into a trained neural network model, classifying the area images, and outputting whether the area images are the labels of the marking information. If the label of the current area image output by the neural network is 'marking information', the video frame image is determined to contain the preset marking information.
The region image for the text type can be used for recognizing the text content by an OCR (Optical Character Recognition) Recognition technology. And after the character content in the area image is identified, extracting keywords, and determining the content of the character content belonging to the mark information according to the extracted keywords. For example, the extracted keyword is "novice" or "practice", etc., it can be determined that the video frame image contains the mark information.
And step S26, when the obstacle vehicle has preset mark information, sending a first-level collision early warning prompt.
And step S27, when no preset mark information exists on the obstacle vehicle, sending out a secondary collision early warning prompt.
The first-level collision early warning prompt and the second-level collision early warning prompt remind a driver in different warning modes. The primary collision warning message is, for example, a message to display a warning message on the dashboard of the vehicle, a sound alarm device in the vehicle is controlled to sound, and a vibration device on the steering wheel or the seat is controlled to vibrate. The secondary collision warning prompt is, for example, a prompt message displayed on an instrument panel of the host vehicle.
Further, the method includes step S28.
And step S28, recording the current driving mileage and correspondingly increasing the driving mileage of the driver.
The vehicle system stores the driving mileage corresponding to the driver, and when the driver drives the vehicle, the system updates the driving mileage of the driver in real time.
The present embodiment is different from the first embodiment mainly in that the present embodiment determines the level of the collision warning notice according to whether there is preset sign information on the preceding obstacle vehicle. When the obstacle vehicle is provided with the marking information, a primary collision early warning prompt is sent out, and when the obstacle vehicle is not provided with the marking information, a secondary collision early warning prompt is sent out, so that a driver can distinguish whether the front obstacle vehicle needs to be carefully treated or not.
Referring to fig. 3, a vehicle collision warning device according to a third embodiment of the present invention includes:
the acquiring module 10 is configured to acquire driver identity information and acquire a driving mileage of the driver driving the vehicle according to the identity information;
the query module 20 is configured to query the current driving experience level of the driver according to the driving mileage, and query a corresponding current safe vehicle distance and current safe collision time according to the current driving experience level;
the first identification module 30 is used for acquiring and identifying video frame images in front of the vehicle in real time so as to determine the relative distance between the vehicle and a nearest obstacle vehicle in front of the vehicle;
the judging module 40 is used for judging whether the relative distance exceeds the current safe vehicle distance;
a calculating module 50, configured to calculate a relative vehicle speed between the obstacle vehicle and the host vehicle according to an image change of a feature area of the obstacle vehicle in the video frame image when the relative distance exceeds the current safe vehicle distance, and calculate a collision time according to the relative distance and the relative vehicle speed;
and the early warning module 60 is configured to send a collision early warning prompt when the collision time is less than the current safe collision time.
Further, the vehicle collision warning device further comprises:
a second identification module 70, configured to identify whether there is preset mark information on the obstacle vehicle in the video frame image, where the mark information is used to identify the obstacle vehicle as a vehicle that needs special protection;
the early warning module 60 is specifically configured to:
when the marking information exists on the obstacle vehicle, sending a first-level collision early warning prompt;
and when the obstacle vehicle does not have the marking information, sending a secondary collision early warning prompt.
Further, the vehicle collision warning apparatus described above, wherein the second identification module 70 includes:
the image extraction module is used for extracting the area images of the video frame images to obtain a plurality of area images and judging the type of each area image;
the first identification submodule is used for identifying the area image by using a trained neural network model and outputting label information of the area image when the judged current area image is of the pattern type, wherein the label information comprises two labels of identification label information and non-label information;
and the second identification submodule identifies the text content in the area image through an OCR technology when the current area image is of a text type, and determines whether the text content belongs to the mark information.
Further, the vehicle collision warning apparatus described above, wherein the query module 20 includes:
the first query submodule is used for querying a current mileage range to which the driving mileage belongs from a pre-stored first relation table according to the driving mileage and querying a current driving experience grade corresponding to the current mileage range from the first relation table, and the first relation table comprises a one-to-one correspondence relationship between a plurality of driving mileage ranges and driving experience grades;
and the second query submodule is used for querying the corresponding current safe vehicle distance and the current safe collision time from a preset second relation table according to the current driving experience grade, and the second relation table comprises the one-to-one corresponding relation among the driving experience grade, the safe vehicle distance and the collision time.
The implementation principle and the generated technical effects of the vehicle collision early warning device provided by the embodiment of the invention are the same as those of the method embodiment, and for brief description, corresponding contents in the method embodiment can be referred to where the device embodiment is not mentioned.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A vehicle collision warning method is characterized by comprising the following steps:
acquiring identity information of a driver, and acquiring the driving mileage of the driver driving the vehicle according to the identity information;
inquiring the current driving experience grade of the driver according to the driving mileage, and inquiring the corresponding current safe vehicle distance and current safe collision time according to the current driving experience grade;
acquiring and identifying video frame images in front of a vehicle in real time to determine the relative distance between the vehicle and a nearest obstacle vehicle in front of the vehicle, and judging whether the relative distance exceeds the current safe vehicle distance;
if so, calculating the relative speed of the obstacle vehicle and the vehicle according to the image change of the characteristic area of the obstacle vehicle in the video frame image, and calculating the collision time according to the relative distance and the relative speed;
and when the collision time is less than the current safe collision time, sending a collision early warning prompt.
2. The vehicle collision warning method according to claim 1, wherein the step of issuing a collision warning notice further comprises, before the step of:
identifying whether preset mark information exists on the obstacle vehicle in the video frame image, wherein the mark information is used for identifying the obstacle vehicle as a vehicle needing special protection;
the step of sending out the collision early warning prompt comprises the following steps:
when the marking information exists on the obstacle vehicle, sending a first-level collision early warning prompt;
and when the obstacle vehicle does not have the marking information, sending a secondary collision early warning prompt.
3. The vehicle collision warning method as claimed in claim 2, wherein the step of recognizing whether there is preset mark information on the obstacle vehicle in the video frame image comprises:
extracting the area images of the video frame images to obtain a plurality of area images, and judging the type of each area image;
when the judged current area image is of the pattern type, recognizing the area image by using a trained neural network model, and outputting label information of the area image, wherein the label information comprises two labels of identification mark information and non-mark information;
and when the current area image is of a character type, recognizing the character content in the area image through an OCR technology, and determining whether the character content belongs to the mark information.
4. The vehicle collision warning method as claimed in claim 1, wherein the step of inquiring the current driving experience level of the driver according to the mileage includes:
inquiring a current mileage range to which the driving mileage belongs from a pre-stored first relation table according to the driving mileage, and inquiring a current driving experience grade corresponding to the current mileage range from the first relation table, wherein the first relation table comprises a one-to-one correspondence relationship between a plurality of driving mileage ranges and driving experience grades;
the step of inquiring the corresponding current safe vehicle distance and current safe collision time according to the current driving experience level comprises the following steps:
and inquiring corresponding current safe vehicle distance and current safe collision time from a preset second relation table according to the current driving experience grade, wherein the second relation table comprises the one-to-one correspondence of the driving experience grade, the safe vehicle distance and the collision time.
5. The vehicle collision warning method according to claim 1, wherein the step of calculating the relative speed of the obstacle vehicle to the host vehicle from the image change of the feature area of the obstacle vehicle in the video frame image includes:
and calculating the relative speed of the obstacle vehicle relative to the vehicle according to the size or position change of the characteristic area of the current moment relative to the previous moment in the video frame image.
6. The vehicle collision warning method according to claim 1, further comprising:
and recording the current driving mileage, and correspondingly increasing the driving mileage of the driver.
7. A vehicle collision warning apparatus, comprising:
the acquisition module is used for acquiring the identity information of a driver and acquiring the driving mileage of the driver driving the vehicle according to the identity information;
the query module is used for querying the current driving experience level of the driver according to the driving mileage and querying the corresponding current safe vehicle distance and current safe collision time according to the current driving experience level;
the first identification module is used for acquiring and identifying video frame images in front of the vehicle in real time so as to determine the relative distance between the vehicle and a nearest obstacle vehicle in front of the vehicle;
the judging module is used for judging whether the relative distance exceeds the current safe vehicle distance;
the computing module is used for computing the relative speed of the obstacle vehicle and the vehicle according to the image change of the characteristic area of the obstacle vehicle in the video frame image when the relative distance exceeds the current safe vehicle distance, and computing the collision time according to the relative distance and the relative speed;
and the early warning module is used for sending out a collision early warning prompt when the collision time is less than the current safe collision time.
