CN115116025A - Driving risk assessment system based on underground road sight distance - Google Patents
Driving risk assessment system based on underground road sight distance Download PDFInfo
- Publication number
- CN115116025A CN115116025A CN202210572703.6A CN202210572703A CN115116025A CN 115116025 A CN115116025 A CN 115116025A CN 202210572703 A CN202210572703 A CN 202210572703A CN 115116025 A CN115116025 A CN 115116025A
- Authority
- CN
- China
- Prior art keywords
- frame
- picture
- vehicle
- driving
- distance
- 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.)
- Granted
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000009466 transformation Effects 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 10
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims abstract description 6
- 230000000007 visual effect Effects 0.000 claims description 21
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 5
- 230000001427 coherent effect Effects 0.000 claims description 3
- 230000035484 reaction time Effects 0.000 claims description 3
- 230000001953 sensory effect Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/14—Adaptive cruise control
- B60W30/143—Speed control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation 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
- B60W40/10—Estimation 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 related to vehicle motion
- B60W40/105—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0816—Indicating performance data, e.g. occurrence of a malfunction
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/146—Display means
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a driving risk assessment system based on the sight distance of an underground road; the automobile data recorder is arranged in front of a windshield at a driving position of an automobile; the process is as follows: 1. collecting a vehicle running video; 2. converting the video into frame-by-frame pictures, and processing each frame picture; 3. extracting initial information of the lane line based on the gradient and the color characteristics of each processed frame of picture; 4. processing a position map of pixels of each frame of picture by using image expansion; 5. affine transformation is carried out by adopting a cross-computer platform vision library to form a top view; 6. continuously searching from the lower left corner to the upper right corner of each top view, and determining the number of lane lines and the starting point and the end point of each lane line according to the wave crest of the histogram of the binary image; 7. and calculating the maximum visible distance as the maximum driving speed provided by the parking sight distance according to the response characteristics of the driver, and reminding the driver. The method can effectively and accurately calculate the maximum distance of the road visibility.
Description
Technical Field
The invention relates to the technical field, in particular to a driving risk assessment system based on the sight distance of an underground road.
Background
Due to the rapid development of city construction in recent years, the overall spatial layout of a city is changed from the original single-center to multi-center and multi-core, the traffic demand structure is changed newly along with the adjustment of the spatial layout of the city, the original elevated and ground traffic system is not enough to meet the increasing traffic demand of the city from east to west, and the urban underground roads are born at the same time.
The underground road engineering is generally positioned in a core area of a city and is influenced by factors such as city subways, pipelines, river channels, ground buildings and the like, and control points are more than those of highway tunnels and underground roads of common road sections, so that higher requirements are provided for linear design of roads. On one hand, the severe change of the speed of the vehicle and the speed difference between adjacent road sections can cause the stability of the traffic flow to be reduced, and are unfavorable for the driving safety; on the other hand, congestion of local links or nodes occurs, and the road traffic capacity is reduced.
Meanwhile, most underground road sections except part of the sections such as an access and a shallow-buried section are excavated by adopting a shield. The diameter of the shield machine mainly adopted at present is below 15m by comprehensively considering factors such as a road structure, construction cost and the like. Therefore, the underground road has the characteristics of narrow width and limited clear height, and has strict requirements on the used vehicle type and size of the road. The side wall often leads to driving visual field scope less to the shelves of driver's sight. Particularly, in sharp bends, the visible distance is sharply reduced, the information of vehicles, roads and environments is not sufficiently obtained, and accidents such as rear-end collision, wall rubbing and the like are easily caused. On the other hand, the clear height is small, and poor driving sight distance can be caused on a section with a large longitudinal slope or a section with horizontal and vertical combination disadvantages.
Whether the underground road driving sight distance is sufficient or not is directly related to the driving safety and efficiency, and is an important index of the use quality of the underground road. The existing road sight distance analysis method mainly comprises a conventional sight distance detection method and three-dimensional dynamic sight distance inspection. The conventional sight distance detection method includes two methods: one is a graphical method of determining whether there is an obstacle affecting the driver's solid line inside the curve by plotting a line-of-sight envelope diagram inside the flat curve. The other method is to determine whether the sight distance provided by the road at a certain position of the road meets the requirement sight distance of the driver by calculating the maximum transverse clear distance of the road.
Another method for detecting the three-dimensional visual range of a road is to restore the road line shape and detect the driver's visual range at a three-dimensional analysis angle in consideration of the three-dimensional geometric line shapes of the road, such as the level, the vertical, and the horizontal, traffic accessories, roadside facilities, vegetation, and house buildings, under a real three-dimensional road environment. The three-dimensional visual range detection method is more accurate than a two-dimensional detection method and can reflect the driving condition more truly. However, the analytical algorithm is often difficult to calculate, difficult to acquire data, and difficult to implement.
Therefore, how to solve the problems that the driver sight distance design is poor in wide and capacitive property and the driving risk is high in the underground road environment becomes a technical problem which needs to be solved urgently by the technical personnel in the field.
Disclosure of Invention
In view of the above defects in the prior art, the invention provides a driving risk assessment system based on the visual range of an underground road, which achieves the purpose of recognizing the marked line of a motor vehicle lane based on the real-time video of a vehicle driving recorder, continuously calculating the visual range of the road, and then reversely deducing the safe driving speed of the current position according to the visual range to ensure that the driving speed of the underground road is within the safe range to the maximum extent.
In order to achieve the purpose, the invention discloses a driving risk assessment system based on the sight distance of an underground road; the automobile data recorder is arranged at the front end of a windshield at the driving position of a vehicle;
the video recorded by the automobile data recorder is consistent with the visual angle of a driver, and has the functions of shooting, storing and reading;
the driving risk assessment process is as follows:
step 1, collecting a video of a vehicle running on an underground road through the automobile data recorder;
step 2, converting the video collected by the automobile data recorder into frame-by-frame pictures, processing each frame of picture, and reserving the lower half part of each frame of picture, namely removing the upper half part of each frame of picture, including the top end of an underground road, illumination and a traffic sign;
the gradient of each frame of the picture is calibrated by using the Sobel values of the pixel points, and all the pixel points with the Sobel values in the four channel regions (35,100), (30,255), (30,255) and (0.7,1.3) are reserved to be used as a pixel set meeting the gradient requirement;
the color of each frame of the picture is calibrated by adopting a hue-saturation-brightness mode (HSL), and the hue, the saturation and the brightness of the color of each frame of the picture are reserved, and pixels which respectively meet the requirements of (180,255), (10,100) and (0,60) for the hue, the saturation and the brightness of the color of each frame of the picture are reserved to be used as a pixel set meeting the color requirements;
superposing and combining the pixel sets meeting the gradient requirement and the color requirement of each frame of picture to form a position map of the pixels of each frame of picture corresponding to the lane line;
step 4, processing the position image of the pixel of each frame of picture by using image expansion, and filling the position image of the pixel of each corresponding frame of picture with a cavity inside a lane line according to the edge of the lane line so as to enable the lane line to be clear and coherent;
step 5, carrying out affine transformation by adopting four-point transformation in an Open-CV (Open-CV) of a cross-computer platform vision library, carrying out affine transformation on a position diagram of the pixel of each frame of the picture which fills the cavity in the lane line, and converting the position diagram into a top view;
step 6, continuously searching by taking the lower left corner of each converted top view as a starting point and the upper right corner as an end point, and determining the number of lane lines and the starting point and the end point of each lane line according to the wave crest of the histogram of the binary image;
meanwhile, scanning the lane lines by using a horizontal straight line to obtain the width of each lane line, and calculating the average width of the lane lines on the image;
then, calculating a scale of each converted top view according to the actual width of the traffic marking being 0.15m, further calculating the length of each traffic marking from the starting point to the end point, and taking the average value of the distances between the left marking and the right marking of each lane as the maximum visible distance;
step 7, according to the reaction characteristics of the driver, calculating the maximum visible distance as the maximum driving speed provided by the parking sight distance;
comparing the maximum driving speed which can be provided by the parking sight distance with the current driving speed of the vehicle and the road speed limit to obtain a risk value of the current driving speed of the vehicle;
if the current vehicle running speed of the vehicle is 110% or more of the maximum running speed provided by the parking sight distance, reminding the driver of 'please slow down and drive';
and if the current vehicle driving speed of the vehicle is more than 100% but less than 110% of the maximum driving speed which can be provided by the parking sight distance, reminding the driver of 'poor front sight distance and cautious driving'.
Preferably, the height from the shooting position of the automobile data recorder to the road surface is 1.2 m.
Preferably, before the driving risk assessment, the driving recorder needs to be corrected, and the specific steps are as follows:
the method comprises the steps of importing a plurality of black-white alternating square chessboard pictures shot by the automobile data recorder from multiple angles into matrix laboratory software Matlab, then calibrating the automobile data recorder by using a camera calibration function in a matrix laboratory software Matlab toolbox, determining the mutual relation between the three-dimensional geometric position of a certain point on the surface of a space object and the corresponding point in an image, and eliminating image distortion caused by internal reasons of the automobile data recorder.
Preferably, in the step 2, in the process of collecting the video of the vehicle running on the underground road through the automobile data recorder, the vertical position of the vehicle body needs to be prevented from shaking, when the vehicle runs over a curve, the vehicle needs to keep running on an inner lane at the curve, when the vehicle runs straight, the vehicle needs to run along the middle of the lane of the road, and the vehicle body is kept parallel to the lane line.
Preferably, in step 7, the method of calculating the maximum visible distance calculated based on the driver response characteristics as the maximum driving speed that can be provided as the parking visual distance is as follows:
the maximum visibility distance, i.e. the parking sight distance S T ＝S 1 +S 2 ；
S 1 ＝V/3.6*(t 1 +t 2 )；
Wherein S is 1 As the reaction distance of the driver, S 2 Is the braking distance of the vehicle;
v is the running speed of the vehicle; t is t 1 Is the driver's sensory time; t is t 2 Is the reaction time of the driver;
Preferably, t is 1 +t 2 ＝2s。
The invention has the beneficial effects that:
1) compared with the traditional sight distance detection technology, the method has the advantages that the road sight distance detection is carried out based on the driving video at the first visual angle of the underground road driver, the detection result can reflect the visual angle of the driver more truly, and the implementation method is more convenient;
2) the method is used for carrying out machine vision analysis based on the driving video at the first visual angle of the driver, and effectively and accurately calculating the maximum distance of road visibility through the identification and length calibration of the traffic marking;
3) the method is not only suitable for the built road, and the driving video with the first visual angle is obtained by the driving simulation technology aiming at the road to be built, but also can conveniently finish the visual distance inspection work;
4) the invention can calculate the maximum visibility distance of each point of the road, carry out road visibility distance inspection, verify the rationality of the speed-limiting strategy, inversely calculate the safe driving speed of the vehicle and provide risk early warning for the underground driving of the driver.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
Fig. 1 shows a black and white chessboard picture when the automobile data recorder corrects the image according to an embodiment of the invention.
Fig. 2 illustrates the conversion of video into frame-by-frame pictures in an embodiment of the present invention.
Fig. 3 shows a truncated form of the effective area left after the frame-by-frame picture processing in an embodiment of the present invention.
Fig. 4 shows a road traffic marking binarization picture after extraction and processing in an embodiment of the invention.
FIG. 5 illustrates a top view of a road traffic marking after affine transformation in one embodiment of the present invention.
FIG. 6 is a schematic view of traffic marking positioning and scale determination in accordance with an embodiment of the present invention.
Detailed Description
Examples
As shown in fig. 2 to 6, a driving risk assessment system based on the underground road visual distance; the automobile data recorder is arranged at the front end of a windshield at the driving position of a vehicle;
the video recorded by the automobile data recorder is consistent with the visual angle of a driver, and has the functions of shooting, storing and reading;
the driving risk assessment process is as follows:
step 1, collecting a video of a vehicle running on an underground road through a vehicle event data recorder;
step 2, converting the video collected by the automobile data recorder into frame-by-frame pictures, processing each frame of picture, and reserving the lower half part of each frame of picture, namely removing the upper half part of each frame of picture, including the top end of the underground road and the illumination and traffic sign;
the gradient of each frame of picture is calibrated by the Sobel values of the pixel points, and all the pixel points with the Sobel values in the four channel regions (35,100), (30,255), (30,255) and (0.7,1.3) are reserved to be used as a pixel set meeting the gradient requirement;
the color of each frame of picture is calibrated by adopting a hue-saturation-brightness mode, namely HSL, and the hue, the saturation and the brightness of the color of each frame of picture are reserved, and pixels which respectively meet (180,255), (10,100) and (0,60) in the hue, the saturation and the brightness of the color of each frame of picture are reserved to be used as a pixel set meeting the color requirement;
sobel values are obelX, sobelY, sobelXY and direction.
Superposing and combining the pixel sets meeting the gradient requirement and the color requirement of each frame of picture to form a position picture of the pixels of each frame of picture corresponding to the lane line;
step 4, processing the position map of the pixels of each frame of image by using image expansion, and filling the position map of the pixels of each frame of image with the internal cavities of the lane line according to the edge of the lane line so as to make the lane line clear and coherent;
step 5, carrying out affine transformation by adopting four-point transformation in an Open-CV (Open-CV) of a cross-computer platform vision library, carrying out affine transformation on a position diagram of the pixel of each frame of image which fills the cavity in the lane line, and converting the position diagram into a top view;
step 6, continuously searching by taking the lower left corner of each converted top view as a starting point and the upper right corner as an end point, and determining the number of lane lines and the starting point and the end point of each lane line according to the wave crest of the histogram of the binary image;
meanwhile, scanning the lane lines by using a horizontal straight line to obtain the width of each lane line, and calculating the average width of the lane lines on the image;
then, calculating a scale of each converted top view according to the actual width of the traffic marking being 0.15m, further calculating the length of each traffic marking from the starting point to the end point, and taking the average value of the distances between the left marking and the right marking of each lane as the maximum visible distance;
step 7, according to the reaction characteristics of the driver, calculating the maximum visible distance as the maximum driving speed which can be provided by the parking sight distance;
comparing the maximum driving speed provided by the parking sight distance with the current driving speed of the vehicle and the road speed limit to obtain a risk value of the current driving speed of the vehicle;
if the current vehicle running speed of the vehicle is 110% or more of the maximum running speed provided by the parking sight distance, reminding a driver of 'please slow down and drive';
if the current vehicle driving speed of the vehicle is more than 100% but less than 110% of the maximum driving speed which can be provided by the parking sight distance, the driver is reminded of 'poor front sight distance and cautious driving'.
In practical application, a camera which can be calibrated and is a driving recorder is used as a video input module to collect driving videos of a driver, a storage module of the driving video input module mainly stores the videos collected by the camera, a visual distance calculation and risk judgment module reads the videos from the storage module and obtains visual distances and risk levels through calculation, an alarm module outputs voice and a screen, and an alarm type is selected according to the result of the calculation module.
The video input module is connected with the storage module, and the shot video is stored in the storage module. The storage module is connected with the shooting module and the calculation module, the calculation module is connected with the storage module and the alarm module, the video image in the storage module is read, and the calculation result is output to the alarm module.
In the step 2, the top of the underground road and the upper half part of the illumination and traffic sign contained in each frame of picture are removed, so that the interference of the illumination, the traffic sign and other complex images in each frame of picture on the image recognition can be prevented, and the recognition precision is enhanced.
In some embodiments, the shooting position of the tachograph is 1.2m from the road surface.
In some embodiments, before the driving risk assessment, the driving recorder needs to be corrected, and the specific steps are as follows:
as shown in fig. 1, a plurality of black and white square chessboard pictures shot by the automobile data recorder from multiple angles are imported into matrix laboratory software Matlab, then the automobile data recorder is calibrated by using a camera calibration function in a matrix laboratory software Matlab toolbox, the correlation between the three-dimensional geometric position of a certain point on the surface of a space object and the corresponding point in the image is determined, and the image distortion caused by the internal reason of the automobile data recorder is eliminated.
A Camera calibration function in a matrix laboratory software Matlab toolbox, namely a Camera call calibration function in the Matlab toolbox.
In some embodiments, in step 2, in the process of acquiring the video of the vehicle running on the underground road by the vehicle data recorder, the vertical position of the vehicle body needs to be prevented from shaking, when the vehicle passes a curve, the vehicle needs to keep running on an inner lane at the curve, and when the vehicle runs straight, the vehicle needs to run along the middle of the lane of the road, so that the vehicle body is kept parallel to the lane line.
In practical application, when a vehicle is collected through a vehicle data recorder during running on an underground road, the transverse clear distance of an inner side lane at a curve is minimum, and the visibility condition is worst, and when the vehicle runs straight, the vehicle should be driven stably because the visibility condition of a position with a large gradient is poor, so that the change of a camera shooting visual angle is avoided.
In some embodiments, the maximum visual distance calculated in step 7 as the maximum driving speed available for the stopping sight distance is calculated as follows, based on the driver reaction characteristics:
maximum visible distance, i.e. parking apparent distance S T ＝S 1 +S 2 ；
S 1 ＝V/3.6*(t 1 +t 2 )；
Wherein S is 1 As a reaction distance of the driver, S 2 Is the braking distance of the vehicle;
v is the running speed of the vehicle; t is t 1 Sensory time for the driver; t is t 2 Reaction time for the driver;
the coefficient of adhesion between the road surface and the tire; psi is the road drag coefficient.
In certain embodiments, t 1 +t 2 ＝2s。
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (6)
1. A driving risk assessment system based on the sight distance of the underground road; the automobile data recorder is characterized by comprising an automobile data recorder arranged at the front end of a windshield at the driving position of an automobile;
the video recorded by the automobile data recorder is consistent with the visual angle of a driver, and has the functions of shooting, storing and reading;
the driving risk assessment process is as follows:
step 1, collecting a video of a vehicle running on an underground road through the automobile data recorder;
step 2, converting the video collected by the automobile data recorder into frame-by-frame pictures, processing each frame of picture, and reserving the lower half part of each frame of picture, namely removing the upper half part of each frame of picture, including the top end of an underground road, illumination and a traffic sign;
step 3, extracting initial information of the lane line based on the gradient and color characteristics of each processed frame of the picture;
the gradient of each frame of the picture is calibrated by using the Sobel values of the pixel points, and all the pixel points with the Sobel values in the four channel regions (35,100), (30,255), (30,255) and (0.7,1.3) are reserved to be used as a pixel set meeting the gradient requirement;
the color of each frame of the picture is calibrated by adopting a hue-saturation-brightness mode (HSL), and the hue, the saturation and the brightness of the color of each frame of the picture are reserved, and pixels which respectively meet (180,255), (10,100) and (0,60) in the hue, the saturation and the brightness of the color of each frame of the picture are reserved to be used as a pixel set meeting the color requirement;
superposing and combining the pixel sets meeting the gradient requirement and the color requirement of each frame of picture to form a position map of the pixels of each frame of picture corresponding to the lane line;
step 4, processing the position image of the pixel of each frame of picture by using image expansion, and filling the position image of the pixel of each corresponding frame of picture with a cavity inside a lane line according to the edge of the lane line so as to enable the lane line to be clear and coherent;
step 5, carrying out affine transformation by adopting four-point transformation in an Open-CV (Open-CV) of a cross-computer platform vision library, carrying out affine transformation on a position diagram of the pixel of each frame of the picture which fills the cavity in the lane line, and converting the position diagram into a top view;
step 6, continuously searching by taking the lower left corner of each converted top view as a starting point and the upper right corner as an end point, and determining the number of lane lines and the starting point and the end point of each lane line according to the wave crest of the histogram of the binary image;
meanwhile, scanning the lane lines by using a horizontal straight line to obtain the width of each lane line, and calculating the average width of the lane lines on the image;
then, calculating a scale of each converted top view according to the actual width of the traffic marking being 0.15m, further calculating the length of each traffic marking from the starting point to the end point, and taking the average value of the distances between the left marking and the right marking of each lane as the maximum visible distance;
step 7, according to the reaction characteristics of the driver, calculating the maximum visible distance as the maximum driving speed provided by the parking sight distance;
comparing the maximum driving speed provided by the parking sight distance with the current driving speed of the vehicle and the road speed limit to obtain a risk value of the current driving speed of the vehicle;
if the current vehicle running speed of the vehicle is 110% or more of the maximum running speed which can be provided by the parking sight distance, reminding the driver of' please slow down;
and if the current vehicle driving speed of the vehicle is more than 100% but less than 110% of the maximum driving speed which can be provided by the parking sight distance, reminding the driver of 'poor front sight distance and cautious driving'.
2. The system for evaluating the driving risk based on the sight distance of the underground road according to claim 1, wherein the height of the shooting position of the driving recorder from the road surface is 1.2 m.
3. The system for driving risk assessment based on underground road sight distance according to claim 1, wherein before driving risk assessment, the driving recorder needs to be corrected, the specific steps are as follows:
the method comprises the steps of importing a plurality of black-white alternating square chessboard pictures shot by the automobile data recorder from multiple angles into matrix laboratory software Matlab, then calibrating the automobile data recorder by using a camera calibration function in a matrix laboratory software Matlab toolbox, determining the mutual relation between the three-dimensional geometric position of a certain point on the surface of a space object and the corresponding point in an image, and eliminating image distortion caused by internal reasons of the automobile data recorder.
4. The system for evaluating the driving risk based on the underground road sight distance according to claim 1, wherein in the step 2, the vehicle recorder is used for collecting the video when the vehicle runs on the underground road, the vertical position of the vehicle body needs to be prevented from shaking, when the vehicle passes a curve, the vehicle needs to keep running on an inner lane at the curve, when the vehicle runs straight, the vehicle needs to run along the middle of a lane of the road, and the vehicle body is kept parallel to the lane line.
5. The system for assessing driving risk based on the sight distance of underground road according to claim 1, wherein the maximum visible distance calculated according to the reaction characteristics of the driver in step 7 is calculated as the maximum driving speed available by the sight distance of parking:
the maximum visibility distance, i.e. the parking sight distance S T ＝S 1 +S 2 ；
S 1 ＝V/3.6*(t 1 +t 2 )；
Wherein S is 1 As the reaction distance of the driver, S 2 Is the braking distance of the vehicle;
v is the transport of vehiclesDriving speed; t is t 1 Is the driver's sensory time; t is t 2 Is the reaction time of the driver;
6. An underground road line-of-sight based driving risk assessment system according to claim 5, wherein t is 1 +t 2 ＝2s。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210572703.6A CN115116025B (en) | 2022-05-25 | 2022-05-25 | Driving risk assessment system based on underground road vision distance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210572703.6A CN115116025B (en) | 2022-05-25 | 2022-05-25 | Driving risk assessment system based on underground road vision distance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115116025A true CN115116025A (en) | 2022-09-27 |
| CN115116025B CN115116025B (en) | 2024-05-07 |
Family
ID=83325813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210572703.6A Active CN115116025B (en) | 2022-05-25 | 2022-05-25 | Driving risk assessment system based on underground road vision distance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115116025B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116311141A (en) * | 2023-05-25 | 2023-06-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Expressway-oriented vehicle-road cooperative visual range expansion method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503636A (en) * | 2016-10-12 | 2017-03-15 | 同济大学 | A kind of road sighting distance detection method of view-based access control model image and device |
| CN111009166A (en) * | 2019-12-04 | 2020-04-14 | 上海市城市建设设计研究总院（集团）有限公司 | Road three-dimensional sight distance checking calculation method based on BIM and driving simulator |
| US20200310452A1 (en) * | 2019-03-28 | 2020-10-01 | Subaru Corporation | Vehicle traveling control apparatus |
-
2022
- 2022-05-25 CN CN202210572703.6A patent/CN115116025B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503636A (en) * | 2016-10-12 | 2017-03-15 | 同济大学 | A kind of road sighting distance detection method of view-based access control model image and device |
| US20200310452A1 (en) * | 2019-03-28 | 2020-10-01 | Subaru Corporation | Vehicle traveling control apparatus |
| CN111009166A (en) * | 2019-12-04 | 2020-04-14 | 上海市城市建设设计研究总院（集团）有限公司 | Road three-dimensional sight distance checking calculation method based on BIM and driving simulator |
Non-Patent Citations (2)
| Title |
|---|
| 刘岩;王宇恒;吕冰雪;张卫正;李灿林;: "基于特征模型融合的实时车道线检测研究", 科技通报, no. 07, 31 July 2020 (2020-07-31) * |
| 王超;王宇雷;姚峰;: "基于机器视觉的车道线智能识别系统的设计", 电子世界, no. 07, 8 April 2018 (2018-04-08) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116311141A (en) * | 2023-05-25 | 2023-06-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Expressway-oriented vehicle-road cooperative visual range expansion method |
| CN116311141B (en) * | 2023-05-25 | 2023-10-20 | 深圳市城市交通规划设计研究中心股份有限公司 | Expressway-oriented vehicle-road cooperative visual range expansion method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115116025B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11989951B2 (en) | Parking detection method, system, processing device and storage medium | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| US5410346A (en) | System for monitoring condition outside vehicle using imaged picture by a plurality of television cameras | |
| US7046822B1 (en) | Method of detecting objects within a wide range of a road vehicle | |
| CN111179152B (en) | Road identification recognition method and device, medium and terminal | |
| EP0747870B1 (en) | An object observing method and device with two or more cameras | |
| JP3522317B2 (en) | Travel guide device for vehicles | |
| CN110210451B (en) | Zebra crossing detection method | |
| CN105206109B (en) | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD | |
| CN107590470B (en) | Lane line detection method and device | |
| JP6442834B2 (en) | Road surface height shape estimation method and system | |
| CN109635737B (en) | Auxiliary vehicle navigation positioning method based on road marking line visual identification | |
| JP5471310B2 (en) | Operation analysis system | |
| CN106918312B (en) | Pavement marking peeling area detection device and method based on mechanical vision | |
| CN113781537B (en) | Rail elastic strip fastener defect identification method and device and computer equipment | |
| CN103577809A (en) | Ground traffic sign real-time detection method based on intelligent driving | |
| CN111694011A (en) | Road edge detection method based on data fusion of camera and three-dimensional laser radar | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| Wei et al. | Damage inspection for road markings based on images with hierarchical semantic segmentation strategy and dynamic homography estimation | |
| CN107220632B (en) | Road surface image segmentation method based on normal characteristic | |
| CN115116025A (en) | Driving risk assessment system based on underground road sight distance | |
| JP3807583B2 (en) | Road area determination device | |
| CN114663859A (en) | Sensitive and accurate complex road condition lane deviation real-time early warning system | |
| JP3914447B2 (en) | Image-type vehicle detection system and image-type vehicle detection method | |
| JP3867890B2 (en) | Image processing method and apparatus |
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 |