CN115995163A - Vehicle collision early warning method and system - Google Patents
Vehicle collision early warning method and system Download PDFInfo
- Publication number
- CN115995163A CN115995163A CN202310287953.XA CN202310287953A CN115995163A CN 115995163 A CN115995163 A CN 115995163A CN 202310287953 A CN202310287953 A CN 202310287953A CN 115995163 A CN115995163 A CN 115995163A
- Authority
- CN
- China
- Prior art keywords
- image
- distance
- vehicle
- road
- longitudinal
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a vehicle collision early warning method and a system, wherein the method comprises the following steps: acquiring a first road image and a second road image in front of a target vehicle, and preprocessing the first road image and the second road image to obtain a first road processing image and a second road processing image; identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle; calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle, and judging whether the obstacle vehicle has a lane change intention or not; if the lane change intention exists, calculating a second longitudinal distance, and judging whether the second longitudinal distance is smaller than a preset safety distance or not; if the lane change intention does not exist, judging whether the first longitudinal distance is smaller than the preset safety distance. The method and the device are suitable for vehicle collision early warning under complex environments, further ensure the safety of the target vehicle in the running process, and reduce the risk of vehicle collision.
Description
Technical Field
The invention belongs to the technical field of vehicle early warning, and particularly relates to a vehicle collision early warning method and system.
Background
In the prior art, most of the laser rangefinders are installed at the head positions of the vehicles to calculate the distance between the current vehicle and the vehicles ahead, but the method has certain defects that when the laser rangefinders measure the distance between the two vehicles, the laser rangefinders are easily interfered by foreign objects, and then the distance measurement result is inaccurate, meanwhile, when the prior art carries out collision early warning on the vehicles, the situation that the vehicles change lanes is not generally considered, and then the collision risk in the running process of the vehicles is increased.
Disclosure of Invention
In order to solve the technical problems, the invention provides a vehicle collision early warning method and a vehicle collision early warning system, which are used for solving the technical problems in the prior art.
In a first aspect, the present invention provides the following technical solutions, and a vehicle collision early warning method, where the method includes:
acquiring a first road image and a second road image in front of a target vehicle through a binocular camera on the target vehicle, and preprocessing the first road image and the second road image to obtain a first road processing image and a second road processing image;
sequentially carrying out lane line identification and driving area division on the first road processing image and the second road processing image to obtain a first driving area image and a second driving area image, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image;
according to the first image coordinates and the second image coordinates, calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle, and judging whether the obstacle vehicle has a lane change intention or not based on the first transverse distance;
If the obstacle vehicle has a lane changing intention, calculating a longitudinal lane changing distance difference between the obstacle vehicle and the target vehicle, calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane changing distance difference, judging whether the second longitudinal distance is smaller than a preset safety distance, and if the second longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle;
if the obstacle vehicle does not have the lane changing intention, judging whether the first longitudinal distance is smaller than the preset safety distance, and if the first longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle.
Compared with the prior art, the beneficial effects of this application are: the method comprises the steps of firstly obtaining a first road image and a second road image, and processing the first road image and the second road image so as to facilitate the follow-up identification of various characteristic information in the images; then lane line identification and driving area division are sequentially carried out on the first road processing image and the second road processing image, and first image coordinates and second image coordinates of the obstacle vehicles are identified and extracted, so that the positions of the obstacle vehicles can be accurately positioned in sequence, and the distance between the target vehicle and the obstacle vehicles can be calculated conveniently; then, according to the first image coordinates and the second image coordinates, calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle, and judging whether the obstacle vehicle has a lane change intention or not based on the first transverse distance; if the obstacle vehicle has a lane changing intention, calculating a longitudinal lane changing distance difference between the obstacle vehicle and the target vehicle, calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane changing distance difference, judging whether the second longitudinal distance is smaller than a preset safety distance, and if the second longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle; if the obstacle vehicle does not have a lane change intention, judging whether the first longitudinal distance is smaller than the preset safety distance, if the first longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle, acquiring a road image through a binocular camera, and acquiring position information of the obstacle vehicle in the road image, so that the position between the target vehicle and the obstacle vehicle is calculated more accurately later, the image is not easily interfered by the outside in the process of calculating the position, the accuracy of data is ensured, and meanwhile, judging whether the obstacle vehicle has the lane change intention according to the position between the target vehicle and the obstacle vehicle, and sequentially calculating different vehicle safety intervals.
Preferably, the step of preprocessing the first road image and the second road image to obtain a first road processed image and a second road processed image includes:
and gray conversion, denoising, image enhancement and feature extraction are sequentially carried out on the first road image and the second road image so as to obtain a first road processing image and a second road processing image.
Preferably, the step of sequentially performing lane line recognition and driving area division on the first road processing image and the second road processing image to obtain a first driving area image and a second driving area image, and recognizing and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image includes:
identifying pixel coordinates of each pixel point in the first road processing image and the second road processing image on an image space coordinate plane, and determining an initial expression for calculating a lane line based on the pixel coordinates:
in the method, in the process of the invention,is the polar diameter of the lane line +.>Is the polar angle of the lane line +.>Is the abscissa of the pixel coordinate, +.>Is the ordinate of the pixel coordinates;
In the gradient direction of the lane lineIs determined in a predetermined vicinity of (2)>And->Establishing a discrete parameter space in the search range, and mapping the pixel coordinates into the discrete parameter space to obtain parameter coordinates;
searching local maxima of collinear points on the corresponding image space coordinate plane in the searching range, and determining the searching parameters of the collinear points on the image coordinate plane based on the local maxima;
The search parameters are setSubstituting the parameters into the initial expression of the lane line, and fitting the parameters by a least square method to obtain the final expression of the lane line;
and carrying out driving region division on the first road processing image and the second road processing image based on the final expression of the lane line, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving region image and the second driving region image.
Preferably, the step of dividing the driving area of the first road processing image and the second road processing image based on the final expression of the lane line, and identifying and extracting the first image coordinates and the second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image includes:
Dividing the first road processing image and the second road processing image into a first driving area image, a first non-driving area image, a second driving area image and a second non-driving area image respectively by taking the lane line as a boundary;
calculating a first average gray value of the first driving area image and a second average gray value of the second driving area image;
dividing an image smaller than a first average gray value in the first driving area image and an image smaller than a second average gray value in the second driving area image to obtain an obstacle vehicle image;
and respectively extracting a first image coordinate and a second image coordinate of the obstacle vehicle image in the first road image and the second road image based on the obstacle vehicle image.
Preferably, the step of calculating a first longitudinal distance and a first lateral distance between the target vehicle and the obstacle vehicle according to the first image coordinates and the second image coordinates includes:
according to the first image coordinatesx p1 ,y p1 ) And the second image coordinatesx p2 ,y p2 ) Calculating a first actual longitudinal distanceL 1 :
In the method, in the process of the invention,ffor the focal length of the binocular camera, L m To be the instituteThe distance between the binocular cameras is such that,dxis the physical unit of a pixel in the X-axis direction;
obtaining first intersection point coordinates of lane lines in the first road image and the second road image respectivelyx j1 ,y j1 ) Coordinates of the second intersection pointx j2 ,y j2 ) According to the first intersection point coordinatesx j1 ,y j1 ) The coordinates of the second intersection pointx j2 ,y j2 ) The first image coordinatesx p1 ,y p1 ) And the second image coordinatesx p2 ,y p2 ) Calculating a second actual longitudinal distanceL 2 :
In the method, in the process of the invention,aas a first coefficient of fit,bas a result of the first fitting index,cis a first fitting constant;
based on the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 Determining the first longitudinal distanceL Z1 And according to the first longitudinal distanceL Z1 Calculating a first lateral distanceL H :
In the method, in the process of the invention,is the slip angle between the target vehicle and the obstacle vehicle.
Preferably, the first actual longitudinal distance is based onL 1 Distance from the second actual longitudinal directionL 2 Determining the first longitudinal distanceL Z1 The method comprises the following steps:
according to the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 Judging the first longitudinal distanceL Z1 Whether within the first preset range or the second preset range;
if the first longitudinal distanceL Z1 Within a first preset range, the first longitudinal distance L Z1 For a first actual longitudinal distanceL 1 If the first longitudinal distanceL Z1 Within a second preset range, the first longitudinal distanceL Z1 For a second actual longitudinal distanceL 2 。
Preferably, the step of determining whether the obstacle vehicle has a lane change intention based on the first lateral distance includes:
based on the first lateral distance and according tosigmoidCalculating the lane change probability of the obstacle vehicle by a function:
in the method, in the process of the invention,representing a lane change event, < >>Represents a scale factor->Indicating lane width +.>Is a first lateral distance;
judging whether the lane change probability is larger than a preset probability threshold value or not;
if the lane change probability is larger than a preset probability threshold, the obstacle vehicle has a lane change intention, and if the lane change probability is not larger than the preset probability threshold, the obstacle vehicle has no lane change intention.
Preferably, the step of calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle, and calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane change distance difference includes:
acquiring a lane change speed of the obstacle vehicle, and calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle based on the lane change speed and the first lateral distance L C :
In the method, in the process of the invention,for the lateral resolution speed of the lane change speed, +.>Longitudinal decomposition speed for lane change speed, +.>For a first lateral distance>The vehicle speed of the target vehicle;
based on the longitudinal lane change distance differenceL C Calculating a second longitudinal distance between the target vehicle and the obstacle vehicleL Z2 :
In the method, in the process of the invention,L Z1 is the first longitudinal distance.
Preferably, in the step of determining whether the second longitudinal distance is smaller than a preset safety distance, the safety distance is presetS safe The method comprises the following steps:
wherein S is 1 For the distance travelled by the target vehicle within the driver' S reaction time S 2 For the braking distance of the target vehicle in the braking time S 3 For obstacle vehicles at the driver reaction time and the driverDistance travelled during braking time S 4 Is a safety threshold.
In a second aspect, the present invention provides a vehicle collision warning system, including:
the processing module is used for acquiring a first road image and a second road image in front of a target vehicle through a binocular camera on the target vehicle, and preprocessing the first road image and the second road image to obtain a first road processing image and a second road processing image;
the coordinate calculation module is used for sequentially carrying out lane line identification and driving area division on the first road processing image and the second road processing image so as to obtain a first driving area image and a second driving area image, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image;
The judging module is used for calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle according to the first image coordinates and the second image coordinates, and judging whether the obstacle vehicle has a lane change intention or not based on the first transverse distance;
the first calculation module is used for calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle if the obstacle vehicle has a lane change intention, calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane change distance difference, judging whether the second longitudinal distance is smaller than a preset safety distance, and sending alarm information to the target vehicle if the second longitudinal distance is smaller than the preset safety distance;
and the second calculation module is used for judging whether the first longitudinal distance is smaller than the preset safety distance or not if the obstacle vehicle does not have the lane change intention, and sending alarm information to the target vehicle if the first longitudinal distance is smaller than the preset safety distance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a vehicle collision warning method according to a first embodiment of the present invention;
fig. 2 is a detailed flowchart of step S2 in the vehicle collision warning method according to the first embodiment of the present invention;
fig. 3 is a detailed flowchart of step S25 in the vehicle collision warning method according to the first embodiment of the present invention;
fig. 4 is a detailed flowchart of step S3 in the vehicle collision warning method according to the first embodiment of the present invention;
fig. 5 is a detailed flowchart of step S303 in the vehicle collision warning method according to the first embodiment of the present invention;
fig. 6 is a detailed flowchart second of step S3 in the vehicle collision warning method according to the first embodiment of the present invention;
fig. 7 is a detailed flowchart of step S4 in the vehicle collision warning method according to the first embodiment of the present invention;
FIG. 8 is a block diagram illustrating a vehicle collision warning system according to a second embodiment of the present invention;
fig. 9 is a block diagram of a hardware structure of a computer device according to another embodiment of the present invention.
Embodiments of the present invention will be further described below with reference to the accompanying drawings.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended to illustrate embodiments of the invention and should not be construed as limiting the invention.
Example 1
As shown in fig. 1, in a first embodiment of the present invention, the present invention provides a vehicle collision warning method, which includes:
s1, acquiring a first road image and a second road image in front of a target vehicle through a binocular camera on the target vehicle, and preprocessing the first road image and the second road image to obtain a first road processing image and a second road processing image;
specifically, in this embodiment, the binocular camera is two cameras mounted on the vehicle and on the same horizontal plane, one of the two cameras is disposed at a position near the left side of the vehicle, and the other one of the two cameras is disposed at a position near the right side of the vehicle, so that road images in front of the vehicle can be acquired through the binocular camera.
The method comprises the steps of preprocessing a first road image and a second road image, namely sequentially carrying out gray level conversion, denoising, image enhancement and feature extraction on the first road image and the second road image to obtain a first road processed image and a second road processed image;
in order to facilitate the extraction of various information, such as lane lines, obstacle vehicles, etc., in the first road image and the second road image, the first road image and the second road image are required to be subjected to gray level conversion, and then the gray level image is subjected to denoising treatment, that is, mean filtering or median filtering, smoothing treatment is performed on the gray level image, points which do not conform to surrounding pixels and isolated noise points are removed, then image enhancement treatment is performed on the image, so as to protrude the pixel points therein, and then feature extraction is performed on the image, so that the position and lane lines of the obstacle vehicles can be identified later.
S2, lane line identification and driving area division are sequentially carried out on the first road processing image and the second road processing image so as to obtain a first driving area image and a second driving area image, and first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image are identified and extracted;
Specifically, since the first road processing image and the second road processing image include the surrounding information of the lane at the same time, but the surrounding information is not used in the present embodiment, in order to quickly separate the driving area image, that is, the first driving area image and the second driving area image, it is necessary to divide the remaining information except for the driving road and the obstacle vehicle to accelerate the speed of subsequently identifying the obstacle vehicle, after the first driving area image and the second driving area image are divided, since the obstacle vehicle forms a shadow of the obstacle vehicle on the driving road during driving, a shadow area is formed in the first driving area image and the second driving area image, and the first image coordinates and the second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image can be identified by identifying the shadow area.
As shown in fig. 2, the step S2 includes:
s21, identifying pixel coordinates of each pixel point in the first road processing image and the second road processing image on an image space coordinate plane, and determining an initial expression for calculating a lane line based on the pixel coordinates:
In the method, in the process of the invention,is the polar diameter of the lane line +.>Is the polar angle of the lane line +.>Is the abscissa of the pixel coordinate, +.>Is the ordinate of the pixel coordinates.
S22, in the gradient direction of the lane lineIs determined in a predetermined vicinity of (2)>And->Establishing a discrete parameter space in the search range, and mapping the pixel coordinates into the discrete parameter space to obtain parameter coordinates;
specifically, the search range of the polar diameter of the lane line and the polar angle of the lane line is limited in the gradient direction of the lane lineTherefore, when determining the search parameters, the search parameters are only searched and obtained within the limited search range without searching each pixel point in the first road processing image and the second road processing image, and in step S2, the improved road processing image is adoptedHoughThe transformation algorithm determines the lane lines, compared with the original lane linesHoughThe algorithm can greatly reduce the number of pixels to be converted, so as to improve the conversion efficiency and accelerate the process of extracting the lane lines.
S23, searching local maxima of collinear points on the corresponding image space coordinate plane in the search range, and determining the image coordinate plane based on the local maxima Search parameters for upper collinear point straight line。
S24, the search parameters are processedSubstituting the parameters into the initial expression of the lane line, and fitting the parameters by a least square method to obtain the final expression of the lane line. />
Specifically, the expressions of the lane lines are fitted through the steps S21-S24, the final expression of the lane line at the final fitting position is more accurate, two lane lines at the final fitting position are in a straight line form, and the two lane lines are in an intersecting state in the first road processing image and the second road processing image.
S25, dividing a driving area of the first road processing image and the second road processing image based on the final expression of the lane line, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image;
as shown in fig. 3, the step S25 includes:
s251, dividing the first road processing image and the second road processing image into a first driving area image, a first non-driving area image, a second driving area image and a second non-driving area image by taking the lane line as a boundary;
Specifically, since the binocular camera is disposed on the target vehicle, the regions surrounded by the target vehicle and the two lane lines in the first road processing image and the second road processing image are a first driving region and a second driving region, respectively, and the remaining regions are a first non-driving region image and a second non-driving region image.
S252, calculating a first average gray value of the first driving area image and a second average gray value of the second driving area image;
s253, dividing an image smaller than a first average gray value in the first driving area image and an image smaller than a second average gray value in the second driving area image to obtain an obstacle vehicle image;
since the obstacle vehicle forms a shadow on the driving road, the obstacle vehicle image can be obtained only by identifying the images which are smaller than the first average gray value and smaller than the second average gray value in the first driving area image and the second driving area image.
S254, based on the obstacle vehicle image, respectively extracting a first image coordinate and a second image coordinate of the obstacle vehicle image in the first road image and the second road image;
Specifically, after the obstacle vehicle image is identified, the first image coordinates and the second image coordinates of the obstacle vehicle image in the first road image and the second road image can be identified according to the obstacle vehicle image.
S3, calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle according to the first image coordinates and the second image coordinates, and judging whether the obstacle vehicle has a lane change intention or not based on the first transverse distance;
specifically, in step S3, during the actual driving process, the target vehicle and the obstacle vehicle may be located on the same lane or may be located on different lanes, if the target vehicle and the obstacle vehicle are located on the same lane, only the first longitudinal distance between the obstacle vehicle and the target vehicle is calculated, but if the obstacle vehicle is located on different lanes, whether the obstacle vehicle changes lanes is required to be determined, so that the lane changing intention of the obstacle vehicle is determined by calculating the lane changing probability of the obstacle vehicle, the driving distance of the obstacle vehicle during the lane changing process and the driving distance of the target vehicle during the lane changing process are calculated, and the second longitudinal distance between the obstacle vehicle and the target vehicle is calculated according to the calculation result.
As shown in fig. 4, the step S3 includes:
s301, according to the first image coordinatesx p1 ,y p1 ) And the institute are connected withThe second image coordinatesx p2 ,y p2 ) Calculating a first actual longitudinal distanceL 1 :
In the method, in the process of the invention,ffor the focal length of the binocular camera,L m for the distance between the binocular cameras,dxis the physical unit of a pixel in the X-axis direction;
specifically, in this step, the first actual longitudinal distance can be calculated according to the parallax of the binocular camera by using the principle of similar triangle, and the calculated first actual longitudinal distance is the distance between the camera and the obstacle vehicle, which is equivalent to the distance between the target vehicle and the obstacle vehicle.
S302, acquiring first intersection point coordinates of lane lines in the first road image and the second road image respectivelyx j1 ,y j1 ) Coordinates of the second intersection pointx j2 ,y j2 ) According to the first intersection point coordinatesx j1 ,y j1 ) The coordinates of the second intersection pointx j2 ,y j2 ) The first image coordinatesx p1 ,y p1 ) And the second image coordinatesx p2 ,y p2 ) Calculating a second actual longitudinal distanceL 2 :
In the method, in the process of the invention,aas a first coefficient of fit,bas a result of the first fitting index,cis a first fitting constant;
specifically, in this step, as the distance between the target vehicle and the obstacle vehicle changes, the distance between the lane-line intersection coordinates and the obstacle vehicle also changes, and the greater the distance between the target vehicle and the obstacle vehicle, the smaller the distance between the lane-line intersection coordinates and the obstacle vehicle, so that the second pair of lane-line intersection coordinates can be determined from the experimental data Fitting the calculation formula of the actual longitudinal distance to obtain an exponential function, and transforming the exponential function to obtain a final second actual longitudinal distanceL 2 Is a calculation formula of (2).
S303, based on the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 Determining the first longitudinal distanceL Z1 And according to the first longitudinal distanceL Z1 Calculating a first lateral distanceL H :
In the method, in the process of the invention,a slip angle between the target vehicle and the obstacle vehicle;
specifically, the first lateral distance refers to a lateral distance between the target vehicle and the obstacle vehicle, and whether the obstacle vehicle has a lane change intention can be determined according to the first lateral distance.
As shown in fig. 5, the step S303 includes:
s3031, according to the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 Judging the first longitudinal distanceL Z1 Whether within the first preset range or within the second preset range.
S3032, if the first longitudinal distanceL Z1 Within a first preset range, the first longitudinal distanceL Z1 For a first actual longitudinal distanceL 1 If the first longitudinal distanceL Z1 Within a second preset range, the first longitudinal distanceL Z1 For a second actual longitudinal distanceL 2 ;
Specifically, since the first actual longitudinal distances are calculated in the above steps S301 and S302, respectively L 1 Distance from the second actual longitudinal directionL 2 But a first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 All have oneThe first actual longitudinal distance can be calculated by collecting different test dataL 1 Distance from the second actual longitudinal directionL 2 Comparing the error rate with the true value to obtain respective error rate, and determining the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 The range with the minimum error value is a first preset range and a second preset range, so that the first longitudinal distance can be freely selected according to the actual calculation resultL Z1 For a first actual longitudinal distanceL 1 Or a second actual longitudinal distanceL 2 To ensure that the first longitudinal distance is calculated more accurately and closely to the true value.
As shown in fig. 6, the step S3 further includes:
s311, based on the first transverse distance and according tosigmoidCalculating the lane change probability of the obstacle vehicle by a function:
in the method, in the process of the invention,representing a lane change event, < >>Represents a scale factor->Indicating lane width +.>Is the first lateral distance.
S312, judging whether the lane change probability is larger than a preset probability threshold.
S313, if the lane change probability is larger than a preset probability threshold, the obstacle vehicle has a lane change intention, and if the lane change probability is not larger than the preset probability threshold, the obstacle vehicle does not have the lane change intention;
Specifically, in step S312, as shown by the formula in step S311, the greater the first lateral distance, the greater the lane change probability, and also in the actual running process of the automobile, if the running vehicle is in running, and if the lateral distance between the running vehicle and the side rear vehicle is observed to be far, the lane change is easier for the driver, and if the lateral distance between the running vehicle and the side rear vehicle is near, the lane change is not easy for the driver in view of the safety relationship, so in this embodiment, the lane change probability is calculated by the magnitude of the first lateral distance and compared with the preset probability threshold, and once the lane change probability is greater than the preset probability threshold, the obstacle vehicle has a lane change intention, and if the lane change probability is not greater than the preset probability threshold, the obstacle vehicle has no lane change intention;
it should be noted that, in this step, the larger the first lateral distance is, the target vehicle and the obstacle vehicle are not located on the same lane, and at this time, the lane change probability is high, so that the obstacle vehicle is easy to generate a lane change condition, and therefore, the longitudinal distance between the two needs to be recalculated by calculating the longitudinal distance traveled by the obstacle vehicle in the lane change process and the distance traveled by the target vehicle when the obstacle vehicle changes lanes, that is, the second longitudinal distance, and correspondingly, if the first lateral distance is smaller, the target vehicle and the obstacle vehicle are located on the same lane, and at this time, the lane change probability of the obstacle vehicle is small, but no matter whether the obstacle vehicle can generate a lane change condition, the lane change condition of the target vehicle can be known only by comparing the first longitudinal distance with the preset safety distance.
S4, if the obstacle vehicle has a lane change intention, calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle, calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane change distance difference, judging whether the second longitudinal distance is smaller than a preset safety distance, and if the second longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle;
as shown in fig. 7, the step S4 includes:
s41, acquiring the lane changing speed of the obstacle vehicle, and based on the lane changing speed and the lane changing speedThe first lateral distance calculates a longitudinal lane change distance difference between the obstacle vehicle and the target vehicleL C :
In the method, in the process of the invention,for the lateral resolution speed of the lane change speed, +.>Longitudinal decomposition speed for lane change speed, +.>For a first lateral distance>Is the speed of the target vehicle.
S42, based on the longitudinal lane change distance differenceL C Calculating a second longitudinal distance between the target vehicle and the obstacle vehicleL Z2 :
In the method, in the process of the invention,L Z1 is a first longitudinal distance;
specifically, since the obstacle vehicle has the lane changing intention, the obstacle vehicle needs to be ensured not to collide with the target vehicle which normally runs in the lane changing process of the obstacle vehicle, therefore, by calculating the longitudinal lane changing distance difference between the obstacle vehicle and the target vehicle, the longitudinal lane changing distance difference is the difference between the longitudinal distance of the obstacle vehicle which runs in the lane changing process and the longitudinal distance of the target vehicle which runs in the lane changing process of the obstacle vehicle, the difference can be positive or negative, the difference can be added with the first longitudinal distance, the predicted longitudinal distance between the obstacle vehicle and the target vehicle after the lane changing can be obtained, namely, the second longitudinal distance is compared with the preset safe distance, and the situation that if the second longitudinal distance is smaller than the preset safe distance, the obstacle vehicle which possibly collides with the target vehicle in the lane changing process of the obstacle vehicle is indicated, at the moment, the driver is reminded of controlling the target vehicle to slow down, if the second longitudinal distance is not smaller than the preset safe distance, the predicted obstacle vehicle which does not collide with the target vehicle in the lane changing process of the obstacle vehicle is indicated, and the target vehicle which can still normally run in the normal running process can be obtained.
In the present embodiment, the safety distance is presetS safe The method comprises the following steps:
wherein S is 1 For the distance travelled by the target vehicle within the driver' S reaction time S 2 For the braking distance of the target vehicle in the braking time S 3 For the distance travelled by the obstacle vehicle between the driver reaction time and the braking time, S 4 Is a safety threshold.
S5, if the obstacle vehicle does not have the lane changing intention, judging whether the first longitudinal distance is smaller than the preset safety distance, and if the first longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle;
specifically, if the obstacle vehicle has no lane change intention, and the first transverse distance between the target vehicle and the obstacle vehicle is smaller at the moment, it can be judged that the two vehicles are located on the same lane, so that a comparison result can be obtained only by comparing the first longitudinal distance between the two vehicles with a preset safety distance, if the first longitudinal distance is smaller than the preset safety distance, the obstacle vehicle is likely to collide with the target vehicle in the running process, at the moment, alarm information is sent to the target vehicle to remind a driver to control the target vehicle to decelerate, and if the first longitudinal distance is not smaller than the preset safety distance, the obstacle vehicle is not collided with the target vehicle in the running process, a certain safety distance still exists between the obstacle vehicle and the target vehicle, and the target vehicle can normally run at the moment.
The first advantage of this embodiment is: firstly, a first road image and a second road image are acquired and processed so as to facilitate the subsequent identification of various characteristic information in the images; then lane line identification and driving area division are sequentially carried out on the first road processing image and the second road processing image, and first image coordinates and second image coordinates of the obstacle vehicles are identified and extracted, so that the positions of the obstacle vehicles can be accurately positioned in sequence, and the distance between the target vehicle and the obstacle vehicles can be calculated conveniently; then, according to the first image coordinates and the second image coordinates, calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle, and judging whether the obstacle vehicle has a lane change intention or not based on the first transverse distance; if the obstacle vehicle has a lane changing intention, calculating a longitudinal lane changing distance difference between the obstacle vehicle and the target vehicle, calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane changing distance difference, judging whether the second longitudinal distance is smaller than a preset safety distance, and if the second longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle; if the obstacle vehicle does not have a lane change intention, judging whether the first longitudinal distance is smaller than the preset safety distance, if the first longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle, acquiring a road image through a binocular camera, and acquiring position information of the obstacle vehicle in the road image, so that the position between the target vehicle and the obstacle vehicle is calculated more accurately later, the image is not easily interfered by the outside in the process of calculating the position, the accuracy of data is ensured, and meanwhile, judging whether the obstacle vehicle has the lane change intention according to the position between the target vehicle and the obstacle vehicle, and sequentially calculating different vehicle safety intervals.
Example two
As shown in fig. 8, in a second embodiment of the present invention, there is provided a vehicle collision warning system including:
the processing module 1 is used for acquiring a first road image and a second road image in front of a target vehicle through a binocular camera on the target vehicle, and preprocessing the first road image and the second road image to obtain a first road processing image and a second road processing image;
the coordinate calculation module 2 is used for sequentially carrying out lane line identification and driving area division on the first road processing image and the second road processing image so as to obtain a first driving area image and a second driving area image, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image;
a judging module 3, configured to calculate a first longitudinal distance and a first lateral distance between the target vehicle and the obstacle vehicle according to the first image coordinate and the second image coordinate, and judge whether the obstacle vehicle has a lane change intention based on the first lateral distance;
a first calculation module 4, configured to calculate a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle if the obstacle vehicle has a lane change intention, calculate a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane change distance difference, and determine whether the second longitudinal distance is smaller than a preset safety distance, and if the second longitudinal distance is smaller than the preset safety distance, send an alarm message to the target vehicle;
And the second calculation module 5 is configured to determine whether the first longitudinal distance is smaller than the preset safety distance if the obstacle vehicle has no lane change intention, and send alarm information to the target vehicle if the first longitudinal distance is smaller than the preset safety distance.
Wherein, the processing module 1 is specifically configured to:
and gray conversion, denoising, image enhancement and feature extraction are sequentially carried out on the first road image and the second road image so as to obtain a first road processing image and a second road processing image.
The coordinate calculation module 2 includes:
the recognition sub-module is used for recognizing pixel coordinates of each pixel point in the first road processing image and the second road processing image on an image space coordinate plane, and determining an initial expression for calculating a lane line based on the pixel coordinates:
in the method, in the process of the invention,is the polar diameter of the lane line +.>Is the polar angle of the lane line +.>Is the abscissa of the pixel coordinate, +.>Is the ordinate of the pixel coordinates;
parameter coordinate determination submodule for determining gradient direction of the lane lineIs determined in a predetermined vicinity of (2)>And->Establishing a discrete parameter space in the search range, and mapping the pixel coordinates into the discrete parameter space to obtain parameter coordinates;
A searching sub-module for searching local maxima of collinear points on the corresponding image space coordinate plane in the searching range and determining searching parameters of the collinear points on the image coordinate plane based on the local maxima;
A lane line determination sub-module for determining the search parameterSubstituting the parameters into the initial expression of the lane line, and fitting the parameters by a least square method to obtain the final expression of the lane line;
and the coordinate determination submodule is used for dividing the driving area of the first road processing image and the second road processing image based on the final expression of the lane line, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image.
The coordinate determination submodule includes:
the dividing unit is used for dividing the first road processing image and the second road processing image into a first driving area image, a first non-driving area image, a second driving area image and a second non-driving area image respectively by taking the lane line as a boundary;
a gradation calculation unit configured to calculate a first average gradation value of the first running area image and a second average gradation value of the second running area image;
A dividing unit configured to divide an image smaller than a first average gray value in the first traveling area image and a second average gray value in the second traveling area image to obtain an obstacle vehicle image;
and the coordinate determining unit is used for respectively extracting first image coordinates and second image coordinates of the obstacle vehicle image in the first road image and the second road image based on the obstacle vehicle image.
The judging module 3 includes:
a first calculation sub-module for calculating the first image coordinates according to the first image coordinatesx p1 ,y p1 ) And the second image coordinatesx p2 ,y p2 ) Meter with a meter bodyCalculating a first actual longitudinal distanceL 1 :
In the method, in the process of the invention,ffor the focal length of the binocular camera,L m for the distance between the binocular cameras,dxis the physical unit of a pixel in the X-axis direction;
a second calculation sub-module for obtaining the first intersection point coordinates of the lane lines in the first road image and the second road image respectivelyx j1 ,y j1 ) Coordinates of the second intersection pointx j2 ,y j2 ) According to the first intersection point coordinatesx j1 ,y j1 ) The coordinates of the second intersection pointx j2 ,y j2 ) The first image coordinatesx p1 ,y p1 ) And the second image coordinatesx p2 ,y p2 ) Calculating a second actual longitudinal distance L 2 :
In the method, in the process of the invention,aas a first coefficient of fit,bas a result of the first fitting index,cis a first fitting constant;
a third calculation sub-module for calculating a third calculation value based on the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 Determining the first longitudinal distanceL Z1 And according to the first longitudinal distanceL Z1 Calculating a first lateral distanceL H :
In the method, in the process of the invention,for the slip angle between the target vehicle and the obstacle vehicle。
The third calculation sub-module includes:
a range judging unit for judging the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 Judging the first longitudinal distanceL Z1 Whether within the first preset range or the second preset range;
a distance determining unit for determining the first longitudinal distanceL Z1 Within a first preset range, the first longitudinal distanceL Z1 For a first actual longitudinal distanceL 1 If the first longitudinal distanceL Z1 Within a second preset range, the first longitudinal distanceL Z1 For a second actual longitudinal distanceL 2 。
The judging module 3 further includes:
a probability determination sub-module for determining a probability based on the first lateral distancesigmoidCalculating the lane change probability of the obstacle vehicle by a function:
in the method, in the process of the invention,representing a lane change event, < >>Represents a scale factor->Indicating lane width +. >Is a first lateral distance;
the probability judging sub-module is used for judging whether the lane change probability is larger than a preset probability threshold value or not;
the intention determining submodule is used for determining that the obstacle vehicle has a lane change intention if the lane change probability is larger than a preset probability threshold value, and the obstacle vehicle does not have the lane change intention if the lane change probability is not larger than the preset probability threshold value.
The first computing module 4 includes:
a distance difference calculation sub-module for obtaining a lane change speed of the obstacle vehicle, and calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle based on the lane change speed and the first lateral distanceL C :
In the method, in the process of the invention,for the lateral resolution speed of the lane change speed, +.>Longitudinal decomposition speed for lane change speed, +.>For a first lateral distance>The vehicle speed of the target vehicle;
a distance calculation sub-module for calculating a distance difference based on the longitudinal variationL C Calculating a second longitudinal distance between the target vehicle and the obstacle vehicleL Z2 :
In the method, in the process of the invention,L Z1 is the first longitudinal distance.
In other embodiments of the present invention, a computer device is provided in the embodiments of the present invention, including a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101, where the processor 101 implements the vehicle collision warning method described above when executing the computer program.
In particular, the processor 101 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the vehicle collision warning method described above.
In some of these embodiments, the computer may also include a communication interface 103 and a bus 100. As shown in fig. 9, the processor 101, the memory 102, and the communication interface 103 are connected to each other via the bus 100 and perform communication with each other.
The communication interface 103 is used to implement communication between modules, devices, units, and/or units in the embodiments of the present application. The communication interface 103 may also enable communication with other components such as: and the external equipment, the image/data acquisition equipment, the database, the external storage, the image/data processing workstation and the like are used for data communication.
The computer equipment can execute the vehicle collision early warning method based on the acquired vehicle collision early warning system, so that the collision early warning in the vehicle running process is realized.
In still other embodiments of the present invention, in combination with the above-described vehicle collision warning method, embodiments of the present invention provide a technical solution, a readable storage medium having a computer program stored thereon, the computer program implementing the above-described vehicle collision warning method when executed by a processor.
Those of skill in the art will appreciate that the logic and/or steps represented in the flow diagrams or otherwise described herein, e.g., a ordered listing of executable instructions for implementing 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 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). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may 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 is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A vehicle collision warning method, the method comprising:
acquiring a first road image and a second road image in front of a target vehicle through a binocular camera on the target vehicle, and preprocessing the first road image and the second road image to obtain a first road processing image and a second road processing image;
Sequentially carrying out lane line identification and driving area division on the first road processing image and the second road processing image to obtain a first driving area image and a second driving area image, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image;
according to the first image coordinates and the second image coordinates, calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle, and judging whether the obstacle vehicle has a lane change intention or not based on the first transverse distance;
if the obstacle vehicle has a lane changing intention, calculating a longitudinal lane changing distance difference between the obstacle vehicle and the target vehicle, calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane changing distance difference, judging whether the second longitudinal distance is smaller than a preset safety distance, and if the second longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle;
if the obstacle vehicle does not have the lane changing intention, judging whether the first longitudinal distance is smaller than the preset safety distance, and if the first longitudinal distance is smaller than the preset safety distance, sending alarm information to the target vehicle.
2. The vehicle collision warning method according to claim 1, wherein the step of preprocessing the first road image and the second road image to obtain a first road processed image and a second road processed image includes:
and gray conversion, denoising, image enhancement and feature extraction are sequentially carried out on the first road image and the second road image so as to obtain a first road processing image and a second road processing image.
3. The vehicle collision warning method according to claim 1, wherein the step of sequentially performing lane line recognition and driving area division on the first road processing image and the second road processing image to obtain a first driving area image and a second driving area image, and recognizing and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image comprises:
identifying pixel coordinates of each pixel point in the first road processing image and the second road processing image on an image space coordinate plane, and determining an initial expression for calculating a lane line based on the pixel coordinates:
In the method, in the process of the invention,is the polar diameter of the lane line +.>Is the polar angle of the lane line +.>Is the abscissa of the pixel coordinate, +.>Is the ordinate of the pixel coordinates;
in the gradient direction of the lane lineIs determined in a predetermined vicinity of (2)>And->Establishing a discrete parameter space in the search range, and mapping the pixel coordinates into the discrete parameter space to obtain parameter coordinates;
searching local maxima of collinear points on the corresponding image space coordinate plane in the searching range, and determining the searching parameters of the collinear points on the image coordinate plane based on the local maxima;
The search parameters are setSubstituting the parameters into the initial expression of the lane line, and fitting the parameters by a least square method to obtain the final expression of the lane line; />
And carrying out driving region division on the first road processing image and the second road processing image based on the final expression of the lane line, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving region image and the second driving region image.
4. The vehicle collision warning method according to claim 3, wherein the step of dividing the first road processing image and the second road processing image into traveling areas based on the final expression of the lane line, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first traveling area image and the second traveling area image includes:
Dividing the first road processing image and the second road processing image into a first driving area image, a first non-driving area image, a second driving area image and a second non-driving area image respectively by taking the lane line as a boundary;
calculating a first average gray value of the first driving area image and a second average gray value of the second driving area image;
dividing an image smaller than a first average gray value in the first driving area image and an image smaller than a second average gray value in the second driving area image to obtain an obstacle vehicle image;
and respectively extracting a first image coordinate and a second image coordinate of the obstacle vehicle image in the first road image and the second road image based on the obstacle vehicle image.
5. The vehicle collision warning method according to claim 1, wherein the step of calculating a first longitudinal distance and a first lateral distance between the target vehicle and the obstacle vehicle from the first image coordinates and the second image coordinates includes:
according to the first image coordinatesx p1 ,y p1 ) And the second image coordinates x p2 ,y p2 ) Calculating a first actual longitudinal distanceL 1 :
In the method, in the process of the invention,ffor the focal length of the binocular camera,L m for the distance between the binocular cameras,dxis the physical unit of a pixel in the X-axis direction;
obtaining first intersection point coordinates of lane lines in the first road image and the second road image respectivelyx j1 ,y j1 ) Coordinates of the second intersection pointx j2 ,y j2 ) According to the first intersection point coordinatesx j1 ,y j1 ) The coordinates of the second intersection pointx j2 ,y j2 ) The first image coordinatesx p1 ,y p1 ) And the second image coordinatesx p2 ,y p2 ) Calculating a second actual longitudinal distanceL 2 :
In the method, in the process of the invention,aas a first coefficient of fit,bas a result of the first fitting index,cis a first fitting constant;
based on the first actual longitudinal distanceL 1 Distance from the second actual longitudinal directionL 2 Determining the first longitudinal distanceL Z1 And according to the first longitudinal distanceL Z1 Calculating a first lateral distanceL H :
6. The vehicle collision warning method according to claim 5, wherein the first actual longitudinal distance is based onL 1 Distance from the second actual longitudinal directionL 2 Determining the first longitudinal distanceL Z1 The method comprises the following steps:
according to the first actual longitudinal distance L 1 Distance from the second actual longitudinal directionL 2 Judging the first longitudinal distanceL Z1 Whether within the first preset range or the second preset range;
if the first longitudinal distanceL Z1 Within a first preset range, the first longitudinal distanceL Z1 For a first actual longitudinal distanceL 1 If the first longitudinal distanceL Z1 Within a second preset range, the first longitudinal distanceL Z1 For a second actual longitudinal distanceL 2 。
7. The vehicle collision warning method according to claim 1, wherein the step of judging whether the obstacle vehicle has a lane change intention based on the first lateral distance includes:
based on the first lateral distance and according tosigmoidCalculating the lane change probability of the obstacle vehicle by a function:
in the method, in the process of the invention,representing a lane change event, < >>Represents a scale factor->Indicating lane width +.>Is a first lateral distance;
judging whether the lane change probability is larger than a preset probability threshold value or not;
if the lane change probability is larger than a preset probability threshold, the obstacle vehicle has a lane change intention, and if the lane change probability is not larger than the preset probability threshold, the obstacle vehicle has no lane change intention.
8. The vehicle collision warning method according to claim 1, wherein the step of calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle, and calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane change distance difference, includes:
Acquiring a lane change speed of the obstacle vehicle, and calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle based on the lane change speed and the first lateral distanceL C :
In the method, in the process of the invention,for the lateral resolution speed of the lane change speed, +.>Longitudinal decomposition speed for lane change speed, +.>For a first lateral distance>The vehicle speed of the target vehicle;
based on the longitudinal lane change distance differenceL C Calculating a second longitudinal distance between the target vehicle and the obstacle vehicleL Z2 :
In the method, in the process of the invention,L Z1 is the first longitudinal distance.
9. The vehicle collision warning method according to claim 1, wherein in the step of determining whether the second longitudinal distance is smaller than a preset safety distance, a preset safety distance is setS safe The method comprises the following steps:
wherein S is 1 For the distance travelled by the target vehicle within the driver' S reaction time S 2 For the braking distance of the target vehicle in the braking time S 3 For obstacle vehicles at the driver reaction time and the brakingDistance travelled in time S 4 Is a safety threshold.
10. A vehicle collision warning system, the system comprising:
the processing module is used for acquiring a first road image and a second road image in front of a target vehicle through a binocular camera on the target vehicle, and preprocessing the first road image and the second road image to obtain a first road processing image and a second road processing image;
The coordinate calculation module is used for sequentially carrying out lane line identification and driving area division on the first road processing image and the second road processing image so as to obtain a first driving area image and a second driving area image, and identifying and extracting first image coordinates and second image coordinates of the obstacle vehicle in the first driving area image and the second driving area image;
the judging module is used for calculating a first longitudinal distance and a first transverse distance between the target vehicle and the obstacle vehicle according to the first image coordinates and the second image coordinates, and judging whether the obstacle vehicle has a lane change intention or not based on the first transverse distance;
the first calculation module is used for calculating a longitudinal lane change distance difference between the obstacle vehicle and the target vehicle if the obstacle vehicle has a lane change intention, calculating a second longitudinal distance between the target vehicle and the obstacle vehicle based on the longitudinal lane change distance difference, judging whether the second longitudinal distance is smaller than a preset safety distance, and sending alarm information to the target vehicle if the second longitudinal distance is smaller than the preset safety distance;
And the second calculation module is used for judging whether the first longitudinal distance is smaller than the preset safety distance or not if the obstacle vehicle does not have the lane change intention, and sending alarm information to the target vehicle if the first longitudinal distance is smaller than the preset safety distance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310287953.XA CN115995163B (en) | 2023-03-23 | 2023-03-23 | Vehicle collision early warning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310287953.XA CN115995163B (en) | 2023-03-23 | 2023-03-23 | Vehicle collision early warning method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115995163A true CN115995163A (en) | 2023-04-21 |
CN115995163B CN115995163B (en) | 2023-06-27 |
Family
ID=85993830
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310287953.XA Active CN115995163B (en) | 2023-03-23 | 2023-03-23 | Vehicle collision early warning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115995163B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101132965A (en) * | 2005-03-03 | 2008-02-27 | 大陆-特韦斯贸易合伙股份公司及两合公司 | Method and device for avoiding a collision as a vehicle is changing lanes |
WO2018058356A1 (en) * | 2016-09-28 | 2018-04-05 | 驭势科技(北京)有限公司 | Method and system for vehicle anti-collision pre-warning based on binocular stereo vision |
CN111383474A (en) * | 2018-12-29 | 2020-07-07 | 长城汽车股份有限公司 | Decision making system and method for automatically driving vehicle |
CN112712728A (en) * | 2019-10-24 | 2021-04-27 | 罗伯特·博世有限公司 | Control unit, method and system for highway driving assistance |
CN113053165A (en) * | 2019-12-26 | 2021-06-29 | 北京宝沃汽车股份有限公司 | Vehicle and collision recognition method, device and equipment thereof |
CN114394095A (en) * | 2022-01-24 | 2022-04-26 | 东风汽车集团股份有限公司 | ACC control method and device based on lane changing intention recognition of side front vehicle |
CN115384508A (en) * | 2022-09-30 | 2022-11-25 | 东风商用车有限公司 | Channel changing decision method, device and equipment and readable storage medium |
WO2023024516A1 (en) * | 2021-08-23 | 2023-03-02 | 上海商汤智能科技有限公司 | Collision early-warning method and apparatus, and electronic device and storage medium |
-
2023
- 2023-03-23 CN CN202310287953.XA patent/CN115995163B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101132965A (en) * | 2005-03-03 | 2008-02-27 | 大陆-特韦斯贸易合伙股份公司及两合公司 | Method and device for avoiding a collision as a vehicle is changing lanes |
WO2018058356A1 (en) * | 2016-09-28 | 2018-04-05 | 驭势科技(北京)有限公司 | Method and system for vehicle anti-collision pre-warning based on binocular stereo vision |
CN111383474A (en) * | 2018-12-29 | 2020-07-07 | 长城汽车股份有限公司 | Decision making system and method for automatically driving vehicle |
CN112712728A (en) * | 2019-10-24 | 2021-04-27 | 罗伯特·博世有限公司 | Control unit, method and system for highway driving assistance |
CN113053165A (en) * | 2019-12-26 | 2021-06-29 | 北京宝沃汽车股份有限公司 | Vehicle and collision recognition method, device and equipment thereof |
WO2023024516A1 (en) * | 2021-08-23 | 2023-03-02 | 上海商汤智能科技有限公司 | Collision early-warning method and apparatus, and electronic device and storage medium |
CN114394095A (en) * | 2022-01-24 | 2022-04-26 | 东风汽车集团股份有限公司 | ACC control method and device based on lane changing intention recognition of side front vehicle |
CN115384508A (en) * | 2022-09-30 | 2022-11-25 | 东风商用车有限公司 | Channel changing decision method, device and equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN115995163B (en) | 2023-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110443225B (en) | Virtual and real lane line identification method and device based on feature pixel statistics | |
CN111712731B (en) | Target detection method, target detection system and movable platform | |
US10032085B2 (en) | Method and system to identify traffic lights by an autonomous vehicle | |
CN110867132B (en) | Environment sensing method, device, electronic equipment and computer readable storage medium | |
Labayrade et al. | In-vehicle obstacles detection and characterization by stereovision | |
US11144770B2 (en) | Method and device for positioning vehicle, device, and computer readable storage medium | |
CN108859952B (en) | Vehicle lane change early warning method and device and radar | |
CN110632617A (en) | Laser radar point cloud data processing method and device | |
CN110341621B (en) | Obstacle detection method and device | |
CN111103587A (en) | Method and apparatus for predicting simultaneous and concurrent vehicles and vehicle including the same | |
JPWO2017130285A1 (en) | Vehicle determination device, vehicle determination method, and vehicle determination program | |
JP2018092596A (en) | Information processing device, imaging device, apparatus control system, mobile body, information processing method, and program | |
CN111857135A (en) | Obstacle avoidance method and apparatus for vehicle, electronic device, and computer storage medium | |
CN110843786A (en) | Method and system for determining and displaying a water-engaging condition and vehicle having such a system | |
CN111497741A (en) | Collision early warning method and device | |
US10953885B2 (en) | Road surface detecting apparatus | |
WO2007046336A1 (en) | Object recognizing device | |
KR102337034B1 (en) | Autonomous driving situation recognition program performance test method and apparatus for porceeding the same | |
CN115995163B (en) | Vehicle collision early warning method and system | |
EP4094046A1 (en) | Method and apparatus for evaluating maps for autonomous driving and vehicle | |
CN114119955A (en) | Method and device for detecting potential dangerous target | |
CN113257036A (en) | Vehicle collision early warning method, device, equipment and storage medium | |
Ben Romdhane et al. | A lane detection and tracking method for driver assistance system | |
CN111874003B (en) | Vehicle driving deviation early warning method and system | |
CN113191238A (en) | Blind area detection method and system based on binocular camera and storage medium |
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 |