8. The vehicle collision warning apparatus according to claim 7, further comprising:
the second identification module is used for identifying whether preset mark information exists on the obstacle vehicle in the video frame image, and the mark information is used for identifying the obstacle vehicle as a vehicle needing special protection;
the early warning module is specifically configured to:
when the marking information exists on the obstacle vehicle, sending a first-level collision early warning prompt;
and when the obstacle vehicle does not have the marking information, sending a secondary collision early warning prompt.
9. The vehicle collision warning apparatus according to claim 8, wherein the second recognition module includes:
the image extraction module is used for extracting the area images of the video frame images to obtain a plurality of area images and judging the type of each area image;
the first identification submodule is used for identifying the area image by using a trained neural network model and outputting label information of the area image when the judged current area image is of the pattern type, wherein the label information comprises two labels of identification label information and non-label information;
and the second identification submodule identifies the text content in the area image through an OCR technology when the current area image is of a text type, and determines whether the text content belongs to the mark information.
10. The vehicle collision warning apparatus according to claim 7, wherein the query module includes:
the first query submodule is used for querying a current mileage range to which the driving mileage belongs from a pre-stored first relation table according to the driving mileage and querying a current driving experience grade corresponding to the current mileage range from the first relation table, and the first relation table comprises a one-to-one correspondence relationship between a plurality of driving mileage ranges and driving experience grades;
and the second query submodule is used for querying the corresponding current safe vehicle distance and the current safe collision time from a preset second relation table according to the current driving experience grade, and the second relation table comprises the one-to-one corresponding relation among the driving experience grade, the safe vehicle distance and the collision time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010898307.3A CN111994074B (en) | 2020-08-31 | 2020-08-31 | Vehicle collision early warning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010898307.3A CN111994074B (en) | 2020-08-31 | 2020-08-31 | Vehicle collision early warning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111994074A true CN111994074A (en) | 2020-11-27 |
CN111994074B CN111994074B (en) | 2021-11-02 |
Family
ID=73464912
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010898307.3A Active CN111994074B (en) | 2020-08-31 | 2020-08-31 | Vehicle collision early warning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111994074B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113658451A (en) * | 2021-07-30 | 2021-11-16 | 三一专用汽车有限责任公司 | Control method and device for vehicle collision early warning, vehicle and readable storage medium |
CN114742456A (en) * | 2022-05-06 | 2022-07-12 | 中铁广州工程局集团第三工程有限公司 | BIM-based narrow space hoisting construction method, system, equipment and storage medium |
CN115171429A (en) * | 2022-06-29 | 2022-10-11 | 合众新能源汽车有限公司 | Test system and method for verifying forward collision warning |
CN115217373A (en) * | 2022-03-31 | 2022-10-21 | 广州汽车集团股份有限公司 | Pre-collision door lock control method and device, vehicle and storage medium |
CN115240393A (en) * | 2021-07-15 | 2022-10-25 | 广州汽车集团股份有限公司 | Collision early warning method and device based on driver driving experience and automobile |
CN115830906A (en) * | 2022-08-25 | 2023-03-21 | 广州汽车集团股份有限公司 | Safety early warning method and device, vehicle and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130261915A1 (en) * | 2012-03-30 | 2013-10-03 | Denso Corporation | Vehicle control device |
CN105501220A (en) * | 2015-11-24 | 2016-04-20 | 东软集团股份有限公司 | Vehicle collision warning method and device and vehicle |
CN106240458A (en) * | 2016-07-22 | 2016-12-21 | 浙江零跑科技有限公司 | A kind of vehicular frontal impact method for early warning based on vehicle-mounted binocular camera |
CN106240566A (en) * | 2016-07-28 | 2016-12-21 | 深圳市安煋信息技术有限公司 | Automotive safety method for early warning, system and automobile |
CN106314428A (en) * | 2016-09-14 | 2017-01-11 | 中国科学院微电子研究所 | Collision avoidance system, collision avoidance method and motor vehicle |
CN107571869A (en) * | 2016-07-04 | 2018-01-12 | 奥迪股份公司 | Driving assistance method and system |
-
2020
- 2020-08-31 CN CN202010898307.3A patent/CN111994074B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130261915A1 (en) * | 2012-03-30 | 2013-10-03 | Denso Corporation | Vehicle control device |
CN105501220A (en) * | 2015-11-24 | 2016-04-20 | 东软集团股份有限公司 | Vehicle collision warning method and device and vehicle |
CN107571869A (en) * | 2016-07-04 | 2018-01-12 | 奥迪股份公司 | Driving assistance method and system |
CN106240458A (en) * | 2016-07-22 | 2016-12-21 | 浙江零跑科技有限公司 | A kind of vehicular frontal impact method for early warning based on vehicle-mounted binocular camera |
CN106240566A (en) * | 2016-07-28 | 2016-12-21 | 深圳市安煋信息技术有限公司 | Automotive safety method for early warning, system and automobile |
CN106314428A (en) * | 2016-09-14 | 2017-01-11 | 中国科学院微电子研究所 | Collision avoidance system, collision avoidance method and motor vehicle |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115240393A (en) * | 2021-07-15 | 2022-10-25 | 广州汽车集团股份有限公司 | Collision early warning method and device based on driver driving experience and automobile |
CN113658451A (en) * | 2021-07-30 | 2021-11-16 | 三一专用汽车有限责任公司 | Control method and device for vehicle collision early warning, vehicle and readable storage medium |
CN113658451B (en) * | 2021-07-30 | 2022-11-22 | 三一专用汽车有限责任公司 | Vehicle collision early warning control method and device, vehicle and readable storage medium |
CN115217373A (en) * | 2022-03-31 | 2022-10-21 | 广州汽车集团股份有限公司 | Pre-collision door lock control method and device, vehicle and storage medium |
CN115217373B (en) * | 2022-03-31 | 2024-05-14 | 广州汽车集团股份有限公司 | Pre-crash door lock control method and device, vehicle and storage medium |
CN114742456A (en) * | 2022-05-06 | 2022-07-12 | 中铁广州工程局集团第三工程有限公司 | BIM-based narrow space hoisting construction method, system, equipment and storage medium |
CN115171429A (en) * | 2022-06-29 | 2022-10-11 | 合众新能源汽车有限公司 | Test system and method for verifying forward collision warning |
CN115171429B (en) * | 2022-06-29 | 2023-11-21 | 合众新能源汽车股份有限公司 | Testing system and method for verifying forward collision early warning |
CN115830906A (en) * | 2022-08-25 | 2023-03-21 | 广州汽车集团股份有限公司 | Safety early warning method and device, vehicle and storage medium |
CN115830906B (en) * | 2022-08-25 | 2024-04-05 | 广州汽车集团股份有限公司 | Safety early warning method and device, vehicle and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111994074B (en) | 2021-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111994074B (en) | Vehicle collision early warning method and device | |
JP5521893B2 (en) | Driving support system, in-vehicle device | |
US6472977B1 (en) | Method for the displaying information in a motor vehicle | |
CN113487874B (en) | System and method for collecting, identifying and classifying following behavior scene data | |
CN109145719B (en) | Driver fatigue state identification method and system | |
CN112590801B (en) | Front collision early warning control method based on fatigue degree of driver | |
CN110400478A (en) | A kind of road condition notification method and device | |
CN103548069B (en) | For the method and apparatus identifying possible colliding object | |
JP2014081947A (en) | Information distribution device | |
CN101101333A (en) | Apparatus and method for producing assistant information of driving vehicle for driver | |
JP4182131B2 (en) | Arousal level determination device and arousal level determination method | |
JP4622749B2 (en) | Vehicle data collection device, vehicle driving support device, and vehicle safe driving support system | |
CN106600748A (en) | Illegal driving recording method and illegal driving recording apparatus | |
CN112927509B (en) | Road driving safety risk assessment system based on traffic conflict technology | |
CN112606831A (en) | Anti-collision warning information external interaction method and system for passenger car | |
CN111260915B (en) | Early warning reminding method for pedestrian stay in expressway traffic abnormal area | |
JP2012256235A (en) | Information providing device for driving support, on-vehicle driving support device and driving support system | |
CN108230717B (en) | Intelligent traffic management system | |
CN212579832U (en) | Man-machine interaction system for vehicle driving safety and vehicle | |
CN102043941B (en) | Dynamic real-time relative relationship identification method and system | |
CN111591294B (en) | Early warning method for vehicle lane change in different traffic environments | |
CN115230713A (en) | Driving assistance method and device, electronic equipment and storage medium | |
JP2009134525A (en) | Vehicle environmental information notification system and vehicle environmental information notification method | |
JP4901287B2 (en) | Driving support device | |
JP3075765B2 (en) | Image processing type overspeed warning device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |