CN115984826B - Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle - Google Patents

Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle Download PDF

Info

Publication number
CN115984826B
CN115984826B CN202310186921.0A CN202310186921A CN115984826B CN 115984826 B CN115984826 B CN 115984826B CN 202310186921 A CN202310186921 A CN 202310186921A CN 115984826 B CN115984826 B CN 115984826B
Authority
CN
China
Prior art keywords
lamp
color
single lamp
lamps
traffic signal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310186921.0A
Other languages
Chinese (zh)
Other versions
CN115984826A (en
Inventor
葛志朋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Weilai Zhijia Technology Co Ltd
Original Assignee
Anhui Weilai Zhijia Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Weilai Zhijia Technology Co Ltd filed Critical Anhui Weilai Zhijia Technology Co Ltd
Priority to CN202310186921.0A priority Critical patent/CN115984826B/en
Publication of CN115984826A publication Critical patent/CN115984826A/en
Application granted granted Critical
Publication of CN115984826B publication Critical patent/CN115984826B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02BCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40Control techniques providing energy savings, e.g. smart controller or presence detection

Landscapes

  • Traffic Control Systems (AREA)

Abstract

The invention relates to the technical field of automatic driving, in particular to a traffic signal lamp sensing method, a vehicle control method, equipment, a medium and a vehicle, and aims to solve the problem of improving the color sensing accuracy of the traffic signal lamp. The method comprises the steps of performing sensing identification on a current image frame of a traffic signal lamp to obtain the lamp cap shape, the color and the 3D position of each single lamp currently lighted in the traffic signal lamp, grouping the single lamps according to the 3D positions of the single lamps to form a single lamp group of the single lamps positioned at the same intersection, obtaining the single lamps with the same lamp cap shape in each single lamp group, and correcting the color of each single lamp in the single lamp group with the same lamp cap shape to the same color. By the method, the single lamp with the same lamp cap shape at the same intersection can be prevented from being identified with different colors, so that the driving safety of the vehicle is ensured.

Description

Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle
Technical Field
The invention relates to the technical field of automatic driving, in particular to a traffic signal lamp sensing method, a vehicle control method, equipment, a medium and a vehicle.
Background
Traffic lights are typically composed of red, green, yellow, red indicating no traffic, green indicating no traffic, and yellow indicating warning. When the automatic driving control is carried out on the vehicle, the color of the traffic signal lamp in the road is required to be accurately perceived, the vehicle can be safely and reliably driven and controlled according to the color of the traffic signal lamp, and the driving safety of the vehicle is ensured.
There may be multiple intersections in the same intersection area of a road (e.g., intersection area), each intersection being provided with a separate traffic light and each traffic light may include multiple individual lights. At present, when the conventional traffic signal lamp sensing method is used for sensing and identifying the image frames of the traffic signal lamp, single lamps positioned at different intersections can be easily and mistakenly identified to be positioned at the same intersection, and the color displayed by each single lamp cannot be accurately identified.
Accordingly, there is a need in the art for a new solution to the above-mentioned problems.
Disclosure of Invention
The present invention has been made to overcome the above-mentioned drawbacks, and provides a traffic light sensing method, a vehicle control method, a device, a medium, and a vehicle that solve or at least partially solve the technical problem of how to accurately sense the color of a traffic light.
In a first aspect, a method for sensing a traffic signal is provided, comprising:
performing perception recognition on a current image frame of a traffic signal lamp to acquire the lamp cap shape, color and 3D position of each single lamp currently lighted in the traffic signal lamp;
grouping the single lamps according to the 3D positions of the single lamps so as to form a single lamp group of the single lamps positioned at the same intersection;
obtaining single lamps with the same lamp cap shape in each single lamp group;
and correcting the color of each single lamp in the single lamps with the same shape in each single lamp group to be the same color.
In one technical scheme of the sensing method of the traffic signal lamp, the step of grouping the single lamps according to the 3D positions of the single lamps so as to form a single lamp group by the single lamps at the same intersection specifically includes:
traversing the 3D position of each single lamp, and grouping the single lamps;
acquiring a plurality of single lamp groups formed after traversing the 3D position of each single lamp;
and carrying out combination treatment on the plurality of single lamp groups in pairs so as to form a final single lamp group by the single lamps positioned at the same intersection.
In one technical scheme of the traffic light perception method, the step of traversing the 3D position of each single light and grouping the single lights specifically includes:
Judging whether the single lamp is added into the formed single lamp group according to the 3D position of the single lamp and the center position of the formed single lamp group;
if yes, adding the single lamp into the formed single lamp group and updating the central position of the formed single lamp group;
if not, a new single lamp group is created, the single lamp is added to the new single lamp group, and the central position of the new single lamp group is updated.
In one technical scheme of the sensing method of the traffic signal lamp, the step of combining the plurality of single lamp groups in pairs so as to form the single lamps at the same intersection into a final single lamp group specifically comprises the following steps:
according to the preset arrangement sequence of the single lamp group numbers, carrying out combination treatment on the plurality of single lamp groups in pairs so as to obtain preliminarily combined single lamp groups;
and carrying out combination treatment on the preliminarily combined single lamp groups two by two again according to the arrangement sequence of the preset single lamp group numbers until the number of the single lamp groups is not changed any more so as to obtain the final single lamp group.
In one technical scheme of the sensing method of the traffic signal lamp, the step of performing the merging process on the plurality of single lamp groups to form the final single lamp group by the single lamps located at the same intersection further comprises the following steps of performing the merging process on the two single lamp groups:
Acquiring the center distance between the center positions of the two single lamp groups;
respectively acquiring the radiuses of the two single lamp groups;
judging whether the center distance is smaller than the maximum value of the radiuses;
if yes, combining the two single lamp groups;
if not, the two single lamp groups are not combined.
In one technical scheme of the sensing method of the traffic signal lamp, the method further comprises the step of updating the radius of the single lamp group by the following steps:
obtaining the maximum distance between a single lamp in the single lamp group and the central position of the single lamp group;
and updating the radius of the single lamp group according to the maximum distance.
In one technical scheme of the above traffic signal lamp sensing method, the step of correcting the color of each single lamp in the shape single lamps in each single lamp group to the same color comprises the following steps:
aiming at each single lamp in the single lamps with the same shape, obtaining the confidence that the single lamps respectively display each different color;
selecting the color with the highest confidence from the confidence that all the single lamps in the single lamps with the same shape respectively display each different color;
and correcting the color of each single lamp in the single lamps with the same shape into the color with the highest confidence.
In one technical scheme of the sensing method of the traffic signal lamp, the step of selecting the color with the highest confidence level from the confidence levels of all the single lamps in the same shape, which respectively display each different color, specifically includes:
for each color, respectively obtaining the confidence coefficient of each single lamp for displaying the color and summing the confidence coefficient to obtain the summed confidence coefficient of the color;
and selecting the color with the highest confidence according to the added confidence of each color.
In one technical scheme of the perception method of the traffic signal lamp, the step of selecting the color with the highest confidence degree according to the summation confidence degree of each color comprises the following steps:
normalizing the summed confidence coefficient of each color to obtain normalized confidence coefficient of each color;
and selecting the color with the highest confidence according to the normalized confidence of each color.
In one technical solution of the above traffic signal perception method, after the step of correcting the color of each single lamp in the shape single lamps in each single lamp group to the same color, the method further includes tracking and smoothing the color of the single lamp obtained by the current image frame by:
Acquiring a plurality of continuous historical image frames positioned before a current image frame;
respectively acquiring the color of the single lamp obtained through each historical image frame;
voting the single lamp colors obtained through the current image frame and the historical image frame, and selecting one color with the largest quantity as the final color of the single lamp obtained through the current image frame.
In a second aspect, there is provided a method of sensing a traffic signal, comprising:
the method for sensing the traffic signal lamp provided in the first aspect is adopted to obtain the lamp cap shape, the color and the single lamp group of the single lamp which is currently lighted in the traffic signal lamp;
determining the intersection where the single lamp is located according to the single lamp group where the single lamp is located;
determining the traffic indication direction of a virtual lamp corresponding to a traffic signal lamp at an intersection according to the lamp cap shape of the single lamp and the intersection;
and determining the color of the traffic indication direction according to the color of the single lamp so as to form a virtual lamp.
In a third aspect, there is provided a vehicle control method, the method comprising:
acquiring an image frame of a traffic signal lamp positioned in the forward direction of a vehicle;
adopting the perception method of the traffic signal lamp provided in the second aspect, and obtaining a virtual lamp corresponding to the traffic signal lamp according to the image frame;
Determining an intersection where the virtual lamp is located;
and according to the color of each traffic indication direction of the virtual lamp, carrying out automatic driving control on the vehicle at the intersection.
In a fourth aspect, a computer device is provided, which comprises a processor and a storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the method according to any one of the above-mentioned methods of perception of traffic signals or methods of vehicle control.
In a fifth aspect, a computer readable storage medium is provided, in which a plurality of program codes are stored, the program codes being adapted to be loaded and run by a processor to perform the method according to any one of the above-mentioned methods for sensing traffic lights or methods for controlling vehicles.
In a sixth aspect, a vehicle is provided, which includes the computer device according to the technical solution of the above computer device.
The technical scheme provided by the invention has at least one or more of the following beneficial effects:
in the technical scheme of implementing the perception method of the traffic signal lamp, firstly, the current image frame of the traffic signal lamp can be subjected to perception recognition to obtain the lamp cap shape, the color and the 3D position of each single lamp currently lighted in the traffic signal lamp, then, the single lamps are grouped according to the 3D positions of the single lamps to form a single lamp group of the single lamps positioned at the same intersection, the single lamps with the same lamp cap shape in each single lamp group are obtained, and the color of each single lamp in the single lamp group with the same shape is corrected to be the same color. The intersection where the single lamp is located can be accurately determined through the method, meanwhile, the single lamp with the same lamp cap shape at the same intersection can be prevented from being identified into different colors, and the driving safety of a vehicle is ensured.
In the technical scheme for implementing the perception method of the traffic signal lamp provided by the invention, firstly, the perception method of the traffic signal lamp can be adopted to obtain the lamp cap shape, the color and the single lamp group of the single lamp which is currently lighted in the traffic signal lamp, the intersection where the single lamp is positioned is determined according to the single lamp group where the single lamp is positioned, the traffic indication direction of the virtual lamp corresponding to the traffic signal lamp at the intersection is determined according to the lamp cap shape and the intersection where the single lamp is positioned, and the color of the traffic indication direction is determined according to the color of the single lamp, so as to form the virtual lamp. By the method, the virtual lamp formed by the traffic indication direction and the color thereof can be uniformly expressed for any type of traffic signal lamp, and the color of the traffic indication direction only needs to be inquired from the virtual lamp when the vehicle is controlled.
In the technical scheme of implementing the vehicle control method provided by the invention, after the image frame of the traffic signal lamp positioned in the forward direction of the vehicle is acquired, the perception method of the traffic signal lamp can be adopted, the virtual lamp corresponding to the traffic signal lamp is acquired according to the image frame, the intersection where the virtual lamp is positioned is determined, and the vehicle is automatically driven and controlled at the intersection according to the color of each traffic indication direction of the virtual lamp. By the method, the state of each intersection traffic signal lamp can be accurately obtained under the condition of not depending on a high-precision map, so that safe and reliable automatic driving control can be carried out on the vehicle, and the driving safety of the vehicle is improved.
Drawings
The present disclosure will become more readily understood with reference to the accompanying drawings. As will be readily appreciated by those skilled in the art: the drawings are for illustrative purposes only and are not intended to limit the scope of the present invention. Wherein:
FIG. 1 is a flow chart of the main steps of a method of perception of a traffic signal according to one embodiment of the invention;
FIG. 2 is a flow chart of the main steps of a single lamp grouping method according to one embodiment of the invention;
FIG. 3 is a flow chart illustrating the main steps of a method for sensing a traffic signal according to another embodiment of the present invention;
FIG. 4 is a flow chart of the main steps of a vehicle control method according to one embodiment of the invention;
fig. 5 is a main structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
Some embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
In the description of the present invention, a "processor" may include hardware, software, or a combination of both. The processor may be a central processor, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and/or signal processing functions. The processor may be implemented in software, hardware, or a combination of both. The computer readable storage medium includes any suitable medium that can store program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, and the like.
An embodiment of a sensing method of the traffic signal lamp of the present invention is described below.
Referring to fig. 1, fig. 1 is a schematic flow chart of main steps of a sensing method of a traffic signal according to an embodiment of the present invention. As shown in fig. 1, the sensing method of the traffic signal lamp in the embodiment of the present invention mainly includes the following steps S101 to S104.
Step S101: and performing perception recognition on the current image frame of the traffic signal lamp to acquire the lamp cap shape, color and 3D position of each single lamp currently lighted in the traffic signal lamp.
The image frames may be obtained by image acquisition of traffic lights by visual sensors (such as cameras) on the vehicle. After the image frame is obtained, the image frame can be input into a preset perception model, and the information such as the lamp cap shape, the color and the like of each single lamp in the image frame can be identified through the perception model. The perception model can be constructed by adopting a conventional method in the technical field of neural networks, and the embodiment of the invention does not limit the specific structure and the training method of the perception model as long as the perception model has the capability of identifying the information from the image frames. It should be noted that, in the present invention, the operations related to the vehicle, such as capturing the image frames through the visual sensor on the vehicle, and performing the automatic driving control on the vehicle, are all performed after the user or each party is fully authorized. That is, the vehicle in the present invention is an authorized vehicle. In some embodiments, whether the authorization information is received may be detected by the vehicle machine or the background server, and if the authorization information is received, the current vehicle is indicated to be an authorized vehicle, otherwise, the current vehicle is an unauthorized vehicle. The authorization information may be sent by a terminal device including, but not limited to, a mobile phone, a tablet computer, a smart watch, and the like.
The lighted single lamp is a single lamp displaying a preset color, and the preset color is a color capable of traffic guidance, for example, the preset color can comprise green, red and yellow, the green indicates that the traffic is allowed, the red indicates that the traffic is forbidden, and the yellow indicates that the traffic is warned. The color of the single lamp displayed in one or more image frames can be obtained by performing perception identification on the image frames, and if the color of the single lamp displayed in one or more image frames is a preset color, the single lamp can be judged to be in a lighting state. In addition, the color of the single lamp may include, in addition to the above-described preset color capable of traffic guidance, a color indicating that traffic guidance is not performed, for example, black may be displayed when the single lamp is turned off.
The lamp cap shape of the single lamp includes, but is not limited to, a round cake, a straight arrow, a left turn arrow, a right turn arrow, a turning arrow, and the like.
The 3D position of the single lamp refers to the position of the single lamp under a preset three-dimensional coordinate system, which may be the body coordinate system of the vehicle in one embodiment, for example. A method of obtaining a 3D position by perceptual recognition will be briefly described. Specifically, after the image frame of the traffic signal lamp is perceived, the 2D position of the single lamp under the image coordinate system can be obtained, and then the 2D position is converted from the image coordinate system to a preset three-dimensional coordinate system by a coordinate system conversion method, so that the 3D position of the single lamp can be obtained. The 3D position of the single lamp may be expressed as (IDi, xi, yi, zi), IDi representing the ID of the i-th single lamp, xi, yi and zi representing the coordinates of the i-th single lamp in the three-dimensional coordinate system X, Y and Z-axis, respectively.
Step S102: the single lamps are grouped according to the 3D positions of the single lamps so as to form a single lamp group by the single lamps positioned at the same intersection.
The single lamps at the same intersection are relatively close, while the single lamps at different intersections are relatively far, so that the single lamps can be grouped by utilizing the principle, and the single lamps at the same intersection are grouped in the same single lamp group.
Step S103: and obtaining the single lamps with the same lamp cap shape in each single lamp group. For example, a traffic signal lamp comprises three lit single lamps, one single lamp having a lamp cap shape of a left turn arrow and the other two single lamps having a lamp cap shape of a pie, and then the traffic signal lamp comprises a group of single lamps having the shape of a pie, and the group of single lamps having the shape of a single lamp comprises two single lamps.
Step S104: the color of each single lamp in the single lamps with the same shape in each single lamp group is corrected to the same color.
Different lamp cap shapes can represent different traffic indication directions, and a plurality of single lamps with the same lamp cap shape can exist in the traffic signal lamp, and when the single lamps are subjected to color sensing identification in the step S101, the single lamps can be identified into different colors due to reflection of objects, poor ambient light and the like, so that the fact that the single lamps with the same lamp cap shape are subjected to color correction can avoid different colors in the same traffic indication direction, and the safe running of a vehicle is influenced.
Based on the method described in the steps S101 to S104, the intersection where the single lamp is located can be accurately determined, and meanwhile, the single lamp with the same lamp cap shape at the same intersection can be prevented from being identified with different colors, so that the driving safety of the vehicle is ensured.
The following further describes the steps S102 to S104.
1. Step S102 will be described.
In order to divide all the lighting single lamps located in the same intersection into the same single lamp group as far as possible, the single lamps may be grouped first and then combined. Specifically, referring to fig. 2, in the embodiment of the present invention, the single lamps may be grouped by the following steps S1021 to S1023 to form a single lamp group from the single lamps located at the same intersection.
Step S1021: the 3D position of each individual lamp is traversed, grouping the individual lamps. The grouped individual lamps may be expressed as { (IDi, gi) }, IDi indicating the ID of the i-th individual lamp, gi indicating the number of the individual lamp group in which the i-th individual lamp is located.
In the embodiment of the invention, a conventional clustering algorithm in the technical field of data processing can be adopted, and the single lamps are clustered according to the 3D position of each lighted single lamp to form a plurality of cluster clusters, wherein one cluster is a single lamp group. In some preferred embodiments, in order to ensure the accuracy of grouping, the number of clusters may not be limited, i.e., the number of clusters is not set.
Step S1022: a plurality of single lamp groups formed after traversing the 3D position of each single lamp are acquired.
Step S1023: and carrying out combination treatment on the plurality of single lamp groups in pairs so as to form the single lamps positioned at the same intersection into a final single lamp group.
Specifically, if the single lamps in the two single lamp groups may be located at the same intersection, the two single lamp groups are combined; otherwise, no merging is performed.
In a preferred embodiment, the single lamp groups can be combined according to the distance between the central positions of the single lamp groups and the radius of the single lamp groups so as to ensure the accuracy of combination. Specifically, the center distance between the center positions of the two single lamp groups can be obtained, the radiuses of the two single lamp groups are respectively obtained, and then whether the center distance is smaller than the maximum value of the two radiuses is judged; if the center distance is smaller than the maximum value, the two single lamp groups are combined, otherwise, the combination is not performed.
In order to ensure the accuracy of the combination of the single lamps, the radius of the single lamp group is dynamically updated according to the single lamps newly added to the single lamp group in the process of grouping the single lamps in step S1021. In particular, the maximum distance between a single lamp in a single lamp set and the center position of the single lamp set may be obtained, and then the radius of the single lamp set may be updated according to the maximum distance. For example, the maximum distance may be set as the radius of the single lamp set, or the maximum distance may be adjusted numerically, and the adjusted distance may be set as the radius of the single lamp set.
Based on the methods described in steps S1021 to S1023, the accuracy of the single lamp set can be improved, and the correction of single lamps with the same shape at different intersections to the same color can be avoided.
Step S1021 and step S1023 are further described below.
Step S1021 is described.
In the embodiment of the invention, the single lamps can be grouped according to the 3D positions of the single lamps and the central position of the single lamp group. Specifically, the individual lamps may be grouped by the following steps 11 to 13.
Step 11: and judging whether the single lamp is added into the formed single lamp group according to the 3D position of the single lamp and the center position of the formed single lamp group. If so, go to step 12; if not, go to step 13.
In the embodiment of the invention, the interval between the 3D position of the single lamp and the central position of the single lamp group can be obtained, and whether the single lamp is added into the single group is judged according to the interval. For example, the spacing may be compared to a preset spacing threshold, and if the spacing is less than the spacing threshold, then the individual lamps are added to the individual lamp group, otherwise the individual lamps are not added to the individual lamp group.
Step 12: adding the single lamp into the formed single lamp group and updating the center position of the formed single lamp group.
Step 13: creating a new single light group, adding a single light to the new single light group, and updating the center position of the new single light group. This newly created single light group will be judged as a "formed single light group" group when the next single light is grouped.
When traversing the 3D position of the first single lamp, a single lamp group can be directly created according to the 3D position of the first single lamp, and the initialization of single lamp groups is realized. That is, step 13 is directly performed for the first single lamp, and grouping is performed for the subsequent single lamps by the methods described in steps 11 to 13.
Based on the methods described in the above steps 11 to 13, grouping of the single lamps can be quickly and accurately completed by using the central position of the single lamp group, and meanwhile, the accuracy and efficiency of grouping are improved.
(II) step S1023 will be described.
In the embodiment of the invention, one-round merging processing can be performed on the single lamp group, and multi-round merging processing can also be performed. When one round of merging processing is carried out, merging processing can be respectively carried out on every two single lamp groups until merging processing on all the single lamp groups is completed.
The number of the rounds of the combination treatment can be preset when the multi-round combination treatment is carried out, and then the multi-round combination treatment is carried out on the single lamp group according to the number of the rounds. The single lamp group obtained in step S1022 is subjected to the first-round merging process, and the single lamp group obtained after the previous-round merging process is subjected to the merging process when the first-round merging process is not performed.
The number of the combination processing may not be set when the multi-round combination processing is performed, and at this time, each round of combination processing may be sequentially performed, and the combination processing may be stopped when the number of the single lamp groups is not changed. In a preferred embodiment, the single lamp group may be subjected to the merging process through the following steps 21 to 22 to ensure the merging accuracy.
Step 21: and carrying out combination treatment on the plurality of single lamp groups in pairs according to the preset arrangement sequence of the single lamp group numbers so as to obtain the preliminarily combined single lamp groups. This step is round 1 merging.
For example, the single lamp groups can be combined in pairs according to the sequence of the serial numbers of the single lamp groups from small to large, and the 1 st round of combination is completed to obtain the preliminarily combined single lamp groups. The arrangement sequence of the single lamp group numbers can be flexibly set by a person skilled in the art according to actual requirements, and the embodiment of the invention is not particularly limited.
Step 22: and carrying out combination treatment on the preliminarily combined single lamp groups again in pairs according to the arrangement sequence of the preset single lamp group numbers until the number of the single lamp groups is not changed any more so as to obtain the final single lamp group.
For example, the primary merging single lamp groups can be merged again in pairs according to the sequence of the serial numbers of the single lamp groups from small to large, so that the 2 nd round of merging is completed. If the number of the single lamp groups obtained by combining the 2 nd round with the 1 st round is the same, the combination is not carried out any more, and the result of the 2 nd round combination is the final single lamp group; if the number of the single lamp groups after the 2 nd round of combination is smaller than the number of the 1 st round of combination, the single lamp groups after the 2 nd round of combination are continuously combined in pairs according to the sequence of the serial numbers of the single lamp groups from small to large until the number of the single lamp groups is not changed any more.
To ensure accuracy of the single lamp set merge, the radius of the single lamp set may be dynamically updated according to the single lamps in the single lamp set after each round of merge of the single lamp set. In particular, the maximum distance between a single lamp in a single lamp set and the center position of the single lamp set may be obtained, and then the radius of the single lamp set may be updated according to the maximum distance. For example, the maximum distance may be set as the radius of the single lamp set, or the maximum distance may be adjusted numerically, and the adjusted distance may be set as the radius of the single lamp set.
Based on the methods described in the above steps 21 to 22, the accuracy of single lamp grouping can be improved, and the accuracy of single lamp grouping can be further improved.
2. Step S103 will be described.
In order to improve the accuracy of color correction, the confidence coefficient of each different color can be displayed by utilizing the single lamp to be lightened, and one color with the highest confidence coefficient is selected for correction. Specifically, in some embodiments, the color of each of the lighting single lamps in the shape single lamp may be corrected by the following steps S1031 to S1033.
Step S1031: and aiming at each single lamp in the single lamps with the same shape, acquiring the confidence that the single lamps respectively display each different color.
The confidence level of the color indicates the confidence level of the color, and when the color of the single lamp is perceptively identified in step S101, the confidence level that the single lamp displays each different color can be obtained. For example, if a perception model constructed by using a neural network is used for color perception recognition, the perception model may output the probability that a single lamp displays each color, then the color with the highest probability is used as the color of the single lamp, and the probability of each color may be used as the confidence of each color.
Step S1032: and selecting the color with the highest confidence from the confidence degrees of all the single lamps in the same shape and respectively displaying each different color.
For example, the shape single lamp includes a single lamp 1 and a single lamp 2, and the kinds of colors include green and red. The confidence levels of the green and red of the single lamp 1 are 0.9 and 0.1, respectively, and the confidence levels of the green and red of the single lamp 2 are 0.4 and 0.6,0.9, respectively, and are maximum values, so green is selected.
Step S1033: the color of each single lamp in the single lamps with the same shape is corrected to be the color with the highest confidence. With continued reference to the above example, the color of the single lamp 2 is corrected to green.
Based on the methods described in the steps S1031 to S1033, the accurate color of the single lamp with the same shape can be obtained by using the confidence coefficient of the color, and the accuracy of color correction is ensured.
Step S1032 is further described below.
In order to conveniently and rapidly select the color with the highest confidence from the confidence degrees of different colors displayed by all the single lamps, the sum of the confidence degrees of each color can be calculated first, and then the color can be selected according to the sum of the confidence degrees. Specifically, the color with the highest confidence level can be selected by the following steps 31 to 32.
Step 31: and respectively acquiring the confidence coefficient of each single lamp display color aiming at each color, and summing the confidence coefficient to acquire the summed confidence coefficient of the color.
Step 32: and selecting the color with the highest confidence coefficient according to the summation confidence coefficient of each color, namely selecting the color with the highest summation confidence coefficient.
Taking the example that preset colors capable of traffic guidance include green, red, and yellow, the single lamps may be expressed as { (IDi, ci, pri, pgi, pyi) }, IDi represents an ID of the ith single lamp, ci represents a color displayed when the ith single lamp is currently lit, pri, pgi, pyi represents a confidence that the ith single lamp displays red, green, and yellow, respectively, a sum confidence of red, green, and yellow is expressed as Qri, qgi, qyi, and a color with the highest sum confidence is csi=argmax (Qri, qgi, qyi), and the single lamp may be expressed as { IDi, csi }, after color correction is completed according to the color.
Further, in some embodiments, in order to facilitate comparing the summed confidence levels of different colors, the highest confidence level is selected, normalization processing may be performed on the summed confidence levels of each color to obtain a normalized confidence level of each color, and then, a color with the highest confidence level is selected according to the normalized confidence level of each color. It should be noted that, in the embodiment of the present invention, a conventional data normalization method in the field of mathematical technology may be used to normalize the correction confidence coefficient of each different color, which is not specifically limited in the embodiment of the present invention.
Based on the steps 31 to 32, the efficiency and accuracy of selecting the color with the highest confidence coefficient can be improved, so that the color correction of the single lamp with the same shape can be rapidly and accurately completed.
3. Step S104 will be described.
After the color of each single lamp in the single lamp group with the same shape is corrected to the same color, the color of each single lamp in the single lamp group can be tracked and smoothed through the following steps S1041 to S1043, so that the color accuracy of each single lamp is improved.
Step S1041: a plurality of consecutive historical image frames preceding the current image frame are acquired.
In order to conveniently and accurately acquire the historical image frames, a sliding window with a preset size can be set first, the image frames are selected in a sliding mode according to the sliding window according to the sequence of the image frame acquisition time from front to back, the image frames falling into the sliding window are acquired, and a plurality of continuous historical image frames positioned in front of the current image frame are selected from the image frames. The size of the sliding window can be flexibly set by a person skilled in the art according to actual requirements, and the embodiment of the invention is not particularly limited. For example, the size of the sliding window may be 10 consecutive image frame acquisition instants.
Step S1042: the color of the individual lamp obtained by each historical image frame is acquired separately. The method of obtaining the single lamp color through the historical image frame is the same as the method adopted by the current image frame, namely the related method described in the embodiment of the method.
Step S1043: voting is carried out on the colors of the single lamps obtained through the current image frame and the historical image frame, and one color with the largest number is selected as the final color of the single lamps obtained through the current image frame.
For example, for a single lamp, the color obtained for the current image frame is green, and the color obtained for 5 consecutive historical image frames before the current image frame is red, then the color obtained for the current image frame is corrected to red.
Based on the methods described in the above steps S1041 to S1043, the problem of inaccurate color of the single lamp due to interference or the like when capturing the image frame can be avoided.
An embodiment of the sensing method of the traffic signal lamp shown in fig. 3 is described below. As shown in fig. 3, the sensing method of the traffic signal lamp in the embodiment of the present invention mainly includes the following steps S201 to S204.
Step S201: the method comprises the steps of obtaining the shape, the color and the single lamp group of a single lamp currently lighted in the traffic signal lamp by adopting a perception method of the traffic signal lamp.
In this step, the lamp head shape, color and single lamp group of the single lamp can be obtained by adopting the sensing method embodiment shown in the foregoing fig. 1 to 2. I.e. the color of the individual lamps in this step is corrected and/or smoothed by the method embodiments described above, and is a more accurate color.
Step S202: and determining the intersection where the single lamp is positioned according to the single lamp group where the single lamp is positioned.
Step S203: and determining the traffic indication direction of the virtual lamp corresponding to the traffic signal lamp of the intersection according to the shape of the lamp cap of the single lamp and the intersection where the single lamp is located.
Different lamp cap shapes can represent different traffic indication directions, so that the traffic indication directions of the virtual lamps corresponding to the traffic signal lamps can be determined according to the lamp cap shapes of all the single lamps in the traffic signal lamps. For example, the traffic signal lamp comprises three single lamps, and the lamp caps of the three single lamps are round cakes, so that the traffic indication direction of the virtual lamp corresponding to the traffic signal lamp comprises straight, left turn and turning around.
It should be noted that, a person skilled in the art may flexibly set the traffic indication directions represented by different lamp cap shapes according to actual requirements, and the embodiment of the present invention is not limited specifically. For example, if according to the historical traffic rules, the round cake may represent two directions of straight and left turn, but according to the latest traffic rules, the round cake may represent three directions of straight, left turn and turn around, and at this time, the traffic indication directions represented by the round cake may be adjusted to be straight, left turn and turn around.
Step S204: and determining the color of the traffic indication direction according to the color of the single lamp to form a virtual lamp.
Based on the methods described in the above steps S201 to S204, for any position and type of traffic signals, these traffic signals can be uniformly expressed as virtual lamps formed by the traffic indication directions and their color fusion, i.e. the virtual lamps are abstracted from the traffic signals existing in the physical world, and are not the traffic signals visually existing in the physical world. When the vehicle is controlled, the color of the corresponding traffic indication direction is only required to be inquired from the virtual lamp, and the automatic driving control can be carried out on the corresponding traffic indication direction according to the color. In addition, the method does not need to mark the information such as the position, the type and the like of the traffic signal lamp on the high-precision map in advance, removes the dependence on the high-precision map, reduces the marking cost of the high-precision map, and solves the problems that the traffic signal lamp can only be perceived and identified in the area covered by the high-precision map in the prior art, and the traffic signal lamp cannot be accurately perceived and identified when the information marked on the high-precision map is inconsistent with the actual information.
The following describes an embodiment of a vehicle control method provided by the present invention.
Referring to fig. 4, fig. 4 is a flowchart illustrating main steps of a vehicle control method according to an embodiment of the present invention. As shown in fig. 4, the vehicle control method in the embodiment of the invention mainly includes the following steps S301 to S304.
Step S301: an image frame of a traffic light located in a forward direction of the vehicle is acquired.
Specifically, image frames of traffic signals may be acquired using a vision sensor disposed on the vehicle with a field of view in a forward direction of the vehicle.
Step S302: and obtaining a virtual lamp corresponding to the traffic signal lamp according to the image frame by adopting a perception method of the traffic signal lamp.
The method for sensing the traffic signal lamp in the step is the method for sensing the traffic signal lamp described in the embodiment of the method.
Step S303: and determining the intersection where the virtual lamp is located.
Step S304: and according to the color of each traffic indication direction of the virtual lamp, automatically driving the vehicle at the intersection.
Specifically, according to the color of the traffic indication direction, it can be determined whether each traffic indication direction is allowed to pass in the intersection, and the automatic driving control is performed on the vehicle according to the determination result. For example, the vehicle travels on a left-hand lane in the road and the left-hand lane is a mixed lane of left-hand and straight-hand, while the driving purpose of the vehicle is to left-hand at this intersection. At this time, the color of the left turn direction in the virtual lamp can be obtained, if the color is red, the vehicle is controlled to stop waiting before stopping the line, and if the color is green, the vehicle is controlled to turn left, and the vehicle passes through the intersection.
Based on the method described in the steps S301 to S304, accurate information such as the position and the color of the traffic signal lamp can be obtained without using a high-precision map, and the vehicle can be safely and reliably automatically driven and controlled, so that the driving safety of the vehicle is improved.
It should be noted that, although the foregoing embodiments describe the steps in a specific order, it will be understood by those skilled in the art that, in order to achieve the effects of the present invention, the steps are not necessarily performed in such an order, and may be performed simultaneously (in parallel) or in other orders, and those solutions after these adjustments belong to equivalent solutions to those described in the present invention, and therefore will also fall within the scope of the present invention.
It will be appreciated by those skilled in the art that the present invention may implement all or part of the above-described methods according to the above-described embodiments, or may be implemented by means of a computer program for instructing relevant hardware, where the computer program may be stored in a computer readable storage medium, and where the computer program may implement the steps of the above-described embodiments of the method when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable storage medium may include: any entity or device, medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier wave signals, telecommunications signals, software distribution media, and the like capable of carrying the computer program code. It should be noted that the computer readable storage medium may include content that is subject to appropriate increases and decreases as required by jurisdictions and by jurisdictions in which such computer readable storage medium does not include electrical carrier signals and telecommunications signals.
Further, the invention also provides computer equipment.
Referring to fig. 5, fig. 5 is a schematic diagram showing the main structure of an embodiment of a computer device according to the present invention. As shown in fig. 5, the computer device in the embodiment of the present invention mainly includes a storage device that may be configured to store a program for executing the traffic signal sensing method or the vehicle control method of the above-described method embodiment, and a processor that may be configured to execute the program in the storage device, including, but not limited to, the program for executing the traffic signal sensing method or the vehicle control method of the above-described method embodiment. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention.
The computer device in the embodiments of the present invention may be a control apparatus device formed by including various electronic devices. In some possible implementations, a computer device may include a plurality of storage devices and a plurality of processors. And the program for executing the traffic light sensing method or the vehicle control method of the above method embodiment may be divided into a plurality of sub-programs, and each sub-program may be loaded and executed by the processor to execute different steps of the traffic light sensing method or the vehicle control method of the above method embodiment, respectively. Specifically, each of the subroutines may be respectively stored in different storage devices, and each of the processors may be configured to execute the programs in one or more storage devices to jointly implement the traffic signal sensing method or the vehicle control method of the above method embodiment, that is, each of the processors respectively executes different steps of the traffic signal sensing method or the vehicle control method of the above method embodiment to jointly implement the traffic signal sensing method or the vehicle control method of the above method embodiment.
The plurality of processors may be processors disposed on the same device, for example, the computer device may be a high-performance device composed of a plurality of processors, and the plurality of processors may be processors configured on the high-performance device. In addition, the plurality of processors may be processors disposed on different devices, for example, the computer device may be a server cluster, and the plurality of processors may be processors on different servers in the server cluster.
Further, the invention also provides a computer readable storage medium.
In an embodiment of a computer-readable storage medium according to the present invention, the computer-readable storage medium may be configured to store a program for executing the traffic signal sensing method or the vehicle control method of the above-described method embodiment, which may be loaded and executed by a processor to implement the traffic signal sensing or vehicle control method described above. For convenience of explanation, only those portions of the embodiments of the present invention that are relevant to the embodiments of the present invention are shown, and specific technical details are not disclosed, please refer to the method portions of the embodiments of the present invention. The computer readable storage medium may be a storage device including various electronic devices, and optionally, the computer readable storage medium in the embodiments of the present invention is a non-transitory computer readable storage medium.
Further, the invention also provides a vehicle.
In an embodiment of a vehicle according to the invention, the vehicle may comprise a computer device as described in the above-mentioned embodiments of the computer device. The vehicle in this embodiment may be an autonomous vehicle, an unmanned vehicle, or the like. In addition, the vehicle in this embodiment may be a fuel vehicle, an electric vehicle, a hybrid vehicle in which electric energy and fuel are mixed, a vehicle using other new energy, or the like, according to the type of power source.
Thus far, the technical solution of the present invention has been described in connection with one embodiment shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will fall within the scope of the present invention.

Claims (15)

1. A method of perception of a traffic signal, the method comprising:
performing perception recognition on a current image frame of a traffic signal lamp to obtain the shape and color of a lamp cap of each single lamp currently lighted in the traffic signal lamp and a 2D position under an image coordinate system, and converting the 2D position into a preset three-dimensional coordinate system to obtain a 3D position of the single lamp;
Grouping the single lamps according to the 3D positions of the single lamps so as to form a single lamp group of the single lamps positioned at the same intersection;
obtaining single lamps with the same lamp cap shape in each single lamp group;
and correcting the color of each single lamp in the single lamps with the same shape in each single lamp group to be the same color.
2. The method of claim 1, wherein the step of grouping the individual lights according to their 3D positions to form an individual light group from individual lights at the same intersection comprises:
traversing the 3D position of each single lamp, and grouping the single lamps;
acquiring a plurality of single lamp groups formed after traversing the 3D position of each single lamp;
and carrying out combination treatment on the plurality of single lamp groups in pairs so as to form a final single lamp group by the single lamps positioned at the same intersection.
3. The method of claim 2, wherein the step of "traversing the 3D position of each individual light and grouping the individual lights" comprises:
judging whether the single lamp is added into the formed single lamp group according to the 3D position of the single lamp and the center position of the formed single lamp group;
If yes, adding the single lamp into the formed single lamp group and updating the central position of the formed single lamp group;
if not, a new single lamp group is created, the single lamp is added to the new single lamp group, and the central position of the new single lamp group is updated.
4. The method according to claim 2, wherein the step of combining the plurality of single lamp groups to form a final single lamp group by single lamps at the same intersection comprises:
according to the preset arrangement sequence of the single lamp group numbers, carrying out combination treatment on the plurality of single lamp groups in pairs so as to obtain preliminarily combined single lamp groups;
and carrying out combination treatment on the preliminarily combined single lamp groups two by two again according to the arrangement sequence of the preset single lamp group numbers until the number of the single lamp groups is not changed any more so as to obtain the final single lamp group.
5. The method of claim 2, wherein the step of merging the plurality of single lamp groups to form a final single lamp group from the single lamps at the same intersection further comprises merging the two single lamp groups by:
Acquiring the center distance between the center positions of the two single lamp groups;
respectively acquiring the radiuses of the two single lamp groups;
judging whether the center distance is smaller than the maximum value of the radiuses;
if yes, combining the two single lamp groups;
if not, the two single lamp groups are not combined.
6. The method of perception of a traffic light according to any one of claims 2 to 5, further comprising updating the radius of a single light group by:
obtaining the maximum distance between a single lamp in the single lamp group and the central position of the single lamp group;
and updating the radius of the single lamp group according to the maximum distance.
7. The method of claim 1, wherein the step of correcting the color of each of the shape individual lamps in each individual lamp group to the same color comprises:
aiming at each single lamp in the single lamps with the same shape, obtaining the confidence that the single lamps respectively display each different color;
selecting the color with the highest confidence from the confidence that all the single lamps in the single lamps with the same shape respectively display each different color;
and correcting the color of each single lamp in the single lamps with the same shape into the color with the highest confidence.
8. The method according to claim 7, wherein the step of selecting the color with the highest confidence level from the confidence levels of each different color displayed by all the single lamps in the single lamp shape comprises:
for each color, respectively obtaining the confidence coefficient of each single lamp for displaying the color and summing the confidence coefficient to obtain the summed confidence coefficient of the color;
and selecting the color with the highest confidence according to the added confidence of each color.
9. The method of claim 8, wherein the step of selecting the color with the highest confidence level based on the summed confidence level of each color comprises:
normalizing the summed confidence coefficient of each color to obtain normalized confidence coefficient of each color;
and selecting the color with the highest confidence according to the normalized confidence of each color.
10. The method of perception of traffic lights according to claim 1, wherein after the step of correcting the color of each individual lamp of the shape individual lamps within each individual lamp group to the same color, respectively, the method further comprises tracking smoothing the color of the individual lamp obtained by the current image frame by:
Acquiring a plurality of continuous historical image frames positioned before a current image frame;
respectively acquiring the color of the single lamp obtained through each historical image frame;
voting the single lamp colors obtained through the current image frame and the historical image frame, and selecting one color with the largest quantity as the final color of the single lamp obtained through the current image frame.
11. A method of perception of a traffic signal, the method comprising:
obtaining the lamp cap shape, the color and the single lamp group of a single lamp currently lighted in the traffic signal lamp by adopting the perception method of the traffic signal lamp according to any one of claims 1 to 10;
determining the intersection where the single lamp is located according to the single lamp group where the single lamp is located;
determining the traffic indication direction of a virtual lamp corresponding to a traffic signal lamp at an intersection according to the lamp cap shape of the single lamp and the intersection;
and determining the color of the traffic indication direction according to the color of the single lamp so as to form a virtual lamp.
12. A vehicle control method, characterized in that the method comprises:
acquiring an image frame of a traffic signal lamp positioned in the forward direction of a vehicle;
the perception method of the traffic signal lamp according to claim 11 is adopted, and virtual lamps corresponding to the traffic signal lamp are obtained according to the image frames;
Determining an intersection where the virtual lamp is located;
and according to the color of each traffic indication direction of the virtual lamp, carrying out automatic driving control on the vehicle at the intersection.
13. Computer device comprising a processor and storage means adapted to store a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by the processor to perform the traffic signal perception method according to any one of claims 1 to 10, or to perform the traffic signal perception method according to claim 11, or to perform the vehicle control method according to claim 12.
14. A computer readable storage medium, in which a plurality of program codes are stored, characterized in that the program codes are adapted to be loaded and executed by a processor to perform the traffic signal perception method according to any one of claims 1 to 10, or to perform the traffic signal perception method according to claim 11, or to perform the vehicle control method according to claim 12.
15. A vehicle, characterized in that it comprises the computer device of claim 13.
CN202310186921.0A 2023-03-02 2023-03-02 Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle Active CN115984826B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310186921.0A CN115984826B (en) 2023-03-02 2023-03-02 Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310186921.0A CN115984826B (en) 2023-03-02 2023-03-02 Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle

Publications (2)

Publication Number Publication Date
CN115984826A CN115984826A (en) 2023-04-18
CN115984826B true CN115984826B (en) 2023-06-09

Family

ID=85968316

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310186921.0A Active CN115984826B (en) 2023-03-02 2023-03-02 Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle

Country Status (1)

Country Link
CN (1) CN115984826B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018063680A (en) * 2016-10-14 2018-04-19 国立大学法人金沢大学 Traffic signal recognition method and traffic signal recognition device
CN110688992A (en) * 2019-12-09 2020-01-14 中智行科技有限公司 Traffic signal identification method and device, vehicle navigation equipment and unmanned vehicle

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103324957B (en) * 2013-06-25 2017-04-12 东软集团股份有限公司 Identification method and identification device of state of signal lamps
CN111565283A (en) * 2019-02-14 2020-08-21 初速度(苏州)科技有限公司 Traffic light color identification method, correction method and device
CN110543814B (en) * 2019-07-22 2022-05-10 华为技术有限公司 Traffic light identification method and device
CN110706494B (en) * 2019-10-30 2022-04-01 北京百度网讯科技有限公司 Control method, device, equipment and storage medium for automatic driving vehicle
CN112991791B (en) * 2019-12-13 2022-07-26 上海商汤临港智能科技有限公司 Traffic information identification and intelligent driving method, device, equipment and storage medium
CN111507210B (en) * 2020-03-31 2023-11-21 华为技术有限公司 Traffic signal lamp identification method, system, computing equipment and intelligent vehicle
CN112970030A (en) * 2021-02-10 2021-06-15 华为技术有限公司 Method and device for detecting traffic light
CN113343872B (en) * 2021-06-17 2022-12-13 亿咖通(湖北)技术有限公司 Traffic light identification method, device, equipment, medium and product
US20230053704A1 (en) * 2021-08-17 2023-02-23 DenseFogg Technology, LLC Traffic and intersection monitoring system
CN114359862A (en) * 2021-12-22 2022-04-15 浙江大华技术股份有限公司 Signal lamp identification method and device, electronic equipment and storage medium
CN114120673B (en) * 2022-01-28 2022-05-13 腾讯科技(深圳)有限公司 Information processing method, device and equipment for signal lamp and storage medium
CN115675520A (en) * 2022-09-23 2023-02-03 深圳元戎启行科技有限公司 Unmanned driving implementation method and device, computer equipment and storage medium
CN115689858A (en) * 2022-11-15 2023-02-03 安徽蔚来智驾科技有限公司 Image signal processor construction method, image signal processor construction apparatus, automatic driving system, and image signal processor

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018063680A (en) * 2016-10-14 2018-04-19 国立大学法人金沢大学 Traffic signal recognition method and traffic signal recognition device
CN110688992A (en) * 2019-12-09 2020-01-14 中智行科技有限公司 Traffic signal identification method and device, vehicle navigation equipment and unmanned vehicle

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Traffic light detection with color and edge information;M Omachi 等;《IEEE》;全文 *
一种基于机器视觉识别交通灯的方法;王厅列 等;《福建电脑》;全文 *

Also Published As

Publication number Publication date
CN115984826A (en) 2023-04-18

Similar Documents

Publication Publication Date Title
CN110688992B (en) Traffic signal identification method and device, vehicle navigation equipment and unmanned vehicle
US11037005B2 (en) Method and apparatus for identifying traffic light
US20220130153A1 (en) Vehicle control method, apparatus, electronic device and vehicle
US10824885B2 (en) Method and apparatus for detecting braking behavior of front vehicle of autonomous vehicle
CN112802092B (en) Obstacle sensing method and device and electronic equipment
CN115984823B (en) Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle
CN110008891A (en) A kind of pedestrian detection localization method, device, cart-mounted computing device and storage medium
CN113221878A (en) Detection frame adjusting method and device applied to signal lamp detection and road side equipment
CN115984826B (en) Traffic signal lamp sensing method, vehicle control method, device, medium and vehicle
CN114298908A (en) Obstacle display method and device, electronic equipment and storage medium
CN110727269B (en) Vehicle control method and related product
CN114972731A (en) Traffic light detection and identification method and device, moving tool and storage medium
KR102395844B1 (en) Method for guiding of vehicles participating in platoon based on vehicle approaching, and device for providing the same method
CN115205820A (en) Object association method, computer device, computer-readable storage medium, and vehicle
CN115984825B (en) Signal lamp flicker sensing method, vehicle control method, device, medium and vehicle
CN116311193A (en) Traffic light detection method, computer equipment and automobile
CN117475411B (en) Signal lamp countdown identification method, computer readable storage medium and intelligent device
CN117935173B (en) Target vehicle identification method, field end server and readable storage medium
CN117292360B (en) Traffic signal lamp identification method and device, storage medium and electronic equipment
CN116092056B (en) Target recognition method, vehicle control method, device, medium and vehicle
CN117197631B (en) Multi-mode sensor fusion sensing method, computer equipment, medium and vehicle
CN113221701B (en) Lane line and track line identification method and device based on direction prediction
CN116071724B (en) Vehicle-mounted camera shielding scene recognition method, electronic equipment, storage medium and vehicle
CN117496486B (en) Traffic light shape recognition method, readable storage medium and intelligent device
CN115713748A (en) Traffic light detection result processing method and device based on time sequence

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