CN114701516A - Method, device and equipment for acquiring turning driving data and storage medium - Google Patents

Method, device and equipment for acquiring turning driving data and storage medium Download PDF

Info

Publication number
CN114701516A
CN114701516A CN202210325025.3A CN202210325025A CN114701516A CN 114701516 A CN114701516 A CN 114701516A CN 202210325025 A CN202210325025 A CN 202210325025A CN 114701516 A CN114701516 A CN 114701516A
Authority
CN
China
Prior art keywords
turning
intersection
driving data
frame
vehicle
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
Application number
CN202210325025.3A
Other languages
Chinese (zh)
Inventor
聂鑫
韩旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Weride Technology Co Ltd
Original Assignee
Guangzhou Weride Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Weride Technology Co Ltd filed Critical Guangzhou Weride Technology Co Ltd
Priority to CN202210325025.3A priority Critical patent/CN114701516A/en
Publication of CN114701516A publication Critical patent/CN114701516A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W60/00Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001Planning or execution of driving tasks
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2552/00Input parameters relating to infrastructure
    • B60W2552/50Barriers

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to the technical field of automatic driving, and discloses a method, a device, equipment and a storage medium for collecting turning driving data, which are used for accurately and efficiently collecting the turning driving data. The method for acquiring the turning driving data comprises the following steps: acquiring multiframe driving data of the main vehicle, and screening intersection range data of the multiframe driving data to obtain multiframe intersection driving data respectively corresponding to at least one intersection, wherein each frame of driving data comprises obstacle information around the main vehicle; performing turning recognition on the main vehicle on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data respectively corresponding to at least one turning; and performing second turning judgment on a plurality of frames of first turning driving data corresponding to each turning based on the obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data.

Description

Method, device and equipment for acquiring turning driving data and storage medium
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method, a device, equipment and a storage medium for acquiring turning driving data.
Background
With the development of the automatic driving technology, the automatic driving vehicle can automatically drive in different scenes, such as a red light scene and a crossroad scene classified according to the road condition, an overtaking scene and a merging scene classified according to the driving behavior, and the like. The turning lane change of the main vehicle and the obstacle vehicle is a complex algorithm scene which is easy to make mistakes in automatic driving.
In the prior art, the collection of turning data is usually realized by manually marking data to train a classification model, but the number of unmanned data is very large, the efficiency of a method for collecting a target scene by manually checking all scenes is too low, the noise of a result obtained by the existing judgment logic is too much, most scenes are concentrated in a crowded road section and are not typical turning scenes, and therefore the turning scene data cannot be accurately and efficiently collected.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for collecting turning driving data, which are used for accurately and efficiently collecting the turning driving data.
The invention provides a method for acquiring turning driving data in a first aspect, which comprises the following steps:
acquiring multi-frame running data of the main vehicle, and screening intersection range data of the multi-frame running data to obtain multi-frame intersection running data respectively corresponding to at least one intersection, wherein each frame of running data comprises obstacle information around the main vehicle;
performing main vehicle turning identification on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
and performing second turning judgment on a plurality of frames of first turning driving data corresponding to each turning based on the obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data.
Optionally, the obtaining of the multiframe driving data of the host vehicle and the screening of the intersection range data of the multiframe driving data to obtain the multiframe intersection driving data corresponding to at least one intersection respectively includes:
acquiring multi-frame driving data of the main vehicle, wherein each frame of driving data comprises intersection range identification information which is used for indicating whether the main vehicle is in an intersection range in the corresponding frame of driving data;
and screening main vehicle intersection range data for each frame of driving data through the intersection range identification information to obtain a plurality of frames of intersection driving data respectively corresponding to at least one intersection.
Optionally, the method for screening the main vehicle intersection range data of each frame of driving data through the intersection range identification information to obtain the multi-frame intersection driving data corresponding to at least one intersection respectively includes:
setting any one frame in the multi-frame driving data as a current frame;
sequentially judging the range of the main vehicle intersection for the current frame and the next frame of the current frame through the intersection range identification information until the range of the main vehicle intersection is judged by all the frames, and obtaining a first target frame of the main vehicle in the intersection range and a second target frame of the main vehicle not in the intersection range;
and determining multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data through the first target frame and the second target frame.
Optionally, the performing of the main vehicle turning recognition on the multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning respectively includes:
calculating the frame number of the multi-frame intersection driving data corresponding to each intersection to obtain the intersection frame number corresponding to each intersection, and judging whether the intersection frame number corresponding to each intersection is smaller than a preset intersection frame number threshold or not;
if the intersection frame number is smaller than the preset intersection frame number threshold, calculating the starting and ending direction difference of the multi-frame intersection driving data of the corresponding intersection to obtain the direction difference value of the host vehicle corresponding to each intersection, determining the multi-frame intersection driving data of the corresponding intersection as the turning driving data of the host vehicle according to the direction difference value of the host vehicle corresponding to each intersection, and obtaining the multi-frame first turning driving data respectively corresponding to at least one turning.
Optionally, the calculating a difference between the starting direction and the ending direction of the multiple frames of intersection driving data of the corresponding intersection to obtain a direction difference of the host vehicle corresponding to each intersection, and determining the multiple frames of intersection driving data of the corresponding intersection as turning driving data of the host vehicle according to the direction difference of the host vehicle corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning respectively, includes:
respectively acquiring orientation angles of a main vehicle at the intersection starting position and the intersection tail end position in the multi-frame intersection driving data to obtain a starting orientation angle and an ending orientation angle corresponding to each intersection;
calculating the orientation difference of the main vehicle according to the starting orientation angle and the ending orientation angle corresponding to each intersection to obtain the orientation difference of the main vehicle corresponding to each intersection, and judging whether the orientation difference of the main vehicle corresponding to each intersection is within a preset orientation difference range;
and if the direction difference value of the main vehicle is within the preset direction difference value range, determining that the multi-frame intersection driving data of the corresponding intersection are multi-frame main vehicle turning driving data, and obtaining multi-frame first turning driving data respectively corresponding to at least one turn.
Optionally, the performing, based on the information of obstacles around the host vehicle in each frame of the first turning driving data, the second turning discrimination on the multiple frames of the first turning driving data corresponding to each turning to obtain the target turning driving data includes:
acquiring vehicle obstacle distance and vehicle obstacle orientation in obstacle information around the host vehicle in each frame of first turning driving data;
judging whether the obstacle information around the main vehicle in each frame of first turning driving data corresponding to each turning meets a preset second turning judgment condition or not according to the vehicle obstacle distance and the vehicle obstacle orientation;
and if the obstacle information around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the corresponding frame of turning driving data as the second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process, and determining target turning driving data according to the total frame number of the second turning driving data corresponding to each second turning process.
Optionally, the determining, according to the vehicle obstacle distance and the vehicle obstacle direction, whether obstacle information around the host vehicle in each frame of first turn driving data corresponding to each turn meets a preset second turn criterion includes:
judging whether the vehicle obstacle distance corresponding to each frame of first turning driving data corresponding to each turning is smaller than a preset vehicle obstacle distance threshold value or not;
if the distance between the vehicle obstacles corresponding to the turning driving data is smaller than the preset slave vehicle distance threshold value, calculating the difference value between the direction of the vehicle obstacles in the turning driving data of the corresponding frame and the direction of the master vehicle in the turning driving data of the corresponding frame to obtain a turning direction difference value;
judging whether the turning direction difference value is smaller than a preset direction difference value threshold value or not;
and if the turning direction difference value is smaller than a preset direction difference value threshold value, judging that the obstacle information around the main vehicle in the turning driving data of the corresponding frame meets a preset second turning judgment condition.
Optionally, if the information of obstacles around the main vehicle in the turning data satisfies the preset second turning judgment condition, determining the turning data of the corresponding frame as the second turning data of the corresponding turning, obtaining the second turning data corresponding to at least one second turning process, and determining the target turning data according to the total frame number of the second turning data corresponding to each second turning process, including:
if the information of obstacles around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the turning driving data of the corresponding frame as second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process;
calculating the total frame number of second turning driving data corresponding to each second turning process to obtain the second turning frame number corresponding to each second turning process;
judging whether the second turning frame number corresponding to each second turning process meets a preset second turning threshold condition or not;
and if the second turning frame number meets a preset second turning threshold value condition, determining a plurality of frames of first turning driving data corresponding to the second turning process as target turning driving data.
Optionally, after performing second turning judgment on multiple frames of first turning driving data corresponding to each turning based on obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data, the method for acquiring turning driving data further includes:
and sequencing the scene relevancy of the target turning driving data corresponding to each second turning process according to the second turning frame number to obtain a second turning driving data sequence.
A second aspect of the present invention provides a device for acquiring turn driving data, including:
the screening module is used for acquiring multiframe driving data of the main vehicle and screening intersection range data of the multiframe driving data to obtain multiframe intersection driving data respectively corresponding to at least one intersection, wherein each frame of driving data comprises obstacle information around the main vehicle;
the recognition module is used for recognizing turning of the main vehicle for multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
and the judging module is used for carrying out second turning judgment on the plurality of frames of first turning driving data corresponding to each turning based on the obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data.
Optionally, the screening module includes:
the system comprises an acquisition unit, a control unit and a display unit, wherein the acquisition unit is used for acquiring multi-frame driving data of a main vehicle, each frame of driving data comprises intersection range identification information, and the intersection range identification information is used for indicating whether the main vehicle is in an intersection range in the corresponding frame of driving data;
and the screening unit is used for screening the main vehicle intersection range data of each frame of driving data through the intersection range identification information to obtain the multi-frame intersection driving data respectively corresponding to at least one intersection.
Optionally, the screening unit is specifically configured to:
setting any one frame in the multi-frame driving data as a current frame;
sequentially judging the range of the main vehicle intersection for the current frame and the next frame of the current frame through the intersection range identification information until the range of the main vehicle intersection is judged by all the frames, and obtaining a first target frame of the main vehicle in the intersection range and a second target frame of the main vehicle not in the intersection range;
and determining multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data through the first target frame and the second target frame.
Optionally, the identification module includes:
the calculating unit is used for calculating the frame number of the multi-frame intersection driving data corresponding to each intersection to obtain the intersection frame number corresponding to each intersection and judging whether the intersection frame number corresponding to each intersection is smaller than a preset intersection frame number threshold value or not;
and the determining unit is used for calculating the starting and ending direction difference of the multi-frame intersection driving data of the corresponding intersection to obtain the main vehicle direction difference value corresponding to each intersection if the intersection frame number is less than the preset intersection frame number threshold, and determining the multi-frame intersection driving data of the corresponding intersection as the main vehicle turning driving data according to the main vehicle direction difference value corresponding to each intersection to obtain the multi-frame first turning driving data respectively corresponding to at least one turning.
Optionally, the determining unit is specifically configured to:
respectively acquiring orientation angles of a main vehicle at the intersection starting position and the intersection tail end position in the multi-frame intersection driving data to obtain a starting orientation angle and an ending orientation angle corresponding to each intersection;
calculating the orientation difference of the main vehicle according to the starting orientation angle and the ending orientation angle corresponding to each intersection to obtain the orientation difference of the main vehicle corresponding to each intersection, and judging whether the orientation difference of the main vehicle corresponding to each intersection is within a preset orientation difference range;
and if the direction difference value of the main vehicle is within the preset direction difference value range, determining that the multi-frame intersection driving data of the corresponding intersection are multi-frame main vehicle turning driving data, and obtaining multi-frame first turning driving data respectively corresponding to at least one turn.
Optionally, the determining module includes:
an extraction unit configured to acquire a vehicle obstacle distance and a vehicle obstacle orientation in obstacle information around the host vehicle in each frame of the first turn traveling data;
the judging unit is used for judging whether the obstacle information around the main vehicle in each frame of first turning driving data corresponding to each turning meets a preset second turning judging condition or not according to the vehicle obstacle distance and the vehicle obstacle direction;
and the judging unit is used for determining the turning driving data of the corresponding frame as the second turning driving data of the corresponding turning if the obstacle information around the main vehicle in the turning driving data meets the preset second turning judging condition, obtaining the second turning driving data respectively corresponding to at least one second turning process, and determining the target turning driving data according to the total frame number of the second turning driving data corresponding to each second turning process.
Optionally, the determining unit is specifically configured to:
judging whether the vehicle obstacle distance corresponding to each frame of first turning driving data corresponding to each turning is smaller than a preset vehicle obstacle distance threshold value or not;
if the distance between the vehicle obstacles corresponding to the turning driving data is smaller than the preset slave vehicle distance threshold value, calculating the difference value between the direction of the vehicle obstacles in the turning driving data of the corresponding frame and the direction of the master vehicle in the turning driving data of the corresponding frame to obtain a turning direction difference value;
judging whether the turning direction difference value is smaller than a preset direction difference value threshold value or not;
and if the turning direction difference value is smaller than a preset direction difference value threshold value, judging that the obstacle information around the main vehicle in the turning driving data of the corresponding frame meets a preset second turning judgment condition.
Optionally, the determining unit is specifically configured to:
if the information of obstacles around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the turning driving data of the corresponding frame as second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process;
calculating the total frame number of the second turning driving data corresponding to each second turning process to obtain the second turning frame number corresponding to each second turning process;
judging whether the second turning frame number corresponding to each second turning process meets a preset second turning threshold condition or not;
and if the second turning frame number meets a preset second turning threshold value condition, determining a plurality of frames of first turning driving data corresponding to the second turning process as target turning driving data.
Optionally, the device for acquiring turning data further includes:
and the sequencing module is used for sequencing the scene relevancy of the target turning driving data corresponding to each second turning process according to the second turning frame number to obtain a second turning driving data sequence.
A third aspect of the present invention provides an apparatus for acquiring turning data, comprising: a memory and at least one processor, the memory having stored therein a computer program; the at least one processor calls the computer program in the memory to cause the apparatus for acquiring turn driving data to execute the above-described method for acquiring turn driving data.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute the above-described method of acquiring turning data.
According to the technical scheme provided by the invention, multi-frame running data of the main vehicle is obtained, and intersection range data screening is carried out on the multi-frame running data to obtain multi-frame intersection running data respectively corresponding to at least one intersection, wherein each frame of running data comprises obstacle information around the main vehicle; performing main vehicle turning identification on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning; and performing second turning judgment on a plurality of frames of first turning driving data corresponding to each turning based on the obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data. In the embodiment of the invention, as the main vehicle is in the intersection as a prerequisite condition for turning, multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data is extracted through the screening of the intersection range data, and the main vehicle turns or not through the intersection, multi-frame first turning driving data respectively corresponding to at least one turning in the multi-frame intersection driving data corresponding to each intersection is obtained through the turning recognition of the main vehicle, and finally whether the main vehicle and the vehicle obstacle perform second turning or not is judged through the obstacle information around the main vehicle, so that the target turning driving data is obtained.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for acquiring turning data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of the method for acquiring turning data according to the embodiment of the invention;
FIG. 3 is a schematic diagram of an embodiment of a device for acquiring turning data according to an embodiment of the present invention;
FIG. 4 is a schematic view of another embodiment of the device for acquiring turning driving data according to the embodiment of the invention;
fig. 5 is a schematic diagram of an embodiment of the device for acquiring turning data according to the embodiment of the invention.
Detailed Description
The embodiment of the invention provides a method, a device and equipment for collecting turn driving data and a storage medium, which are used for accurately and efficiently collecting second turn driving data.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It is understood that the executing subject of the present invention may be a device for acquiring turning driving data, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
For convenience of understanding, a specific flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for acquiring turning driving data according to an embodiment of the present invention includes:
101. acquiring multiframe driving data of the main vehicle, and screening intersection range data of the multiframe driving data to obtain multiframe intersection driving data respectively corresponding to at least one intersection, wherein each frame of driving data comprises obstacle information around the main vehicle;
the host vehicle refers to an automatic drive control vehicle, and the multi-frame travel data of the host vehicle may be actual travel data of the host vehicle or drive test data of the host vehicle. The multi-frame running data comprises main vehicle running control data with preset time length, each frame of running data comprises, but is not limited to, main vehicle basic information, main vehicle position information, main vehicle orientation information, main vehicle intersection range identification information and main vehicle surrounding obstacle information, wherein the main vehicle surrounding obstacle information is used for indicating vehicle information causing obstacle effect on the main vehicle, and the main vehicle surrounding obstacle information comprises, but is not limited to, position information and orientation information of vehicle obstacles.
In one embodiment, in order to control the amount of data for the collection operation, that is, the amount of data for the multi-frame travel data, the multi-frame travel data of the host vehicle is acquired through a preset collection time range and a collection vehicle range, thereby improving the collection efficiency of the turn travel data.
It should be noted that, since the host vehicle may pass through one or more intersections in the multi-frame driving data, in order to improve the accuracy of acquiring the turning driving data and reduce the noise of the acquired data, in an embodiment, the multi-frame intersection driving data corresponding to at least one intersection is extracted from the multi-frame driving data, specifically, whether the host vehicle is at the intersection position is determined according to the position information of the host vehicle in each frame of driving data, and if the host vehicle is at the intersection position, the corresponding frame of driving data is determined as the intersection driving data of the corresponding intersection, so as to obtain the multi-frame intersection driving data corresponding to at least one intersection.
102. Performing main vehicle turning identification on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
it can be understood that, since the host vehicle passes through the intersections but does not necessarily turn, in order to improve the accuracy of the turning data acquisition and reduce the data noise, the host vehicle turning recognition is performed on the multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turn, in one embodiment, the host vehicle direction difference of the multiple frames of intersection driving data corresponding to each intersection is calculated through the direction information of the host vehicle in each frame of intersection driving data to obtain the host vehicle direction difference corresponding to each intersection, and then whether the host vehicle turns at the corresponding intersection is judged according to the host vehicle direction difference corresponding to each intersection, if the host vehicle turns at the corresponding intersection, the multiple frames of intersection driving data corresponding to the corresponding intersection are determined as the multiple frames of first turning driving data to obtain the multiple frames of first turning driving data corresponding to at least one turn, further, whether the host vehicle turns at the corresponding intersection is judged by judging whether the orientation difference value of the host vehicle corresponding to each intersection is larger than a preset orientation difference value threshold value, wherein the orientation difference value of the host vehicle is used for indicating that the host vehicle is positioned at the orientation angle difference value of the intersection starting position and the intersection tail end position. For example, assuming that the current multiple frames of intersection driving data corresponding to the intersection a, the intersection B, and the intersection C respectively correspond to multiple frames of intersection driving data, the direction difference of the host vehicle corresponding to the intersection a is calculated to be 20 degrees, the direction difference of the host vehicle corresponding to the intersection B is 90 degrees, the direction difference of the host vehicle corresponding to the intersection C is 190 degrees, and the preset direction difference threshold is 60 degrees, it is determined that the host vehicle turns at the intersection B and the intersection C, and then the multiple frames of intersection driving data corresponding to the intersection B are determined as the multiple frames of first turning driving data of one turning, and the multiple frames of intersection driving data corresponding to the intersection C are determined as the multiple frames of first turning driving data of another turning, so as to obtain the multiple frames of first turning driving data corresponding to two turning respectively.
In one embodiment, because the data of the non-typical turning scene in the congestion state is difficult to be applied to other application scenes of typical turning scenes, such as the research and development of an automatic driving algorithm or iterative test data, in order to reduce the noise of the turning data acquisition and improve the accuracy of the turning data acquisition, after obtaining the multi-frame intersection driving data corresponding to at least one intersection, before performing main vehicle turning recognition on the multi-frame intersection driving data corresponding to each intersection, the intersection driving time length calculation is performed on the multi-frame intersection driving data corresponding to each intersection to obtain the intersection driving time length corresponding to each intersection, whether the intersection driving time length corresponding to each intersection is less than a preset intersection driving time length threshold value is judged, if the intersection driving time length is less than the preset intersection driving time length threshold value, the multi-frame intersection driving data corresponding to the intersection is determined to be multi-frame smooth driving data, and obtaining multi-frame smooth running data corresponding to at least one intersection, and performing turning recognition on the main vehicle according to the multi-frame smooth running data corresponding to each intersection to obtain multi-frame first turning running data corresponding to at least one turning.
103. And performing second turning judgment on a plurality of frames of first turning driving data corresponding to each turning based on the obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data.
It is understood that the second turning may be a parallel turning between the host vehicle and the surrounding obstacle vehicle, a following turning between the host vehicle and the surrounding obstacle vehicle, or a turning in which other host vehicle and the surrounding obstacle vehicle keep a specific turning relationship, that is, the target turning data may be turning data in which the host vehicle and the surrounding obstacle vehicle keep a specific turning relationship, such as parallel turning data in which the host vehicle and the surrounding obstacle vehicle keep a certain degree of relative parallelism during turning, following turning data in which the host vehicle and the surrounding obstacle vehicle keep a following relationship during turning. In order to accurately acquire turning driving data, second turning judgment is performed on a plurality of frames of first turning driving data corresponding to each turning based on obstacle information around the main vehicle in each frame of first turning driving data, and target turning driving data is obtained. In one embodiment, a second turning vehicle obstacle recognition is performed on a plurality of frames of first turning travel data corresponding to each turn based on orientation information and position information of the host vehicle in the respective frames of first turning travel data and orientation information and position information in obstacle information around the host vehicle to obtain a recognition result, wherein the second turning vehicle obstacle is used for indicating a vehicle obstacle keeping a specific turning relationship with the host vehicle, such as a parallel turning vehicle obstacle, a following turning vehicle obstacle, and the like, the recognition result is used for indicating the number of second turning vehicle obstacles in the corresponding frame of turning travel data, if the recognition result indicates that the number of second turning vehicle obstacles in the corresponding frame of turning travel data is greater than a preset number threshold value, the corresponding frame is determined as the second turning travel data to obtain at least one frame of second turning travel data corresponding to each turn, and determining target turning driving data according to at least one frame of second turning driving data corresponding to each turning.
Further, determining the target turning travel data based on at least one frame of the second turning travel data corresponding to each turn includes: and if the second turning frame number meets the preset second turning threshold condition, determining the second turning driving data corresponding to the turning as second turning driving data corresponding to one second turning to obtain target turning driving data.
In the embodiment of the invention, as the main vehicle is in the intersection as a prerequisite condition for turning, multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data is extracted through the screening of the intersection range data, and the main vehicle turns or not through the intersection, multi-frame first turning driving data respectively corresponding to at least one turning in the multi-frame intersection driving data corresponding to each intersection is obtained through the turning recognition of the main vehicle, and finally whether the main vehicle and the vehicle obstacle perform second turning or not is judged through the obstacle information around the main vehicle, so that the target turning driving data is obtained.
Referring to fig. 2, another embodiment of the method for acquiring turning data according to the embodiment of the present invention includes:
201. acquiring multiframe driving data of the main vehicle, and screening intersection range data of the multiframe driving data to obtain multiframe intersection driving data respectively corresponding to at least one intersection, wherein each frame of driving data comprises obstacle information around the main vehicle;
specifically, step 201 includes: acquiring multi-frame driving data of the main vehicle, wherein each frame of driving data comprises intersection range identification information which is used for indicating whether the main vehicle is in an intersection range in the corresponding frame of driving data; and screening main vehicle intersection range data for each frame of driving data through the intersection range identification information to obtain multi-frame intersection driving data respectively corresponding to at least one intersection. In the present embodiment, in order to quickly perform intersection range data screening on multiple frames of driving data, efficiently screen out the driving data of the host vehicle in the intersection range, and acquire intersection range identification information in each frame of driving data, where the intersection range identification information is used to indicate whether the host vehicle in the corresponding frame of driving data is in the intersection range, for example, if the intersection range identification information is 1, it indicates that the host vehicle in the frame of driving data is in the intersection range, and if the intersection range identification information is 0, it indicates that the host vehicle in the frame of driving data is not in the intersection range, and this is not particularly limited. And extracting the intersection driving data in the multi-frame driving data through the intersection range identification information to obtain the multi-frame intersection driving data respectively corresponding to at least one intersection.
Further, the method for screening the main vehicle intersection range data of each frame of driving data through the intersection range identification information to obtain the multi-frame intersection driving data respectively corresponding to at least one intersection comprises the following steps: setting any one frame in the multi-frame driving data as a current frame; sequentially judging the range of the main vehicle intersection for the current frame and the next frame of the current frame through the intersection range identification information until the range of the main vehicle intersection is judged by all the frames, and obtaining a first target frame of the main vehicle in the intersection range and a second target frame of the main vehicle not in the intersection range; and determining multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data through the first target frame and the second target frame. In the embodiment, any one frame in the multi-frame driving data is set as a current frame, the range of the intersection of the host vehicle is judged for each frame in the multi-frame driving data, a first target frame of the host vehicle in the range of the intersection and a second target frame of the host vehicle not in the range of the intersection are obtained, and then the intersection data of the multi-frame driving data are divided according to the first target frame and the second target frame, so that the multi-frame intersection driving data respectively corresponding to at least one intersection are obtained. The method and the device can rapidly determine the intersection driving data of different intersections, thereby improving the acquisition efficiency of the turning driving data.
202. Performing main vehicle turning identification on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
specifically, step 202 includes: calculating the frame number of the multi-frame intersection driving data corresponding to each intersection to obtain the intersection frame number corresponding to each intersection, and judging whether the intersection frame number corresponding to each intersection is smaller than a preset intersection frame number threshold or not; if the number of crossing frames is less than the preset crossing frame number threshold, calculating the starting and ending orientation difference of multi-frame crossing driving data of the corresponding crossing, and obtaining the orientation difference of the host vehicle corresponding to each crossing, for example, the orientation information when the host vehicle is located at the starting position of the crossing in the multi-frame crossing driving data corresponding to a certain crossing is 10 degrees, the orientation information when the host vehicle is located at the end position of the crossing is 180 degrees, then the starting and ending orientation difference corresponding to the crossing is 180-10 degrees to 170 degrees, that is, the orientation difference of the host vehicle corresponding to the crossing is 170 degrees. And then determining multiframe intersection driving data of corresponding intersections as main vehicle turning driving data according to the main vehicle direction difference value corresponding to each intersection to obtain multiframe first turning driving data respectively corresponding to at least one turn.
It should be noted that, in order to eliminate the turning data under the condition of overcrowding and improve the accuracy of the turning data acquisition, calculating the frame number of the multi-frame crossing driving data corresponding to each crossing to obtain the crossing frame number corresponding to each crossing and judging whether the crossing frame number corresponding to each crossing is smaller than the preset crossing frame number threshold value or not, if the crossing frame number is smaller than the preset crossing frame number threshold value, indicating that the main vehicle passes through the crossing, the intersection is not in a congestion state, the intersection turns within a preset threshold frame number of the intersection frame number, calculating the direction difference of the beginning and the end of the multi-frame intersection driving data of the corresponding intersection to obtain the direction difference of the main vehicle corresponding to each intersection, and determining multiple frames of intersection running data of corresponding intersections as turning running data of the host vehicle according to the heading difference value of the host vehicle corresponding to each intersection to obtain multiple frames of first turning running data respectively corresponding to at least one turn. If the intersection frame number is greater than or equal to the preset intersection frame number threshold, the intersection is in a congestion state when the main vehicle passes through the intersection, and the intersection turning is not finished within the preset intersection frame number threshold frame number, the multi-frame intersection driving data corresponding to the intersection are not included in the subsequent processing, so that the second turning driving data under the congestion condition are eliminated, and the accuracy of the turning driving data acquisition is improved.
In one embodiment, if the intersection frame number is less than the preset intersection frame number threshold, the heading difference of the multi-frame intersection driving data corresponding to each intersection is calculated according to the heading information of the starting frame and the ending frame in the multi-frame intersection driving data corresponding to each intersection, the heading difference of the host vehicle corresponding to each intersection is obtained, whether the heading difference of the host vehicle corresponding to each intersection is greater than the preset heading difference threshold or not is judged, if the heading difference of the host vehicle is greater than the preset heading difference threshold, the multi-frame intersection driving data corresponding to the intersection is taken as the turning driving data of the host vehicle, and the first turning driving data of the multi-frame corresponding to at least one turning is obtained. The embodiment can quickly identify whether the main vehicle turns at the intersection or not, so that the efficiency of turning driving data acquisition is improved.
Further, calculating the direction difference of the start and the end of the multi-frame intersection driving data of the corresponding intersection to obtain the direction difference of the main vehicle corresponding to each intersection, determining the multi-frame intersection driving data of the corresponding intersection as the main vehicle turning driving data according to the direction difference of the main vehicle corresponding to each intersection to obtain the multi-frame first turning driving data respectively corresponding to at least one turning, and the method comprises the following steps: respectively acquiring orientation angles of a main vehicle at the intersection starting position and the intersection tail end position in the multi-frame intersection driving data to obtain a starting orientation angle and an ending orientation angle corresponding to each intersection; calculating the orientation difference of the main vehicle according to the starting orientation angle and the ending orientation angle corresponding to each intersection to obtain the orientation difference of the main vehicle corresponding to each intersection, and judging whether the orientation difference of the main vehicle corresponding to each intersection is within a preset orientation difference range; and if the direction difference value of the main vehicle is within the preset direction difference value range, determining that the multi-frame intersection driving data of the corresponding intersection are multi-frame main vehicle turning driving data, and obtaining multi-frame first turning driving data respectively corresponding to at least one turn. In the embodiment, the initial orientation angle corresponding to each intersection is determined through the orientation angle of the main vehicle at the initial position of the intersection in the multi-frame intersection driving data, the ending orientation angle corresponding to each intersection is determined through the orientation angle of the main vehicle at the tail end of the intersection in the multi-frame intersection driving data, the orientation difference value of the main vehicle corresponding to each intersection is calculated through the initial orientation angle and the ending orientation angle corresponding to each intersection, and whether the orientation difference value of the main vehicle corresponding to each intersection is within a preset orientation difference value range is judged; if the direction difference value of the main vehicle is within the preset direction difference value range, the main vehicle turns at the intersection, and then the multi-frame intersection driving data of the corresponding intersection is determined to be multi-frame main vehicle turning driving data, and multi-frame first turning driving data corresponding to at least one turning is obtained. By way of example and not limitation, assuming that the preset orientation difference range is 60-190 degrees, if the starting orientation angle and the ending orientation angle of a certain intersection are 30 degrees and 200 degrees respectively, the orientation difference of the host vehicle corresponding to the intersection is 170 degrees and falls into the range of 60-190 degrees, and the multi-frame intersection driving data corresponding to the intersection is determined to be the multi-frame first turning driving data.
203. Acquiring vehicle obstacle distance and vehicle obstacle orientation in obstacle information around the host vehicle in each frame of first turning driving data;
it is understood that the obstacle information around the host vehicle in each frame of the first turn traveling data includes a vehicle obstacle distance indicating a distance between the vehicle obstacle and the host vehicle and a vehicle obstacle orientation indicating orientation information of the vehicle obstacle.
204. Judging whether the obstacle information around the main vehicle in each frame of first turning driving data corresponding to each turning meets a preset second turning judgment condition or not according to the distance and the direction of the obstacle of the vehicle;
specifically, step 204 includes: judging whether the vehicle obstacle distance corresponding to each frame of first turning driving data corresponding to each turning is smaller than a preset vehicle obstacle distance threshold value or not; if the distance between the vehicle obstacle corresponding to the turning driving data is smaller than a preset secondary vehicle distance threshold value, calculating a difference value between the orientation of the vehicle obstacle in the turning driving data of the corresponding frame and the orientation of the main vehicle in the turning driving data of the corresponding frame to obtain a turning orientation difference value; judging whether the turning direction difference value is smaller than a preset direction difference value threshold value or not; and if the turning direction difference value is smaller than the preset direction difference value threshold value, judging that the obstacle information around the main vehicle in the turning driving data of the corresponding frame meets a preset second turning judgment condition. In one embodiment, a preset second turning judgment condition is used for indicating the parallel turning judgment condition, in order to accurately identify the vehicle obstacle which makes a parallel turn with the host vehicle, firstly, whether the vehicle obstacle distance corresponding to each frame of first turning running data corresponding to each turn is smaller than a preset vehicle obstacle distance threshold value is judged, if the vehicle obstacle distance corresponding to the turning running data is smaller than a preset slave vehicle distance threshold value, the situation that the vehicle obstacle is closer to the host vehicle and the parallel turning running exists is indicated, then, the difference value between the orientation of the vehicle obstacle in the corresponding frame of turning running data and the orientation of the host vehicle in the corresponding frame of turning running data is calculated to obtain the turning orientation difference value, and whether the turning orientation difference value is smaller than the preset orientation difference value threshold value is judged to determine whether the vehicle obstacle closer to the host vehicle is also close to the host vehicle orientation, if the turning direction difference value is smaller than the preset direction difference value threshold value, which indicates that the directions of the vehicle barrier and the host vehicle are also similar, judging that the barrier information around the host vehicle in the turning driving data of the corresponding frame meets the preset second turning judgment condition, and determining that the vehicle barrier in the turning driving data of the corresponding frame and the host vehicle perform parallel turning.
205. And if the obstacle information around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the corresponding frame of turning driving data as the second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process, and determining target turning driving data according to the total frame number of the second turning driving data corresponding to each second turning process.
It should be noted that, since the non-second turning travel data may include turning travel data satisfying the preset second turning determination condition, in order to avoid the one-sidedness of the second turning travel data determined as long as the turning travel data satisfying the preset second turning determination condition exists, after the second turning travel data corresponding to each of the at least one second turning course is obtained, it is determined whether the second turning travel data corresponding to each of the second turning courses satisfies the preset second turning threshold condition according to the total number of frames of the second turning travel data corresponding to each of the second turning courses, and the target turning travel data is determined according to the determination result. For example, the total number of frames of the second turning travel data needs to be more than 50 frames to satisfy the preset second turning threshold condition.
Specifically, step 205 includes: if the information of obstacles around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the turning driving data of the corresponding frame as second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process; calculating the total frame number of second turning driving data corresponding to each second turning process to obtain the second turning frame number corresponding to each second turning process; judging whether the second turning frame number corresponding to each second turning process meets a preset second turning threshold condition or not; and if the second turning frame number meets the preset second turning threshold value condition, determining the plurality of frames of the first turning driving data corresponding to the second turning process as the target turning driving data. In one embodiment, after second turning data corresponding to at least one second turning process is obtained, a total frame number of the second turning data corresponding to each second turning process is calculated, a second turning frame number corresponding to each second turning process is obtained, the proportion of the second turning frame number corresponding to each second turning process to the total frame number is calculated, a second turning proportion corresponding to each second turning process is obtained, whether the second turning frame number corresponding to each second turning process and the second turning proportion meet a preset second turning threshold condition or not is judged, and if the second turning frame number and the second turning proportion meet the preset second turning threshold condition, multiple frames of first turning data corresponding to the second turning process are determined as target turning driving data. For example, when the second turning frame number is greater than 50 and the second turning proportion is greater than 70%, the plurality of frames of the first turning travel data corresponding to the second turning course are determined as the target turning travel data.
Further, after performing second turning discrimination on a plurality of frames of the first turning travel data corresponding to each turning based on obstacle information around the host vehicle in each frame of the first turning travel data to obtain target turning travel data, the method further includes: and sequencing the scene relevancy of the target turning driving data corresponding to each second turning process according to the second turning frame number to obtain a second turning driving data sequence. Since the second turning frame number and the second turning proportion can indicate the scene relevancy of the corresponding target turning driving data, that is, the more the second turning driving frame number is matched with the second turning driving scene, in order to obtain the second turning driving data with different scene relevancy, according to the second turning frame number or the second turning proportion, the target turning driving data corresponding to each second turning process is subjected to scene relevancy descending sorting to obtain a second turning driving data sequence, so as to meet the requirement of obtaining different scene relevancy data.
In the embodiment of the invention, as the main vehicle is in the intersection as the prerequisite condition of turning, multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data is extracted through the screening of the intersection range data, and whether the main vehicle turns or not is judged through the turning recognition of the main vehicle, and whether the main vehicle and the vehicle obstacle perform second turning or not is judged through the vehicle obstacle distance and the vehicle obstacle orientation in the surrounding obstacle information of the main vehicle, so that the target turning driving data is obtained.
With reference to fig. 3, the method for acquiring turning data according to the embodiment of the present invention is described above, and an embodiment of the apparatus for acquiring turning data according to the embodiment of the present invention includes:
the screening module 301 is configured to acquire multi-frame driving data of the host vehicle, and perform intersection range data screening on the multi-frame driving data to obtain multi-frame intersection driving data corresponding to at least one intersection, where each frame of driving data includes information of obstacles around the host vehicle;
the identification module 302 is configured to perform main vehicle turning identification on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
the judging module 303 is configured to perform second turning judgment on multiple frames of first turning driving data corresponding to each turning based on obstacle information around the main vehicle in each frame of first turning driving data, so as to obtain target turning driving data.
In the embodiment of the invention, as the main vehicle is in the intersection as a prerequisite condition for turning, multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data is extracted through the screening of the intersection range data, and the main vehicle turns or not through the intersection, multi-frame first turning driving data respectively corresponding to at least one turning in the multi-frame intersection driving data corresponding to each intersection is obtained through the turning recognition of the main vehicle, and finally whether the main vehicle and the vehicle obstacle perform second turning or not is judged through the obstacle information around the main vehicle, so that the target turning driving data is obtained.
Referring to fig. 4, another embodiment of the device for acquiring turning data according to the embodiment of the present invention includes:
the screening module 301 is configured to acquire multi-frame driving data of the host vehicle, and screen intersection range data of the multi-frame driving data to obtain multi-frame intersection driving data corresponding to at least one intersection, where each frame of driving data includes information of obstacles around the host vehicle;
the identification module 302 is configured to perform main vehicle turning identification on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
the judging module 303 is configured to perform second turning judgment on multiple frames of first turning driving data corresponding to each turning based on obstacle information around the main vehicle in each frame of first turning driving data, so as to obtain target turning driving data.
Optionally, the screening module 301 includes:
an obtaining unit 3011, configured to obtain multiple frames of driving data of a host vehicle, where each frame of driving data includes intersection range identification information, and the intersection range identification information is used to indicate whether the host vehicle is in an intersection range in corresponding frames of driving data;
and the screening unit 3012 is configured to perform main vehicle intersection range data screening on each frame of driving data according to the intersection range identification information, so as to obtain multiple frames of intersection driving data corresponding to at least one intersection respectively.
Optionally, the screening unit 3012 is specifically configured to:
setting any one frame in the multi-frame driving data as a current frame;
sequentially judging the range of the main vehicle intersection for the current frame and the next frame of the current frame through the intersection range identification information until the range of the main vehicle intersection is judged by all the frames, and obtaining a first target frame of the main vehicle in the intersection range and a second target frame of the main vehicle not in the intersection range;
and determining multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data through the first target frame and the second target frame.
Optionally, the identifying module 302 includes:
a calculating unit 3021, configured to perform frame number calculation on the multi-frame intersection driving data corresponding to each intersection to obtain an intersection frame number corresponding to each intersection, and determine whether the intersection frame number corresponding to each intersection is smaller than a preset intersection frame number threshold;
the determining unit 3022 is configured to, if the number of intersection frames is less than the preset intersection frame number threshold, calculate a start-end direction difference of the multi-frame intersection driving data of the corresponding intersection to obtain a host vehicle direction difference value corresponding to each intersection, determine, according to the host vehicle direction difference value corresponding to each intersection, the multi-frame intersection driving data of the corresponding intersection as host vehicle turning driving data, and obtain multi-frame first turning driving data corresponding to at least one turn.
Optionally, the determining unit 3022 is specifically configured to:
respectively acquiring orientation angles of a main vehicle at the intersection starting position and the intersection tail end position in the multi-frame intersection driving data to obtain a starting orientation angle and an ending orientation angle corresponding to each intersection;
calculating the orientation difference of the main vehicle according to the starting orientation angle and the ending orientation angle corresponding to each intersection to obtain the orientation difference of the main vehicle corresponding to each intersection, and judging whether the orientation difference of the main vehicle corresponding to each intersection is within a preset orientation difference range;
and if the direction difference value of the main vehicle is within the preset direction difference value range, determining that the multi-frame intersection driving data of the corresponding intersection are multi-frame main vehicle turning driving data, and obtaining multi-frame first turning driving data respectively corresponding to at least one turn.
Optionally, the determining module 303 includes:
an extraction unit 3031 configured to acquire a vehicle obstacle distance and a vehicle obstacle orientation in the obstacle information around the host vehicle in each frame of the first turn traveling data;
a determination unit 3032, configured to determine whether obstacle information around the main vehicle in each frame of first turn driving data corresponding to each turn satisfies a preset second turn determination condition according to the vehicle obstacle distance and the vehicle obstacle direction;
a determining unit 3033, configured to determine the turning driving data of the corresponding frame as the second turning driving data of the corresponding turning if the obstacle information around the main vehicle in the turning driving data satisfies the preset second turning determining condition, to obtain second turning driving data corresponding to at least one second turning process, and to determine the target turning driving data according to the total frame number of the second turning driving data corresponding to each second turning process.
Optionally, the determining unit 3032 is specifically configured to:
judging whether the vehicle obstacle distance corresponding to each frame of first turning driving data corresponding to each turning is smaller than a preset vehicle obstacle distance threshold value or not;
if the distance between the vehicle obstacles corresponding to the turning driving data is smaller than the preset slave vehicle distance threshold value, calculating the difference value between the direction of the vehicle obstacles in the turning driving data of the corresponding frame and the direction of the master vehicle in the turning driving data of the corresponding frame to obtain a turning direction difference value;
judging whether the turning direction difference value is smaller than a preset direction difference value threshold value or not;
and if the turning direction difference value is smaller than a preset direction difference value threshold value, judging that the obstacle information around the main vehicle in the turning driving data of the corresponding frame meets a preset second turning judgment condition.
Optionally, the determining unit 3033 is specifically configured to:
if the information of obstacles around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the turning driving data of the corresponding frame as second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process;
calculating the total frame number of second turning driving data corresponding to each second turning process to obtain the second turning frame number corresponding to each second turning process;
judging whether the second turning frame number corresponding to each second turning process meets a preset second turning threshold value condition or not;
and if the second turning frame number meets a preset second turning threshold value condition, determining a plurality of frames of first turning driving data corresponding to the second turning process as target turning driving data.
Optionally, the device for acquiring turning data further includes:
and the sorting module 304 is configured to perform scene relevancy sorting on the target turning driving data corresponding to each second turning process according to the second turning frame number to obtain a second turning driving data sequence.
In the embodiment of the invention, as the main vehicle is in the intersection as the prerequisite condition of turning, multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data is extracted through the screening of the intersection range data, and whether the main vehicle turns or not is judged through the turning recognition of the main vehicle, and whether the main vehicle and the vehicle obstacle perform second turning or not is judged through the vehicle obstacle distance and the vehicle obstacle orientation in the surrounding obstacle information of the main vehicle, so that the target turning driving data is obtained.
Fig. 3 and 4 describe the device for acquiring turning driving data in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the device for acquiring turning driving data in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a device for acquiring turning driving data according to an embodiment of the present invention, where the device 500 for acquiring turning driving data may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of computer program operations in the acquisition device 500 of the turning travel data. Still further, the processor 510 may be configured to communicate with the storage medium 530, and execute a series of computer program operations in the storage medium 530 on the acquisition device 500 of the turning travel data.
The turn driving data collection device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of the acquisition device of the turning travel data shown in fig. 5 does not constitute a limitation of the acquisition device of the turning travel data, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
The present invention also provides a computer device including a memory and a processor, wherein the memory stores a computer readable computer program, and when the computer readable computer program is executed by the processor, the processor executes the steps of the method for acquiring turning circle data in the above embodiments.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein a computer program, which, when run on a computer, causes the computer to execute the steps of the method for acquiring turning travel data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may substantially or partially contribute to the prior art, or all or part of the technical solution may be embodied in the form of a software product, which is stored in a storage medium and includes several computer programs to enable a computer device (which may be a personal computer, a server, or a network device) to execute 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 portable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (12)

1. A method of collecting turning travel data, characterized by comprising:
acquiring multiframe driving data of the main vehicle, and screening intersection range data of the multiframe driving data to obtain multiframe intersection driving data respectively corresponding to at least one intersection, wherein each frame of driving data comprises obstacle information around the main vehicle;
performing main vehicle turning identification on multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
and performing second turning judgment on a plurality of frames of first turning driving data corresponding to each turning based on the obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data.
2. The method for acquiring turning driving data according to claim 1, wherein the acquiring of the multiframe driving data of the host vehicle and the screening of the intersection range data of the multiframe driving data to obtain the multiframe intersection driving data corresponding to at least one intersection respectively comprises:
acquiring multi-frame driving data of the main vehicle, wherein each frame of driving data comprises intersection range identification information which is used for indicating whether the main vehicle is in an intersection range in the corresponding frame of driving data;
and screening the range data of the main vehicle intersection for each frame of driving data through the intersection range identification information to obtain multiple frames of intersection driving data respectively corresponding to at least one intersection.
3. The method for collecting turning driving data according to claim 2, wherein the screening of main intersection range data for each frame of driving data by the intersection range identification information to obtain multiple frames of intersection driving data corresponding to at least one intersection respectively comprises:
setting any one frame in the multi-frame driving data as a current frame;
sequentially judging the range of the main vehicle intersection for the current frame and the next frame of the current frame through the intersection range identification information until the range of the main vehicle intersection is judged by all the frames, and obtaining a first target frame of the main vehicle in the intersection range and a second target frame of the main vehicle not in the intersection range;
and determining multi-frame intersection driving data respectively corresponding to at least one intersection in the multi-frame driving data through the first target frame and the second target frame.
4. The method for collecting turning driving data according to claim 1, wherein the performing main vehicle turning recognition on the multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turn respectively comprises:
calculating the frame number of the multi-frame intersection driving data corresponding to each intersection to obtain the intersection frame number corresponding to each intersection, and judging whether the intersection frame number corresponding to each intersection is smaller than a preset intersection frame number threshold or not;
if the intersection frame number is smaller than the preset intersection frame number threshold, calculating the starting and ending direction difference of the multi-frame intersection driving data of the corresponding intersection to obtain the main vehicle direction difference value corresponding to each intersection, determining the multi-frame intersection driving data of the corresponding intersection as main vehicle turning driving data according to the main vehicle direction difference value corresponding to each intersection, and obtaining the multi-frame first turning driving data respectively corresponding to at least one turning.
5. The method for acquiring turning travel data according to claim 4, wherein the step of calculating the direction difference between the beginning and the end of the multi-frame intersection travel data of the corresponding intersection to obtain the direction difference of the host vehicle corresponding to each intersection, and determining the multi-frame intersection travel data of the corresponding intersection as the turning travel data of the host vehicle according to the direction difference of the host vehicle corresponding to each intersection to obtain the multi-frame first turning travel data corresponding to at least one turning respectively comprises:
respectively acquiring orientation angles of a main vehicle at the intersection starting position and the intersection tail end position in the multi-frame intersection driving data to obtain a starting orientation angle and an ending orientation angle corresponding to each intersection;
calculating the orientation difference of the host vehicle according to the starting orientation angle and the ending orientation angle corresponding to each intersection to obtain the orientation difference of the host vehicle corresponding to each intersection, and judging whether the orientation difference of the host vehicle corresponding to each intersection is within a preset orientation difference range or not;
and if the direction difference value of the main vehicle is within the preset direction difference value range, determining that the multi-frame intersection driving data of the corresponding intersection are multi-frame main vehicle turning driving data, and obtaining multi-frame first turning driving data respectively corresponding to at least one turn.
6. The method for collecting turning travel data according to claim 1, wherein the second turning discrimination for a plurality of frames of the first turning travel data corresponding to each turning based on the obstacle information around the host vehicle in each frame of the first turning travel data to obtain target turning travel data includes:
acquiring vehicle obstacle distance and vehicle obstacle orientation in obstacle information around the host vehicle in each frame of first turning driving data;
judging whether the obstacle information around the main vehicle in each frame of first turning driving data corresponding to each turning meets a preset second turning judgment condition or not according to the vehicle obstacle distance and the vehicle obstacle orientation;
and if the obstacle information around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the corresponding frame of turning driving data as the second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process, and determining target turning driving data according to the total frame number of the second turning driving data corresponding to each second turning process.
7. The method for acquiring turning travel data according to claim 6, wherein the determining, from the vehicle obstacle distance and the vehicle obstacle orientation, whether the obstacle information around the host vehicle in each frame of first turning travel data corresponding to each turn satisfies a preset second turn criterion includes:
judging whether the vehicle obstacle distance corresponding to each frame of first turning driving data corresponding to each turning is smaller than a preset vehicle obstacle distance threshold value or not;
if the distance between the vehicle obstacle corresponding to the turning driving data is smaller than a preset secondary vehicle distance threshold value, calculating a difference value between the orientation of the vehicle obstacle in the turning driving data of the corresponding frame and the orientation of the main vehicle in the turning driving data of the corresponding frame to obtain a turning orientation difference value;
judging whether the turning direction difference value is smaller than a preset direction difference value threshold value or not;
and if the turning direction difference value is smaller than a preset direction difference value threshold value, judging that the obstacle information around the main vehicle in the turning driving data of the corresponding frame meets a preset second turning judgment condition.
8. The method for acquiring turning driving data according to claim 6, wherein if the obstacle information around the host vehicle in the turning driving data satisfies the preset second turning discrimination condition, determining the corresponding frame turning driving data as the second turning driving data corresponding to the turning, obtaining the second turning driving data corresponding to each of at least one second turning course, and determining the target turning driving data according to the total number of frames of the second turning driving data corresponding to each of the second turning courses, comprises:
if the information of obstacles around the main vehicle in the turning driving data meets the preset second turning judgment condition, determining the turning driving data of the corresponding frame as second turning driving data of the corresponding turning to obtain second turning driving data respectively corresponding to at least one second turning process;
calculating the total frame number of second turning driving data corresponding to each second turning process to obtain the second turning frame number corresponding to each second turning process;
judging whether the second turning frame number corresponding to each second turning process meets a preset second turning threshold condition or not;
and if the second turning frame number meets a preset second turning threshold value condition, determining a plurality of frames of first turning driving data corresponding to the second turning process as target turning driving data.
9. The method for collecting turning travel data according to claim 8, wherein after the second turning discrimination is performed on the plurality of frames of the first turning travel data corresponding to each turning based on the obstacle information around the host vehicle in each frame of the first turning travel data to obtain the target turning travel data, the method for collecting turning travel data further comprises:
and sequencing the scene relevancy of the target turning driving data corresponding to each second turning process according to the second turning frame number to obtain a second turning driving data sequence.
10. A device for acquiring turn traveling data, characterized by comprising:
the screening module is used for acquiring multiframe driving data of the main vehicle and screening intersection range data of the multiframe driving data to obtain multiframe intersection driving data respectively corresponding to at least one intersection, wherein each frame of driving data comprises obstacle information around the main vehicle;
the recognition module is used for recognizing turning of the main vehicle for multiple frames of intersection driving data corresponding to each intersection to obtain multiple frames of first turning driving data corresponding to at least one turning;
and the judging module is used for carrying out second turning judgment on the plurality of frames of first turning driving data corresponding to each turning based on the obstacle information around the main vehicle in each frame of first turning driving data to obtain target turning driving data.
11. An apparatus for acquiring turn traveling data, characterized by comprising: a memory and at least one processor, the memory having stored therein a computer program;
the at least one processor calls the computer program in the memory to cause the acquisition device of the turning travel data to execute the acquisition method of the turning travel data according to any one of claims 1 to 9.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a method of acquiring turning travel data according to any one of claims 1 to 9.
CN202210325025.3A 2022-03-29 2022-03-29 Method, device and equipment for acquiring turning driving data and storage medium Pending CN114701516A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210325025.3A CN114701516A (en) 2022-03-29 2022-03-29 Method, device and equipment for acquiring turning driving data and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210325025.3A CN114701516A (en) 2022-03-29 2022-03-29 Method, device and equipment for acquiring turning driving data and storage medium

Publications (1)

Publication Number Publication Date
CN114701516A true CN114701516A (en) 2022-07-05

Family

ID=82171300

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210325025.3A Pending CN114701516A (en) 2022-03-29 2022-03-29 Method, device and equipment for acquiring turning driving data and storage medium

Country Status (1)

Country Link
CN (1) CN114701516A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109649489A (en) * 2018-12-21 2019-04-19 北京经纬恒润科技有限公司 Recognition methods, device, electronic equipment and the storage medium of Vehicular turn state
CN109801508A (en) * 2019-02-26 2019-05-24 百度在线网络技术(北京)有限公司 The motion profile prediction technique and device of barrier at crossing
CN112014856A (en) * 2019-05-30 2020-12-01 初速度(苏州)科技有限公司 Road edge extraction method and device suitable for cross road section
CN113119946A (en) * 2019-12-26 2021-07-16 北京宝沃汽车股份有限公司 Control method and device for safe running of vehicle and vehicle
CN113450571A (en) * 2021-09-01 2021-09-28 深圳市鼎粤科技有限公司 Traffic intersection-based driving direction reminding method and device and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109649489A (en) * 2018-12-21 2019-04-19 北京经纬恒润科技有限公司 Recognition methods, device, electronic equipment and the storage medium of Vehicular turn state
CN109801508A (en) * 2019-02-26 2019-05-24 百度在线网络技术(北京)有限公司 The motion profile prediction technique and device of barrier at crossing
CN112014856A (en) * 2019-05-30 2020-12-01 初速度(苏州)科技有限公司 Road edge extraction method and device suitable for cross road section
CN113119946A (en) * 2019-12-26 2021-07-16 北京宝沃汽车股份有限公司 Control method and device for safe running of vehicle and vehicle
CN113450571A (en) * 2021-09-01 2021-09-28 深圳市鼎粤科技有限公司 Traffic intersection-based driving direction reminding method and device and storage medium

Similar Documents

Publication Publication Date Title
CN110188807B (en) Tunnel pedestrian target detection method based on cascading super-resolution network and improved Faster R-CNN
US10212397B2 (en) Abandoned object detection apparatus and method and system
CN109993031B (en) Method and device for detecting target illegal driving behaviors of livestock-powered vehicle and camera
KR101589711B1 (en) Methods and systems for processing of video data
CN108133484B (en) Automatic driving processing method and device based on scene segmentation and computing equipment
CN104077594A (en) Image recognition method and device
CN101221623A (en) Object type on-line training and recognizing method and system thereof
CN110096975A (en) A kind of parking space state recognition methods, equipment and system
CN111295666A (en) Lane line detection method, device, control equipment and storage medium
CN113221750A (en) Vehicle tracking method, device, equipment and storage medium
CN111524350B (en) Method, system, terminal device and medium for detecting abnormal driving condition of vehicle and road cooperation
CN112991807B (en) Parking space state detection method, device, equipment and storage medium
CN115762126A (en) Scene screening method, device and equipment based on lane matching and storage medium
CN115545281A (en) Risk scene identification method, device, equipment and storage medium
CN114529883A (en) Method and electronic device for detecting traffic light
CN115083199A (en) Parking space information determination method and related equipment thereof
CN112163521A (en) Vehicle driving behavior identification method, device and equipment
CN114701516A (en) Method, device and equipment for acquiring turning driving data and storage medium
KR102197251B1 (en) Deep learning based traffic signal control method and device for rlr detection and accident prevention
CN115257771B (en) Intersection identification method, electronic equipment and storage medium
CN114693722B (en) Vehicle driving behavior detection method, detection device and detection equipment
CN113361299A (en) Abnormal parking detection method and device, storage medium and electronic equipment
CN114547403B (en) Method, device, equipment and storage medium for collecting variable-track scene
CN114407918B (en) Takeover scene analysis method, takeover scene analysis device, takeover scene analysis equipment and storage medium
CN112163471A (en) Congestion detection method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination