CN116749968B - Target vehicle detection method, device, equipment and medium - Google Patents
Target vehicle detection method, device, equipment and medium Download PDFInfo
- Publication number
- CN116749968B CN116749968B CN202311029438.8A CN202311029438A CN116749968B CN 116749968 B CN116749968 B CN 116749968B CN 202311029438 A CN202311029438 A CN 202311029438A CN 116749968 B CN116749968 B CN 116749968B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driven
- current
- lane
- cut
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 58
- 238000004590 computer program Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 description 14
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 7
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 7
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/14—Adaptive cruise control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
Abstract
The invention discloses a method, a device, equipment and a medium for detecting a target vehicle, and relates to the field of detection. The method comprises the steps that through rasterization processing is carried out on the current to-be-driven area of the own vehicle, each grid of the current to-be-driven area has a corresponding value, the value of each grid represents the probability that the vehicle to be cut into the own vehicle lane enters the current to-be-driven area, and the probability that the vehicle to be cut into the own vehicle lane is in the current to-be-driven area is determined by taking the grids as units, so that the accuracy of selecting the target vehicle can be greatly improved; the value of the grid and the distance from the grid to the current track to be driven are in a negative correlation relationship in the direction perpendicular to the current track to be driven, namely, the closer the grid is to the current track to be driven, the larger the assignment of the grid is, otherwise, the smaller the assignment is, and therefore, the target vehicle can be accurately determined according to the size of the probability value by assigning different probability values to the grid of the area to be driven, and the accuracy of identifying the target vehicle is improved.
Description
Technical Field
The present invention relates to the field of detection, and in particular, to a method, apparatus, device, and medium for detecting a target vehicle.
Background
The adaptive cruise control (Adaptive Cruise Control, ACC) function in advanced driving assistance systems (Advanced Driving Assistance System, ADAS) requires the identification of a primary target for control, which is implemented in a primary target selection (Target Object Select, TOS) module. The main purpose of TOS is to select a front target for control use of ACC. The accuracy of target selection embodies the performance of the whole ACC.
For the target always running in front of the own vehicle, the selection is generally accurate. However, if the selection of the vehicle target to be cut into the self-lane is not accurate enough, the vehicle target which may affect the self-lane cannot be timely used as a reference, and planning of the running speed, the running route, and the like will have a great influence on the ACC performance.
Therefore, how to determine the target vehicle more accurately is a technical problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a medium for detecting a target vehicle, so as to solve the problem of low accuracy of a selected target vehicle.
In order to solve the above technical problems, the present invention provides a method for detecting a target vehicle, including:
Acquiring a current to-be-driven track of a self-vehicle and determining a current to-be-driven area of the self-vehicle according to the current to-be-driven track;
carrying out rasterization processing on the current area to be driven and assigning a value to each grid; the value of each grid is used for representing the probability that a vehicle to be cut into a vehicle lane enters the current region to be driven; the value of the grid and the distance between the grid and the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship;
acquiring the position of the vehicle to be cut into the vehicle lane and determining the probability of the vehicle to be cut into the vehicle lane in the current to-be-driven area according to the value of the grid corresponding to the position;
and determining a target vehicle from the vehicles to be cut into the self-vehicle lane according to the probability that the vehicles to be cut into the self-vehicle lane are in the current driving area.
Preferably, the current track to be driven of the self-vehicle comprises one of the following modes:
mode one: determining the current track to be driven of the own vehicle according to the driving parameters of the own vehicle; wherein the driving parameters at least comprise: steering wheel angle, yaw rate;
Mode two: under the condition that two side lane lines in the current track direction to be driven are detected, determining a center lane line between the two side lane lines; taking the central lane line as the current track to be driven of the own vehicle;
mode three: the current track to be driven comprises a first section of current track to be driven and a second section of current track to be driven; the moment when the first section of current track to be driven is generated is earlier than the moment when the second section of current track to be driven is generated;
determining the current track to be driven of the first section of the own vehicle according to the driving parameters of the own vehicle;
determining the center lane line between the two side lane lines under the condition that the two side lane lines of the current track direction to be driven are detected; taking the central lane line as the current track to be driven of the second section of the own vehicle; connecting the first section of current track to be driven and the second section of current track to be driven to serve as the current track to be driven of the self-vehicle;
under the condition that the lane lines on the two sides of the current track to be driven are not detected, extending the first section of current track to be driven along the current track to be driven; taking an extension line of the first section of current track to be driven as the second section of current track to be driven; and connecting the first section of current track to be driven with the second section of current track to be driven to serve as the current track to be driven of the self-vehicle.
Preferably, the determining the current waiting area of the own vehicle according to the current waiting track includes:
respectively widening preset areas at two sides of the current track to be driven;
taking the widened area as the current area to be driven of the own vehicle;
the preset area is a half area of a lane area formed by the two side lane lines when the two side lane lines in the current track direction to be driven are detected;
and under the condition that the lane lines at the two sides of the current to-be-driven track direction are not detected, the preset area is a half standard lane area.
Preferably, the rasterizing the current area to be driven includes:
determining the size of each grid according to the preset result accuracy of determining the target vehicle;
and carrying out rasterization processing on the current area to be driven according to the size of each grid.
Preferably, the value of the grid is in positive correlation with the distance of the grid from the own vehicle in the current track direction to be driven.
Preferably, the obtaining the position of the vehicle to be cut into the self-vehicle lane and determining the probability of the vehicle to be cut into the self-vehicle lane in the current driving area according to the value of the grid corresponding to the position includes:
Acquiring coordinates of the length, width and rear center point of the vehicle to be cut into the vehicle lane;
determining coordinates of four corner points of the vehicle to be cut into the vehicle lane as positions of the vehicle to be cut into the vehicle lane according to the length, the width and the coordinates of the rear center point of the vehicle to be cut into the vehicle lane;
if the coordinates of the current corner point fall in the current area to be driven, determining that the probability that the current corner point of the vehicle to be cut into the vehicle lane is in the current area to be driven is the value of the grid corresponding to the current corner point;
if the coordinates of the current corner point do not fall in the current area to be driven, determining that the value of the current corner point corresponding to the grid is 0; and determining that the probability of the current corner point of the vehicle to be cut into the self-vehicle lane in the current to-be-driven area is 0 according to the value of the grid.
Preferably, determining the probability of each corner in the current area to be travelled includes:
acquiring the probability of each angular point in the current area to be driven in a plurality of preset periods;
and carrying out low-pass filtering on the probabilities of the same angular points in the current region to be driven in a plurality of preset periods to obtain the final probability of each angular point in the current region to be driven.
Preferably, the determining the target vehicle from the vehicles to be cut into the self-vehicle lane according to the probability that the vehicles to be cut into the self-vehicle lane are in the current driving area comprises:
obtaining the maximum probability of the four corner points of the vehicle to be cut into the self-vehicle lane in the current region to be driven as the corresponding probability of the vehicle to be cut into the self-vehicle lane in the current region to be driven;
when the probability of the vehicle to be cut into the self-vehicle lane in the current to-be-driven area is larger than a threshold value, taking the vehicle to be cut into the self-vehicle lane as a candidate main target vehicle;
and acquiring the candidate main target vehicle closest to the own vehicle in the current track direction to be driven from the candidate main target vehicle as the target vehicle.
Preferably, the threshold value corresponding to each corner point of the vehicle to be cut into the lane of the own vehicle is different, wherein the threshold value and the distance between each corner point and the own vehicle in the direction perpendicular to the current track to be driven have a negative correlation.
In order to solve the above technical problem, the present invention further provides a detection apparatus for a target vehicle, including:
The acquisition module is used for acquiring the current to-be-driven track of the self-vehicle and determining the current to-be-driven area of the self-vehicle according to the current to-be-driven track;
the processing and assigning module is used for carrying out rasterization processing on the current area to be driven and assigning values to the grids; the value of each grid is used for representing the probability that a vehicle to be cut into a vehicle lane enters the current region to be driven; the value of the grid and the distance between the grid and the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship;
the acquisition and determination module is used for acquiring the position of the vehicle to be cut into the vehicle lane and determining the probability of the vehicle to be cut into the vehicle lane in the current to-be-driven area according to the grid value corresponding to the position;
and the determining module is used for determining a target vehicle from the vehicles to be cut into the self-vehicle lane according to the probability that the vehicles to be cut into the self-vehicle lane are in the current driving area.
In order to solve the above technical problem, the present invention further provides a detection apparatus for a target vehicle, including:
a memory for storing a computer program;
And the processor is used for realizing the steps of the target vehicle detection method when executing the computer program.
In order to solve the above technical problem, the present invention further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method for detecting a target vehicle described above.
The invention provides a target vehicle detection method, which comprises the steps of carrying out rasterization processing on a current to-be-driven area of a vehicle and assigning values to grids; determining the probability of the vehicle to be cut into the vehicle lane in the current region to be driven according to the value of the grid corresponding to the position of the vehicle to be cut into the vehicle lane; and finally, determining the target vehicle according to the probability that the vehicle to be cut into the vehicle lane is in the current area to be driven. Therefore, when the position of the vehicle to be cut into the self-vehicle lane is determined, the probability of the vehicle to be cut into the self-vehicle lane in the current region to be driven can be determined by taking the grid as a unit, so that the accuracy of selecting the target vehicle can be greatly improved; in addition, when the grids are assigned, the value of the grids and the distance between the grids and the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship, namely, the closer the grids are to the current track to be driven, the larger the assignment to the grids is, otherwise, the smaller the assignment is, and the target vehicles can be accurately determined according to the size of the probability values by assigning different probability values to the grids of the area to be driven, so that the accuracy of identifying the target vehicles is improved.
In addition, the invention also provides a detection device of the target vehicle, a detection device of the target vehicle and a computer readable storage medium, which have the same or corresponding technical characteristics as the detection method of the target vehicle, and the effects are the same.
Drawings
For a clearer description of embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described, it being apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
Fig. 1 is a flowchart of a method for detecting a target vehicle according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a driving area rasterizing process according to an embodiment of the present invention;
FIG. 3 is a schematic illustration of a vehicle to be cut into a host lane according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a method for calculating four particle coordinates of a vehicle to be cut into a host lane according to an embodiment of the present invention;
fig. 5 is a block diagram of a detection device for a target vehicle according to an embodiment of the present invention;
Fig. 6 is a block diagram of a detection apparatus for a target vehicle according to another embodiment of the present invention;
fig. 7 is a flowchart of a target vehicle selection method based on travel area rasterization according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without making any inventive effort are within the scope of the present invention.
The invention provides a method, a device, equipment and a medium for detecting a target vehicle, which are used for accurately determining the target vehicle.
The ACC function in the ADAS needs to identify a main target for control, and the identification of the main target is implemented in the TOS module. The main purpose of TOS is to select a front target for control use of ACC. The accuracy of target selection embodies the performance of the whole ACC.
For the target always running in front of the own vehicle, the selection is generally accurate. However, if the selection of the vehicle target to be cut into the self-lane is not accurate enough, the vehicle target which may affect the self-lane cannot be timely used as a reference, and planning of the running speed, the running route, and the like will have a great influence on the ACC performance. If the speed of the two targets cut into the vehicle is slower than the speed of the own vehicle, if the cut-into vehicle targets cannot be accurately determined, the ACC cannot program the deceleration in time for the actuator to execute, and the risk of rear-end collision is possibly caused.
Therefore, the invention provides a detection method of a target vehicle, wherein the target vehicle is detected according to the probability that the vehicle to be cut into a vehicle lane enters the vehicle to be driven area and the probability that the vehicle to be cut into the vehicle lane enters the vehicle to be driven area by carrying out rasterization processing on the vehicle to be driven area and giving different probability values to each grid and determining the probability that the vehicle to be cut into the vehicle to be driven area according to the probability that the grid corresponding to the position of the vehicle to be cut into the vehicle to be driven. It should be noted that, the method for detecting the target vehicle provided by the invention is not only applicable to the forward driving path, but also can be a reversing path, a parking path and the like.
In order to better understand the aspects of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description. Fig. 1 is a flowchart of a method for detecting a target vehicle according to an embodiment of the present invention, as shown in fig. 1, where the method includes:
s10: acquiring a current to-be-driven track of the own vehicle and determining a current to-be-driven area of the own vehicle according to the current to-be-driven track;
s11: carrying out rasterization processing on the current area to be driven and assigning values to each grid;
the value of each grid is used for representing the probability that a vehicle to be cut into a vehicle lane enters a current region to be driven; the value of the grid and the distance from the grid to the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship;
S12: acquiring the position of a vehicle to be cut into a vehicle lane and determining the probability of the vehicle to be cut into the vehicle lane in a current to-be-driven area according to the value of a grid corresponding to the position;
s13: and determining the target vehicle from the vehicles to be cut into the self-vehicle lane according to the probability that the vehicles to be cut into the self-vehicle lane are in the current driving area.
First, a host vehicle and a vehicle to be cut into a host lane will be described. If the vehicle a runs on the lane 1, the vehicle B runs on the lane 2, and the vehicle B is about to cut into the lane 1 where the vehicle a is located, the vehicle a is called a vehicle itself, and the vehicle B is called a vehicle to be cut into the vehicle itself. The current track to be driven of the own vehicle can be determined according to the driving parameters, lane lines and the like of the own vehicle. When the current to-be-driven area of the own vehicle is determined according to the current to-be-driven track of the own vehicle, the current to-be-driven track of the own vehicle can be taken as a central line, and the two sides of the current to-be-driven track of the own vehicle are respectively expanded by a certain width value so as to be used as the current to-be-driven area of the own vehicle. In practice, the length of the current area to be travelled (along the current trajectory to be travelled) of the vehicle is determined according to the distance that can be detected by the detector on the vehicle. The width values of the two-side extensions are not limited, and are determined according to practical situations. If the expanded width value is too large, the determined area to be driven is too large, and the vehicle is likely to not drive on the determined area to be driven completely at last; if the width of the extension is too small (smaller than the width of the whole vehicle), the determined area to be driven is too small and cannot completely cover the area to be driven of the vehicle, so that in practice, if lane lines on the left and right sides can be detected, the extension width can be determined according to the lane lines on the left and right sides of the vehicle; if the lane line is blocked, the lane line cannot be detected, and the expanded width can be determined by the width (3.7 m) of the standard lane. In addition, it is noted that when the vehicle is running forward, the current track to be run and the current area to be run are both located in front of the head of the vehicle; when the vehicle is reversed, the current track to be driven and the current area to be driven are both positioned behind the tail of the vehicle.
In the process of driving a vehicle in a vehicle lane, the condition that the vehicle in another vehicle lane is to cut into the vehicle lane often occurs. In the forward running process, a vehicle on the left side of the vehicle may cut into the vehicle lane or a vehicle on the right side of the vehicle may cut into the vehicle lane, and if the vehicle to enter the vehicle lane cannot be determined accurately, the running speed, direction and the like of the vehicle cannot be adjusted in time according to the speed of the vehicle to enter the vehicle lane, so that a safety problem is caused. Therefore, in this embodiment, the determined area to be traveled of the own vehicle is rasterized.
The size of the grid divided from the area to be driven of the own vehicle is not limited, and is determined according to practical situations, for example, 50cm×50cm as the size of one grid. The rasterizing processing of the current area to be driven comprises the following steps: determining the size of each grid according to the preset result accuracy of determining the target vehicle; and rasterizing the current area to be driven according to the size of each grid. The accuracy of the preset result of determining the target vehicle is not limited, and the result is determined according to actual requirements. It should be noted that, if the size of the grid is too small, although the accuracy of the determined target vehicle is higher, the calculation amount is increased correspondingly, and in practice, if the size of the grid is too small, it is not significant, as in the embodiment of the present invention, if 4 particles are selected, the coordinates and probabilities of the rest of the particles do not need to be obtained, so that the size of the grid does not need to be too small; if the grid size is too large, the accuracy of the determined target vehicle may be low, so that in practice, a suitable grid size is selected. After the size of each grid is determined, the number of grids in the whole current area to be driven can be determined according to the current area to be driven of the own vehicle.
In the process of entering the current waiting areaAfter the rasterization processing, each grid is assigned, and because the value of each grid is used for representing the probability that the vehicle to be cut into the vehicle lane enters the current region to be driven, the assignment of each grid can be directly called probability assignment to the grid. In order to accurately determine the target vehicle, in this embodiment, when each grid is assigned, the value of the grid and the distance between the grid and the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship, that is, the distance between the grid and the current track to be driven in the direction perpendicular to the current track to be driven is far, and the assigned value of the grid is small; otherwise, the grid is assigned a larger value. Specifically, assuming that the host vehicle travels forward, the direction perpendicular to the current trajectory to be traveled is the direction perpendicular to the direction of travel of the host vehicle, and the value of the grid and the distance of the grid from the current trajectory to be traveled in the direction perpendicular to the direction of travel of the host vehicle are in a negative correlation. In addition, when the grid is far from the own vehicle, even if the vehicle cut into the own lane enters the grid, the own vehicle does not need to perform processing in time, so that in practice, the value of the grid has a positive correlation with the distance from the own vehicle in the current track direction to be driven. Fig. 2 is a schematic diagram of a process of rasterizing a driving area according to an embodiment of the present invention, and in fig. 2, a vehicle enters a current area to be driven from the last row from bottom to top. The probability value of each grid represents the probability that a vehicle to be cut into a vehicle lane enters a current region to be driven by the vehicle, and the probability is larger, namely the probability that a target is in the current region to be driven by the vehicle is larger; secondly, each grid is assigned in a differentiated mode, as shown in fig. 2, the probability of the grid which is closer to the current to-be-driven track of the own vehicle is larger, and the probability of the target vehicle in the area in the current to-be-driven area of the own vehicle is larger; in contrast, the farther the grid is from the current track to be traveled by the own vehicle, the smaller the probability value is, indicating that the target vehicle is less likely to be within the current track to be traveled by the own vehicle. Therefore, the magnitude relation of the probability values in fig. 2 is as follows: p (P) 0 <P 1 <P 2 <P 3 . Further, the longitudinal direction in fig. 2 indicates the distance of the grid from the own vehicle, and the more the upper grid is, the more the distance from the own vehicle is, as described aboveAs described, when the grid is far from the own vehicle, even if the vehicle cut into the own lane is entered into the grid, the own vehicle is not required to make a timely process, and thus the value of the grid at the uppermost is given as P 0 (minimum).
After determining the value of each grid, the vehicle to be cut into the own lane is determined. In order to determine whether a vehicle to be cut into the host lane is approaching, a sensor on the host vehicle may detect whether a vehicle is approaching, and if so, the vehicle may be defined as a vehicle to be cut into the host lane. When the vehicle runs forward, the attention is paid to the vehicle to be cut into the vehicle lane in the left side direction and the right side direction of the head of the vehicle; when the own vehicle is running in reverse, attention is paid to the vehicle to be cut into the own vehicle lane in the left side direction of the tail and the right side direction of the tail of the own vehicle. When the vehicle position of the vehicle to be cut into the vehicle lane is obtained, the distance between the vehicle to be cut into the vehicle lane and the vehicle can be positioned according to the distance sensor; however, in this embodiment, since the region to be driven is rasterized, that is, each grid has its own corresponding position coordinate (x, y), in order to accurately determine the position of the vehicle to be cut into the vehicle lane, in this embodiment, the position coordinate of the vehicle to be cut into the vehicle lane needs to be accurately determined. The coordinates of the center point of the tail of the vehicle to be cut into the vehicle lane can be obtained in real time, so that the position of the vehicle to be cut into the vehicle lane can be determined according to the center point of the tail of the vehicle.
After the vehicle position of the vehicle lane to be cut in is obtained, matching can be carried out according to the vehicle position of the vehicle lane to be cut in and grid coordinates, a grid where the vehicle position of the vehicle lane to be cut in falls is determined, and then the probability that the vehicle of the vehicle lane to be cut in enters the current area to be driven is determined according to the value of the grid.
When the probability that the vehicle to be cut into the vehicle lane enters the current region to be driven is greater than the threshold value, it can be determined that the vehicle to be cut into the vehicle lane is the target vehicle (the vehicle is closer to the vehicle), and it is required to be noted that in practice, the probability that the vehicle enters the current region to be driven is greater due to the fact that the vehicle is closer to the vehicle driving side by side, so that the embodiment of the invention further judges the longitudinal distance between the vehicle to be cut into the vehicle lane, which is greater than the threshold value, and takes the vehicle to be cut into the vehicle lane closest to the vehicle as the target vehicle.
The detection method of the target vehicle comprises the steps of carrying out rasterization processing on the current area to be driven of the own vehicle and assigning values to grids; determining the probability of the vehicle to be cut into the vehicle lane in the current region to be driven according to the value of the grid corresponding to the position of the vehicle to be cut into the vehicle lane; and finally, determining the target vehicle according to the probability that the vehicle to be cut into the vehicle lane is in the current area to be driven. Therefore, when the position of the vehicle to be cut into the self-vehicle lane is determined, the probability of the vehicle to be cut into the self-vehicle lane in the current region to be driven can be determined by taking the grid as a unit, so that the accuracy of selecting the target vehicle can be greatly improved; in addition, when the grids are assigned, the value of the grids and the distance between the grids and the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship, namely, the closer the grids are to the current track to be driven, the larger the assignment to the grids is, otherwise, the smaller the assignment is, and the target vehicles can be accurately determined according to the size of the probability values by assigning different probability values to the grids of the area to be driven, so that the accuracy of identifying the target vehicles is improved.
In order to determine the current track to be traveled by the vehicle, in an implementation, the current track to be traveled by the vehicle is obtained by one of the following means:
mode one: determining the current track to be driven of the own vehicle according to the driving parameters of the own vehicle; wherein, the driving parameters at least comprise: steering wheel angle, yaw rate;
mode two: under the condition that two side lane lines in the current track direction to be driven are detected, a center lane line between the two side lane lines is determined; taking the central lane line as the current track to be driven of the own vehicle;
mode three: the current track to be driven comprises a first section of current track to be driven and a second section of current track to be driven; the moment when the first section of current track to be driven is generated is earlier than the moment when the second section of current track to be driven is generated;
determining a first section of current track to be driven of the own vehicle according to the driving parameters of the own vehicle;
under the condition that two side lane lines in the current track direction to be driven are detected, a center lane line between the two side lane lines is determined; taking the central lane line as a second section of current track to be driven of the own vehicle; connecting the first section of current track to be driven and the second section of current track to be driven to serve as the current track to be driven of the own vehicle;
Under the condition that lane lines on two sides of the current track to be driven are not detected, extending the first section of current track to be driven along the current track to be driven; taking an extension line of the first section of current track to be driven as a second section of current track to be driven; and connecting the first section of current track to be driven with the second section of current track to be driven to serve as the current track to be driven of the own vehicle.
In the third mode, when determining the current track to be driven in the first section and in the first mode, the driving parameters of the vehicle are determined. Such as steering wheel angle, yaw rate (yawrate), and when both parameters are 0, determining that the current track to be traveled is a straight line.
When the current track to be driven of the second section is determined in the third mode and in the second mode, the sensor of the own vehicle detects that the lane lines can be clearly observed, and the center lane line between the lane lines at the two sides is used as the current track to be driven of the second section of the own vehicle.
In the method provided by the embodiment, the current track to be driven is acquired more flexibly.
On the basis of determining the current to-be-driven track in the above embodiment, determining the current to-be-driven area of the own vehicle according to the current to-be-driven track includes:
Respectively widening preset areas on two sides of a current track to be driven;
taking the widened area as a current area to be driven of the own vehicle;
under the condition that two side lane lines in the current track direction to be driven are detected, the preset area is a half area of a lane area formed by the two side lane lines;
and under the condition that lane lines on two sides of the current track direction to be driven are not detected, the preset area is a half standard lane area.
Taking a preset area as a half of a standard lane area as an example, under the condition that lane lines on two sides of the current track to be driven are not detected, widening the current track to be driven by 1.85m on two sides of the current track to be driven respectively, and determining the current area to be driven, wherein the width of the current area to be driven is the width of the standard lane area. In addition, the size of the listed grids is 50cm multiplied by 50cm, and at the moment, the current area to be driven obtained after the rasterization treatment is a grid with a plurality of rows and 8 columns; the number of rows is determined based on the distance that can be detected by the detector of the vehicle.
In the method provided by the embodiment, the mode of determining the current area to be driven is more flexible.
When the position of the vehicle to be cut into the own vehicle lane is calculated, the vehicle is regarded as a plurality of mass points, if the position of all the mass points is acquired, the calculated amount is large, and the target vehicle cannot be determined in time; if the selected particles are fewer or the selected particles are not suitable, the determined target vehicle is inaccurate and the target vehicle cannot be timely determined, so in implementation, obtaining the position of the vehicle to be cut into the vehicle lane and determining the probability of the vehicle to be cut into the vehicle lane in the current driving area according to the value of the grid corresponding to the position includes:
Acquiring coordinates of the length, width and rear center point of a vehicle to be cut into a self-vehicle lane;
determining coordinates of four corner points of the vehicle to be cut into the self-vehicle lane as positions of the vehicle to be cut into the self-vehicle lane according to the length, the width and the coordinates of the rear center point of the vehicle to be cut into the self-vehicle lane;
if the coordinates of the current corner point fall in the current area to be driven, determining the probability that the current corner point of the vehicle to be cut into the vehicle lane is in the current area to be driven as the value of the grid corresponding to the current corner point;
if the coordinates of the current corner point do not fall in the current area to be driven, determining that the value of the grid corresponding to the current corner point is 0; and determining that the probability of the current corner point of the vehicle to be cut into the self-vehicle lane in the current driving area is 0 according to the value of the grid.
Regarding the particle formation of the vehicle to be cut into the own vehicle lane, if the position of the vehicle to be cut into the own vehicle lane is determined by the position of only one particle in front of the left of the vehicle to be cut into the own vehicle lane, the target vehicle can be determined in time when the vehicle to be cut into the own vehicle lane is cutting into the own vehicle lane, but after cutting into the vehicle, the tail of the vehicle to be cut into the own vehicle lane may be close to the own vehicle distance, so that the own vehicle cannot be detected in time when the vehicle to be cut into the lane of the own vehicle is driven out, and rear-end collision may occur. Therefore, in this embodiment, according to the fact that the vehicle to be cut into the own vehicle lane is textured, and the mass points are four corner points of the vehicle to be cut into the own vehicle lane, the positions of the 4 vehicle lamps can be understood. Fig. 3 is a schematic illustration of a vehicle to be cut into a host lane according to an embodiment of the present invention. As shown in fig. 3, 1 is a host vehicle, and 2 is a vehicle to be cut into a host vehicle lane. The vehicle 2 to be cut into the own vehicle lane is atomized into C 1 、C 2 、C 3 、C 4 Wherein C 1 、C 4 Located at the head of the vehicle, C 2 、C 3 Is positioned at the tail of the vehicle, C 0 Representing the rear center point of the vehicle.
Since the coordinates of the rear center point of the vehicle to be cut into the own lane are available in real time, as shown in C in FIG. 3 0 And determining coordinates of four corner points of the vehicle to be cut into the self-vehicle lane according to the length, the width and the coordinates of the rear center point of the vehicle to be cut into the self-vehicle lane.
FIG. 4 shows the embodiment of the present inventionEmbodiments provide a schematic diagram that calculates four particle coordinates of a vehicle to be cut into a host lane. The coordinate system is established by the vehicle, and the coordinates of the vehicle to be cut into the lane of the vehicle under the coordinate system are (x) 0 ，y 0 ) The angle between the center line of the vehicle to be cut into the own vehicle lane and the center line of the own vehicle is θ (the angle between the vehicle to be cut into the own vehicle lane and the own vehicle is represented by), L represents the length of the vehicle to be cut into the own vehicle lane, W represents the width of the vehicle to be cut into the own vehicle lane, and C is assumed 1 Is (x) 1 ，y 1 ），C 2 Is (x) 2 ，y 2 ），C 3 Is (x) 3 ，y 3 ），C 4 Is (x) 4 ，y 4 ) C is then 1 The coordinates of (2) are calculated as follows:
x 1 = x 0 -L*sinθ-W/2*cosθ；
y 1 = y 0 + L*cosθ-W/2*sinθ。
C 2 the coordinates of (2) are calculated as follows:
x 2 = x 0 -W/2*cosθ；
y 2 = y 0 -W/2*sinθ。
C 3 the coordinates of (2) are calculated as follows:
x 3 = x 0 +W/2*cosθ；
y 3 = y 0 +W/2*sinθ。
C 4 the coordinates of (2) are calculated as follows:
x 4 = x 0 -L*sinθ+W/2*cosθ；
y 4 = y 0 + L*cosθ+W/2*sinθ。
it can be seen that the relationship of the four corner points relative to the vehicle is calculated according to the length and width of the target and the included angle between the target and the vehicle. Judging whether each angular point is positioned in a grid of a current area to be driven of the vehicle according to the calculated position relation of each angular point relative to the vehicle, and if not, judging that the probability of the angular point in the current area to be driven of the vehicle is 0; if the vehicle is in the current area to be driven, judging which grid the corner falls in, and giving the probability value of the grid to the corner.
The embodiment provides a vehicle to be cut into a self-vehicle lane is textured and divided into four corner points, so that a vehicle entering and exiting a current region to be driven can be timely judged, and a target vehicle can be timely judged. The method has the advantages that targets can be selected earlier by materializing the targets, and the ADAS can timely process the targets by timely selecting the main targets, so that the safety and the reliability of an ADAS system are ensured.
In an implementation, to reduce the probability of false recognition of the target vehicle, determining the probability of each corner in the current area to be driven includes:
acquiring the probability of each corner point in a current area to be driven in a plurality of preset periods;
and carrying out low-pass filtering on the probabilities of the same angular points in the current region to be driven in a plurality of preset periods to obtain the final probability of each angular point in the current region to be driven.
The duration of the preset period and the number of the preset periods are not limited, and the preset period is determined according to actual conditions. As corner C 1 The probability determined in the first preset period is 30%, the probability determined in the second preset period is 35%, and the probability determined in the third preset period is 38%, then the corner point C 1 The final probability in the current area to be driven is: p=w 1 *30%+w 2 *35%+w 3 *38, wherein w is 1 、w 2 、w 3 The specific value is determined according to the actual situation.
In the method provided by the embodiment, the probability that the target particle falls in the running area grid is integrated, and the probability of false recognition is reduced by continuously tracking the same target for a period of time.
When the probability that the vehicle to be cut into the own vehicle lane enters the current area to be driven is greater than the threshold value, it may be determined that the vehicle to be cut into the own vehicle lane is the target vehicle (the vehicle is closer to the own vehicle), in practice, the probability that the determined vehicle enters the current area to be driven may be greater due to the fact that the distance between the own vehicle and the vehicle driving in parallel is closer to the own vehicle, so in this embodiment, determining the target vehicle from the vehicles to be cut into the own vehicle lane according to the probability that the vehicle to be cut into the own vehicle lane is in the current area to be driven includes:
obtaining the maximum probability of four corner points of the vehicle to be cut into the self-vehicle lane in the current region to be driven as the corresponding probability of the vehicle to be cut into the self-vehicle lane in the current region to be driven;
when the probability of the vehicle to be cut into the self-vehicle lane in the current to-be-driven area is larger than a threshold value, taking the vehicle to be cut into the self-vehicle lane as a candidate main target vehicle;
The candidate host target vehicle closest to the own vehicle in the current track direction to be driven is acquired from the candidate host target vehicles as the target vehicle.
The threshold is not limited, and the probability threshold corresponding to the four corner points can be set to be the same, for example, 80%, or the probability threshold corresponding to the four corner points can be set to be different. In practice, taking the forward running of the vehicle as an example, the vehicle to be cut into the lane of the vehicle may cut into the lane of the vehicle from the left side or the right side, and the time and the position of cutting into the lane of the vehicle at different angles are different, so that the preferred embodiment is that the threshold values corresponding to the corner points of the vehicle to be cut into the lane of the vehicle are different, wherein the threshold values and the distance from the corner points to the vehicle in the direction perpendicular to the current track to be driven have a negative correlation. Regarding the vehicle with the textured structure in fig. 3, taking the vehicle cut into the own lane from the left side as an example, C 4 、C 3 The corresponding probability threshold may be small, e.g. C 4 、C 3 The probability threshold value is set to be 60%, C 1 、C 2 The probability threshold was set at 80%.
In the embodiment of the invention, the longitudinal distance between the vehicle to be cut into the vehicle lane and the vehicle is further judged, wherein the probability that the vehicle to be cut into the vehicle lane enters the current to-be-driven area is larger than the threshold value, the vehicle to be cut into the vehicle lane closest to the vehicle is taken as the target vehicle, so that the determined target vehicle is more accurate, different selection thresholds are set for four mass points of the vehicle to be cut into the vehicle lane, the probability threshold value set for the mass points closer to the vehicle is smaller, the target vehicle can be timely screened out, the running state of the vehicle is timely adjusted according to the target vehicle, the false recognition probability is reduced, and the safety and reliability of an ADAS system are ensured.
In the above embodiments, the method for detecting the target vehicle is described in detail, and the invention also provides a detection device for the target vehicle and a corresponding embodiment of a detection device for the target vehicle. It should be noted that the present invention describes an embodiment of the device portion from two angles, one based on the angle of the functional module and the other based on the angle of the hardware.
Fig. 5 is a block diagram of a detection device for a target vehicle according to an embodiment of the present invention. The embodiment is based on the angle of the functional module, and comprises:
the acquisition module 10 is used for acquiring the current track to be driven of the own vehicle and determining the current area to be driven of the own vehicle according to the current track to be driven;
the processing and assigning module 11 is used for carrying out rasterization processing on the current area to be driven and assigning values to the grids; the value of each grid is used for representing the probability that a vehicle to be cut into a vehicle lane enters a current region to be driven; the value of the grid and the distance from the grid to the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship;
the acquiring and determining module 12 is configured to acquire a position of a vehicle to be cut into the vehicle lane and determine a probability of the vehicle to be cut into the vehicle lane in a current region to be driven according to a value of a grid corresponding to the position;
The determining module 13 is configured to determine the target vehicle from the vehicles to be cut into the vehicle lane according to the probability that the vehicles to be cut into the vehicle lane are in the current area to be driven.
Since the embodiments of the apparatus portion and the embodiments of the method portion correspond to each other, the embodiments of the apparatus portion are referred to the description of the embodiments of the method portion, and are not repeated herein. And has the same advantageous effects as the above-mentioned detection method of the target vehicle.
Fig. 6 is a block diagram of a detection apparatus for a target vehicle according to another embodiment of the present invention. The present embodiment is based on a hardware angle, and as shown in fig. 6, the detection apparatus of the target vehicle includes:
a memory 20 for storing a computer program;
the processor 21 is configured to implement the steps of the method for detecting a target vehicle as mentioned in the above-described embodiment when executing the computer program.
Processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in hardware in at least one of a digital signal processor (Digital Signal Processor, DSP), a Field programmable gate array (Field-Programmable Gate Array, FPGA), a programmable logic array (Programmable Logic Array, PLA). The processor 21 may also comprise a main processor, which is a processor for processing data in an awake state, also called central processor (Central Processing Unit, CPU), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 may be integrated with a graphics processor (Graphics Processing Unit, GPU) for taking care of rendering and drawing of content that the display screen is required to display. In some embodiments, the processor 21 may also include an artificial intelligence (Artificial Intelligence, AI) processor for processing computing operations related to machine learning.
Memory 20 may include one or more computer-readable storage media, which may be non-transitory. Memory 20 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used for storing a computer program 201, which, when loaded and executed by the processor 21, is capable of implementing the relevant steps of the method for detecting a target vehicle disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may further include an operating system 202, data 203, and the like, where the storage manner may be transient storage or permanent storage. The operating system 202 may include Windows, unix, linux, among others. The data 203 may include, but is not limited to, the data related to the above-mentioned detection method of the target vehicle, and the like.
In some embodiments, the detection device of the target vehicle may further include a display 22, an input/output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 does not constitute a limitation of the detection apparatus of the target vehicle, and may include more or less components than those illustrated.
The detection device for the target vehicle provided by the embodiment of the invention comprises a memory and a processor, wherein the processor can realize the following method when executing a program stored in the memory: the detection method of the target vehicle has the same effects.
The invention also provides a corresponding embodiment of the computer readable storage medium. The computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps as described in the method embodiments above.
It will be appreciated that the methods of the above embodiments, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium for performing all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The computer readable storage medium provided by the invention comprises the detection method of the target vehicle, and the effects are the same as the above.
In order to better understand the solution of the present invention, the following describes the present invention in further detail with reference to fig. 7 and the detailed description. Fig. 7 is a flowchart of a target vehicle selection method based on travel area rasterization according to an embodiment of the present invention, as shown in fig. 7, the method includes:
s14: calculating the running track of the own vehicle;
s15: calculating a self-vehicle driving area;
s16: rasterizing a driving area;
s17: assigning grid probability;
s18: performing targeted quality spotting;
s19: calculating a corner probability value;
s20: a target vehicle is determined.
In the method provided by the embodiment of the invention, 1) the object is textured, one object is described by four corner points which are closer to the vehicle, and when any one corner point accords with the condition of selecting the object, the object is taken as a candidate main object;
2) Rasterizing the driving area, namely rasterizing the driving area, and judging target selection according to the grid position of target particles;
3) The grid probability distribution is used for distributing different probability values to the grid of the running area according to the distance between the target and the central line of the running track of the own vehicle, so that the probability of identifying the target by mistake is reduced;
4) Selecting and distinguishing target particles, integrating probabilities of different mass points of the same target falling in a running area grid, setting different selection thresholds for four particles of the same target, and reducing false recognition probability;
5) And the probability integration of the target particles is carried out, so that the probability of the target particles falling in the running area grid is integrated, the same target can be continuously tracked for a period of time, and the probability of false identification is reduced.
Therefore, the method of the embodiment of the invention can timely select any target vehicle which enters the self-vehicle running area; according to different probability values of different grids, the probability of target false selection can be reduced; the method has the advantages that targets can be selected earlier and timely by materializing the targets, ADAS can timely process the targets, and safety and reliability of an ADAS system are ensured.
The method, the device, the equipment and the medium for detecting the target vehicle provided by the invention are described in detail. In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
It should also be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Claims (12)
1. A method of detecting a target vehicle, comprising:
acquiring a current to-be-driven track of a self-vehicle and determining a current to-be-driven area of the self-vehicle according to the current to-be-driven track;
carrying out rasterization processing on the current area to be driven and assigning a value to each grid; the value of each grid is used for representing the probability that a vehicle to be cut into a vehicle lane enters the current region to be driven; the value of the grid and the distance between the grid and the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship;
Acquiring the position of the vehicle to be cut into the vehicle lane and determining the probability of the vehicle to be cut into the vehicle lane in the current to-be-driven area according to the value of the grid corresponding to the position; the method comprises the steps of obtaining the position of a vehicle to be cut into a vehicle lane, wherein the obtaining of the position of the vehicle to be cut into the vehicle lane comprises the steps of obtaining the coordinates of the center point of the tail part of the vehicle to be cut into the vehicle lane, and determining the position of the vehicle to be cut into the vehicle lane according to the coordinates of the center point of the tail part of the vehicle;
and determining a target vehicle from the vehicles to be cut into the self-vehicle lane according to the probability that the vehicles to be cut into the self-vehicle lane are in the current driving area.
2. The method for detecting a target vehicle according to claim 1, wherein the current trajectory to be traveled of the own vehicle includes one of:
mode one: determining the current track to be driven of the own vehicle according to the driving parameters of the own vehicle; wherein the driving parameters at least comprise: steering wheel angle, yaw rate;
mode two: under the condition that two side lane lines in the current track direction to be driven are detected, determining a center lane line between the two side lane lines; taking the central lane line as the current track to be driven of the own vehicle;
Mode three: the current track to be driven comprises a first section of current track to be driven and a second section of current track to be driven; the moment when the first section of current track to be driven is generated is earlier than the moment when the second section of current track to be driven is generated;
determining the current track to be driven of the first section of the own vehicle according to the driving parameters of the own vehicle;
determining the center lane line between the two side lane lines under the condition that the two side lane lines of the current track direction to be driven are detected; taking the central lane line as the current track to be driven of the second section of the own vehicle; connecting the first section of current track to be driven and the second section of current track to be driven to serve as the current track to be driven of the self-vehicle;
under the condition that the lane lines on the two sides of the current track to be driven are not detected, extending the first section of current track to be driven along the current track to be driven; taking an extension line of the first section of current track to be driven as the second section of current track to be driven; and connecting the first section of current track to be driven with the second section of current track to be driven to serve as the current track to be driven of the self-vehicle.
3. The method according to claim 2, wherein the determining the current waiting area of the own vehicle according to the current waiting trajectory includes:
respectively widening preset areas at two sides of the current track to be driven;
taking the widened area as the current area to be driven of the own vehicle;
the preset area is a half area of a lane area formed by the two side lane lines when the two side lane lines in the current track direction to be driven are detected;
and under the condition that the lane lines at the two sides of the current to-be-driven track direction are not detected, the preset area is a half standard lane area.
4. A detection method of a target vehicle according to any one of claims 1 to 3, wherein the rasterizing the current region to be traveled includes:
determining the size of each grid according to the preset result accuracy of determining the target vehicle;
and carrying out rasterization processing on the current area to be driven according to the size of each grid.
5. The method according to claim 4, wherein the value of the grid is in positive correlation with the distance of the grid from the own vehicle in the current track direction to be traveled.
6. The method according to claim 1, wherein the obtaining the position of the vehicle to be cut into the host vehicle lane and determining the probability of the vehicle to be cut into the host vehicle lane in the current area to be driven according to the value of the grid corresponding to the position includes:
acquiring coordinates of the length, width and rear center point of the vehicle to be cut into the vehicle lane;
determining coordinates of four corner points of the vehicle to be cut into the vehicle lane as positions of the vehicle to be cut into the vehicle lane according to the length, the width and the coordinates of the rear center point of the vehicle to be cut into the vehicle lane;
if the coordinates of the current corner point fall in the current area to be driven, determining that the probability that the current corner point of the vehicle to be cut into the vehicle lane is in the current area to be driven is the value of the grid corresponding to the current corner point;
if the coordinates of the current corner point do not fall in the current area to be driven, determining that the value of the current corner point corresponding to the grid is 0; and determining that the probability of the current corner point of the vehicle to be cut into the self-vehicle lane in the current to-be-driven area is 0 according to the value of the grid.
7. The method of detecting a target vehicle according to claim 6, wherein determining the probability of each corner point being in the current area to be travelled comprises:
acquiring the probability of each angular point in the current area to be driven in a plurality of preset periods;
and carrying out low-pass filtering on the probabilities of the same angular points in the current region to be driven in a plurality of preset periods to obtain the final probability of each angular point in the current region to be driven.
8. The method according to claim 6, wherein the determining the target vehicle from the vehicles to be cut into the host lane according to the probability that the vehicles to be cut into the host lane are in the current area to be traveled includes:
obtaining the maximum probability of the four corner points of the vehicle to be cut into the self-vehicle lane in the current region to be driven as the corresponding probability of the vehicle to be cut into the self-vehicle lane in the current region to be driven;
when the probability of the vehicle to be cut into the self-vehicle lane in the current to-be-driven area is larger than a threshold value, taking the vehicle to be cut into the self-vehicle lane as a candidate main target vehicle;
And acquiring the candidate main target vehicle closest to the own vehicle in the current track direction to be driven from the candidate main target vehicle as the target vehicle.
9. The method according to claim 8, wherein the threshold value corresponding to each of the corner points of the vehicle to be cut into the host lane is different, and wherein the threshold value has a negative correlation with a distance from the host vehicle in a direction perpendicular to the current track to be traveled by each of the corner points.
10. A detection apparatus for a target vehicle, characterized by comprising:
the acquisition module is used for acquiring the current to-be-driven track of the self-vehicle and determining the current to-be-driven area of the self-vehicle according to the current to-be-driven track;
the processing and assigning module is used for carrying out rasterization processing on the current area to be driven and assigning values to the grids; the value of each grid is used for representing the probability that a vehicle to be cut into a vehicle lane enters the current region to be driven; the value of the grid and the distance between the grid and the current track to be driven in the direction perpendicular to the current track to be driven are in a negative correlation relationship;
The acquisition and determination module is used for acquiring the position of the vehicle to be cut into the vehicle lane and determining the probability of the vehicle to be cut into the vehicle lane in the current to-be-driven area according to the grid value corresponding to the position; the method comprises the steps of obtaining the position of a vehicle to be cut into a vehicle lane, wherein the obtaining of the position of the vehicle to be cut into the vehicle lane comprises the steps of obtaining the coordinates of the center point of the tail part of the vehicle to be cut into the vehicle lane, and determining the position of the vehicle to be cut into the vehicle lane according to the coordinates of the center point of the tail part of the vehicle;
and the determining module is used for determining a target vehicle from the vehicles to be cut into the self-vehicle lane according to the probability that the vehicles to be cut into the self-vehicle lane are in the current driving area.
11. A detection apparatus of a target vehicle, characterized by comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for detecting a target vehicle according to any one of claims 1 to 9 when executing the computer program.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method for detecting a target vehicle according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311029438.8A CN116749968B (en) | 2023-08-16 | 2023-08-16 | Target vehicle detection method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311029438.8A CN116749968B (en) | 2023-08-16 | 2023-08-16 | Target vehicle detection method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116749968A CN116749968A (en) | 2023-09-15 |
| CN116749968B true CN116749968B (en) | 2023-11-03 |
Family
ID=87949984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311029438.8A Active CN116749968B (en) | 2023-08-16 | 2023-08-16 | Target vehicle detection method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116749968B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010078387A (en) * | 2008-09-25 | 2010-04-08 | Clarion Co Ltd | Lane determining apparatus |
| CN110550029A (en) * | 2019-08-12 | 2019-12-10 | 华为技术有限公司 | obstacle avoiding method and device |
| CN110884490A (en) * | 2019-10-28 | 2020-03-17 | 广州小鹏汽车科技有限公司 | Method and system for judging vehicle intrusion and assisting driving, vehicle and storage medium |
| CN111913183A (en) * | 2020-07-27 | 2020-11-10 | 中国第一汽车股份有限公司 | Vehicle lateral obstacle avoidance method, device and equipment and vehicle |
| CN115087573A (en) * | 2020-03-31 | 2022-09-20 | 华为技术有限公司 | Key target selection method, device and system |
| CN115339445A (en) * | 2022-08-02 | 2022-11-15 | 中国第一汽车股份有限公司 | Following target determination method and device and storage medium |
| CN115366921A (en) * | 2022-09-26 | 2022-11-22 | 重庆长安汽车股份有限公司 | Behavior decision method and device for automatic driving vehicle, vehicle and storage medium |
| WO2023115987A1 (en) * | 2021-12-23 | 2023-06-29 | 北京国家新能源汽车技术创新中心有限公司 | Control decision-making method based on vehicle-infrastructure perception fusion technology in front vehicle cut-in scenario |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6363517B2 (en) * | 2015-01-21 | 2018-07-25 | 株式会社デンソー | Vehicle travel control device |
| US10583839B2 (en) * | 2017-12-28 | 2020-03-10 | Automotive Research & Testing Center | Method of lane change decision-making and path planning |
-
2023
- 2023-08-16 CN CN202311029438.8A patent/CN116749968B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010078387A (en) * | 2008-09-25 | 2010-04-08 | Clarion Co Ltd | Lane determining apparatus |
| CN110550029A (en) * | 2019-08-12 | 2019-12-10 | 华为技术有限公司 | obstacle avoiding method and device |
| CN110884490A (en) * | 2019-10-28 | 2020-03-17 | 广州小鹏汽车科技有限公司 | Method and system for judging vehicle intrusion and assisting driving, vehicle and storage medium |
| CN115087573A (en) * | 2020-03-31 | 2022-09-20 | 华为技术有限公司 | Key target selection method, device and system |
| CN111913183A (en) * | 2020-07-27 | 2020-11-10 | 中国第一汽车股份有限公司 | Vehicle lateral obstacle avoidance method, device and equipment and vehicle |
| WO2023115987A1 (en) * | 2021-12-23 | 2023-06-29 | 北京国家新能源汽车技术创新中心有限公司 | Control decision-making method based on vehicle-infrastructure perception fusion technology in front vehicle cut-in scenario |
| CN115339445A (en) * | 2022-08-02 | 2022-11-15 | 中国第一汽车股份有限公司 | Following target determination method and device and storage medium |
| CN115366921A (en) * | 2022-09-26 | 2022-11-22 | 重庆长安汽车股份有限公司 | Behavior decision method and device for automatic driving vehicle, vehicle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116749968A (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11623644B2 (en) | Apparatus and method for controlling vehicle based on cut-in prediction in junction section | |
| CN108629231B (en) | Obstacle detection method, apparatus, device and storage medium | |
| EP3392109A1 (en) | Parking support method and device | |
| CN110632617B (en) | Laser radar point cloud data processing method and device | |
| KR102054926B1 (en) | System and method for detecting close cut-in vehicle based on free space signal | |
| EP3425341B1 (en) | Information processing apparatus, vehicle information processing method, and computer-readable medium | |
| CN111052201B (en) | Collision prediction device, collision prediction method, and storage medium | |
| CN110641461B (en) | Vehicle early warning method, vehicle road cooperative system and storage medium | |
| CN111661061B (en) | Vehicle driving intention identification method and device | |
| CN113267199A (en) | Driving track planning method and device | |
| CN113428137B (en) | Parking control method and device and storage medium | |
| JP2011196699A (en) | Device for detecting road edge | |
| WO2021093335A1 (en) | Method for automatically labeling lane changing intention based on high-noise trajectory data of vehicle | |
| CN114384491B (en) | Point cloud processing method and device for laser radar and storage medium | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| CN114384492B (en) | Point cloud processing method and device for laser radar and storage medium | |
| CN113740874A (en) | Road edge detection method, electronic equipment and vehicle | |
| CN111971724B (en) | Action selection device, computer-readable storage medium, and action selection method | |
| CN116749968B (en) | Target vehicle detection method, device, equipment and medium | |
| CN113432615A (en) | Detection method and system based on multi-sensor fusion drivable area and vehicle | |
| CN112172829A (en) | Lane departure warning method and device, electronic equipment and storage medium | |
| US20210208588A1 (en) | Sensor coverage analysis for automated driving scenarios involving intersections | |
| CN113176562A (en) | Multi-target tracking method and device, electronic equipment and readable storage medium | |
| CN112346046A (en) | Single-target tracking method and system based on vehicle-mounted millimeter wave radar | |
| CN116682095B (en) | Method, device, equipment and storage medium for determining attention target |
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 |