CN113178081B - Vehicle immission early warning method and device and electronic equipment - Google Patents
Vehicle immission early warning method and device and electronic equipment Download PDFInfo
- Publication number
- CN113178081B CN113178081B CN202110534828.5A CN202110534828A CN113178081B CN 113178081 B CN113178081 B CN 113178081B CN 202110534828 A CN202110534828 A CN 202110534828A CN 113178081 B CN113178081 B CN 113178081B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- target
- sensor
- state data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000005070 sampling Methods 0.000 claims description 46
- 230000004927 fusion Effects 0.000 claims description 18
- 230000015572 biosynthetic process Effects 0.000 claims description 14
- 238000003786 synthesis reaction Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 10
- 230000008676 import Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229910052755 nonmetal Inorganic materials 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004941 influx Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Abstract
The invention provides a vehicle immission early warning method, a vehicle immission early warning device and electronic equipment, and relates to the technical field of intelligent traffic safety control, wherein the method comprises the following steps: respectively acquiring moving state data of a first vehicle and moving state data of a second vehicle, wherein the first vehicle runs in a first lane, the second vehicle runs in a second lane, and an intersection point exists between the first lane and the second lane; determining a first time period when the first vehicle passes through a collision risk area corresponding to the first lane according to the movement state data of the first vehicle, and determining a second time period when the second vehicle passes through the collision risk area corresponding to the second lane according to the movement state data of the second vehicle, wherein the collision risk area is an area including an intersection point; and under the condition that the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period, collision early warning is carried out. According to the embodiment of the invention, the collision early warning is carried out in advance, so that the early warning effect of vehicle entry can be improved.
Description
Technical Field
The invention relates to the technical field of intelligent traffic safety control, in particular to a vehicle entry early warning method and device and electronic equipment.
Background
With the improvement of living standard of people, the automobile keeping amount in China is gradually increased year by year, the incidence rate of traffic accidents on expressways, particularly at the entrance of a ramp, is also improved year by year, and when vehicles are cooperatively converged from the ramp, collision is easy to occur at the convergence point. Among the prior art, for reducing traffic accident incidence, can set up the notice board at the ramp entrance, the suggestion is gone slowly to can warn the driver before the vehicle gets into the junction, however, the notice board can not indicate to different vehicles, and the driver ignores the notice board easily, leads to the vehicle to converge the effect of early warning relatively poor.
Disclosure of Invention
The embodiment of the invention provides a vehicle import early warning method, a vehicle import early warning device and electronic equipment, and aims to solve the problems that in the prior art, a notice board cannot prompt different vehicles, and a driver easily ignores the notice board, so that the vehicle import early warning effect is poor.
In order to solve the technical problem, the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a vehicle entry early warning method, where the method includes:
respectively acquiring moving state data of a first vehicle and moving state data of a second vehicle, wherein the first vehicle runs in a first lane, the second vehicle runs in a second lane, and an intersection point exists between the first lane and the second lane;
determining a first time period when the first vehicle passes through a collision risk area corresponding to the first lane according to the movement state data of the first vehicle, and determining a second time period when the second vehicle passes through the collision risk area corresponding to the second lane according to the movement state data of the second vehicle, wherein the collision risk area is an area including the junction;
and under the condition that the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period, performing collision early warning.
Optionally, before the obtaining of the moving state data of the first vehicle and the second vehicle, the method further includes:
acquiring identification data corresponding to each sensor in at least one sensor, wherein the identification data corresponding to each sensor is data obtained by identifying a target object moving on the first lane or the second lane;
D-S evidence reasoning is carried out according to the identification data, and whether the target object is a first target vehicle or not is determined;
wherein, when it is determined that the target object is the first target vehicle, movement state data of the first target vehicle is acquired, the first target vehicle being the first vehicle or the second vehicle.
Optionally, the identification data comprises a probability value of the target object belonging to each of a plurality of object categories, the plurality of object categories comprising vehicles;
the performing D-S evidence reasoning according to the identification data to determine whether the target object is a first target vehicle comprises:
performing fusion calculation on the probability value corresponding to each object type aiming at the at least one sensor according to a D-S evidence synthesis rule to obtain a basic credible number corresponding to each object type;
taking the object class corresponding to the maximum basic credibility number in the basic credibility numbers corresponding to the object classes as the object class to which the target object belongs;
determining whether the target object is a first target vehicle based on an object class to which the target object belongs;
wherein, when the object class to which the target object belongs is a vehicle, it is determined that the target object is the first target vehicle.
Optionally, the acquiring identification data corresponding to each sensor in the at least one sensor includes:
acquiring identification data corresponding to each sensor in at least one sensor at the current sampling moment;
acquiring identification data corresponding to each sensor at the previous sampling moment;
and respectively fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the previous sampling moment to obtain the identification data corresponding to each sensor.
Optionally, the identification data includes the movement state data and probability values corresponding to the movement state data, and the number of the sensors is multiple;
after obtaining the identification data corresponding to each sensor of the at least one sensor, the method further includes:
determining moving state data corresponding to the target object according to the moving state data obtained by the at least one sensor through identification and the corresponding probability value;
the moving state data corresponding to the target object is the moving state data with the maximum probability value in the moving state data obtained by the at least one sensor through identification.
Optionally, the collision risk area corresponding to the target lane includes a road section between a target position point on the target lane and the intersection point, a distance between the target position point and the intersection point is a safety distance corresponding to the target lane, the safety distance corresponding to the target lane is determined based on a highest speed limit of the target lane, and the target lane is the first lane or the second lane.
Optionally, when it is determined that there is a risk of collision between the first vehicle and the second vehicle according to the first time period and the second time period, performing collision warning includes:
determining whether the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period;
under the condition that the first vehicle and the second vehicle are judged to have collision risks, sending a road passing prompt to a second target vehicle and sending a deceleration and slow running prompt to a third target vehicle;
wherein the second target vehicle is a preset type of vehicle of the first vehicle and the second vehicle, or the second target vehicle is a vehicle of the first vehicle and the second vehicle that is expected to arrive at the intersection first; the third target vehicle is a vehicle other than the second target vehicle, of the first vehicle and the second vehicle.
In a second aspect, an embodiment of the present invention provides a vehicle entry early warning device, where the device includes:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for respectively acquiring movement state data of a first vehicle and movement state data of a second vehicle, the first vehicle runs in a first lane, the second vehicle runs in a second lane, and an intersection point exists between the first lane and the second lane;
the first determining module is used for determining a first time period when the first vehicle passes through a collision risk area corresponding to the first lane according to the movement state data of the first vehicle, and determining a second time period when the second vehicle passes through the collision risk area corresponding to the second lane according to the movement state data of the second vehicle, wherein the collision risk area is an area including the junction;
and the early warning module is used for carrying out collision early warning under the condition that the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period.
Optionally, the apparatus further comprises:
the second acquisition module is used for acquiring identification data corresponding to each sensor in at least one sensor, wherein the identification data corresponding to each sensor is data obtained by identifying a target object moving on the first lane or the second lane;
the second determination module is used for performing D-S evidence reasoning according to the identification data and determining whether the target object is a first target vehicle;
wherein, when it is determined that the target object is the first target vehicle, movement state data of the first target vehicle is acquired, the first target vehicle being the first vehicle or the second vehicle.
Optionally, the identification data comprises a probability value of the target object belonging to each of a plurality of object categories, the plurality of object categories comprising vehicles;
the second determining module is specifically configured to:
performing fusion calculation on the probability value corresponding to each object type aiming at the at least one sensor according to a D-S evidence synthesis rule to obtain a basic credible number corresponding to each object type;
taking the object class corresponding to the maximum basic credibility number in the basic credibility numbers corresponding to the object classes as the object class to which the target object belongs;
determining whether the target object is a first target vehicle based on an object class to which the target object belongs;
wherein, when the object class to which the target object belongs is a vehicle, it is determined that the target object is the first target vehicle.
Optionally, the second obtaining module is specifically configured to:
acquiring identification data corresponding to each sensor in at least one sensor at the current sampling moment;
acquiring identification data corresponding to each sensor at the previous sampling moment;
and respectively fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the previous sampling moment to obtain the identification data corresponding to each sensor.
Optionally, the identification data includes the movement state data and probability values corresponding to the movement state data, and the number of the sensors is multiple;
the device further comprises:
a third determining module, configured to determine moving state data corresponding to the target object according to the moving state data identified by the at least one sensor and the corresponding probability value;
the moving state data corresponding to the target object is the moving state data with the maximum probability value in the moving state data obtained by the at least one sensor through identification.
Optionally, the collision risk area corresponding to the target lane includes a road section between a target position point on the target lane and the intersection point, a distance between the target position point and the intersection point is a safety distance corresponding to the target lane, the safety distance corresponding to the target lane is determined based on a highest speed limit of the target lane, and the target lane is the first lane or the second lane.
Optionally, the early warning module is specifically configured to:
determining whether the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period;
under the condition that the first vehicle and the second vehicle are judged to have collision risks, sending a road passing prompt to a second target vehicle and sending a deceleration and slow running prompt to a third target vehicle;
wherein the second target vehicle is a preset type of vehicle of the first vehicle and the second vehicle, or the second target vehicle is a vehicle of the first vehicle and the second vehicle that is expected to arrive at the intersection first; the third target vehicle is a vehicle other than the second target vehicle, of the first vehicle and the second vehicle.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor, a memory and a program stored on the memory and executable on the processor, the program, when executed by the processor, implementing the steps of the vehicle intrusion warning method of the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the vehicle entry warning method according to the first aspect.
In the embodiment of the invention, the moving state data of a first vehicle and the moving state data of a second vehicle are respectively obtained, wherein the first vehicle runs in a first lane, the second vehicle runs in a second lane, and an intersection point exists between the first lane and the second lane; determining a first time period when the first vehicle passes through a collision risk area corresponding to the first lane according to the movement state data of the first vehicle, and determining a second time period when the second vehicle passes through the collision risk area corresponding to the second lane according to the movement state data of the second vehicle, wherein the collision risk area is an area including the junction; and under the condition that the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period, performing collision early warning. Therefore, the collision risk is predicted through the moving state data of the vehicle, collision early warning is carried out in advance, and the vehicle entry early warning effect can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart of a vehicle intrusion warning method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a vehicle entry warning system according to an embodiment of the present invention;
FIG. 3 is one of the schematic diagrams of a vehicle merge scenario provided by the embodiments of the present invention;
fig. 4 is a second schematic diagram of a vehicle influx scenario according to the embodiment of the present invention;
fig. 5 is a schematic structural diagram of a vehicle entry warning device according to an embodiment of the present invention;
fig. 6 is a second schematic structural diagram of a vehicle entry warning device according to an embodiment of the present invention;
fig. 7 is a third schematic structural diagram of a vehicle entry warning device according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a vehicle import early warning method, a vehicle import early warning device and electronic equipment, and aims to solve the problems that in the prior art, a notice board cannot prompt different vehicles, and a driver easily ignores the notice board, so that the vehicle import early warning effect is poor.
Referring to fig. 1, fig. 1 is a flowchart of a vehicle intrusion warning method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
Wherein the mobility state data may include at least one of: speed, position and orientation. For example, the movement status data may include: speed, position and orientation. The intersection may be an intersection of a center line of the first lane and a center line of the second lane.
In addition, identification data corresponding to each sensor of the at least one sensor may be acquired, the identification data corresponding to each sensor is data obtained by identifying a target object moving on the first lane or the second lane, and vehicle identification may be performed according to the identification data to determine whether a first vehicle and a second vehicle exist in the target object, so as to acquire moving state data of the first vehicle and moving state data of the second vehicle. The method can utilize the algorithm advantages of the deep learning algorithm in the aspects of anti-interference performance, recognition accuracy, processing speed and the like, the deep learning algorithm is applied to vehicle recognition, a proper algorithm and a proper model can be determined, an experiment scene is extracted according to the characteristics of an actual production scene to construct required core elements, the establishment of an experiment environment is completed, the at least one sensor can comprise a camera, and the vehicle recognition can be completed by performing analysis such as denoising, enhancing, feature extraction, recognition and the like on images collected by the camera.
And the collision risk area corresponding to the first lane and the collision risk area corresponding to the second lane both comprise the intersection point. The collision risk zone corresponding to the first lane may be different from the collision risk zone corresponding to the second lane. The collision risk area corresponding to the first lane may be a circular area, or a square area, or may also be an area with another shape, which is not limited in this embodiment. The collision risk area corresponding to the second lane may be a circular area, or a square area, or may also be an area with another shape, which is not limited in this embodiment. The first time period may be a time period between a time at which the first vehicle enters the collision risk zone corresponding to the first lane and a time at which the first vehicle exits the collision risk zone corresponding to the first lane; the second time period may be a time period between a time at which the second vehicle enters the collision risk zone corresponding to the second lane and a time at which the second vehicle exits the collision risk zone corresponding to the second lane. Taking the first vehicle as an example, the movement state data may include a position, and a time when the first vehicle enters the collision risk area corresponding to the first lane and a time when the first vehicle leaves the collision risk area corresponding to the first lane may be determined according to the position of the first vehicle, so that the first time period may be determined; or, the movement state data may include a position and a speed, and the time when the first vehicle enters the collision risk area corresponding to the first lane may be determined according to the position of the first vehicle, and the time when the first vehicle leaves the collision risk area corresponding to the first lane may be calculated according to the speed of the first vehicle, so that the first time period may be determined; and so on. This embodiment does not limit this.
103, performing collision early warning when the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period.
Wherein it may be determined that the first vehicle and the second vehicle have a risk of collision if there is a temporal overlap between the first time period and the second time period. The performing collision warning when it is determined that there is a collision risk between the first vehicle and the second vehicle according to the first time period and the second time period may include: determining whether the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period; under the condition that the first vehicle and the second vehicle are judged to have collision risks, sending a road passing prompt to a second target vehicle and sending a deceleration slow-moving prompt to a third target vehicle, wherein the second target vehicle is a preset type of vehicle in the first vehicle and the second vehicle, or the second target vehicle is a vehicle which is predicted to arrive at the junction point first in the first vehicle and the second vehicle; the third target vehicle is a vehicle other than the second target vehicle, of the first vehicle and the second vehicle. Or, the performing collision warning when it is determined that there is a collision risk between the first vehicle and the second vehicle according to the first time period and the second time period may include: determining whether the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period; and sending a deceleration and jogging prompt to the first vehicle and the second vehicle when the first vehicle and the second vehicle are judged to have the collision risk. And the like, which are not limited in this respect by the embodiments of the present invention.
In the embodiment of the invention, the moving state data of a first vehicle and the moving state data of a second vehicle are respectively obtained, wherein the first vehicle runs in a first lane, the second vehicle runs in a second lane, and an intersection point exists between the first lane and the second lane; determining a first time period when the first vehicle passes through a collision risk area corresponding to the first lane according to the movement state data of the first vehicle, and determining a second time period when the second vehicle passes through the collision risk area corresponding to the second lane according to the movement state data of the second vehicle, wherein the collision risk area is an area including the junction; and under the condition that the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period, performing collision early warning. Therefore, the collision risk is predicted through the moving state data of the vehicle, collision early warning is carried out in advance, and the vehicle entry early warning effect can be improved.
Optionally, before the obtaining of the moving state data of the first vehicle and the second vehicle, the method further includes:
acquiring identification data corresponding to each sensor in at least one sensor, wherein the identification data corresponding to each sensor is data obtained by identifying a target object moving on the first lane or the second lane;
D-S evidence reasoning is carried out according to the identification data, and whether the target object is a first target vehicle or not is determined;
wherein, when it is determined that the target object is the first target vehicle, movement state data of the first target vehicle is acquired, the first target vehicle being the first vehicle or the second vehicle.
The acquiring identification data corresponding to each sensor of the at least one sensor may include: acquiring identification data corresponding to each sensor in at least one sensor at the current sampling moment, acquiring identification data corresponding to each sensor at the previous sampling moment, and fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the previous sampling moment respectively to obtain the identification data corresponding to each sensor; or may include: acquiring identification data corresponding to each sensor in at least one sensor at the current sampling moment, acquiring identification data corresponding to each sensor at a plurality of sampling moments before the current sampling moment, and fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the plurality of sampling moments before the current sampling moment respectively to obtain the identification data corresponding to each sensor; etc., which are not limited by the present embodiment.
It should be noted that the D-S evidence reasoning includes three main points: a basic probability assignment function, a trust function, and a likelihood function. The reasoning structure of the D-S evidence reasoning is from top to bottom and can be divided into three levels of target synthesis, updating and inference. In the target synthesis, the identification data of a plurality of sensors may be synthesized into one total output result. When updating, the identification data corresponding to each sensor in at least one sensor at the current sampling time can be acquired, the identification data corresponding to each sensor at the previous sampling time can be acquired, and the identification data corresponding to each sensor at the current sampling time and the identification data corresponding to each sensor at the previous sampling time are respectively fused to obtain the identification data corresponding to each sensor. When the inference is performed, fusion calculation may be performed on a probability value corresponding to each object category for the at least one sensor according to a D-S evidence synthesis rule to obtain a basic credibility corresponding to each object category, an object category corresponding to a maximum basic credibility number among the basic credibility numbers corresponding to the plurality of object categories is used as the object category to which the target object belongs, and the identification data includes a probability value that the target object belongs to each object category among the plurality of object categories.
Taking the example that the at least one sensor includes a millimeter wave radar, a laser radar, and a camera, the movement state data S may include a speed S1Position S2And in the direction S3The object class H of the target object may include a motor vehicle H1Non-motor vehicle H2And pedestrian H3The millimeter wave radar, the laser radar and the camera detect the same target object, and for the sensors, the nine detection combination results shown in table 1 are shown, so that target synthesis can be realized, and the identification data of the sensors are synthesized into a total output result.
TABLE 1
In addition, the at least one sensor may include a radar, a camera, and the like. Illustratively, the at least one sensor may include a millimeter wave radar, a laser radar, and a camera. The millimeter wave radar has the advantages that the detection distance is long, the accuracy is high, the millimeter wave radar is not influenced by weather and light, the millimeter wave radar is sensitive to moving metal objects, but is not sensitive to static metal or nonmetal objects and moving nonmetal objects, the resolution ratio is low, the outlines of obstacles are not easy to obtain, and the millimeter wave radar is suitable for detecting the obstacles on the expressway, comprises the identification of lane lines and can acquire information through intensity imaging. The range finding precision of laser radar is very high, can reach plus or minus one centimetre or plus or minus two centimetres basically, has arrived the millimeter level even, and resolution ratio is also very high, and mechanical laser radar can 360 degrees rotations, and angular resolution ratio is higher than other radars simultaneously also, and laser radar's operating temperature is generally at-10 below zero to-60 above zero. The camera can carry out all kinds of recognition operation through abundant formation of image information, for example pedestrian, the object of deformation, the horizontal pole in parking area and traffic sign etc. in addition.
In the embodiment, D-S evidence reasoning is carried out according to the identification data, whether the target object is the first target vehicle is determined, and vehicle identification is carried out through the D-S evidence reasoning, so that the accuracy of vehicle identification can be improved.
Optionally, the identification data comprises a probability value of the target object belonging to each of a plurality of object categories, the plurality of object categories comprising vehicles;
the performing D-S evidence reasoning according to the identification data to determine whether the target object is a first target vehicle comprises:
performing fusion calculation on the probability value corresponding to each object type aiming at the at least one sensor according to a D-S evidence synthesis rule to obtain a basic credible number corresponding to each object type;
taking the object class corresponding to the maximum basic credibility number in the basic credibility numbers corresponding to the object classes as the object class to which the target object belongs;
determining whether the target object is a first target vehicle based on an object class to which the target object belongs;
wherein, when the object class to which the target object belongs is a vehicle, it is determined that the target object is the first target vehicle.
The probability value that the target object belongs to each object class may be a basic probability assignment that the target object belongs to each object class. The vehicle may be an automobile, and the plurality of object categories may include automobiles, non-automobiles, and pedestrians; alternatively, the plurality of object categories may include vehicles and pedestrians; alternatively, the plurality of object categories may include vehicles and non-vehicles; and so on. The probability value corresponding to each object category can be fused and calculated for the at least one sensor according to a D-S evidence synthesis rule, inference in D-S evidence reasoning can be realized, the identification data of the at least one sensor is expanded into a target report, and the theoretical basis of inference in D-S evidence reasoning is as follows: certain sensor reports can logically generate certain credible target reports with certain credibility, data are obtained from all sensor platforms through centralized fusion and processed in a fusion center, and data fusion can be achieved in a recursive mode through a D-S method combination rule. The D-S evidence theory provides a powerful method for the expression and synthesis of uncertain information. The D-S evidence synthesis rule may be as follows:
K＝∑mc(Hi)×…mR(Hi)
wherein i is an integer from 1 to N, N is the number of object classes, mc(Hi) The target object identified for sensor C belongs to object class HiProbability value of (m)R(Hi) The target object identified for the sensor R belongs to the object class HiThe probability value of (2).
Additionally, taking as an example that the at least one sensor includes a millimeter wave radar, a laser radar, and a camera, the object class H of the target object may include a motor vehicle H1Non-motor vehicle H2And pedestrian H3. The probability values of the target object identified by the millimeter wave radar, the laser radar and the camera belonging to each of the object classes may be: m isC、mL、mR. At time T, the same target object is detected by the millimeter wave radar, the laser radar and the camera, and for each sensor, the detection result is as shown in table 2:
TABLE 2
It should be noted that, fusion calculation may be performed on the probability value corresponding to each object category at the time T by aiming at the at least one sensor, so as to obtain a basic credible number corresponding to each object category; or, the probability value corresponding to each object category at the time T and the probability value corresponding to each object category at the time T-1 may be fused to serve as the probability value corresponding to each current object category, and the probability value corresponding to each current object category is fused and calculated for the at least one sensor, so as to obtain the basic credible number corresponding to each object category.
In this embodiment, fusion calculation is performed on the probability value corresponding to each object category for the at least one sensor according to a D-S evidence synthesis rule to obtain a basic credible number corresponding to each object category; and taking the object class corresponding to the maximum basic credibility number in the basic credibility numbers corresponding to the plurality of object classes as the object class to which the target object belongs. In this way, the accuracy of vehicle recognition can be further improved by fusing the detection data of the multiple sensors to determine the object class to which the target object belongs.
Optionally, the acquiring identification data corresponding to each sensor in the at least one sensor includes:
acquiring identification data corresponding to each sensor in at least one sensor at the current sampling moment;
acquiring identification data corresponding to each sensor at the previous sampling moment;
and respectively fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the previous sampling moment to obtain the identification data corresponding to each sensor.
The identification data corresponding to each sensor at the current sampling time and the identification data corresponding to each sensor at the previous sampling time are fused, and an average value of the identification data corresponding to the current sampling time and the identification data corresponding to the previous sampling time is calculated to obtain a first average value, where the identification data corresponding to each sensor is the first average value; or, a first product of the identification data corresponding to the current sampling time and a first preset coefficient may be calculated, a second product of the identification data corresponding to the previous sampling time and a second preset coefficient may be calculated, an average value of the first product and the second product may be calculated to obtain a second average value, and the identification data corresponding to each sensor is the second average value; and the like, which is not limited by the present embodiment.
It should be noted that each sensor is generally usedThere is a random error, so a set of consecutive reports from the same sensor sufficiently independent in time is more reliable than any single report. Taking the probability value corresponding to each object type in the identification data as an example, the probability value m (H) of each object type at time T-1 in Table 3 can be usedT-1Probability value m (H) of each object class at time TTAnd fusing to obtain the probability value corresponding to each object category.
TABLE 3
The degree of accuracy can be improved by fusing the two recognition results of each sensor, and the probability value corresponding to each object category obtained after fusion is shown in table 4:
TABLE 4
In the embodiment, identification data corresponding to each sensor in at least one sensor at the current sampling moment is acquired; acquiring identification data corresponding to each sensor at the previous sampling moment; and respectively fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the previous sampling moment to obtain the identification data corresponding to each sensor. In this way, the identification data corresponding to each sensor is determined by fusing the identification data at the current sampling time and the identification data at the previous sampling time, so that the accuracy of the identification data corresponding to each sensor can be improved.
Optionally, the identification data includes the movement state data and probability values corresponding to the movement state data, and the number of the sensors is multiple;
after obtaining the identification data corresponding to each sensor of the at least one sensor, the method further includes:
determining moving state data corresponding to the target object according to the moving state data obtained by the at least one sensor through identification and the corresponding probability value;
the moving state data corresponding to the target object is the moving state data with the maximum probability value in the moving state data obtained by the at least one sensor through identification.
Additionally, the movement state data may include speed, position, and orientation. For each sensor, the velocity, position and orientation may correspond to probability values, respectively. The speed with the maximum probability value in the speeds identified by the at least one sensor can be used as the speed corresponding to the target object; the position with the maximum probability value in the positions identified by the at least one sensor can be used as the position corresponding to the target object; the orientation with the highest probability value among the orientations identified by the at least one sensor may be used as the orientation corresponding to the target object.
In this embodiment, the moving state data corresponding to the target object is determined according to the moving state data identified by the at least one sensor and the corresponding probability value, so that the obtained moving state data corresponding to the target object is more accurate.
Optionally, the collision risk area corresponding to the target lane includes a road section between a target position point on the target lane and the intersection point, a distance between the target position point and the intersection point is a safety distance corresponding to the target lane, the safety distance corresponding to the target lane is determined based on a highest speed limit of the target lane, and the target lane is the first lane or the second lane.
The safe distance can be the driving distance of the vehicle under emergency braking measures after the driver receives the early warning for T seconds. First lane L1Corresponding safety distance LOACan be as follows:
wherein the content of the first and second substances,
is L1Highest speed limit of the lane, μ1Represents L1Coefficient of friction of the roadway, T1Is shown at L1The time for reaction of the lane early warning can be determined according to the specific road speed limit, and the higher the speed limit is, the higher the early warning time T is1The larger, g is the gravitational constant.
Safe distance L corresponding to second laneOBCan be as follows:
wherein the content of the first and second substances,
is L2Maximum speed limit of the lane, mu2Represents L2Coefficient of friction of the roadway, T2Is shown at L2The time for reaction of the lane early warning can be determined according to the specific road speed limit, and the higher the speed limit is, the higher the early warning time T is2The larger.
For example, the collision risk area corresponding to the first lane may be a circular area with a diameter of a road segment between the target position point on the first lane and the intersection, and the collision risk area corresponding to the second lane may be a circular area with a diameter of a road segment between the target position point on the second lane and the intersection.
In this embodiment, the collision risk zone corresponding to the target lane includes a road segment between a target position point on the target lane and the intersection point, a distance between the target position point and the intersection point is a safe distance corresponding to the target lane, so that the size of the collision risk zone of different lanes is related to the characteristics of the lanes, and the accuracy of determining the collision risk of the vehicle running on the lane is high.
Optionally, the performing collision warning when it is determined that there is a collision risk between the first vehicle and the second vehicle according to the first time period and the second time period includes:
determining whether the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period;
under the condition that the first vehicle and the second vehicle are judged to have collision risks, sending a road passing prompt to a second target vehicle and sending a deceleration and slow running prompt to a third target vehicle;
wherein the second target vehicle is a preset type of vehicle of the first vehicle and the second vehicle, or the second target vehicle is a vehicle of the first vehicle and the second vehicle that is expected to arrive at the intersection first; the third target vehicle is a vehicle other than the second target vehicle, of the first vehicle and the second vehicle.
In addition, if there is a time overlap between the first time period and the second time period, it may be determined that there is a risk of collision between the first vehicle and the second vehicle; if there is no time overlap between the first time period and the second time period, it may be determined that there is no risk of collision between the first vehicle and the second vehicle. Illustratively, the first time period is: 9:20 to 9:22, the second time period being: 9:21 to 9:24, a first time period and a second time period overlap in time, it may be determined that the first vehicle and the second vehicle are at risk of collision. The sending of the road passing prompt to the second target vehicle and the sending of the deceleration and slow movement prompt to the third target vehicle may be sending of the road passing prompt to the second target vehicle through a 5G network and sending of the deceleration and slow movement prompt to the third target vehicle through the 5G network.
In addition, the preset type of vehicle can be a police vehicle, a fire truck, an ambulance and other vehicles bearing special tasks, and the preset type of vehicle is taken as a second target vehicle; alternatively, the time at which the first vehicle and the second vehicle are expected to reach the intersection may be calculated based on the positions and the speeds of the first vehicle and the second vehicle, and the vehicle that is expected to reach the intersection first may be taken as the second target vehicle.
For example, the risk of an entering and leaving collision may be calculated from the vehicle speed of the first vehicleRegion LOAFirst period of time L in betweenOA[Tin，Tout](ii) a Simultaneously calculating the risk of a second vehicle entering and leaving the collision zone LOBA second period of time L in betweenOB[Tin，Tout]. If L isOA[Tin，Tout]And LOB[Tin，Tout]If there is overlap, it can be considered that there is a risk of collision and road priority assignment is required.
In a case where it is determined that there is a risk of collision between the first vehicle and the second vehicle, it may be determined whether there is a vehicle of a preset type in the first vehicle and the second vehicle; if a preset type of vehicle exists, a road priority may be assigned to the preset type of vehicle; if there are no vehicles of the predetermined type, road priority may be assigned to vehicles that are expected to arrive first at the intersection. A road passage prompt may be sent to vehicles assigned a road priority and a slowdown prompt may be sent to vehicles not assigned a road priority.
In this embodiment, it is determined whether there is a risk of collision between the first vehicle and the second vehicle according to the first time period and the second time period, and when it is determined that there is a risk of collision between the first vehicle and the second vehicle, a road passing prompt is sent to a second target vehicle, and a deceleration and slow-moving prompt is sent to a third target vehicle, so that the collision risk warning effect is good.
As a specific implementation manner, as shown in fig. 2, the vehicle import early warning method may be applied to a vehicle import early warning system, and the vehicle import early warning system may include a plurality of sensors, an intelligent computing module, and a vehicle-side communication module. The plurality of sensors and the intelligent computing module can be communicated through optical fibers, and the intelligent computing module and the vehicle-end communication module can be communicated through a 5G network. As shown in fig. 3, the plurality of sensors may include a laser radar 1, a camera 2, and a millimeter wave radar 3. The intelligent computing module can comprise a perception fusion unit, a road priority distribution unit and a 5G communication unit. The vehicle merging early warning system can be used for solving the problem that the collision probability of the vehicles merging from the ramp is high under the condition of no traffic lights, and for example, as shown in fig. 3, the vehicle merging early warning system can be used for solving the problem that the collision probability of the first vehicle and the second vehicle at the intersection point is high when the first vehicle merges into the lane where the second vehicle is located. The vehicle immigration early warning system can realize road perception and road right of pass distribution based on 5G vehicle cooperation. The position and the speed of the vehicle can be acquired based on the millimeter wave radar, the laser radar and the camera, the road priority of the vehicle is calculated based on the intelligent calculation module, the calculated road priority is sent to the vehicle through the 5G network, the road priority of the ramp is distributed to the vehicle, the collision risk is reduced, and the driving safety of the vehicle is guaranteed.
For example, the ramp merging scenario may be as shown in fig. 4, assuming that: the lanes where the ramps merge are L1 and L2, the intersection point 4 of L1 and L2 is the intersection point of the central line of L1 and the central line of L2, the collision risk area corresponding to the L1 lane comprises a road section OA, and the collision risk area corresponding to the L2 lane comprises a road section OB. L1 and L2 are both one-way lanes, composite lanes such as 'straight going-right turning' and the like are not considered, and turning is not considered; vehicles on the ramp L2 converge into the main lane L1, and vehicles on the L3 lane do not change into the main lane L1; only motor vehicles are considered, and special condition interference such as pedestrians, non-motor vehicles, obstacles and the like is not supposed to exist. Whether vehicles enter two lanes merged into a ramp or not can be identified, D-S evidence reasoning can be carried out according to identification data of a millimeter wave radar, a laser radar and a camera, a first vehicle and a second vehicle are determined based on a reasoning result, and moving state data of the first vehicle and the second vehicle are obtained, wherein the moving state data comprise speed, position and orientation; the positions of the first vehicle and the second vehicle can be searched in a high-precision map, and a first lane L1 where the first vehicle is located and a second lane L2 where the second vehicle is located are determined; a first time period when the first vehicle passes through a collision risk area corresponding to the first lane can be determined according to the movement state data of the first vehicle, and a second time period when the second vehicle passes through the collision risk area corresponding to the second lane can be determined according to the movement state data of the second vehicle; and under the condition that time overlaps exists between the first time period and the second time period, judging that the first vehicle and the second vehicle have a collision risk, and performing collision early warning.
It should be noted that the vehicle intrusion warning system can be used for vehicle-road coordination, and the vehicle-road coordination usually involves three terminals: the vehicle end, the road side end and the cloud end are provided with computing nodes generally. Because the vehicle-road cooperation requires lower time delay, the calculation node can be sunk to the road side end in the embodiment of the invention, the perception fusion function of merging vehicles into a ramp is carried out at the road side end, and the function realized by the fusion of multiple sensors is far superior to the function sum which can be realized by the independent sensors. The use of different kinds of sensors may additionally provide a certain redundancy in the case of an environmental condition where all of one kind of sensors fail. The different types of sensors have respective advantages, and the camera is sensitive to the color and texture of the target object, so that tasks such as target classification, detection, segmentation, identification and the like can be completed; the laser radar can obtain accurate 3D information of a target object, and the detection range can reach 150 meters; the millimeter wave radar can provide accurate distance and speed information, has a long detection distance and can work all the day.
In the embodiment of the invention, multi-sensor target data layer fusion in automatic driving sensing and positioning is applied, a vehicle-road cooperative computing node is sunk to a road side end of a road edge, each sensor is used for independently generating identification data, a road side intelligent computing module is used for fusion to realize sensing fusion, analysis and extraction are carried out according to moving state data of vehicles, and ramp road right of way is distributed according to the principles of efficiency and safety. A5G communication unit is arranged in the roadside end, vehicles interact with road infrastructure through an edge gateway through 5G, the sensing range is improved, and a road right-of-way distribution structure of a ramp is obtained, so that cooperation between vehicles and roads is achieved, and the probability of accidents is reduced through means of accident early warning and avoidance.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a vehicle entrance warning apparatus according to an embodiment of the present invention, and as shown in fig. 5, a vehicle entrance warning apparatus 200 includes:
a first obtaining module 201, configured to obtain moving state data of a first vehicle and moving state data of a second vehicle, respectively, where the first vehicle travels in a first lane, the second vehicle travels in a second lane, and an intersection exists between the first lane and the second lane;
a first determining module 202, configured to determine, according to the movement state data of the first vehicle, a first time period when the first vehicle passes through a collision risk zone corresponding to the first lane, and determine, according to the movement state data of the second vehicle, a second time period when the second vehicle passes through a collision risk zone corresponding to the second lane, where the collision risk zone is an area including the intersection;
and the early warning module 203 is configured to perform collision early warning when it is determined that the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period.
Optionally, as shown in fig. 6, the apparatus 200 further includes:
a second obtaining module 204, configured to obtain identification data corresponding to each sensor in at least one sensor, where the identification data corresponding to each sensor is data obtained by identifying a target object moving on the first lane or the second lane;
a second determining module 205, configured to perform D-S evidence reasoning according to the identification data, and determine whether the target object is a first target vehicle;
wherein, when it is determined that the target object is the first target vehicle, movement state data of the first target vehicle is acquired, the first target vehicle being the first vehicle or the second vehicle.
Optionally, the identification data comprises a probability value of the target object belonging to each of a plurality of object categories, the plurality of object categories comprising vehicles;
the second determining module 205 is specifically configured to:
performing fusion calculation on the probability value corresponding to each object type aiming at the at least one sensor according to a D-S evidence synthesis rule to obtain a basic credible number corresponding to each object type;
taking the object class corresponding to the maximum basic credibility number in the basic credibility numbers corresponding to the object classes as the object class to which the target object belongs;
determining whether the target object is a first target vehicle based on an object class to which the target object belongs;
wherein, when the object class to which the target object belongs is a vehicle, it is determined that the target object is the first target vehicle.
Optionally, the second obtaining module 204 is specifically configured to:
acquiring identification data corresponding to each sensor in at least one sensor at the current sampling moment;
acquiring identification data corresponding to each sensor at the previous sampling moment;
and respectively fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the previous sampling moment to obtain the identification data corresponding to each sensor.
Optionally, the identification data includes the movement state data and probability values corresponding to the movement state data, and the number of the sensors is multiple;
as shown in fig. 7, the apparatus 200 further includes:
a third determining module 206, configured to determine moving state data corresponding to the target object according to the moving state data identified by the at least one sensor and the corresponding probability value;
the moving state data corresponding to the target object is the moving state data with the maximum probability value in the moving state data obtained by the at least one sensor through identification.
Optionally, the collision risk area corresponding to the target lane includes a road section between a target position point on the target lane and the intersection point, a distance between the target position point and the intersection point is a safety distance corresponding to the target lane, the safety distance corresponding to the target lane is determined based on a highest speed limit of the target lane, and the target lane is the first lane or the second lane.
Optionally, the early warning module 203 is specifically configured to:
determining whether the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period;
under the condition that the first vehicle and the second vehicle are judged to have collision risks, sending a road passing prompt to a second target vehicle and sending a deceleration and slow running prompt to a third target vehicle;
wherein the second target vehicle is a preset type of vehicle of the first vehicle and the second vehicle, or the second target vehicle is a vehicle of the first vehicle and the second vehicle that is expected to arrive at the intersection first; the third target vehicle is a vehicle other than the second target vehicle, of the first vehicle and the second vehicle.
The vehicle entry early warning device can realize each process realized in the method embodiment of fig. 1, and can achieve the same technical effect, and is not described herein again to avoid repetition.
As shown in fig. 8, an embodiment of the present invention further provides an electronic device 300, including: the vehicle immigration early warning system comprises a processor 301, a memory 302 and a program which is stored in the memory 302 and can run on the processor 301, wherein the program realizes each process of the vehicle immigration early warning method embodiment when being executed by the processor 301, and can achieve the same technical effect, and in order to avoid repetition, the description is omitted here.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the above-mentioned vehicle entry early warning method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer readable storage medium is, for example, ROM, RAM, magnetic disk or optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. A vehicle intrusion warning method, comprising:
respectively acquiring moving state data of a first vehicle and moving state data of a second vehicle, wherein the first vehicle runs in a first lane, the second vehicle runs in a second lane, and an intersection point exists between the first lane and the second lane;
determining a first time period when the first vehicle passes through a collision risk area corresponding to the first lane according to the movement state data of the first vehicle, and determining a second time period when the second vehicle passes through the collision risk area corresponding to the second lane according to the movement state data of the second vehicle, wherein the collision risk area is an area including the junction;
performing collision early warning under the condition that the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period;
the collision risk area corresponding to the target lane comprises a road section between a target position point on the target lane and the intersection point, the distance between the target position point and the intersection point is a safe distance corresponding to the target lane, the safe distance corresponding to the target lane is determined based on the highest speed limit of the target lane, and the target lane is the first lane or the second lane;
the first lane L1Corresponding safety distance LOAComprises the following steps:
wherein the content of the first and second substances,
is L1Maximum speed limit of the lane, mu1Represents L1Coefficient of friction of the roadway, T1Is shown at L1The lane early-warning method comprises the steps of early warning time for reaction by a lane, wherein g is a gravity constant;
the safe distance L corresponding to the second laneOBComprises the following steps:
wherein, the first and the second end of the pipe are connected with each other,
is L2Maximum speed limit of the lane, mu2Represents L2Coefficient of friction of the roadway, T2Is shown at L2The lane warns ahead of time for reaction.
2. The method of claim 1, wherein prior to obtaining the movement state data of the first vehicle and the second vehicle, the method further comprises:
acquiring identification data corresponding to each sensor in at least one sensor, wherein the identification data corresponding to each sensor is data obtained by identifying a target object moving on the first lane or the second lane;
D-S evidence reasoning is carried out according to the identification data, and whether the target object is a first target vehicle or not is determined;
wherein, when it is determined that the target object is the first target vehicle, movement state data of the first target vehicle is acquired, the first target vehicle being the first vehicle or the second vehicle.
3. The method of claim 2, wherein the identification data comprises a probability value of the target object belonging to each of a plurality of object categories, the plurality of object categories comprising vehicles;
the performing D-S evidence reasoning according to the identification data to determine whether the target object is a first target vehicle comprises:
performing fusion calculation on the probability value corresponding to each object type aiming at the at least one sensor according to a D-S evidence synthesis rule to obtain a basic credible number corresponding to each object type;
taking the object class corresponding to the maximum basic credibility number in the basic credibility numbers corresponding to the object classes as the object class to which the target object belongs;
determining whether the target object is a first target vehicle based on an object class to which the target object belongs;
wherein, when the object class to which the target object belongs is a vehicle, it is determined that the target object is the first target vehicle.
4. The method of claim 2, wherein the obtaining identification data corresponding to each of the at least one sensor comprises:
acquiring identification data corresponding to each sensor in at least one sensor at the current sampling moment;
acquiring identification data corresponding to each sensor at the previous sampling moment;
and respectively fusing the identification data corresponding to each sensor at the current sampling moment and the identification data corresponding to each sensor at the previous sampling moment to obtain the identification data corresponding to each sensor.
5. The method of claim 2, wherein the identification data comprises the movement state data and probability values corresponding to the movement state data, and the number of the sensors is plural;
after obtaining the identification data corresponding to each sensor of the at least one sensor, the method further includes:
determining moving state data corresponding to the target object according to the moving state data obtained by the at least one sensor through identification and the corresponding probability value;
the moving state data corresponding to the target object is the moving state data with the maximum probability value in the moving state data obtained by the at least one sensor through identification.
6. The method of claim 1, wherein the performing collision warning if it is determined that the first vehicle and the second vehicle are at risk of collision based on the first time period and the second time period comprises:
determining whether the first vehicle and the second vehicle have a collision risk according to the first time period and the second time period;
under the condition that the first vehicle and the second vehicle are judged to have collision risks, a road passing prompt is sent to a second target vehicle, and a deceleration and slow running prompt is sent to a third target vehicle;
wherein the second target vehicle is a preset type of vehicle of the first vehicle and the second vehicle, or the second target vehicle is a vehicle of the first vehicle and the second vehicle that is expected to arrive at the intersection first; the third target vehicle is a vehicle other than the second target vehicle, of the first vehicle and the second vehicle.
7. A vehicle intrusion warning device, comprising:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for respectively acquiring movement state data of a first vehicle and movement state data of a second vehicle, the first vehicle runs in a first lane, the second vehicle runs in a second lane, and an intersection point exists between the first lane and the second lane;
the first determining module is used for determining a first time period when the first vehicle passes through a collision risk area corresponding to the first lane according to the movement state data of the first vehicle, and determining a second time period when the second vehicle passes through the collision risk area corresponding to the second lane according to the movement state data of the second vehicle, wherein the collision risk area is an area including the junction;
the early warning module is used for carrying out collision early warning under the condition that the first vehicle and the second vehicle are judged to have collision risks according to the first time period and the second time period;
the collision risk area corresponding to the target lane comprises a road section between a target position point on the target lane and the intersection point, the distance between the target position point and the intersection point is a safe distance corresponding to the target lane, the safe distance corresponding to the target lane is determined based on the highest speed limit of the target lane, and the target lane is the first lane or the second lane;
the first lane L1Corresponding safety distance LOAComprises the following steps:
wherein the content of the first and second substances,
is L1Maximum speed limit of the lane, mu1Represents L1Coefficient of friction of the roadway, T1Is shown at L1The lane early-warning method comprises the steps of early warning time for reaction by a lane, wherein g is a gravity constant;
the safe distance L corresponding to the second laneOBComprises the following steps:
wherein the content of the first and second substances,
is L2Maximum speed limit of the lane, mu2Represents L2Coefficient of friction of the roadway, T2Is shown at L2The lane warns ahead of time for reaction.
8. An electronic device, comprising: a processor, a memory and a program stored on the memory and executable on the processor, the program when executed by the processor implementing the steps of the vehicle ingress warning method as claimed in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the vehicle intrusion warning method according to one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110534828.5A CN113178081B (en) | 2021-05-17 | 2021-05-17 | Vehicle immission early warning method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110534828.5A CN113178081B (en) | 2021-05-17 | 2021-05-17 | Vehicle immission early warning method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113178081A CN113178081A (en) | 2021-07-27 |
| CN113178081B true CN113178081B (en) | 2022-05-03 |
Family
ID=76929229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110534828.5A Active CN113178081B (en) | 2021-05-17 | 2021-05-17 | Vehicle immission early warning method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113178081B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113911111B (en) * | 2021-10-19 | 2024-03-26 | 中国第一汽车股份有限公司 | Vehicle collision detection method, system, electronic device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110299006A (en) * | 2019-06-28 | 2019-10-01 | 浙江吉利控股集团有限公司 | A kind of vehicle collision alarm method, device and equipment |
| CN111091721A (en) * | 2019-12-23 | 2020-05-01 | 清华大学 | Ramp confluence control method and system for intelligent train traffic system |
| CN111292557A (en) * | 2020-02-19 | 2020-06-16 | 安徽达尔智能控制系统股份有限公司 | Non-lamp control intersection safety early warning method and system based on vehicle speed control |
| CN111532274A (en) * | 2020-02-28 | 2020-08-14 | 南京航空航天大学 | Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion |
| CN112416004A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Control method and device based on automatic driving, vehicle and related equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469617A (en) * | 2014-08-20 | 2016-04-06 | 中兴通讯股份有限公司 | Driving safety assisting method and driving safety assisting device |
| CN106114507B (en) * | 2016-06-21 | 2018-04-03 | 百度在线网络技术（北京）有限公司 | Local path planning method and device for intelligent vehicle |
| US10783787B2 (en) * | 2017-05-31 | 2020-09-22 | Regents Of The University Of Minnesota | Freeway queue warning system |
| CN111354225B (en) * | 2020-03-03 | 2022-05-03 | 中交第一公路勘察设计研究院有限公司 | Expressway vehicle accident risk assessment and early warning intervention method |
| CN111768652B (en) * | 2020-06-15 | 2022-05-10 | 长安大学 | Early warning device and method for vehicle collision at turnout of expressway diversion ramp |
-
2021
- 2021-05-17 CN CN202110534828.5A patent/CN113178081B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110299006A (en) * | 2019-06-28 | 2019-10-01 | 浙江吉利控股集团有限公司 | A kind of vehicle collision alarm method, device and equipment |
| CN111091721A (en) * | 2019-12-23 | 2020-05-01 | 清华大学 | Ramp confluence control method and system for intelligent train traffic system |
| CN111292557A (en) * | 2020-02-19 | 2020-06-16 | 安徽达尔智能控制系统股份有限公司 | Non-lamp control intersection safety early warning method and system based on vehicle speed control |
| CN111532274A (en) * | 2020-02-28 | 2020-08-14 | 南京航空航天大学 | Intelligent vehicle lane change auxiliary system and method based on multi-sensor data fusion |
| CN112416004A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Control method and device based on automatic driving, vehicle and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113178081A (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11024165B2 (en) | Driver behavior monitoring | |
| CN113165652B (en) | Verifying predicted trajectories using a mesh-based approach | |
| CN107346612B (en) | Vehicle anti-collision method and system based on Internet of vehicles | |
| RU2719495C2 (en) | Method and device for driving assistance | |
| JP5620147B2 (en) | Movable object prediction apparatus and program | |
| US11912286B2 (en) | Driving risk identification model calibration method and system | |
| CN113044059A (en) | Safety system for a vehicle | |
| WO2017123665A1 (en) | Driver behavior monitoring | |
| CN110738870A (en) | System and method for avoiding collision routes | |
| WO2019213982A1 (en) | Driver control behavior quantification method and device employing principle of least action | |
| CN112106124A (en) | System and method for using V2X and sensor data | |
| CN112606831A (en) | Anti-collision warning information external interaction method and system for passenger car | |
| CN113748448B (en) | Vehicle-based virtual stop-line and yield-line detection | |
| CN113178081B (en) | Vehicle immission early warning method and device and electronic equipment | |
| CN110606081B (en) | Moving body assistance system and moving body assistance method | |
| CN116052472A (en) | Vehicle-mounted V2X collision early warning method based on road perception information fusion | |
| US20230109909A1 (en) | Object detection using radar and lidar fusion | |
| CN115240470A (en) | NR-V2X-based weak traffic participant collision early warning system and method | |
| Lai et al. | Sensor fusion of camera and MMW radar based on machine learning for vehicles | |
| CN112927514B (en) | Motor vehicle yellow light running behavior prediction method and system based on 3D laser radar | |
| Manikandan et al. | Energy-aware vehicle/pedestrian detection and close movement alert at nighttime in dense slow traffic on Indian urban roads using a depth camera | |
| WO2023132055A1 (en) | Evaluation device, evaluation method, and program | |
| US11967230B2 (en) | System and method for using V2X and sensor data | |
| JP2024051893A (en) | Area monitoring system and area monitoring method | |
| JP2024051892A (en) | Area monitoring system and area monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |