CN110082128B - Natural driving data-oriented dangerous fragment acquisition system and method thereof - Google Patents

Natural driving data-oriented dangerous fragment acquisition system and method thereof Download PDF

Info

Publication number
CN110082128B
CN110082128B CN201910404559.3A CN201910404559A CN110082128B CN 110082128 B CN110082128 B CN 110082128B CN 201910404559 A CN201910404559 A CN 201910404559A CN 110082128 B CN110082128 B CN 110082128B
Authority
CN
China
Prior art keywords
vehicle
test vehicle
camera
acceleration
module
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910404559.3A
Other languages
Chinese (zh)
Other versions
CN110082128A (en
Inventor
王进
陈龙
李鹏辉
郭景华
李爽
熊英志
陈华
吴平
张磊敏
陈涛
夏芹
张强
杨良义
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.)
China Automotive Engineering Research Institute Co Ltd
Original Assignee
China Automotive Engineering Research Institute 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 China Automotive Engineering Research Institute Co Ltd filed Critical China Automotive Engineering Research Institute Co Ltd
Priority to CN201910404559.3A priority Critical patent/CN110082128B/en
Publication of CN110082128A publication Critical patent/CN110082128A/en
Application granted granted Critical
Publication of CN110082128B publication Critical patent/CN110082128B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles
    • G01M17/0078—Shock-testing of vehicles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a dangerous fragment acquisition system and a dangerous fragment acquisition method for natural driving data, wherein the acquisition system comprises a data acquisition module and a data storage module; the data acquisition module comprises a vehicle body stable data acquisition module, an image data acquisition module and a position data acquisition module; when the test vehicle receives the danger triggering signal, the image acquired by the image data acquisition module is stored in the storage module. The method and the device can extract scenes of driving under dangerous working conditions.

Description

Natural driving data-oriented dangerous fragment acquisition system and method thereof
Technical Field
The invention relates to the technical field of intelligent automobile test scenes, in particular to a dangerous fragment acquisition system and a dangerous fragment acquisition method for natural driving data.
Background
In the aspect of scene library construction, a great deal of research has been carried out at home and abroad at present, and a typical dangerous scene is the basis of demand analysis and test evaluation of an intelligent automobile safety system and also determines the working range of the system, so that the dangerous scene is always the key point of research on intelligent automobile safety technology, particularly active collision avoidance technology.
The most common method for extracting dangerous scenes is analysis of traffic accident data, such as 37 types of pre-collision scenes proposed by the U.S. highway safety administration (NHTSA) based on the 2004 ges (general Estimates system) accident database. Typical dangerous forms can be obtained from traffic accident data, but the available parameters are few, the accuracy is limited, and more importantly, the main causes of the traffic accident and the driving behavior data are lacked. Therefore, the research on the natural driving data is gradually paid attention by the industry and researchers.
At present, aiming at the problems that no effective dangerous scene extraction method exists in natural data acquisition and cannot be integrated into data acquisition equipment, the invention provides a dangerous scene segment acquisition system and method for natural driving data based on the existing problems.
Disclosure of Invention
The invention aims to at least solve the technical problems in the prior art, and particularly provides a dangerous segment acquisition system and a dangerous segment acquisition method for natural driving data.
In order to achieve the above object, the present invention provides a dangerous segment collecting system facing natural driving data, which comprises a data collecting module and a data storing module;
the data acquisition module comprises a vehicle body stable data acquisition module, an image data acquisition module and a position data acquisition module;
the vehicle body stability data acquisition module comprises a transverse acceleration sensor module arranged on the front suspension rack or the rear suspension rack, a longitudinal acceleration sensor module arranged on the rear suspension rack or the front suspension rack, and a yaw angular velocity sensor module arranged on the front axle beam or the rear front beam;
the transverse acceleration sensor module is used for acquiring transverse acceleration of the test vehicle running in real time, and a transverse acceleration signal output end of the transverse speed sensor module is connected with a transverse acceleration signal input end of a test vehicle controller;
the longitudinal acceleration sensor module is used for acquiring the longitudinal acceleration of the test vehicle running in real time, and the longitudinal acceleration signal output end of the longitudinal speed sensor module is connected with the longitudinal acceleration signal input end of the test vehicle controller;
the yaw rate sensor module is used for acquiring the yaw rate of the test vehicle running in real time, and the yaw rate signal output end of the yaw rate sensor module is connected with the yaw rate signal input end of the test vehicle controller;
the image data acquisition module comprises M vehicle-mounted cameras which are arranged on a vehicle body of the test vehicle and used for shooting a driving scene, wherein M is a positive integer, and an image signal output end of each vehicle-mounted camera is correspondingly connected with an image signal input end of the test vehicle controller;
the position data acquisition module comprises a GPS module which is arranged in the test vehicle and used for acquiring the geographical position of the test vehicle, and the geographical position signal output end of the GPS module is connected with the geographical position input end of the test vehicle controller;
when the test vehicle receives the danger triggering signal, the image acquired by the image data acquisition module is stored in the storage module.
In a preferred embodiment of the present invention, the vehicle testing system further comprises a wireless transceiver module disposed in the vehicle under test, a transceiver end of the wireless transceiver module is connected to a transceiver end of the vehicle under test controller, and the vehicle under test controller transmits the data stored in the data storage module to the remote monitoring center through the wireless transceiver module. And the acquired data parameters are sent to the remote monitoring center in time, so that the remote monitoring center can know the conditions conveniently.
In a preferred embodiment of the present invention, M is 6; the system comprises a vehicle-mounted first camera, a vehicle-mounted second camera, a vehicle-mounted third camera, a vehicle-mounted fourth camera, a vehicle-mounted fifth camera and a vehicle-mounted sixth camera, wherein the vehicle-mounted first camera is arranged at the head of a test vehicle and used for acquiring a front view image of the vehicle, the vehicle-mounted second camera and the vehicle-mounted third camera are arranged at the left side of a body of the test vehicle and used for acquiring a front view image and a rear view image of the left side of the vehicle, the vehicle-mounted fourth camera and the vehicle-mounted fifth camera are arranged at the right side of the body of the test vehicle and;
the image signal output end of the vehicle-mounted first camera is connected with the image signal first input end of the test vehicle controller, the image signal output end of the vehicle-mounted second camera is connected with the image signal second input end of the test vehicle controller, the image signal output end of the vehicle-mounted third camera is connected with the image signal third input end of the test vehicle controller, the image signal output end of the vehicle-mounted fourth camera is connected with the image signal fourth input end of the test vehicle controller, the image signal output end of the vehicle-mounted fifth camera is connected with the image signal fifth input end of the test vehicle controller, and the image signal output end of the vehicle-mounted sixth camera is connected with the image signal sixth input end of the test vehicle controller. The driving scenes of the test vehicles are collected through six paths of vehicle-mounted cameras, and finally the scenes are spliced into a panoramic scene.
The invention also provides a dangerous segment acquisition method facing natural driving data, which comprises the following steps:
s1, the test vehicle controller judges the road section where the test vehicle is located according to the geographic position where the test vehicle is located and collected by the position data collection module, wherein the road section where the test vehicle is located comprises a high-speed road section and a common road section;
if the road section where the test vehicle is located is the highway section, executing step S2;
if the road section where the test vehicle is located is the ordinary road section, executing step S3;
s2, if the road section where the test vehicle is located is a highway section, judging the dangerous working condition of the highway section:
s21, the test vehicle controller obtains the longitudinal acceleration a collected by the vehicle body stability data collection modulexLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000031
S22, the longitudinal acceleration a collected in the step S21xLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000032
Obtaining longitudinal acceleration derivative through difference
Figure BDA0002060799840000033
Derivative of lateral acceleration
Figure BDA0002060799840000034
And yaw angular acceleration
Figure BDA0002060799840000035
S23, judging whether one of the following conditions exists:
ax< -Ag and
Figure BDA0002060799840000041
a is a positive number, and B is a positive number; g is the gravity acceleration and s is the time unit second;
or, | ayL > Cg and
Figure BDA0002060799840000042
c is a positive number, and D is a positive number;
s24, if one of the conditions in the step S23 exists, generating a danger triggering signal;
s25, storing image data segments collected by the image data collecting modules in X seconds before and Y seconds after the occurrence of the danger; x, Y is a positive number;
s3, if the road section where the test vehicle is located is a common road section, judging the dangerous working condition of the common road section:
s31, the test vehicle controller obtains the longitudinal speed v acquired by the vehicle body stability data acquisition modulexLongitudinal acceleration axLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000043
S32, the longitudinal acceleration a collected in the step S31xLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000044
Obtaining longitudinal acceleration derivative through difference
Figure BDA0002060799840000045
Lateral acceleration derivative and yaw angular acceleration
Figure BDA0002060799840000046
S33, judging whether one of the following conditions exists:
ax< -A' g and
Figure BDA0002060799840000047
a 'is a positive number greater than A, and B' is a positive number greater than or equal to B;
or, | ayI > C' g and
Figure BDA0002060799840000048
c 'is a positive number greater than or equal to C, and D' is a positive number greater than or equal to D;
or, when the longitudinal speed v isxMore than or equal to Em/s, E is positive number, m is displacement unit meter, and yaw velocity
Figure BDA0002060799840000049
Within a time window of Fs, F is a positive number varying from + -G DEG/s to the opposite direction
Figure BDA00020607998400000410
G is a positive number, and DEG is an angle unit;
or, when the longitudinal vehicle speed vxWhen the absolute value of the yaw angular acceleration is greater than or equal to Hm/s, the H is a positive number, the yaw angular acceleration is fitted, and the maximum value of the absolute value of the yaw angular acceleration is within a period similar to a sine function
Figure BDA00020607998400000411
I is a positive number;
s34, if one of the conditions in the step S33 exists, generating a danger triggering signal;
s35, storing image data segments collected by the image data collecting modules in X 'seconds before and Y' seconds after the occurrence of the danger; x 'is a positive number greater than or equal to X, and Y' is a positive number greater than or equal to Y.
In a preferred embodiment of the present invention, in step S23, a is 0.3; b is 1; c is 0.75; d is 1.
In a preferred embodiment of the present invention, in step S33, a' ═ 0.5; b' ═ 1; c' is 0.75; d' ═ 1; e ═ 13.4; f is 0.75; g is 8; h ═ 5; i-15.
In a preferred embodiment of the present invention, in step S25, X ═ Y ═ 10.
In a preferred embodiment of the present invention, in step S35, X '═ Y' ═ 10.
In a preferred embodiment of the present invention, the method further comprises step S26, sending the image data segments collected by the image data collecting modules X seconds before and Y seconds after the occurrence of the risk to the remote monitoring center;
and step S36, sending the image data segments collected by the image data collecting modules in X 'seconds before and Y' seconds after the danger occurs to the remote monitoring center.
In a preferred embodiment of the present invention, the method further includes performing panorama stitching on the intercepted six videos.
In conclusion, due to the adoption of the technical scheme, the scene extraction method can be used for extracting scenes of driving under dangerous working conditions.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic block diagram of the process of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
The invention provides a dangerous fragment acquisition system for natural driving data, which comprises a data acquisition module and a data storage module, wherein the data acquisition module is used for acquiring dangerous fragments of natural driving data;
the data acquisition module comprises a vehicle body stable data acquisition module, an image data acquisition module and a position data acquisition module;
the vehicle body stability data acquisition module comprises a transverse acceleration sensor module arranged on the front suspension rack or the rear suspension rack, a longitudinal acceleration sensor module arranged on the rear suspension rack or the front suspension rack, and a yaw angular velocity sensor module arranged on the front axle beam or the rear front beam;
the transverse acceleration sensor module is used for acquiring transverse acceleration of the test vehicle running in real time, and a transverse acceleration signal output end of the transverse speed sensor module is connected with a transverse acceleration signal input end of a test vehicle controller;
the longitudinal acceleration sensor module is used for acquiring the longitudinal acceleration of the test vehicle running in real time, and the longitudinal acceleration signal output end of the longitudinal speed sensor module is connected with the longitudinal acceleration signal input end of the test vehicle controller;
the yaw rate sensor module is used for acquiring the yaw rate of the test vehicle running in real time, and the yaw rate signal output end of the yaw rate sensor module is connected with the yaw rate signal input end of the test vehicle controller;
the image data acquisition module comprises M vehicle-mounted cameras which are arranged on a vehicle body of the test vehicle and used for shooting a driving scene, wherein M is a positive integer, and an image signal output end of each vehicle-mounted camera is correspondingly connected with an image signal input end of the test vehicle controller;
the position data acquisition module comprises a GPS module which is arranged in the test vehicle and used for acquiring the geographical position of the test vehicle, and the geographical position signal output end of the GPS module is connected with the geographical position input end of the test vehicle controller;
when the test vehicle receives the danger triggering signal, the image acquired by the image data acquisition module is stored in the storage module.
In a preferred embodiment of the present invention, the vehicle testing system further comprises a wireless transceiver module disposed in the vehicle under test, a transceiver end of the wireless transceiver module is connected to a transceiver end of the vehicle under test controller, and the vehicle under test controller transmits the data stored in the data storage module to the remote monitoring center through the wireless transceiver module.
In a preferred embodiment of the present invention, M is 6; the system comprises a vehicle-mounted first camera, a vehicle-mounted second camera, a vehicle-mounted third camera, a vehicle-mounted fourth camera, a vehicle-mounted fifth camera and a vehicle-mounted sixth camera, wherein the vehicle-mounted first camera is arranged at the head of a test vehicle and used for acquiring a front view image of the vehicle, the vehicle-mounted second camera and the vehicle-mounted third camera are arranged at the left side of a body of the test vehicle and used for acquiring a front view image and a rear view image of the left side of the vehicle, the vehicle-mounted fourth camera and the vehicle-mounted fifth camera are arranged at the right side of the body of the test vehicle and;
the image signal output end of the vehicle-mounted first camera is connected with the image signal first input end of the test vehicle controller, the image signal output end of the vehicle-mounted second camera is connected with the image signal second input end of the test vehicle controller, the image signal output end of the vehicle-mounted third camera is connected with the image signal third input end of the test vehicle controller, the image signal output end of the vehicle-mounted fourth camera is connected with the image signal fourth input end of the test vehicle controller, the image signal output end of the vehicle-mounted fifth camera is connected with the image signal fifth input end of the test vehicle controller, and the image signal output end of the vehicle-mounted sixth camera is connected with the image signal sixth input end of the test vehicle controller.
The invention also provides a dangerous segment acquisition method facing natural driving data, which comprises the following steps:
s1, the test vehicle controller judges the road section where the test vehicle is located according to the geographic position where the test vehicle is located and collected by the position data collection module, wherein the road section where the test vehicle is located comprises a highway section (highway) and a common road section (cityroad);
if the road section where the test vehicle is located is the highway section, executing step S2;
if the road section where the test vehicle is located is the ordinary road section, executing step S3;
s2, if the road section where the test vehicle is located is a highway section, judging the dangerous working condition of the highway section:
s21, the test vehicle controller obtains the longitudinal acceleration a collected by the vehicle body stability data collection modulexLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000071
S22, the longitudinal acceleration a collected in the step S21xLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000072
Obtaining longitudinal acceleration derivative through difference
Figure BDA0002060799840000081
Derivative of lateral acceleration
Figure BDA0002060799840000082
And yaw angular acceleration
Figure BDA0002060799840000083
S23, judging whether one of the following conditions exists:
ax< -Ag and
Figure BDA0002060799840000084
a is a positive number, and B is a positive number; g is the gravity acceleration and s is the time unit second;
or, | ayL > Cg and
Figure BDA0002060799840000085
c is a positive number, and D is a positive number; in this embodiment, a is 0.3; b is 1; c is 0.75; d is 1.
S24, if one of the conditions in the step S23 exists, generating a danger triggering signal;
s25, storing image data segments collected by the image data collecting modules in X seconds before and Y seconds after the occurrence of the danger; x, Y is a positive number; in the present embodiment, X ═ Y ═ 10.
S26, sending the image data segments collected by the image data collecting modules in X seconds before and Y seconds after the danger occurs to a remote monitoring center;
s3, if the road section where the test vehicle is located is a common road section, judging the dangerous working condition of the common road section:
s31, the test vehicle controller obtains the longitudinal speed v acquired by the vehicle body stability data acquisition modulexLongitudinal acceleration axLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000086
S32, the longitudinal acceleration a collected in the step S31xLateral acceleration ayAnd yaw rate
Figure BDA0002060799840000087
Obtaining longitudinal acceleration derivative through difference
Figure BDA0002060799840000088
Lateral acceleration derivative and yaw angular acceleration
Figure BDA0002060799840000089
S33, judging whether one of the following conditions exists:
ax< -A' g and
Figure BDA00020607998400000810
a 'is a positive number greater than A, and B' is a positive number greater than or equal to B;
or, | ayI > C' g and
Figure BDA00020607998400000811
c 'is a positive number greater than or equal to C, and D' is a positive number greater than or equal to D;
or, when the longitudinal speed v isxMore than or equal to Em/s, E is positive number, m is displacement unit meter, and yaw velocity
Figure BDA00020607998400000812
Within a time window of Fs, F is a positive number varying from + -G DEG/s to the opposite direction
Figure BDA00020607998400000813
G is a positive number, and DEG is an angle unit; in the present embodiment, the angle changes from + -G DEG/s to the opposite direction
Figure BDA00020607998400000814
It is understood that: changing from G/s to-G/s; or from-G/s to G/s.
Or, when the longitudinal vehicle speed vxWhen the absolute value of the yaw angular acceleration is greater than or equal to Hm/s, the H is a positive number, the yaw angular acceleration is fitted, and the maximum value of the absolute value of the yaw angular acceleration is within a period similar to a sine function
Figure BDA0002060799840000091
I is a positive number; in this embodiment, a' is 0.5; b' ═ 1; c' is 0.75; d' ═ 1; e ═ 13.4; f is 0.75; g is 8; h ═ 5; i-15.
S34, if one of the conditions in the step S33 exists, generating a danger triggering signal;
s35, storing image data segments collected by the image data collecting modules in X 'seconds before and Y' seconds after the occurrence of the danger; x 'is a positive number greater than or equal to X, and Y' is a positive number greater than or equal to Y. In the present embodiment, X '═ Y' ═ 10.
And S36, sending the image data segments collected by the image data collection modules in X 'seconds before and Y' seconds after the danger occurs to the remote monitoring center.
In a preferred embodiment of the present invention, the method further includes performing panorama stitching on the intercepted six videos. The panoramic stitching method comprises the following steps:
s101, acquiring single-frame images shot by two adjacent vehicle-mounted cameras in a target area;
s102, acquiring an overlapping area of single-frame images shot by two adjacent vehicle-mounted cameras in the step S101;
s103, dividing the overlapping area in the step S102 into K sub-overlapping areas, wherein K is a positive integer, and finding a reference point in each sub-overlapping area; the method for searching the reference point comprises the following steps:
Figure BDA0002060799840000092
wherein r isqIs the pixel value of the feature point q, rpIs the pixel value of a feature point p adjacent to the feature point q, N is the number of feature points p adjacent to the feature point q, rmaxIs the maximum pixel value of the feature point p adjacent to the feature point q, rminIs the minimum pixel value of the feature point p adjacent to the feature point q; taking the characteristic point corresponding to the minimum value of the P value in each sub-overlapping area as a reference point;
s104, converting the coordinates of the single-frame images shot by the two adjacent vehicle-mounted cameras in the step S101 into cylindrical coordinates from screen coordinates;
s105, extracting feature points of the single-frame images shot by the two adjacent vehicle-mounted cameras in the step S101 according to the reference points selected in the step S103 and the cylindrical coordinates converted in the step S104;
s106, matching all the characteristic points in the step S105; the matching method of the characteristic points comprises the following steps: taking the absolute value of the pixel difference value of the feature point on one single frame image and all the feature points on the other single frame image, and taking the minimum value as a matching point;
and S107, matching the single-frame images shot by all the two adjacent vehicle-mounted cameras in the target area according to the steps S101 to S106, and acquiring the panoramic single-frame image of the target area.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims (10)

1. A dangerous segment collection method for natural driving data is characterized by comprising the following steps:
s1, the test vehicle controller judges the road section where the test vehicle is located according to the geographic position where the test vehicle is located and collected by the position data collection module, wherein the road section where the test vehicle is located comprises a high-speed road section and a common road section;
if the road section where the test vehicle is located is the highway section, executing step S2;
if the road section where the test vehicle is located is the ordinary road section, executing step S3;
s2, if the road section where the test vehicle is located is a highway section, judging the dangerous working condition of the highway section:
s21, the test vehicle controller obtains the longitudinal acceleration a collected by the vehicle body stability data collection modulexLateral acceleration ayAnd yaw rate
Figure FDA0002363033120000011
S22, the longitudinal acceleration a collected in the step S21xLateral acceleration ayAnd yaw rate
Figure FDA0002363033120000012
Is subjected to differenceObtaining longitudinal acceleration derivative
Figure FDA0002363033120000013
Derivative of lateral acceleration
Figure FDA0002363033120000014
And yaw angular acceleration
Figure FDA0002363033120000015
S23, judging whether one of the following conditions exists:
ax< -A and
Figure FDA0002363033120000016
the unit of A is g, the unit of B is g/s, g is the gravity acceleration, and s is the time unit second;
or, | ayL > C and
Figure FDA0002363033120000017
c is a positive number, and D is a positive number; the unit of C is g, and the unit of D is g/s;
s24, if one of the conditions in the step S23 exists, generating a danger triggering signal;
s25, storing image data segments collected by the image data collecting modules in X seconds before and Y seconds after the occurrence of the danger; x, Y is a positive number;
s3, if the road section where the test vehicle is located is a common road section, judging the dangerous working condition of the common road section:
s31, the test vehicle controller obtains the longitudinal speed v acquired by the vehicle body stability data acquisition modulexLongitudinal acceleration axLateral acceleration ayAnd yaw rate
Figure FDA0002363033120000018
S32, the longitudinal acceleration a collected in the step S31xLateral acceleration ayAnd yaw rate
Figure FDA0002363033120000019
Obtaining longitudinal acceleration derivative through difference
Figure FDA00023630331200000110
Derivative of lateral acceleration
Figure FDA00023630331200000111
And yaw angular acceleration
Figure FDA00023630331200000112
S33, judging whether one of the following conditions exists:
ax< -A' and
Figure FDA0002363033120000021
a 'is a positive number greater than A, and B' is a positive number greater than or equal to B; the unit of A 'is g, and the unit of B' is g/s;
or, | ayL > C' and
Figure FDA0002363033120000022
c 'is a positive number greater than or equal to C, and D' is a positive number greater than or equal to D; the unit of C 'is g, and the unit of D' is g/s;
or, when the longitudinal speed v isxMore than or equal to E, wherein E is a positive number, and the yaw rate
Figure FDA0002363033120000023
Within the time window of F, the F is a positive number and changes from G to the opposite direction
Figure FDA0002363033120000025
G is a positive number; the unit of E is m/s, the unit of F is s, and the unit of G is DEG/s; m is displacement unit meter, and degree is angle unit degree;
or, when the longitudinal vehicle speed vxWhen the ratio of H to H is more than or equal to H, the H is positiveCounting, and fitting yaw angular acceleration to maximum absolute value of yaw angular acceleration within a period similar to a sine function
Figure FDA0002363033120000024
I is a positive number; the units of H are m/s and I are DEG/s2；
S34, if one of the conditions in the step S33 exists, generating a danger triggering signal;
s35, storing image data segments collected by the image data collecting modules in X 'seconds before and Y' seconds after the occurrence of the danger; x 'is a positive number greater than or equal to X, and Y' is a positive number greater than or equal to Y.
2. The natural driving data-oriented dangerous segment collecting method according to claim 1, characterized by comprising a data collecting module and a data storing module;
the data acquisition module comprises a vehicle body stable data acquisition module, an image data acquisition module and a position data acquisition module;
the vehicle body stability data acquisition module comprises a transverse acceleration sensor module arranged on the front suspension rack or the rear suspension rack, a longitudinal acceleration sensor module arranged on the rear suspension rack or the front suspension rack, and a yaw angular velocity sensor module arranged on the front axle beam or the rear front beam;
the transverse acceleration sensor module is used for acquiring transverse acceleration of the test vehicle running in real time, and a transverse acceleration signal output end of the transverse speed sensor module is connected with a transverse acceleration signal input end of a test vehicle controller;
the longitudinal acceleration sensor module is used for acquiring the longitudinal acceleration of the test vehicle running in real time, and the longitudinal acceleration signal output end of the longitudinal speed sensor module is connected with the longitudinal acceleration signal input end of the test vehicle controller;
the yaw rate sensor module is used for acquiring the yaw rate of the test vehicle running in real time, and the yaw rate signal output end of the yaw rate sensor module is connected with the yaw rate signal input end of the test vehicle controller;
the image data acquisition module comprises M vehicle-mounted cameras which are arranged on a vehicle body of the test vehicle and used for shooting a driving scene, wherein M is a positive integer, and an image signal output end of each vehicle-mounted camera is correspondingly connected with an image signal input end of the test vehicle controller;
the position data acquisition module comprises a GPS module which is arranged in the test vehicle and used for acquiring the geographical position of the test vehicle, and the geographical position signal output end of the GPS module is connected with the geographical position input end of the test vehicle controller;
when the test vehicle receives the danger triggering signal, the image acquired by the image data acquisition module is stored in the storage module.
3. The natural driving data-oriented dangerous segment collecting method according to claim 2, further comprising a wireless transceiver module disposed in the test vehicle, wherein a transceiver end of the wireless transceiver module is connected with a transceiver end of the test vehicle controller, and the test vehicle controller transmits the data stored in the data storage module to the remote monitoring center through the wireless transceiver module.
4. The nature driving data oriented dangerous segment collecting method according to claim 2, wherein said M is 6; the system comprises a vehicle-mounted first camera, a vehicle-mounted second camera, a vehicle-mounted third camera, a vehicle-mounted fourth camera, a vehicle-mounted fifth camera and a vehicle-mounted sixth camera, wherein the vehicle-mounted first camera is arranged at the head of a test vehicle and used for acquiring a front view image of the vehicle, the vehicle-mounted second camera and the vehicle-mounted third camera are arranged at the left side of a body of the test vehicle and used for acquiring a front view image and a rear view image of the left side of the vehicle, the vehicle-mounted fourth camera and the vehicle-mounted fifth camera are arranged at the right side of the body of the test vehicle and;
the image signal output end of the vehicle-mounted first camera is connected with the image signal first input end of the test vehicle controller, the image signal output end of the vehicle-mounted second camera is connected with the image signal second input end of the test vehicle controller, the image signal output end of the vehicle-mounted third camera is connected with the image signal third input end of the test vehicle controller, the image signal output end of the vehicle-mounted fourth camera is connected with the image signal fourth input end of the test vehicle controller, the image signal output end of the vehicle-mounted fifth camera is connected with the image signal fifth input end of the test vehicle controller, and the image signal output end of the vehicle-mounted sixth camera is connected with the image signal sixth input end of the test vehicle controller.
5. The natural driving data-oriented dangerous segment collecting method according to claim 1, wherein in step S23, a is 0.3; b is 1; c is 0.75; d is 1.
6. The natural driving data-oriented dangerous segment collecting method according to claim 1, wherein in step S33, a' ═ 0.5; b' ═ 1; c' is 0.75; d' ═ 1; e ═ 13.4; f is 0.75; g is 8; h ═ 5; i-15.
7. The free-driving-data-oriented dangerous segment collecting method according to claim 1, wherein in step S25, X-Y-10.
8. The free-driving-data-oriented dangerous segment collecting method according to claim 1, wherein in step S35, X '═ Y' ═ 10.
9. The natural driving data-oriented dangerous segment collecting method according to claim 1, further comprising a step S26 of sending image data segments collected by the image data collecting modules of X seconds before and Y seconds after the occurrence of the danger to a remote monitoring center;
and step S36, sending the image data segments collected by the image data collecting modules in X 'seconds before and Y' seconds after the danger occurs to the remote monitoring center.
10. The nature driving data oriented dangerous segment collecting method as claimed in claim 1, further comprising panoramic stitching of the intercepted six videos.
CN201910404559.3A 2019-05-16 2019-05-16 Natural driving data-oriented dangerous fragment acquisition system and method thereof Active CN110082128B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910404559.3A CN110082128B (en) 2019-05-16 2019-05-16 Natural driving data-oriented dangerous fragment acquisition system and method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910404559.3A CN110082128B (en) 2019-05-16 2019-05-16 Natural driving data-oriented dangerous fragment acquisition system and method thereof

Publications (2)

Publication Number Publication Date
CN110082128A CN110082128A (en) 2019-08-02
CN110082128B true CN110082128B (en) 2020-03-31

Family

ID=67420425

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910404559.3A Active CN110082128B (en) 2019-05-16 2019-05-16 Natural driving data-oriented dangerous fragment acquisition system and method thereof

Country Status (1)

Country Link
CN (1) CN110082128B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007323281A (en) * 2006-05-31 2007-12-13 Denso Corp Danger occurrence point information collection system, on-vehicle device, and danger occurrence point information collection device
CN106200626A (en) * 2016-08-26 2016-12-07 上海瑞言信息科技有限公司 Natural driving data acquisition system and security algorithm thereof
CN207624060U (en) * 2017-08-08 2018-07-17 中国汽车工程研究院股份有限公司 A kind of automated driving system scene floor data acquisition system
CN108985530A (en) * 2017-05-31 2018-12-11 北京嘀嘀无限科技发展有限公司 Vehicle risk behavior management method and device
JP6448880B1 (en) * 2017-06-22 2019-01-09 三菱電機株式会社 Danger information collection device
CN109564724A (en) * 2017-07-27 2019-04-02 松下电器（美国）知识产权公司 Information processing method, information processing unit and message handling program

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007323281A (en) * 2006-05-31 2007-12-13 Denso Corp Danger occurrence point information collection system, on-vehicle device, and danger occurrence point information collection device
CN106200626A (en) * 2016-08-26 2016-12-07 上海瑞言信息科技有限公司 Natural driving data acquisition system and security algorithm thereof
CN108985530A (en) * 2017-05-31 2018-12-11 北京嘀嘀无限科技发展有限公司 Vehicle risk behavior management method and device
JP6448880B1 (en) * 2017-06-22 2019-01-09 三菱電機株式会社 Danger information collection device
CN109564724A (en) * 2017-07-27 2019-04-02 松下电器（美国）知识产权公司 Information processing method, information processing unit and message handling program
CN207624060U (en) * 2017-08-08 2018-07-17 中国汽车工程研究院股份有限公司 A kind of automated driving system scene floor data acquisition system

Also Published As

Publication number Publication date
CN110082128A (en) 2019-08-02

Similar Documents

Publication Publication Date Title
CN109870456B (en) Rapid detection system and method for road surface health condition
KR102507905B1 (en) Real-time Port Hall Detection Device Using Police Cars
CN105989724A (en) Traffic sign determination device
CN109905847B (en) Collaborative correction system and method for accumulated errors of GNSS blind area intelligent vehicle auxiliary positioning system
KR101735557B1 (en) System and Method for Collecting Traffic Information Using Real time Object Detection
EP3224820B1 (en) Double stereoscopic sensor
CN102542843A (en) Early warning method for preventing vehicle collision and device
CN103630122A (en) Monocular vision lane line detection method and distance measurement method thereof
KR102061264B1 (en) Unexpected incident detecting system using vehicle position information based on C-ITS
CN106564501A (en) Intelligent automobile assisting system and method based on cloud technology
CN105303826A (en) Violating side parking evidence obtaining device and method
CN109874099B (en) Networking vehicle-mounted equipment flow control system
WO2022115987A1 (en) Method and system for automatic driving data collection and closed-loop management
CN107145825A (en) Ground level fitting, camera calibration method and system, car-mounted terminal
CN111703424B (en) Intelligent networking automobile multi-sensor fusion auxiliary lane changing method and system
CN106846369A (en) Vehicular turn condition discrimination method and device based on binocular vision
CN105303827A (en) Traffic violation image obtaining device and method
KR20180024757A (en) Traffic information offering system using multi view blackbox camera image
CN114841188A (en) Vehicle fusion positioning method and device based on two-dimensional code
CN110082128B (en) Natural driving data-oriented dangerous fragment acquisition system and method thereof
CN103673977A (en) Method and device for detecting rear dead zone of vehicle
CN105303825A (en) Violating inclined side parking evidence obtaining device and method
EP3389015A1 (en) Roll angle calibration method and roll angle calibration device
CN112598705A (en) Vehicle body posture detection method based on binocular vision
CN113378719A (en) Lane line recognition method and device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant