CN107545754B - Method and device for acquiring traffic sign information threshold - Google Patents
Method and device for acquiring traffic sign information threshold Download PDFInfo
- Publication number
- CN107545754B CN107545754B CN201710587388.3A CN201710587388A CN107545754B CN 107545754 B CN107545754 B CN 107545754B CN 201710587388 A CN201710587388 A CN 201710587388A CN 107545754 B CN107545754 B CN 107545754B
- Authority
- CN
- China
- Prior art keywords
- traffic sign
- visual recognition
- traffic
- combination
- recognition time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for acquiring a traffic sign information threshold, wherein the method comprises the following steps: acquiring a visual recognition time threshold value when an experimenter drives and the visual recognition time of the experimenter to each traffic sign in different traffic sign combinations; acquiring a target traffic sign combination meeting the maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold; and constructing an information threshold value model according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, and acquiring a traffic sign information threshold value according to the information threshold value model. The system is used for executing the method. The embodiment of the invention comprehensively considers the visibility of the driver to the traffic sign in the driving process, and comprehensively considers the influence of different traffic sign combinations on the visibility of the traffic sign by the driver, thereby improving the accuracy of obtaining the traffic information threshold value and further providing an accurate theoretical basis for the setting of the traffic sign in the road.
Description
Technical Field
The embodiment of the invention relates to the technical field of transportation, in particular to a method and a device for acquiring a traffic sign information threshold value.
Background
With the development of science and technology, automobiles become more and more necessities in people's lives, more and more people use automobiles as transportation tools, and more reasonable traffic rules and traffic signs are correspondingly needed to guide people to drive correctly.
The reasonable setting of the traffic signs on the road can accurately guide the driver to move on the road, and the operation error rate of the driver is reduced. When setting a road traffic sign and designing a traffic sign pattern, it is necessary to study a traffic sign information threshold value. The traffic sign information threshold is also called a traffic sign information overload threshold, and refers to a value of the maximum amount of information that can be obtained by the driver within a limited time, that is, the maximum number of traffic sign information that can be obtained by the driver within a limited time or the maximum number of traffic signs that can be viewed by the driver within a limited time. In the prior art, a method for acquiring a traffic sign information threshold is mainly used for studying that the visual recognition time is linearly increased along with the increase of the number of traffic sign information, and when the linear mutation occurs, the corresponding number of information is the information threshold, and the method is called a visual recognition time mutation method. The method is only suitable for static visual traffic sign experiments, and has relatively accurate data requirements, otherwise, a linear relation cannot be formed. The method is too single, the information threshold value is pushed down only by the linear relation between the information number and the visual recognition time, and the method is only suitable for the research of the static traffic sign information threshold value. In real life, the judgment of the information threshold is judged by combining with dynamic driving, and the accuracy of obtaining the traffic sign information threshold can influence the setting of a traffic sign on a road.
Therefore, how to provide a scheme can improve the accuracy of obtaining the traffic sign information threshold value, and further provide an accurate theoretical basis for setting the traffic sign in the road, which becomes a problem to be solved urgently.
Disclosure of Invention
Aiming at the defects in the prior art, the embodiment of the invention provides a method and a device for acquiring a traffic sign information threshold value.
In one aspect, an embodiment of the present invention provides a method for obtaining a traffic sign information threshold, including:
acquiring a visual recognition time threshold value when an experimenter drives and the visual recognition time of the experimenter to each traffic sign in different traffic sign combinations;
acquiring a target traffic sign combination meeting the maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold;
and constructing an information threshold value model according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, and acquiring a traffic sign information threshold value according to the information threshold value model.
Further, the acquiring a target traffic sign combination meeting a maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold value includes:
acquiring the sum of the visual recognition time corresponding to all traffic sign combinations according to the visual recognition time;
taking the traffic sign combinations with the same number of traffic signs as the same type of traffic sign combinations to construct a traffic combination array, and marking the traffic combination array as Mi ═ m1 m2.. mj ], wherein i represents the number of the traffic signs in the traffic combination array, mj represents the jth traffic sign combination in the traffic combination array, and i >1, j > 1;
and if the visual recognition time sum corresponding to all the traffic sign combinations in the traffic sign array Mi is not more than the visual recognition time threshold value, and the visual recognition time sum corresponding to one traffic sign combination in the traffic sign array Mi +1 is more than the visual recognition time threshold value, taking each traffic sign combination in the traffic sign array Mi as the target traffic sign combination.
Further, the constructing an information threshold model according to the recognition time corresponding to each traffic sign in the target traffic sign combination includes:
constructing a multivariate linear equation set according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, wherein the number of the unknown quantities of the multivariate linear equation set is the number of the traffic signs in the target traffic sign combination;
and taking the multivariate linear equation set as the information threshold model.
Further, the method further comprises:
and determining the coefficient of the unknown quantity in the multivariate linear equation set according to the visual recognition time of experimenters with different driving ages on each traffic sign in the target traffic sign combination.
Further, the obtaining the traffic sign information threshold according to the information threshold model includes:
obtaining the value of each unknown quantity according to the multivariate linear equation set, and taking the unknown quantity with the minimum value as a reference unknown quantity;
normalizing the values of the reference unknown quantities, and taking the ratio of the values of the unknown quantities in the target traffic sign combination to the values of the reference unknown quantities as the values of the unknown quantities;
and taking the sum of the values of the unknown quantities in the linear equations as the traffic sign information threshold value.
Further, the acquiring the visual recognition time threshold value when the experimenter drives comprises:
and acquiring the average visual recognition distance and the average driving speed of a plurality of experimenters according to the visual recognition distance and the driving speed of each experimenter, and taking the ratio of the average visual recognition distance to the average driving speed as the visual recognition time threshold.
Further, the acquiring the visual recognition time of the experimenter for each traffic sign in different traffic sign combinations comprises:
recording an experiment video of the traffic sign viewed by each experimenter through an eye tracker;
and acquiring the start time and the end time of the experimenter for the visual recognition of each traffic sign in different traffic sign combinations according to the experimental video, and taking the time difference between the end time of the visual recognition and the start time of the visual recognition as the visual recognition time.
On the other hand, an embodiment of the present invention provides an apparatus for acquiring a traffic sign information threshold, including:
the system comprises a visual recognition time acquisition unit, a traffic sign combination acquisition unit and a traffic sign recognition unit, wherein the visual recognition time acquisition unit is used for acquiring a visual recognition time threshold value when an experimenter drives and the visual recognition time of the experimenter to each traffic sign in different traffic sign combinations;
the traffic sign combination acquisition unit is used for acquiring a target traffic sign combination meeting the maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold;
and the information threshold value acquisition unit is used for constructing an information threshold value model according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination and acquiring a traffic sign information threshold value according to the information threshold value model.
In another aspect, an embodiment of the present invention provides an electronic device for acquiring a threshold value of traffic sign information, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for acquiring the traffic sign information threshold.
In another aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, which stores computer instructions, where the computer instructions cause the computer to execute the method for obtaining the traffic sign information threshold.
According to the method and the device for acquiring the traffic sign information threshold, provided by the embodiment of the invention, the target traffic sign combination meeting the maximum visual recognition condition is acquired according to the acquired visual recognition time and the visual recognition time threshold of each experimenter for each traffic sign in different traffic sign combinations by acquiring the visual recognition time threshold of the experimenter in the driving process, and the traffic sign information threshold is acquired by further combining the visual recognition time corresponding to the target traffic sign combination to establish an information threshold model. The method comprehensively considers the visibility of the driver to the traffic sign in the driving process, comprehensively considers the influence of different traffic sign combinations on the visibility of the traffic sign by the driver, improves the accuracy of obtaining the traffic information threshold value, and further provides an accurate theoretical basis for the setting of the traffic sign in the road.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating a method for obtaining a threshold value of traffic sign information according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a traffic sign information threshold value obtaining apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for acquiring a traffic sign information threshold according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for acquiring a traffic sign information threshold value according to an embodiment of the present invention, and as shown in fig. 1, the method for acquiring a traffic sign information threshold value according to an embodiment of the present invention includes:
s1, acquiring a visual recognition time threshold value when an experimenter drives and the visual recognition time of the experimenter for each traffic sign in different traffic sign combinations;
specifically, the embodiment of the invention selects a certain amount of experimenters to perform the experiment of visually recognizing the traffic sign, simulates the experimenters to perform the experiment of visually recognizing the traffic sign in the driving process, and particularly can perform the experiment of visually recognizing the traffic sign by driving the simulation cabin. Firstly, acquiring a visual recognition time threshold of a driver, namely an experimenter, in a driving process, wherein the visual recognition time threshold refers to: the time difference between the traffic sign going into the driver's field of view and going out of the driver's field of view in the forward direction of the driver's driving road. For example: a traffic sign is arranged in the advancing direction of a driving road of a driver, when the driver drives along the road, the position of the traffic sign entering the visual field of the driver is a point A, and the position of the traffic sign out of the visual field of the driver is a point B (namely, the traffic sign can not be seen in the visual field of the driver from the point B). It can be seen that the distance between the point a and the traffic sign is greater than the distance between the point B and the traffic sign, and the driving time from the point a to the point B of the driver is used as the visual recognition time threshold. And then acquiring the visual recognition time of each experimenter for each traffic sign in different traffic sign combinations, specifically classifying the traffic signs in advance, randomly selecting one traffic sign from each class for an experiment, randomly combining the selected traffic signs, and acquiring the visual recognition time of each experimenter for each traffic sign in different traffic sign combinations. The visual recognition time refers to the time interval from the time when the experimenter sees the picture of the traffic sign to the time when the experimenter reflects the meaning of the traffic sign, and can be obtained by obtaining the time from the time when the experimenter sees the picture of the traffic sign to the time when the experimenter speaks the meaning, or by analyzing the brain activity of the experimenter through software.
The experimenter can select according to the requirement, and in order to ensure the accuracy of the obtained visual understanding time, the experimenter corresponding to different sexes, driving ages and ages is selected according to the sex, the driving age and the age in the embodiment of the invention. Of course, the experimenters may be selected according to other conditions to perform the experiment according to needs, and the number of the experimenters may also be selected according to needs, and the embodiment of the present invention is not particularly limited.
It can be seen that the experimenter in the embodiment of the invention needs to have driving experience to ensure the accuracy of obtaining the time for seeing and recognizing the traffic sign. For the classification of the traffic signs, the classification may be performed according to the time for the driver to recognize the traffic signs, or may be performed according to other manners, and the embodiment of the present invention is not particularly limited.
For example: if the traffic signs are classified into 5 types in advance, 5 different types of traffic signs are randomly selected from the 5 types of traffic signs, the selected traffic signs are randomly combined, the number of the traffic signs in each combination mode can be different, that is, each traffic sign combination can include 5 or 4 or 3 or 2 traffic signs. Such as: if the selected traffic signs are: the lane driving direction sign, the parking yielding sign, the road indicating sign, the speed limit sign and the left turn forbidding sign can be combined together to form a combination mode, and 4 combinations can be selected randomly, such as: the lane driving direction sign, the parking yielding sign, the road indicating sign and the speed limiting sign are used as a combination mode, or the parking yielding sign, the road indicating sign, the speed limiting sign and the left-turning forbidding sign are used as a combination mode, and the like. The method comprises the steps of obtaining the visual recognition time of each traffic sign when an experimenter combines different traffic signs by simulating the experiment of visually recognizing the traffic signs during the driving process of a driver in a road. Such as: when 5 traffic signs of a lane driving direction sign, a parking concession sign, a road directing sign, a speed limiting sign and a left turn forbidding sign are combined, the visual recognition time of an experimenter to the lane driving direction sign, the visual recognition time of the parking concession sign, the visual recognition time of the road directing sign, the visual recognition time of the speed limiting sign and the visual recognition time of the left turn forbidding sign are obtained.
S2, acquiring a target traffic sign combination meeting the maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold;
specifically, according to the obtained visual recognition time of each traffic sign by the experimenter when different traffic signs are combined and the obtained visual recognition time threshold value of the experimenter in the driving process, the embodiment of the invention obtains the target traffic sign combination meeting the maximum visual recognition condition.
S3, constructing an information threshold value model according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, and acquiring a traffic sign information threshold value according to the information threshold value model.
Specifically, after a target traffic sign combination is obtained, an information threshold model is constructed according to the target traffic sign combination and the recognition time of an experimenter to each traffic sign in the target traffic sign combination, and a traffic sign information threshold is obtained by using the information threshold model. After the traffic sign information threshold value is acquired, various traffic signs can be reasonably set and distributed on the road by using the information threshold value, so that the distribution of the traffic signs can improve the visual recognition effect of a driver when the driver drives in the road.
According to the method for acquiring the traffic sign information threshold value provided by the embodiment of the invention, the target traffic sign combination meeting the maximum visual recognition condition is acquired according to the acquired visual recognition time and the visual recognition time threshold value by acquiring the visual recognition time threshold value of an experimenter in the driving process and the visual recognition time of each traffic sign in different traffic sign combinations by each experimenter, and an information threshold value model is established by further combining the visual recognition time corresponding to the target traffic sign combination to acquire the traffic sign information threshold value. The method comprehensively considers the visibility of the driver to the traffic sign in the driving process, comprehensively considers the influence of different traffic sign combinations on the visibility of the traffic sign by the driver, improves the accuracy of obtaining the traffic information threshold value, and further provides an accurate theoretical basis for the setting of the traffic sign in the road.
On the basis of the above embodiment, the acquiring a target traffic sign combination satisfying a maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold includes:
acquiring the sum of the visual recognition time corresponding to all traffic sign combinations according to the visual recognition time;
the traffic sign combinations with the same number of traffic signs are used as the same type of traffic sign combinations to construct a traffic combination array which is marked as Mi＝[m1m2...mj]I represents the number of traffic signs in the traffic combination array, mjRepresents the jth traffic sign combination, i, in the traffic combination array>1，j>1；
If the traffic sign array MiThe sum of the visual recognition time corresponding to all the traffic sign combinations is not more than the visual recognition time threshold, and the traffic sign array Mi+1If the sum of the visual recognition time corresponding to one traffic sign combination is greater than the visual recognition time threshold value, the traffic sign array M is processediAs the target traffic sign combination.
Specifically, the sum of the viewing times of all traffic signs in different traffic sign combinations is obtained first, for example: if a certain traffic sign combination comprises 5 traffic signs, acquiring the visual recognition time of each traffic sign in the traffic sign combination by an experimenter, and taking the sum of the visual recognition times of the five traffic signs as the sum of the visual recognition times of the traffic signs. Taking the traffic sign combinations with the same number of traffic signs as a class of traffic sign combinations, constructing a traffic combination array, and recording the traffic combination array as Mi＝[m1m2...mj]I represents the number of traffic signs in the traffic combination array, mjRepresenting the jth traffic sign combination, i, in the traffic combination array>1，j>1. Such as: if 5 types of traffic signs are in total, randomly selecting one traffic sign from each type of traffic signs to combine, and assuming that the selected traffic signs are A, B, C, D and E respectively. There is only one combination [ AB C D E ] of 5 traffic signs in the traffic sign combination]There are 3 combinations of 4 traffic signs [ AB C D]、[A B C E]And [ B C D E]There are 5 combinations of 3 traffic signs, 10 combinations of 2 traffic signs, and 5 combinations of 1 traffic sign. The combination with the same number of traffic signs is taken as a traffic sign combination, for example: if there are 4 traffic signs and there are 3 combinations, then the array M is constructed4＝[m1m2m3]Wherein m is1、m2And m3Can respectively represent traffic sign combination [ AB C D]、[AB C E]And [ B C D E]。
After the traffic sign array is constructed, the relation between the visual recognition time sum corresponding to each traffic sign combination in different traffic sign arrays and the visual recognition time threshold value is judged. If traffic sign array MiThe sum of the visual recognition time corresponding to all the traffic sign combinations is not more than the visual recognition time threshold, and the traffic sign array Mi+1If the sum of the visual recognition time corresponding to one traffic sign combination is greater than the visual recognition time threshold value, the traffic sign array M is divided into a plurality of groupsiEach traffic sign combination is used as the target traffic sign combination.
For example: with 4 traffic signs in combinationTraffic combination array M4＝[m1m2m3]Wherein m is1、m2And m3Can respectively represent traffic sign combination [ AB C D]、[A B C E]And [ B C D E]If the traffic sign combination [ AB CD]、[A B C E]And [ B C D E]The sum of the corresponding visual recognition time is not greater than the pre-acquired visual recognition time threshold. And, there is a traffic combination array M corresponding to the combination of 5 traffic signs5＝[m1]Wherein m is1Indicating a traffic sign combination [ AB C D E]If the traffic sign combination [ AB C D E]The sum of the corresponding visual recognition times is greater than a pre-acquired visual recognition time threshold. There will be a combination of 4 traffic signs [ AB C D]、[A B C E]And [ B C D E]As a target traffic sign combination.
According to the method for acquiring the traffic sign information threshold value, which is provided by the embodiment of the invention, the target traffic sign combination meeting the maximum visual recognition condition is acquired by acquiring the relation between the visual recognition time sum and the visual recognition time threshold value corresponding to different traffic sign combinations, namely the traffic sign combination with the visual recognition time sum smaller than the visual recognition time threshold value is acquired, so that an accurate data basis is provided for the subsequent acquisition of the traffic sign threshold value. The method comprehensively considers the visibility of the driver to the traffic sign in the driving process, comprehensively considers the influence of different traffic sign combinations on the visibility of the traffic sign by the driver, improves the accuracy of obtaining the traffic information threshold value, and further provides an accurate theoretical basis for the setting of the traffic sign in the road.
On the basis of the above embodiment, the constructing an information threshold model according to the recognition time corresponding to each traffic sign in the target traffic sign combination includes:
constructing a multivariate linear equation set according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, wherein the number of the unknown quantities is the number of the traffic signs in the target traffic sign combination;
and taking the multivariate linear equation set as the information threshold model.
Specifically, according to the obtained visual recognition time corresponding to each traffic sign in the target traffic sign combination, a multivariate linear equation set is constructed, wherein the number of unknown quantities of the multivariate linear equation set is the same as the number of the traffic signs in the target traffic sign combination, and the multivariate linear equation set is used as an information threshold model. For example: if the combination [ A B C D ], [ A B C E ] and [ B C D E ] of 4 traffic signs is the target traffic sign combination, 4-element linear equation sets can be constructed according to the corresponding visual recognition time of each traffic sign in the traffic sign combination, namely 4 unknowns exist, and the traffic sign information threshold value can be obtained by solving the value of the unknowns.
On the basis of the above embodiment, the method further includes:
and determining the coefficient of the unknown quantity in the multivariate linear equation set according to the visual recognition time of experimenters with different driving ages on each traffic sign in the target traffic sign combination.
Specifically, in the research process of the embodiment of the invention, the driving age is found to have a significant influence on the time for experimenters to visually recognize each traffic sign, so that the embodiment of the invention determines the coefficient of each unknown quantity in the multi-linear equation set according to the driving age of the experimenters and the visual recognition time of each traffic sign in the target traffic sign combination by the experimenters with different driving ages. Of course, according to the requirement, the obtained visual recognition time of each traffic sign in the target traffic sign combination may be subjected to data processing in other manners to determine the coefficients of the multiple linear equations, which is not specifically limited in the embodiment of the present invention.
For example: if the target traffic sign combination determined by the embodiment of the invention is a combination mode comprising 4 traffic signs, a four-element linear equation set is established as follows:
wherein x, y, z and w are the quantities to be solved, namely the interrelation of the four traffic signs, and the values of a, b, c and d are the visual recognition time data of 40 experimenters, namely drivers. a represents the average visual recognition time of 1-2 years of driving age, a1、a2、a3And a4Respectively representing the average visual recognition time corresponding to the first, second, third and fourth traffic signs visually recognized by experimenters with the driving ages of 1-2 years in the target traffic sign combination; b represents the average visual recognition time of 2-3 years of driving age, b1、b2、b3And b4Respectively representing the average visual recognition time corresponding to the first, second, third and fourth traffic signs visually recognized by experimenters with the driving ages of 2-3 years in the target traffic sign combination; c represents the average visual recognition time of 3-4 years of driving age, c1、c2、c3And c4Respectively representing the average visual recognition time corresponding to the first, second, third and fourth traffic signs visually recognized by experimenters with the driving ages of 3-4 years in the target traffic sign combination; d represents an average visual recognition time of 5 years or more in driving age, d1、d2、d3And d4The average visual recognition times of experimenters with the driving ages of 5 years for visually recognizing the first, second, third and fourth traffic signs in the target traffic sign combination are respectively shown. The value e is the sum of the visual recognition time of the four traffic signs when the traffic signs are singly set, namely, an experimenter only visually recognizes one traffic sign in the four traffic signs at a time, and the sum of the visual recognition time corresponding to the four traffic signs is used as the value e.
The obtained visual recognition time of each experimenter for each traffic sign in the target traffic sign combination is arranged according to the driving age of the experimenter, so that the coefficients of the quaternary linear equation set are obtained, and the specific results are as follows in the following table 1:
TABLE 1 traffic sign visibility time classification results based on driving experience
| Known number | 1 | 2 | 3 | 4 |
| a | 432 | 411 | 397 | 282 |
| b | 508 | 488 | 472 | 379 |
| c | 719 | 692 | 628 | 548 |
| d | 1147 | 952 | 1022 | 1208 |
| e | 4106 | 4106 | 4106 | 4106 |
By solving the quaternary linear equation set, the values of the unknown quantities can be obtained, and the traffic sign threshold value can be obtained according to the obtained values of the unknown quantities.
On the basis of the above embodiment, the obtaining of the traffic sign information threshold according to the information threshold model includes:
obtaining the value of each unknown quantity according to the multivariate linear equation set, and taking the unknown quantity with the minimum value as a reference unknown quantity;
normalizing the values of the reference unknown quantities, and taking the ratio of the values of the unknown quantities in the target traffic sign combination to the values of the reference unknown quantities as the values of the unknown quantities;
and taking the sum of the values of the unknown quantities in the linear equations as the traffic sign information threshold value.
Specifically, values of the respective unknown quantities are obtained by solving the system of equations of a multivariate linear equation, and the unknown quantity of which the value is the smallest is taken as the reference unknown quantity. And (3) normalizing the reference unknown quantity, namely taking the value of the reference unknown quantity as 1, acquiring the ratio of each other unknown quantity to the reference unknown quantity as the value of each position quantity, and taking the sum of each unknown quantity as the information threshold of the traffic sign. In solving the multiple linear equations, the unknown quantity corresponding to the traffic sign with the minimum view time of the experimenter may be used as the reference unknown quantity, and the value of the reference unknown quantity may be directly used as 1 to solve the multiple linear equations.
According to the method for acquiring the traffic sign information threshold value, provided by the embodiment of the invention, a multivariate linear equation set is constructed by using a mathematical method according to the acquired visual recognition time of each traffic sign in the target traffic sign combination meeting the maximum visual recognition condition, and the traffic sign information threshold value is acquired by solving the multivariate linear equation set. The interaction effect among different traffic signs is comprehensively considered, the information multiple among different traffic signs can be obtained by solving the multivariate linear equation, and the traffic sign information threshold value is further obtained. The influence of different traffic sign combinations on the driver to see and recognize the traffic signs is comprehensively considered, the accuracy of obtaining the traffic information threshold value is improved, and an accurate theoretical basis is further provided for the setting of the traffic signs in the road.
On the basis of the foregoing embodiment, the acquiring the visual recognition time threshold when the experimenter is driving includes:
and acquiring the average visual recognition distance and the average driving speed of a plurality of experimenters according to the visual recognition distance and the driving speed of each experimenter, and taking the ratio of the average visual recognition distance to the average driving speed as the visual recognition time threshold.
Specifically, in the embodiment of the invention, a plurality of experimenters are selected in advance to carry out a visual recognition experiment of the traffic sign, the visual recognition distances and the driving speeds of the plurality of experimenters are obtained, the average visual recognition distances and the average driving speeds of the plurality of experimenters are obtained according to the visual recognition distances and the driving speeds of the plurality of experimenters, and the ratio of the average visual recognition distances to the average driving speeds is used as the visual recognition time threshold.
For example: the method comprises the steps of setting a traffic sign in a preset road section, obtaining coordinates corresponding to the traffic sign when 10 drivers drive in the preset road section and coordinates corresponding to the traffic sign cannot be seen, obtaining the visual recognition distance of each driver according to the coordinates, and further obtaining the average visual recognition distance of the 10 drivers. And simultaneously acquiring the driving speed of each driver within the visual recognition distance, and further acquiring the average driving speed of 10 drivers. And taking the ratio of the average visual recognition distance to the average driving speed as a visual recognition time threshold value. The specific data processing procedure can be seen in table 2:
TABLE 2 visibility time threshold data processing sheet
On the basis of the above embodiment, the acquiring the time for the experimenter to visually recognize each traffic sign in different traffic sign combinations includes:
recording an experiment video of the traffic sign viewed by each experimenter through an eye tracker;
and acquiring the start time and the end time of the experimenter for the visual recognition of each traffic sign in different traffic sign combinations according to the experimental video, and taking the time difference between the end time of the visual recognition and the start time of the visual recognition as the visual recognition time.
Specifically, the embodiment of the invention utilizes the driving simulation cabin and the eye tracker to perform the traffic sign visual recognition experiment, the experimenter wears the eye tracker to simulate driving in the driving simulation cabin, different traffic sign combinations are set in the simulated driving scene, and the experimenter visually recognizes each traffic sign in the simulated scene. The method comprises the steps of recording an experimental video of the traffic sign viewed by an experimenter through an eye tracker, analyzing and processing the obtained experimental video, obtaining the viewing start time and the viewing end time of the experimenter for each traffic sign in different traffic sign combinations, and taking the time difference between the viewing end time and the viewing start time as the viewing time of each traffic sign.
The following describes a specific implementation manner of the embodiment of the present invention to better understand the technical solution of the embodiment of the present invention:
(1) experimental data acquisition
1) Preliminary experiments
The pre-experiment mainly comprises 10 drivers, and the experiment contents are viewed by a single sign. The experimental procedure was as follows:
a. the driver carries out questionnaire training and informs the driver of specifying a driving route;
b. determining whether a driver recognizes 5 marks, namely a lane driving direction mark, a parking yielding mark, a road indicating mark, a speed limit mark and a left turn forbidding mark;
c. wearing an eye tracker to calibrate coordinates;
d. the driver starts the simulator, the computer records the experimental video, and the background of the operator records the coordinates and the speed of the driver starting the cognitive mark and finishing the cognitive mark;
and (4) checking the data of the operating platform by an operator, sorting out experimental materials, ensuring that no information is omitted, and completing the experiment.
The pre-experiment mainly draws the average driving speed and the average visual recognition distance of the driver so as to determine the visual recognition time threshold value.
2) Formal experiment
The official experiment is participated in by 40 drivers, and the experiment contents are viewed and recognized by various traffic sign combinations. The experimental procedure was as follows:
a. the driver carries out questionnaire training and informs the driver of the driving behavior corresponding to each mark;
b. informing a driver of appointing a driving route in each scene, and carrying out experiments in three scenes and 15 intersections;
c. wearing an eye tracker to calibrate coordinates;
d. the driver starts the simulator, and the computer records the video of each experiment;
e. and (4) checking the data of the operating platform by an operator, sorting out experimental materials, ensuring that no information is omitted, and completing the experiment.
(2) Processing experimental data to obtain target traffic sign combination
1) Pre-experimental data processing
And extracting an experimental video file recorded by the eye tracker, and extracting the time of the fixation point of the driver on the traffic sign. The extraction method uses programmed software, and the background records the time for starting and finishing the visual recognition of the fixation point of each traffic sign, so as to obtain the visual recognition time corresponding to each traffic sign. Through a large amount of video data processing, the visual recognition time of each traffic sign when a single traffic sign is viewed can be obtained as shown in table 3 (namely, only one traffic sign is arranged at one position, and a driver visually recognizes the traffic sign):
TABLE 3 Single sign recognition time and ratio
The specific data of the visual recognition time threshold obtained through the preliminary experiment are shown in table 2 above, and the visual recognition time threshold in the embodiment of the present invention is 3.95 s.
2) Official experimental data processing
The formal experiment data processing is similar to the theoretic pre-experiment, and mainly extracts the visual recognition time of the eye tracker for recording the experiment video. The method comprises the steps of extracting the fixation point of a driver in the visual recognition time of each traffic sign, processing 40 videos in total, extracting 15 intersection data from each video, and extracting the fixation time of each traffic sign in each intersection, wherein the total number of 3000 big data is obtained. In the embodiment of the invention, the traffic signs are divided into 5 classes, and one traffic sign combination is selected from each class for visual recognition, and the selected traffic signs are the right-driving forbidding, the lane driving direction, the speed limit 40, the parking yielding and road directing signs.
When the combination mode including 5 traffic signs is only one, and the right-hand driving prohibition, the lane driving direction, the speed limit 40, the parking giving way and the road indicating sign are combined together, the visual recognition time of each traffic sign by an experimenter is shown in the following table 4:
TABLE 4 summary table of the time for viewing and recognizing each traffic sign when five kinds of traffic signs are combined
According to the data processing of the 5 traffic sign combination forms, the total visual recognition time 3997 milliseconds of the 5 traffic signs is larger than the visual recognition time threshold 3950 milliseconds of the driver, so that the setting of the 5 traffic signs is known to exceed the information threshold understood by the driver. According to the data processing result, when the traffic signs are subjected to various combinations, the visual recognition time of the driver is obviously shorter than that of the single sign, and the visual recognition relations among the signs are different (the visual recognition proportions of the traffic signs are different and the proportions are reduced). The reason why the visual recognition time is shortened is mainly the influence of the combination of various traffic signs, and a driver needs to visually recognize all the signs in a limited time, so that the eye movement is more complicated and the energy is more concentrated than that when the driver visually recognizes a single sign, and the psychology of the driver generates more sense of urgency. The fact that the visibility time ratio between the signs is reduced indicates that the traffic signs and the signs have mutual influence, and the visibility relationship changes along with the increase or reduction of the signs, so that the information relationship of various traffic signs needs to be researched according to the complexity and the arrangement rule of the signs instead of the inherent univocal and ambiguous information when the information relationship of the traffic signs is researched.
The combination mode including 4 traffic signs is 3, when the left driving is prohibited, the speed limit is 40, the driving direction of the lane and the road indicating sign are combined together, the visual recognition time of the experimenter to each traffic sign is shown in a table 5:
when right turn prohibition, parking give way, lane driving direction and road indication sign are combined together, the visual recognition time of experimenters for each traffic sign is shown in table 6:
TABLE 5 summary of the time for viewing each traffic sign when four traffic signs are combined
TABLE 6 summary table of the viewing time of each traffic sign when four traffic signs are combined
The experimenter's visibility times for each traffic sign when the speed limit 40, the stop giving way, the lane driving direction and the road sign are combined together are shown in table 7:
TABLE 7 summary of the time for viewing each traffic sign when four traffic signs are combined
According to the three cases of the 4 traffic sign combination forms, the data processing shows that the total visual recognition time of the 4 traffic signs is 3063 milliseconds, 3790 milliseconds and 3476 milliseconds respectively, and is smaller than the visual recognition time threshold 3950 milliseconds of the cognitive psychology of the driver, so that the setting of the 4 traffic sign combination forms is in the information threshold range which can be received by the driver. And the sum of the visual recognition time in the 5 traffic sign combinations is greater than the visual recognition time threshold, so that the conclusion can be drawn that the visual recognition time of each traffic sign in the 4 traffic sign combinations is less than that of a single traffic sign, the visual recognition ratio between the signs is reduced, and the interaction of the influence between the traffic signs is also explained. Moreover, the proportional relationship between various traffic signs changes correspondingly with the different combination forms of various traffic signs.
The above experimental data processing results have proved that the relationship between the traffic sign information is not simply superimposed by increasing the information content, and the correlation thereof needs to be studied by a certain mathematical method. In order to explore the information relationship of the four traffic signs, only the proportional relationship of the time average values is considered, which is unscientific and not strictly forbidden. In the embodiment of the invention, after comparing the merits of the structural equation, the equation set solution and other methods, a typical research method for solving the correlation among the four parameters, namely a quaternary linear equation set, is finally selected, and the formula (1) is specifically referred to.
The unknown quantity x is normalized, the four-element linear equation set is solved, the values of the unknown quantity x, y, z and w are respectively 1, 1.4, 1.6 and 2, so that the corresponding relation of the four marks is 1:1.4:1.6:2, namely when 4 traffic marks are combined, the information multiple relation is 1:1.4:1.6:2, and the obtained traffic mark information threshold value is 6. When the traffic signs are laid out, the information number of the traffic signs which can be laid at most at the same intersection cannot exceed 6, the relationship among the traffic signs can be obtained by the method, and the information threshold of the traffic sign combination is obtained according to the relationship among the traffic signs to lay out the traffic signs. The number of information items of the traffic signs of the same category may be considered to be the same, and the traffic signs of the same category may be replaced when the traffic signs are laid out.
TABLE 8 comparison of single traffic sign visibility and combined traffic sign visibility
| Type of mark | Ratio of viewing time in single case | Ratio of viewing time in combination |
| Forbidding right turn | 1 | 1 |
| Speed limit 40 | 1.47 | 1.4 |
| Direction of travel of lane | 2.35 | 1.6 |
| Road sign (6 road number) | 4.84 | 2 |
The table 8 is a comparison table of the visual recognition ratios when the single set visual recognition traffic sign ratio is combined with the traffic sign, and it can be known through data comparison that the visual recognition ratios of the signs are different due to the mutual influence between the traffic signs when the traffic sign is set singly and when the traffic sign is set in multiple sets, that is, the information multiples of the traffic signs are different.
According to the method for acquiring the traffic sign information threshold, the target traffic sign combination is determined according to the magnitude relation between the visual recognition time of the driver for each traffic sign in different traffic sign combinations and the visual recognition time threshold. And further establishing an information threshold model and a multiple linear equation set according to the target traffic sign combination, and solving the equation set to obtain the information multiple relation among all traffic signs in the target traffic sign combination so as to obtain the traffic sign information threshold. The influence of different traffic sign combinations on the driver to see and recognize the traffic signs and the influence relationship among the traffic signs when the different traffic sign combinations are considered comprehensively, so that the accuracy of obtaining the traffic information threshold value is improved, and an accurate theoretical basis is further provided for the setting of the traffic signs in the road.
Fig. 2 is a schematic structural diagram of a traffic sign information threshold value obtaining device in an embodiment of the present invention, and as shown in fig. 2, the traffic sign information threshold value obtaining device provided in the embodiment of the present invention includes: a visual recognition time acquisition unit 21, a traffic sign combination acquisition unit 22, and an information threshold acquisition unit 23, wherein:
the visual recognition time acquisition unit 21 is configured to acquire a visual recognition time threshold value when an experimenter drives and a visual recognition time of the experimenter for each traffic sign in different traffic sign combinations; the traffic sign combination obtaining unit 22 is configured to obtain a target traffic sign combination meeting a maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold; the information threshold value obtaining unit 23 is configured to construct an information threshold value model according to the recognition time corresponding to each traffic sign in the target traffic sign combination, and obtain a traffic sign information threshold value according to the information threshold value model.
Specifically, the embodiment of the invention selects a certain amount of experimenters to perform the experiment of visually recognizing the traffic sign, simulates the experimenters to perform the experiment of visually recognizing the traffic sign in the driving process, and particularly can perform the experiment of visually recognizing the traffic sign by driving the simulation cabin. The visual recognition time acquisition unit 21 acquires a visual recognition time threshold value of a driver, namely an experimenter, in the driving process and the visual recognition time of each experimenter for each traffic sign in different traffic sign combinations. The specific obtaining method is the same as the above embodiment, and is not described herein again. The traffic sign combination obtaining unit 22 obtains a target traffic sign combination meeting the maximum visual recognition condition according to the obtained visual recognition time of each traffic sign by the experimenter when different traffic signs are combined and the obtained visual recognition time threshold of the experimenter in the driving process. After the target traffic sign combination is obtained, the information threshold value obtaining unit 23 constructs an information threshold value model according to the target traffic sign combination and the recognition time of the experimenter for each traffic sign in the target traffic sign combination, and obtains the traffic sign information threshold value by using the information threshold value model. After the traffic sign information threshold value is acquired, various traffic signs can be reasonably set and distributed on the road by using the information threshold value, so that the distribution of the traffic signs can improve the visual recognition effect of a driver when the driver drives in the road.
The apparatus for acquiring a traffic sign information threshold according to the embodiment of the present invention is specifically configured to execute the method for acquiring a traffic sign information threshold, and a specific implementation manner of the apparatus is consistent with the embodiment described above, which is not described herein again.
The device for acquiring the traffic sign information threshold provided by the embodiment of the invention acquires the target traffic sign combination meeting the maximum visual recognition condition according to the acquired visual recognition time and the visual recognition time threshold of each experimenter for each traffic sign in different traffic sign combinations by acquiring the visual recognition time threshold of the experimenter in the driving process and the visual recognition time of each experimenter, and further establishes an information threshold model by combining the visual recognition time corresponding to the target traffic sign combination to acquire the traffic sign information threshold. The method comprehensively considers the visibility of the driver to the traffic sign in the driving process, comprehensively considers the influence of different traffic sign combinations on the visibility of the traffic sign by the driver, improves the accuracy of obtaining the traffic information threshold value, and further provides an accurate theoretical basis for the setting of the traffic sign in the road.
Fig. 3 is a schematic structural diagram of an electronic device for acquiring a traffic sign information threshold according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)31, a memory (memory)32 and a communication bus 33, wherein the processor 31 and the memory 32 are communicated with each other via the communication bus 33. The processor 31 may call logic instructions in the memory 32 to perform the following method: acquiring a visual recognition time threshold value when an experimenter drives and the visual recognition time of the experimenter to each traffic sign in different traffic sign combinations; acquiring a target traffic sign combination meeting the maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold; and constructing an information threshold value model according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, and acquiring a traffic sign information threshold value according to the information threshold value model.
Furthermore, the logic instructions in the memory 32 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing 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 removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention provide a non-transitory computer-readable storage medium, which stores computer instructions, where the computer instructions cause the computer to perform the methods provided by the above method embodiments, for example, the methods include: acquiring a visual recognition time threshold value when an experimenter drives and the visual recognition time of the experimenter to each traffic sign in different traffic sign combinations; acquiring a target traffic sign combination meeting the maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold; and constructing an information threshold value model according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, and acquiring a traffic sign information threshold value according to the information threshold value model.
The above-described embodiments of the apparatus and system are only schematic, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Claims (7)
1. A method for acquiring a traffic sign information threshold value is characterized by comprising the following steps:
the method for acquiring the visual recognition time threshold value of the experimenter during driving comprises the following steps:
acquiring the average visual recognition distance and the average driving speed of a plurality of experimenters according to the visual recognition distance and the driving speed of each experimenter, and taking the ratio of the average visual recognition distance to the average driving speed as the visual recognition time threshold;
and the experimenter's time of recognition of each traffic sign in different traffic sign combinations;
according to the visual recognition time and the visual recognition time threshold value, acquiring a target traffic sign combination meeting the maximum visual recognition condition, wherein the method comprises the following steps:
acquiring the sum of the visual recognition time corresponding to all traffic sign combinations according to the visual recognition time;
the traffic sign combinations with the same number of traffic signs are used as the same type of traffic sign combinations to construct a traffic combination array which is marked as Mi＝[m1m2...mj]I represents the number of traffic signs in the traffic combination array, mjRepresents the jth traffic sign combination, i, in the traffic combination array>1，j>1；
If the traffic sign array MiThe sum of the visual recognition time corresponding to all the traffic sign combinations is not more than the visual recognition time threshold, and the traffic sign array Mi+1If the sum of the visual recognition time corresponding to one traffic sign combination is greater than the visual recognition time threshold value, the traffic sign array M is processediEach traffic sign combination is used as the target traffic sign combination;
constructing an information threshold model according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, wherein the information threshold model comprises the following steps:
constructing a multivariate linear equation set according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, wherein the number of the unknown quantities of the multivariate linear equation set is the number of the traffic signs in the target traffic sign combination;
taking the multivariate linear equation set as the information threshold model;
and acquiring a traffic sign information threshold according to the information threshold model.
2. The method of claim 1, further comprising:
and determining the coefficient of the unknown quantity in the multivariate linear equation set according to the visual recognition time of experimenters with different driving ages on each traffic sign in the target traffic sign combination.
3. The method of claim 1, wherein obtaining the traffic sign information threshold according to the information threshold model comprises:
obtaining the value of each unknown quantity according to the multivariate linear equation set, and taking the unknown quantity with the minimum value as a reference unknown quantity;
normalizing the values of the reference unknown quantities, and taking the ratio of the values of the unknown quantities in the target traffic sign combination to the values of the reference unknown quantities as the values of the unknown quantities;
and taking the sum of the values of the unknown quantities in the linear equations as the traffic sign information threshold value.
4. The method of claim 1, wherein obtaining the experimenter's time of visibility of each traffic sign in different combinations of traffic signs comprises:
recording an experiment video of the traffic sign viewed by each experimenter through an eye tracker;
and acquiring the start time and the end time of the experimenter for the visual recognition of each traffic sign in different traffic sign combinations according to the experimental video, and taking the time difference between the end time of the visual recognition and the start time of the visual recognition as the visual recognition time.
5. An apparatus for obtaining a traffic sign information threshold, comprising:
the visual recognition time acquisition unit is used for acquiring a visual recognition time threshold value when an experimenter drives, and comprises:
acquiring the average visual recognition distance and the average driving speed of a plurality of experimenters according to the visual recognition distance and the driving speed of each experimenter, and taking the ratio of the average visual recognition distance to the average driving speed as the visual recognition time threshold;
and the experimenter's time of recognition of each traffic sign in different traffic sign combinations;
the traffic sign combination acquiring unit is used for acquiring a target traffic sign combination meeting the maximum visual recognition condition according to the visual recognition time and the visual recognition time threshold, and comprises the following steps:
acquiring the sum of the visual recognition time corresponding to all traffic sign combinations according to the visual recognition time;
the traffic sign combinations with the same number of traffic signs are used as the same type of traffic sign combinations to construct a traffic combination array which is marked as Mi＝[m1m2...mj]I represents the number of traffic signs in the traffic combination array, mjRepresents the jth traffic sign combination, i, in the traffic combination array>1，j>1；
If the traffic sign array MiThe sum of the visual recognition time corresponding to all the traffic sign combinations is not more than the visual recognition time threshold, and the traffic sign array Mi+1If the sum of the visual recognition time corresponding to one traffic sign combination is greater than the visual recognition time threshold value, the traffic sign array M is processediEach traffic sign combination is used as the target traffic sign combination;
an information threshold obtaining unit, configured to construct an information threshold model according to the recognition time corresponding to each traffic sign in the target traffic sign combination, where the information threshold obtaining unit includes:
constructing a multivariate linear equation set according to the visual recognition time corresponding to each traffic sign in the target traffic sign combination, wherein the number of the unknown quantities of the multivariate linear equation set is the number of the traffic signs in the target traffic sign combination;
taking the multivariate linear equation set as the information threshold model;
and acquiring a traffic sign information threshold according to the information threshold model.
6. An electronic device for acquisition of traffic sign information thresholds, comprising:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 4.
7. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710587388.3A CN107545754B (en) | 2017-07-18 | 2017-07-18 | Method and device for acquiring traffic sign information threshold |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710587388.3A CN107545754B (en) | 2017-07-18 | 2017-07-18 | Method and device for acquiring traffic sign information threshold |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107545754A CN107545754A (en) | 2018-01-05 |
| CN107545754B true CN107545754B (en) | 2020-07-14 |
Family
ID=60970197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710587388.3A Active CN107545754B (en) | 2017-07-18 | 2017-07-18 | Method and device for acquiring traffic sign information threshold |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107545754B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181149B (en) * | 2020-09-30 | 2022-12-20 | 山东理工大学 | Driving environment recognition method and device and simulated driver |
| CN114724104B (en) * | 2022-05-24 | 2022-09-09 | 交通运输部公路科学研究所 | Method, device, electronic equipment, system and medium for detecting visual recognition distance |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102011109387A1 (en) * | 2011-08-04 | 2013-02-07 | Conti Temic Microelectronic Gmbh | Method for detecting traffic signs |
| CN103069153A (en) * | 2010-07-07 | 2013-04-24 | 罗伯特·博世有限公司 | System and method for controlling the engine of a vehicle |
| CN103760774A (en) * | 2013-12-26 | 2014-04-30 | 西南交通大学 | Simulation assessment system for reasonability of traffic sign design and set position |
| CN104851307A (en) * | 2014-02-18 | 2015-08-19 | 中国移动通信集团公司 | Road signboard setting rationality determination method, device and system |
| KR20170033716A (en) * | 2015-09-17 | 2017-03-27 | 계명대학교 산학협력단 | Apparatus and method about real-time speed limit sign detection and recognition using spatial pyramid feature |
-
2017
- 2017-07-18 CN CN201710587388.3A patent/CN107545754B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103069153A (en) * | 2010-07-07 | 2013-04-24 | 罗伯特·博世有限公司 | System and method for controlling the engine of a vehicle |
| DE102011109387A1 (en) * | 2011-08-04 | 2013-02-07 | Conti Temic Microelectronic Gmbh | Method for detecting traffic signs |
| CN103760774A (en) * | 2013-12-26 | 2014-04-30 | 西南交通大学 | Simulation assessment system for reasonability of traffic sign design and set position |
| CN104851307A (en) * | 2014-02-18 | 2015-08-19 | 中国移动通信集团公司 | Road signboard setting rationality determination method, device and system |
| KR20170033716A (en) * | 2015-09-17 | 2017-03-27 | 계명대학교 산학협력단 | Apparatus and method about real-time speed limit sign detection and recognition using spatial pyramid feature |
Non-Patent Citations (4)
| Title |
|---|
| 基于认知心理学的城市道路交通标志动静态视认研究;李志;《CNKI优秀硕士学位论文全文库》;20180715;全文 * |
| 基于驾驶负荷的交通标志信息量度研究进展分析;付强; 吴超仲; 吕能超;《第七届中国智能交通年会优秀论文集》;20120926;80-88 * |
| 道路交通标志信息过载阈值的计算;樊大可; 王建军; 常振文; 吴海刚;《长安大学学报(自然科学版)》;20091115(第6期);82-87 * |
| 道路交通标志信息过载阈值研究;王建军; 王娟; 吴海刚;《公路》;20090425(第4期);174-180 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107545754A (en) | 2018-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3951713A1 (en) | Method and apparatus for training image semantic segmentation network, device, and storage medium | |
| EP3796112B1 (en) | Virtual vehicle control method, model training method, control device and storage medium | |
| KR102114357B1 (en) | Method and device for constructing a table including information on a pooling type and testing method and testing device using the same | |
| DE112019005750T5 (en) | Learning to generate synthetic data sets for training neural networks | |
| US20230409903A1 (en) | Multi-agent simulations | |
| DE102013222322B4 (en) | Method and device for providing augmented reality | |
| CN105930771A (en) | Driving behavior grading method and device | |
| CN107862270A (en) | Face classification device training method, method for detecting human face and device, electronic equipment | |
| JP2017117406A5 (en) | ||
| Jurecki et al. | Driver model for the analysis of pre-accident situations | |
| CN109871829B (en) | Detection model training method and device based on deep learning | |
| CN104463855A (en) | Significant region detection method based on combination of frequency domain and spatial domain | |
| CN107545754B (en) | Method and device for acquiring traffic sign information threshold | |
| CN106022297A (en) | Gesture identification method and gesture identification device | |
| CN110582783A (en) | Training device, image recognition device, training method, and program | |
| DE102019216206A1 (en) | Device and method for determining a U-turn strategy of an autonomous vehicle | |
| DE112016006921T5 (en) | Estimation of human orientation in images using depth information | |
| DE112020002874T5 (en) | Scene attribute annotation of complex street typographies | |
| US10417358B2 (en) | Method and apparatus of obtaining feature information of simulated agents | |
| DE102013203300A1 (en) | Image processing apparatus for use in vehicle control system for detecting pedestrian captured by camera, has object region estimating unit estimating object region in which object is present on basis of partial regions | |
| JP5673373B2 (en) | Traffic simulation device and traffic simulation program | |
| CN106228233A (en) | The construction method of a kind of intelligent body for automatic driving vehicle test and device | |
| CN113268057A (en) | Obstacle avoidance processing method and device for unmanned vehicle | |
| Gao et al. | Which factors are most relevant to drivers’ overtaking choices at two-lane highways: A comparative analysis between questionnaire surveys and driving simulation | |
| DE102019220574A1 (en) | Method and device for testing a machine |
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 |