CN114999156A - Automatic identification method and device for crossing scene of pedestrian in front of vehicle, medium and vehicle - Google Patents
Automatic identification method and device for crossing scene of pedestrian in front of vehicle, medium and vehicle Download PDFInfo
- Publication number
- CN114999156A CN114999156A CN202210593238.4A CN202210593238A CN114999156A CN 114999156 A CN114999156 A CN 114999156A CN 202210593238 A CN202210593238 A CN 202210593238A CN 114999156 A CN114999156 A CN 114999156A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- vehicle
- target
- data
- track
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automatic identification method, device, medium and vehicle for a pedestrian crossing scene in front of the vehicle, wherein the method comprises the following steps: acquiring target list data, and screening out target data corresponding to the pedestrian type from the target list data; performing secondary screening on target data corresponding to the pedestrian type to obtain target data corresponding to pedestrians crossing the road; carrying out data cleaning on target data corresponding to pedestrians crossing the road to remove abnormal data, and respectively fitting a pedestrian track and a vehicle track according to the cleaned target data corresponding to the pedestrians crossing the road and the GPS data; and when the pedestrian track intersects with the vehicle track at a close distance, determining the current scene as a crossing scene of the pedestrian in front of the vehicle. Therefore, automatic identification of the pedestrian crossing scene in front of the vehicle is realized based on kinematic parameters, the algorithm is simple and easy to implement, the calculation complexity is low, data convenience is provided for application of PCW and AEBP functions in an ADAS function scene, and pedestrian collision accidents are effectively prevented.
Description
Technical Field
The invention relates to the technical field of recognition of a crossing scene of a pedestrian in front of a vehicle, in particular to an automatic recognition method of the crossing scene of the pedestrian in front of the vehicle, a computer-readable storage medium, an automatic recognition device of the crossing scene of the pedestrian in front of the vehicle and a vehicle.
Background
The automatic driving vehicle realizes automatic driving through technologies such as environment perception, cognition, decision making, whole vehicle control and the like. The automatic driving vehicle improves the reaction speed to the traffic environment through autonomous perception, cognition, decision and control, and rapidly performs corresponding operations such as braking and steering under different scenes including dangerous scenes, thereby improving traffic safety. Pedestrians are used as main users and vulnerable persons of roads, and the recognition of the pedestrians and the behavior recognition of the pedestrians and the avoidance of the pedestrians are indispensable key technologies of automatically driving vehicles.
However, the problem of the related art is that the capability of automatically identifying the crossing scene of the vehicle and the pedestrian is lacking at present, so that the vehicle cannot timely acquire PCW (pedestrian collision warning) and AEBP (automatic emergency braking) function data in an ADAS (Advanced Driving Assistance System) function scene, and the automatically driven vehicle cannot timely adopt corresponding avoidance measures, thereby preventing the occurrence of pedestrian collision accidents.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art. Therefore, the first purpose of the invention is to provide an automatic identification method for a pedestrian crossing scene in front of a vehicle, which can realize automatic identification for the pedestrian crossing scene in front of the vehicle based on kinematic parameters, has simple and easy algorithm and low calculation complexity, is beneficial to providing data convenience for PCW and AEBP function application in an ADAS function scene, and effectively prevents the occurrence of pedestrian collision accidents.
A second object of the invention is to propose a computer-readable storage medium.
The third purpose of the invention is to provide an automatic identification device for the pedestrian crossing scene in front of the vehicle.
A fourth object of the invention is to propose a vehicle.
In order to achieve the above object, an embodiment of the first aspect of the present invention provides an automatic identification method for a front pedestrian crossing scene, including the following steps: acquiring target list data, and screening out target data corresponding to the pedestrian type from the target list data; performing secondary screening on the target data corresponding to the pedestrian type to obtain target data corresponding to pedestrians crossing the road; carrying out data cleaning on the target data corresponding to the pedestrian crossing the road to remove abnormal data, and respectively fitting a pedestrian track and a vehicle track according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data; and when the pedestrian track and the vehicle track are intersected at a close distance, determining the current scene as a scene crossed by a pedestrian in front of the vehicle.
According to the automatic identification method for the crossing scene of the pedestrian in front of the vehicle, provided by the embodiment of the invention, target list data are obtained, target data corresponding to the pedestrian type are screened out from the target list data, further, the target data corresponding to the pedestrian type are secondarily screened, the target data corresponding to the pedestrian crossing the road are obtained, then, data cleaning is carried out on the target data corresponding to the pedestrian crossing the road to remove abnormal data, the pedestrian track and the vehicle track are respectively fitted according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data, and when the pedestrian track and the vehicle track are intersected at a short distance, the current scene is determined as the crossing scene of the pedestrian in front of the vehicle. Therefore, automatic identification of the pedestrian crossing scene in front of the vehicle is realized based on kinematic parameters, the algorithm is simple and easy to implement, the calculation complexity is low, data convenience is provided for application of PCW and AEBP functions in an ADAS function scene, and pedestrian collision accidents are effectively prevented.
In addition, the automatic identification method for the pedestrian crossing scene in front of the vehicle, which is provided by the embodiment of the invention, can also have the following additional technical characteristics:
according to an embodiment of the present invention, the secondary screening of the target data corresponding to the pedestrian type includes: judging whether the same pedestrian target appears in the continuous data frames of the target data corresponding to the pedestrian type and whether the transverse position of the same pedestrian target relative to the vehicle changes from positive to negative or from negative to positive; and if the same pedestrian target appears in the continuous data frames and the transverse position of the same pedestrian target relative to the vehicle changes from positive to negative or from negative to positive, determining the target data corresponding to the same pedestrian target as the target data corresponding to the pedestrian crossing the road.
According to one embodiment of the invention, the data cleaning of the target data corresponding to the pedestrian crossing the road comprises the following steps: acquiring a first quartile and a third quartile of each pedestrian target relative to the position data of the vehicle, and acquiring a quartile interval according to the first quartile and the third quartile; determining a data cleaning upper limit value and a data cleaning lower limit value according to the third quartile and the quartile distance; and eliminating the target data corresponding to the pedestrian crossing the road, which is larger than the data cleaning upper limit value or smaller than the data cleaning lower limit value.
According to an embodiment of the present invention, after the data cleaning of the target data corresponding to the pedestrian crossing the road, the method further includes: judging whether the data volume of the target data corresponding to the pedestrian crossing the road after cleaning is greater than 0; and if the data volume is larger than 0, respectively fitting the pedestrian track and the vehicle track according to the target data corresponding to the pedestrian crossing the road after the cleaning treatment and the GPS data.
According to one embodiment of the invention, the automatic identification method for the pedestrian crossing scene in front of the vehicle further comprises the following steps: judging whether the pedestrian track and the vehicle track intersect within a preset distance threshold value or not, and whether an included angle between the pedestrian track and the vehicle track is larger than a preset angle threshold value or not; and if the pedestrian track and the vehicle track are intersected within a preset distance threshold value and the included angle between the pedestrian track and the vehicle track is larger than a preset angle threshold value, determining that the pedestrian track and the vehicle track are intersected closely.
According to one embodiment of the invention, the automatic identification method for the front pedestrian crossing the scene further comprises the following steps: acquiring CAN data acquired by a vehicle, wherein the CAN data comprises vehicle speed information of the vehicle; and screening target list data under the driving state of the vehicle along the lane according to the vehicle speed information of the vehicle.
According to one embodiment of the invention, the target list data includes target object information collected by a camera or a laser radar, and the target object information includes a target object ID, a target object type, a target object relative vehicle position, a target object relative vehicle speed, and a target object length, width and height.
In order to achieve the above object, a computer-readable storage medium is provided in an embodiment of the second aspect of the present invention, on which an automatic recognition program of a vehicle-front pedestrian crossing scene is stored, and the automatic recognition program of the vehicle-front pedestrian crossing scene is executed by a processor to implement the automatic recognition method of the vehicle-front pedestrian crossing scene as described in the embodiment of the first aspect.
According to the computer readable storage medium provided by the embodiment of the invention, the processor executes the automatic identification program of the crossing scene of the pedestrian in front stored on the computer readable storage medium, the automatic identification of the crossing scene of the pedestrian in front can be realized based on the kinematic parameters, the algorithm is simple and easy to implement, the calculation complexity is low, the data convenience is favorably provided for the application of PCW and AEBP functions in the ADAS function scene, and the occurrence of collision accidents of the pedestrian is effectively prevented.
In order to achieve the above object, an automatic recognition device for a pedestrian crossing scene in front of a vehicle according to a third aspect of the present invention includes: the data acquisition module is used for acquiring target list data and screening out target data corresponding to the pedestrian type from the target list data; the data screening module is used for carrying out secondary screening on the target data corresponding to the pedestrian type to obtain the target data corresponding to the pedestrian crossing the road; the data cleaning module is used for cleaning the target data corresponding to the pedestrian crossing the road to remove abnormal data; the track fitting module is used for respectively fitting the pedestrian track and the vehicle track according to the cleaned target data and the GPS data corresponding to the pedestrian crossing the road; and the scene recognition module is used for determining the current scene as a crossing scene of the pedestrian in front of the vehicle when the pedestrian track is intersected with the vehicle track at a close distance.
According to the automatic recognition device for the crossing scene of the pedestrian in front of the vehicle, provided by the embodiment of the invention, the data acquisition module is used for acquiring the target list data, the target data corresponding to the pedestrian type is screened out from the target list data, then the data screening module is used for carrying out secondary screening on the target data corresponding to the pedestrian type to obtain the target data corresponding to the pedestrian crossing the road, then the data cleaning module is used for carrying out data cleaning on the target data corresponding to the pedestrian crossing the road to remove abnormal data, the track fitting module is used for respectively fitting the pedestrian track and the vehicle track according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data, and the scene recognition module is used for determining the current scene as the crossing scene of the pedestrian crossing in front of the vehicle when the pedestrian track and the vehicle track are intersected at a short distance. Therefore, automatic identification of the pedestrian crossing scene in front of the vehicle is realized based on kinematic parameters, the algorithm is simple and easy to implement, the calculation complexity is low, data convenience is provided for application of PCW and AEBP functions in an ADAS function scene, and pedestrian collision accidents are effectively prevented.
In order to achieve the above object, a vehicle according to a fourth aspect of the present invention includes an automatic vehicle front pedestrian crossing scene recognition apparatus according to the third aspect of the present invention.
According to the vehicle provided by the embodiment of the invention, the automatic identification device for the pedestrian crossing scene in front is adopted, the automatic identification for the pedestrian crossing scene in front can be realized based on the kinematic parameters, the algorithm is simple and easy to implement, the calculation complexity is low, the data convenience is provided for the application of PCW and AEBP functions in the ADAS functional scene, and the occurrence of pedestrian collision accidents is effectively prevented.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flow diagram illustrating an automatic identification method for a pedestrian crossing scene in front of a vehicle according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a secondary screening of target data corresponding to a pedestrian type according to an embodiment of the present invention;
FIG. 3 is a flow diagram illustrating data cleansing of target data corresponding to pedestrians crossing a road, according to one embodiment of the present invention;
FIG. 4 is a schematic flow diagram after data cleansing of target data corresponding to a pedestrian crossing a road according to one embodiment of the present invention;
FIG. 5 is a flow diagram of a method for automatic identification of a preceding pedestrian crossing a scene, according to one embodiment of the invention;
FIG. 6 is a flow diagram illustrating a method for automatically identifying a crossing scene of a pedestrian in front of a vehicle, in accordance with one embodiment of the present invention;
FIG. 7 is a block schematic diagram of an automatic identification device for a front pedestrian crossing a scene in accordance with an embodiment of the present invention;
FIG. 8 is a block schematic diagram of a vehicle according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present invention and should not be construed as limiting the present invention.
An automatic recognition method of a preceding pedestrian crossing scene, a computer-readable storage medium, an automatic recognition apparatus of a preceding pedestrian crossing scene, and a vehicle according to an embodiment of the present invention will be described below with reference to the drawings.
Fig. 1 is a flow chart of an automatic identification method for a front pedestrian crossing scene according to an embodiment of the invention.
As shown in fig. 1, the automatic identification method for a pedestrian crossing scene in front of a vehicle includes the following steps:
s101, acquiring target list data, and screening out target data corresponding to the pedestrian type from the target list data.
Optionally, the target list data may include target object information acquired by a camera or a laser radar, where the target object information includes a target object ID, a type of the target object, a position of the target object relative to the vehicle, a speed of the target object relative to the vehicle, and a length, a width, and a height of the target object.
It should be understood that, since the target object information collected by the camera or the laser radar may include a vehicle target and a pedestrian target, in the embodiment of the present invention, target data corresponding to a pedestrian type may be screened from the target list data according to a target object type in the target object information.
And S102, performing secondary screening on the target data corresponding to the pedestrian type to obtain the target data corresponding to the pedestrian crossing the road.
It should be understood that, since there may exist a plurality of pedestrian targets in the target data corresponding to the pedestrian type, in the embodiment of the present invention, the target data corresponding to the pedestrian type needs to be secondarily screened so as to screen out the target data corresponding to the pedestrian crossing the road.
S103, data cleaning is carried out on target data corresponding to the pedestrian crossing the road to remove abnormal data, and the pedestrian track and the vehicle track are respectively fitted according to the target data corresponding to the pedestrian crossing the road and the GPS data after cleaning processing.
It is understood that, in the embodiment of the present invention, the target data corresponding to the pedestrian crossing the road may be subjected to data cleaning through, for example, distribution of the boxcar map description data, so as to remove the abnormal data, and further, the pedestrian trajectory and the host vehicle trajectory may be respectively fitted according to the target data corresponding to the pedestrian crossing the road after the cleaning processing and the GPS data, so as to determine whether the current scene is the pedestrian crossing scene in front of the vehicle according to the pedestrian trajectory and the host vehicle trajectory.
And S104, when the pedestrian track is intersected with the vehicle track at a short distance, determining the current scene as a crossing scene of the pedestrian in front of the vehicle.
It is understood that if the pedestrian actually crosses the road in front of the vehicle, the pedestrian track and the vehicle track will certainly intersect in a close distance, and therefore, in the embodiment of the present invention, when the pedestrian track and the vehicle track intersect in a close distance, the current scene may be determined as the crossing scene of the pedestrian in front of the vehicle, so as to realize the automatic identification of the crossing scene of the pedestrian in front of the vehicle based on the kinematic parameters.
Further, as shown in fig. 2, the secondary screening of the target data corresponding to the pedestrian type includes:
s201, judging whether the same pedestrian target appears in the continuous data frames of the target data corresponding to the pedestrian type and whether the transverse position of the same pedestrian target relative to the vehicle changes from positive to negative or from negative to positive.
It is understood that the appearance of the same pedestrian target in the continuous data frames means that the pedestrian target exists in the continuous data frames, and the change of the lateral position of the same pedestrian target relative to the host vehicle from positive to negative or from negative to positive means that the position of the pedestrian target in the continuous data frames and the position of the host vehicle change from near to far or from far to near.
And S202, if the same pedestrian target appears in the continuous data frames and the transverse position of the same pedestrian target relative to the vehicle changes from positive to negative or from negative to positive, determining the target data corresponding to the same pedestrian target as the target data corresponding to the pedestrian crossing the road.
For example, in the embodiment of the present invention, assuming that a pedestrian crosses the road in front of the vehicle, the pedestrian target appears in the continuous data frames, and in addition, the lateral position of the pedestrian target relative to the host vehicle changes from positive to negative or from negative to positive, so that when the same pedestrian target appears in the continuous data frames and the lateral position of the same pedestrian target relative to the host vehicle changes from positive to negative or from negative to positive, the target data corresponding to the same pedestrian target may be determined as the target data corresponding to the pedestrian crossing the road, thereby determining that the pedestrian target crosses the road in front of the vehicle.
Further, as shown in fig. 3, the data cleaning of the target data corresponding to the pedestrian crossing the road includes:
s301, a first quartile and a third quartile of each pedestrian target relative to the vehicle position data are obtained, and a quartile distance is obtained according to the first quartile and the third quartile.
It can be understood that, in the embodiment of the present invention, the target data corresponding to the pedestrian crossing the road is subjected to data cleaning through the box plot, it should be noted that, in the box plot, after sorting the data according to size, the data is divided into 4 equal divisions, the numbers at the 3 division points are the quartiles, and the three quartiles are the first quartile, the second quartile and the third quartile respectively according to the order from small to large, wherein the first quartile (Q1), also called as "smaller quartile", is equal to the 25 th number after sorting the sample data from small to large, the third quartile (Q3), also called "larger quartile", is equal to the 75 th number after sorting the sample data from small to large, and the quartile distance (IQR: intersquartile Range) is Q3-Q1.
Specifically, in the embodiment of the invention, the first quartile Q1 of each pedestrian target relative to the host vehicle position data is determined by acquiring the number of the 25 th% of each pedestrian target relative to the host vehicle position data after sorting from small to large, the third quartile Q3 of each pedestrian target relative to the host vehicle position data is determined by acquiring the number of the 75 th% of each pedestrian target relative to the host vehicle position data after sorting from small to large, and the quartile pitch IQR is acquired from the difference between the first quartile Q1 and the third quartile Q3.
S302, determining a data cleaning upper limit value and a data cleaning lower limit value according to the third quartile and the quartile distance.
Alternatively, the data cleansing upper limit value and the data cleansing lower limit value may be determined by the following formulas: qmax ═ Q3+1.5 × IQR; qmin is Q3-1.5 i qr, where Qmax is the upper limit of data cleaning, Q3 is the third quartile of each pedestrian target relative to the vehicle position data, IQR is the interquartile distance, and Qmin is the lower limit of data cleaning, so that the target data corresponding to the pedestrian crossing the road can be data-cleaned according to the upper limit of data cleaning and the lower limit of data cleaning.
S303, eliminating target data corresponding to the pedestrian crossing the road and larger than the upper limit value of data cleaning or smaller than the lower limit value of data cleaning.
Specifically, in the embodiment of the present invention, when the target data corresponding to the pedestrian crossing the road is greater than the data cleaning upper limit value or less than the data cleaning lower limit value, it may be determined that the current pedestrian target is out of the range between the maximum value and the minimum value of the boxcar map with respect to the vehicle position data, that is, the data belongs to the abnormal data, and in order to improve the data accuracy and the scene recognition accuracy, the target data corresponding to the pedestrian crossing the road may be eliminated from the plurality of target data corresponding to the pedestrian crossing the road.
Further, as shown in fig. 4, after the data cleaning of the target data corresponding to the pedestrian crossing the road, the method further includes:
and S401, judging whether the data quantity of the target data corresponding to the pedestrian crossing the road after the cleaning processing is larger than 0.
It is understood that after the data cleaning of the target data corresponding to the pedestrian crossing the road, it may be determined whether the data amount of the target data corresponding to the pedestrian crossing the road after the cleaning process is greater than 0. To thereby determine whether sufficient target data corresponding to pedestrians crossing the road is available for fitting the pedestrian's trajectory to the host-vehicle's trajectory.
And S402, if the data volume is larger than 0, respectively fitting the pedestrian track and the vehicle track according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data.
When enough target data corresponding to pedestrians crossing the road are used for fitting the pedestrian track and the vehicle track, the tracks can be linearly fitted by using longitude and latitude coordinates of the pedestrians and the vehicle respectively, wherein the latitude coordinate is an X-axis coordinate, the longitude coordinate is a Y-axis coordinate, and a straight line is fitted by using a least square method under an XY coordinate system to be respectively used as the pedestrian track and the vehicle track.
Specifically, the longitude and latitude coordinates of the vehicle are directly stored in the GPS data, and may be converted into coordinates of a geodetic coordinate system by applying the prior art, and then a straight line is fitted as the vehicle trajectory by using a least square method according to the coordinates.
Further, as shown in fig. 5, the method for automatically identifying a pedestrian in front of a vehicle crossing a scene further includes:
s501, judging whether the pedestrian track and the vehicle track intersect within a preset distance threshold value or not, and whether the included angle between the pedestrian track and the vehicle track is larger than a preset angle threshold value or not.
Alternatively, the preset distance threshold and the preset angle threshold may be set according to scene factors, for example, the preset distance threshold may be preferably 10m, and the preset angle threshold may be preferably 45 °.
S502, if the pedestrian track and the vehicle track intersect within a preset distance threshold value and an included angle between the pedestrian track and the vehicle track is larger than a preset angle threshold value, it is determined that the pedestrian track and the vehicle track intersect in a close range.
It can be understood that when the pedestrian trajectory and the vehicle trajectory intersect within the preset distance threshold and an included angle between the pedestrian trajectory and the vehicle trajectory is greater than a preset angle threshold, it may be determined that the pedestrian trajectory and the vehicle trajectory will intersect at a close distance.
Further, the automatic identification method for the pedestrian in front of the vehicle crossing the scene further comprises the following steps: the method comprises the steps of obtaining CAN data collected by a vehicle, wherein the CAN data comprise vehicle speed information of the vehicle, and screening target list data under the driving state of the vehicle along a lane according to the vehicle speed information of the vehicle.
It CAN be understood that the CAN data collected by the vehicle includes vehicle speed information of the vehicle, and target list data in a driving state of the vehicle along a lane CAN be screened out according to the condition that the vehicle speed is greater than 0, so that the accuracy of scene recognition is improved, and PCW and AEBP function applications in an ADAS function scene are prevented from being triggered when the vehicle is stationary.
The following describes specific steps of the method for automatically identifying a crossing scene of a pedestrian in front of a vehicle according to an embodiment of the present invention with reference to fig. 6 and an embodiment of the present invention, and as shown in the drawing, when the vehicle turns on the ADAS function, step S1 is executed.
And S1, screening out target data corresponding to the pedestrian type from the target list data.
And S2, performing secondary screening on the target data corresponding to the pedestrian type to obtain the target data corresponding to the pedestrian crossing the road.
And S3, performing data cleaning on the target data corresponding to the pedestrian crossing the road to remove abnormal data.
And S4, respectively fitting the pedestrian track and the vehicle track according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data.
And S5, judging whether the pedestrian track and the vehicle track are intersected at a short distance, if so, executing a step S5, and if not, executing a step S7.
And S6, determining the current scene as a crossing scene of the pedestrian in front of the vehicle.
And S7, determining the current scene as a non-front pedestrian crossing scene.
In summary, according to the automatic identification method for a crossing scene of a pedestrian in front of a vehicle, provided by the embodiment of the invention, the target list data is obtained, the target data corresponding to the pedestrian type is screened from the target list data, then, the target data corresponding to the pedestrian type is secondarily screened to obtain the target data corresponding to the pedestrian crossing the road, then, the target data corresponding to the pedestrian crossing the road is subjected to data cleaning to remove abnormal data, the pedestrian track and the vehicle track are respectively fitted according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data, and when the pedestrian track and the vehicle track are intersected at a short distance, the current scene is determined as the crossing scene of the pedestrian in front of the vehicle. Therefore, automatic identification of the pedestrian crossing scene in front of the vehicle is realized based on kinematic parameters, the algorithm is simple and easy to implement, the calculation complexity is low, data convenience is provided for application of PCW and AEBP functions in an ADAS function scene, and pedestrian collision accidents are effectively prevented.
Based on the foregoing method for automatically identifying a crossing scene of a vehicle-front pedestrian according to the embodiment of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, on which an automatic identification program for a crossing scene of a vehicle-front pedestrian is stored, and when the automatic identification program is executed by a processor, the method for automatically identifying a crossing scene of a vehicle-front pedestrian according to the foregoing embodiment of the present invention is implemented.
It should be noted that, when the computer-readable storage medium according to the embodiment of the present invention executes the automatic identification program stored thereon for the crossing scene of the pedestrian in front of the vehicle, the specific implementation manner corresponding to the automatic identification method for the crossing scene of the pedestrian in front of the vehicle according to the foregoing embodiment of the present invention can be implemented one to one, and is not described herein again to reduce redundancy.
In summary, according to the computer-readable storage medium provided by the embodiment of the present invention, the processor executes the automatic identification program stored thereon for the pedestrian crossing scene in front of the vehicle, so as to realize automatic identification for the pedestrian crossing scene in front of the vehicle based on the kinematic parameters, and the algorithm is simple and easy to implement, has low computation complexity, and is beneficial to providing data convenience for the application of PCW and AEBP functions in the ADAS function scene, and effectively preventing the occurrence of pedestrian collision accidents.
Fig. 7 is a block schematic diagram of an automatic recognition device for a front pedestrian crossing a scene according to an embodiment of the present invention.
As shown in fig. 7, the automatic recognition apparatus 100 for a pedestrian crossing a scene in front of a vehicle includes: the system comprises a data acquisition module 10, a data screening module 20, a data cleaning module 30, a trajectory fitting module 40 and a scene recognition module 50.
Specifically, the data acquisition module 10 is configured to acquire target list data and screen out target data corresponding to a pedestrian type from the target list data; the data screening module 20 is configured to perform secondary screening on target data corresponding to a pedestrian type to obtain target data corresponding to a pedestrian crossing a road; the data cleaning module 30 is used for performing data cleaning on target data corresponding to pedestrians crossing the road to remove abnormal data; the track fitting module 40 is used for respectively fitting a pedestrian track and a vehicle track according to target data and GPS data corresponding to the pedestrian crossing the road after cleaning; the scene recognition module 50 is configured to determine the current scene as a pedestrian crossing scene in front of the vehicle when the pedestrian trajectory intersects the vehicle trajectory at a close distance.
Further, the data screening module 20 is further configured to determine whether the same pedestrian target appears in the continuous data frames of the target data corresponding to the pedestrian type, and whether the lateral position of the same pedestrian target relative to the host vehicle changes from positive to negative or from negative to positive; and if the same pedestrian target appears in the continuous data frames and the transverse position of the same pedestrian target relative to the vehicle changes from positive to negative or from negative to positive, determining the target data corresponding to the same pedestrian target as the target data corresponding to the pedestrian crossing the road.
Further, the data cleaning module 30 is further configured to obtain a first quartile and a third quartile of each pedestrian target relative to the vehicle position data, and obtain a quartile distance according to the first quartile and the third quartile; determining a data cleaning upper limit value and a data cleaning lower limit value according to the third quartile and the quartile distance; and eliminating target data corresponding to pedestrians crossing the road, wherein the target data is greater than the data cleaning upper limit value or less than the data cleaning lower limit value.
Further, the trajectory fitting module 40 is further configured to determine whether the data amount of the target data corresponding to the pedestrian crossing the road after the cleaning processing is greater than 0; and if the data volume is larger than 0, respectively fitting the pedestrian track and the vehicle track according to the target data corresponding to the pedestrian crossing the road after cleaning and the GPS data.
Further, the scene recognition module 50 is further configured to determine whether the pedestrian trajectory and the vehicle trajectory intersect within a preset distance threshold, and whether an included angle between the pedestrian trajectory and the vehicle trajectory is greater than a preset angle threshold; and if the pedestrian track and the vehicle track are intersected within a preset distance threshold value and the included angle between the pedestrian track and the vehicle track is larger than a preset angle threshold value, determining that the pedestrian track and the vehicle track are intersected at a close distance.
Further, the data acquisition module 10 is further configured to acquire CAN data acquired by the vehicle, where the CAN data includes vehicle speed information of the vehicle; and screening target list data under the driving state of the vehicle along the lane according to the vehicle speed information of the vehicle.
Further, the target list data includes target object information acquired by a camera or a laser radar, and the target object information includes a target object ID, a target object type, a relative vehicle position of the target object, a relative vehicle speed of the target object, and a length, width and height of the target object.
It should be noted that, the automatic identification device 100 for a crossing scene of a pedestrian in front of the vehicle according to the embodiment of the present invention can implement a specific implementation manner corresponding to the automatic identification method for a crossing scene of a pedestrian in front of the vehicle according to the foregoing embodiment of the present invention, and for reducing redundancy, no further description is provided here.
In summary, according to the automatic recognition device for a crossing scene of a pedestrian in front of a vehicle, provided by the embodiment of the invention, the data acquisition module is used for acquiring the target list data, the target data corresponding to the pedestrian type is screened out from the target list data, the data screening module is used for carrying out secondary screening on the target data corresponding to the pedestrian type to obtain the target data corresponding to the pedestrian crossing the road, the data cleaning module is used for carrying out data cleaning on the target data corresponding to the pedestrian crossing the road to remove abnormal data, the trajectory fitting module is used for respectively fitting the pedestrian trajectory and the vehicle trajectory according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data, and the scene recognition module is used for determining the current scene as the crossing scene of the pedestrian crossing in front of the vehicle when the pedestrian trajectory and the vehicle trajectory are intersected at a short distance. Therefore, automatic identification of the pedestrian crossing scene in front of the vehicle is realized based on the kinematic parameters, the algorithm is simple and easy to implement, the calculation complexity is low, data convenience is provided for application of PCW and AEBP functions in the ADAS functional scene, and the pedestrian collision accident is effectively prevented.
FIG. 8 is a block schematic diagram of a vehicle according to an embodiment of the invention.
As shown in fig. 8, the vehicle 1000 includes the automatic recognition apparatus 100 for a pedestrian crossing scene in front of the vehicle according to the embodiment of the present invention.
It should be noted that the vehicle 1000 according to the embodiment of the present invention can implement a specific implementation manner corresponding to the automatic identification method for crossing a scene by a pedestrian in front of the vehicle according to the foregoing embodiment of the present invention, and in addition, other configurations and functions of the vehicle 1000 according to the embodiment of the present invention are known to those skilled in the art, and are not described herein again to reduce redundancy.
In summary, according to the vehicle provided by the embodiment of the invention, by adopting the automatic identification device for the pedestrian crossing scene in front of the vehicle, the automatic identification of the pedestrian crossing scene in front of the vehicle can be realized based on the kinematic parameters, and the algorithm is simple, convenient and easy to implement, has low calculation complexity, is beneficial to providing data convenience for the application of the PCW and AEBP functions in the ADAS function scene, and effectively prevents the occurrence of pedestrian collision accidents.
It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be interconnected within two elements or in a relationship where two elements interact with each other unless otherwise specifically limited. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless expressly stated or limited otherwise, the first feature "on" or "under" the second feature may be directly contacting the second feature or the first and second features may be indirectly contacting each other through intervening media. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. An automatic identification method for a front pedestrian crossing a scene, the method comprising the steps of:
acquiring target list data, and screening out target data corresponding to the pedestrian type from the target list data;
performing secondary screening on the target data corresponding to the pedestrian type to obtain target data corresponding to pedestrians crossing the road;
carrying out data cleaning on the target data corresponding to the pedestrian crossing the road to remove abnormal data, and respectively fitting a pedestrian track and a vehicle track according to the cleaned target data corresponding to the pedestrian crossing the road and the GPS data;
and when the pedestrian track and the vehicle track are intersected at a close range, determining the current scene as a crossing scene of a pedestrian in front of the vehicle.
2. The method according to claim 1, wherein the secondary screening of the target data corresponding to the pedestrian type comprises:
judging whether the same pedestrian target appears in the continuous data frames of the target data corresponding to the pedestrian type and whether the transverse position of the same pedestrian target relative to the vehicle changes from positive to negative or from negative to positive;
and if the same pedestrian target appears in the continuous data frames and the transverse position of the same pedestrian target relative to the vehicle changes from positive to negative or from negative to positive, determining the target data corresponding to the same pedestrian target as the target data corresponding to the pedestrian crossing the road.
3. The method of claim 1, wherein the data cleansing of the target data corresponding to the cross-road pedestrian comprises:
acquiring a first quartile and a third quartile of each pedestrian target relative to the position data of the vehicle, and acquiring a quartile distance according to the first quartile and the third quartile;
determining a data cleaning upper limit value and a data cleaning lower limit value according to the third quartile and the quartile distance;
and eliminating the target data corresponding to the pedestrian crossing the road, which is larger than the upper limit value of the data cleaning or smaller than the lower limit value of the data cleaning.
4. The method of claim 3, wherein after the data cleaning of the target data corresponding to the pedestrian crossing the road, the method further comprises:
judging whether the data volume of the target data corresponding to the pedestrian crossing the road after cleaning is greater than 0;
and if the data volume is larger than 0, respectively fitting the pedestrian track and the vehicle track according to the target data corresponding to the pedestrian crossing the road after the cleaning treatment and the GPS data.
5. The method of automatically identifying an in-vehicle pedestrian crossing scene of claim 1, further comprising:
judging whether the pedestrian track and the vehicle track intersect within a preset distance threshold value or not, and whether an included angle between the pedestrian track and the vehicle track is larger than a preset angle threshold value or not;
and if the pedestrian track and the vehicle track are intersected within a preset distance threshold value and the included angle between the pedestrian track and the vehicle track is larger than a preset angle threshold value, determining that the pedestrian track and the vehicle track are intersected closely.
6. The method of automatically identifying an in-vehicle pedestrian crossing scene of claim 1, further comprising:
acquiring CAN data acquired by a vehicle, wherein the CAN data comprises vehicle speed information of the vehicle;
and screening target list data under the driving state of the vehicle along the lane according to the vehicle speed information of the vehicle.
7. The method according to claim 1, wherein the target list data includes target information collected by a camera or a laser radar, and the target information includes a target ID, a target type, a target relative vehicle position, a target relative vehicle speed, and a target length, width, and height.
8. A computer-readable storage medium, on which an automatic recognition program of a vehicle-front pedestrian crossing scene is stored, which when executed by a processor implements the automatic recognition method of a vehicle-front pedestrian crossing scene according to any one of claims 1 to 7.
9. An automatic vehicle front pedestrian crossing scene recognition device, the device comprising:
the data acquisition module is used for acquiring target list data and screening out target data corresponding to the pedestrian type from the target list data;
the data screening module is used for carrying out secondary screening on the target data corresponding to the pedestrian type to obtain the target data corresponding to the pedestrian crossing the road;
the data cleaning module is used for cleaning the target data corresponding to the pedestrian crossing the road to remove abnormal data;
the track fitting module is used for respectively fitting the pedestrian track and the vehicle track according to the cleaned target data and the GPS data corresponding to the pedestrian crossing the road;
and the scene recognition module is used for determining the current scene as a crossing scene of the pedestrian in front of the vehicle when the pedestrian track is intersected with the vehicle track at a close distance.
10. A vehicle characterized by comprising an automatic recognition device of a pedestrian crossing scene in front of a vehicle according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210593238.4A CN114999156A (en) | 2022-05-27 | 2022-05-27 | Automatic identification method and device for crossing scene of pedestrian in front of vehicle, medium and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210593238.4A CN114999156A (en) | 2022-05-27 | 2022-05-27 | Automatic identification method and device for crossing scene of pedestrian in front of vehicle, medium and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114999156A true CN114999156A (en) | 2022-09-02 |
Family
ID=83029329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210593238.4A Pending CN114999156A (en) | 2022-05-27 | 2022-05-27 | Automatic identification method and device for crossing scene of pedestrian in front of vehicle, medium and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114999156A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096803A (en) * | 2010-11-29 | 2011-06-15 | 吉林大学 | Safe state recognition system for people on basis of machine vision |
| CN107025301A (en) * | 2017-04-25 | 2017-08-08 | 西安理工大学 | Flight ensures the method for cleaning of data |
| CN107615356A (en) * | 2015-05-27 | 2018-01-19 | 株式会社电装 | Controller of vehicle and control method for vehicle |
| CN108847042A (en) * | 2018-08-24 | 2018-11-20 | 讯飞智元信息科技有限公司 | A kind of traffic information dissemination method and device |
| CN109074651A (en) * | 2016-02-12 | 2018-12-21 | 日立汽车系统株式会社 | The ambient enviroment identification device of moving body |
| CN112880627A (en) * | 2019-11-29 | 2021-06-01 | 丰田自动车株式会社 | Road surface damage detection device, road surface damage detection method, and medium |
| CN112965876A (en) * | 2021-03-10 | 2021-06-15 | 中国民航信息网络股份有限公司 | Monitoring alarm method and device |
| CN113486302A (en) * | 2021-07-12 | 2021-10-08 | 浙江网商银行股份有限公司 | Data processing method and device |
-
2022
- 2022-05-27 CN CN202210593238.4A patent/CN114999156A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096803A (en) * | 2010-11-29 | 2011-06-15 | 吉林大学 | Safe state recognition system for people on basis of machine vision |
| CN107615356A (en) * | 2015-05-27 | 2018-01-19 | 株式会社电装 | Controller of vehicle and control method for vehicle |
| CN109074651A (en) * | 2016-02-12 | 2018-12-21 | 日立汽车系统株式会社 | The ambient enviroment identification device of moving body |
| CN107025301A (en) * | 2017-04-25 | 2017-08-08 | 西安理工大学 | Flight ensures the method for cleaning of data |
| CN108847042A (en) * | 2018-08-24 | 2018-11-20 | 讯飞智元信息科技有限公司 | A kind of traffic information dissemination method and device |
| CN112880627A (en) * | 2019-11-29 | 2021-06-01 | 丰田自动车株式会社 | Road surface damage detection device, road surface damage detection method, and medium |
| CN112965876A (en) * | 2021-03-10 | 2021-06-15 | 中国民航信息网络股份有限公司 | Monitoring alarm method and device |
| CN113486302A (en) * | 2021-07-12 | 2021-10-08 | 浙江网商银行股份有限公司 | Data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109254289B (en) | Detection method and detection equipment for road guardrail | |
| CN111382768A (en) | Multi-sensor data fusion method and device | |
| US9400897B2 (en) | Method for classifying parking scenarios for a system for parking a motor vehicle | |
| DE102016109592A1 (en) | Collision mitigation and avoidance | |
| US9360332B2 (en) | Method for determining a course of a traffic lane for a vehicle | |
| CN101135558A (en) | Vehicle anti-collision early warning method and apparatus based on machine vision | |
| EP3722169B1 (en) | Vehicle and method for avoiding collision | |
| US20090303234A1 (en) | Method for object formation | |
| US10967867B2 (en) | Method and apparatus for efficiently providing occupancy information on the surroundings of a vehicle | |
| CN105684039B (en) | Condition analysis for driver assistance systems | |
| CN110008891B (en) | Pedestrian detection positioning method and device, vehicle-mounted computing equipment and storage medium | |
| CN109871787A (en) | A kind of obstacle detection method and device | |
| CN109823342B (en) | Vehicle intersection driving method, device and terminal | |
| CN111932881A (en) | Traffic intersection management method and device, terminal device and storage medium | |
| EP3867601A1 (en) | Method and system for determining a model of the environment of a vehicle | |
| CN110969843B (en) | Traffic sign identification alarm method with inhibition strategy | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| CN113432615B (en) | Detection method and system based on multi-sensor fusion drivable area and vehicle | |
| CN115626155A (en) | Conical barrel visualization method and device based on grid map | |
| CN115257726B (en) | Method and device for controlling vehicle, vehicle and storage medium | |
| CN116853235A (en) | Collision early warning method, device, computer equipment and storage medium | |
| CN113787997B (en) | Emergency braking control method, electronic device, and storage medium | |
| CN114999156A (en) | Automatic identification method and device for crossing scene of pedestrian in front of vehicle, medium and vehicle | |
| DE102019131667A1 (en) | VEHICLE AND METHOD OF PREDICTING A COLLISION | |
| CN116148860A (en) | Method and device for identifying static obstacle, vehicle and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |