CN116563815A - Signal lamp identification method and device, vehicle and storage medium - Google Patents

Signal lamp identification method and device, vehicle and storage medium Download PDF

Info

Publication number
CN116563815A
CN116563815A CN202310002871.6A CN202310002871A CN116563815A CN 116563815 A CN116563815 A CN 116563815A CN 202310002871 A CN202310002871 A CN 202310002871A CN 116563815 A CN116563815 A CN 116563815A
Authority
CN
China
Prior art keywords
signal lamp
current
lamp state
vehicle
state
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310002871.6A
Other languages
Chinese (zh)
Inventor
尹长林
周宏伟
马旭
查小东
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.)
Chongqing Changan Automobile Co Ltd
Original Assignee
Chongqing Changan Automobile 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 Chongqing Changan Automobile Co Ltd filed Critical Chongqing Changan Automobile Co Ltd
Priority to CN202310002871.6A priority Critical patent/CN116563815A/en
Publication of CN116563815A publication Critical patent/CN116563815A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/095—Traffic lights
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • Y—GENERAL 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a signal lamp identification method, a signal lamp identification device, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring the running information of vehicles of at least one other lane while identifying the current signal lamp state of the current intersection; calculating a theoretical signal lamp state of the current intersection according to the running information of vehicles of at least one other lane, and judging whether the current signal lamp state is consistent with the theoretical signal lamp state; if the current signal lamp state is inconsistent with the theoretical signal lamp state, judging that the current signal lamp state is wrong in recognition, generating a target running state according to the theoretical signal lamp state and running information of the opposite same-lane vehicles, and controlling the current vehicle to pass through the current intersection according to the target running state. The method and the device can compare the recognized current signal lamp state with the theoretical signal lamp state, confirm whether the signal lamp is recognized accurately, and then control the vehicle to pass through the current intersection so as to ensure the safety of the vehicle passing through the intersection in the expected functional safety level.

Description

Signal lamp identification method and device, vehicle and storage medium
Technical Field
The application relates to the technical field of intelligent driving expected functional safety, in particular to a signal lamp identification method, a signal lamp identification device, a vehicle and a storage medium.
Background
The expected functional safety (SOTIF. Safety of the Intended Functionality) is defined as that unreasonable risks caused by the dangerous behaviors caused by insufficient functions do not exist, the biggest obstacle for intelligent driving is an expected functional safety problem from the current intelligent driving test effect and capability level, and in the perception decision control related to intelligent driving, a perception layer is a layer with the largest expected functional safety risks, accurate identification of targets, accurate cognition of target attributes and accurate prediction of target situations are all the difficulties in industry.
For traffic light identification applied to intersection assistance, as the function is for L4-level or even higher-level intelligent driving, the research on the function in the related technology is concentrated on the function implementation level, the research on the safety aspect of the expected function is very lacking, and the intersection is an area with higher probability of traffic accidents, the safety research on the expected function of the function can effectively avoid unexpected movement behaviors of vehicles when the vehicles run at the intersection, effectively ensure the safety of drivers and pedestrians, and has important significance to be improved.
Disclosure of Invention
The application provides a signal lamp identification method, a signal lamp identification device, a vehicle and a storage medium, which are used for solving the technical problems that in the related technology, the identification of the signal lamp at the intersection is in a function implementation level, the research on an expected function safety level is lacking, and the safety of drivers and pedestrians is difficult to effectively guarantee.
An embodiment of a first aspect of the present application provides a signal lamp identification method, including the following steps: acquiring the running information of vehicles of at least one other lane while identifying the current signal lamp state of the current intersection; calculating a theoretical signal lamp state of the current intersection according to the running information of the vehicles of the at least one other lane, and judging whether the current signal lamp state is consistent with the theoretical signal lamp state; if the current signal lamp state is inconsistent with the theoretical signal lamp state, judging that the current signal lamp state is wrong in recognition, generating a target running state according to the theoretical signal lamp state and running information of the opposite lane vehicles, and controlling the current vehicle to pass through the current intersection according to the target running state.
According to the technical means, the theoretical signal lamp state of the current intersection can be judged based on the running information of vehicles in other lanes, the identified current signal lamp state is compared with the theoretical signal lamp state, whether the identification is accurate or not is confirmed, and then the target running state is generated, so that the vehicles can be controlled to pass through the current intersection, the accuracy of the generated target running state is guaranteed in the aspect of expected functional safety, and therefore safety of drivers and pedestrians is effectively guaranteed.
Optionally, in one embodiment of the present application, after determining that the current signal lamp status has a recognition error, the method further includes: obtaining the error type of the current signal lamp state while generating the error prompt of the current signal lamp state; and matching an optimal error reminding mode according to the error type, and sending the error reminding to a vehicle terminal or a preset terminal according to the optimal error reminding mode.
According to the technical means, the embodiment of the application can remind in different modes based on different signal lamp state error types.
Optionally, in one embodiment of the present application, after obtaining the error type of the current signal lamp state, the method further includes: calculating an actual risk rating of the current vehicle when the error type is an identified error type; and when the actual risk rating is larger than a preset rating, controlling the current vehicle to move according to a preset safety strategy.
According to the technical means, the embodiment of the application can control the current vehicle to execute different safety strategies according to the risk rating.
Optionally, in one embodiment of the present application, the calculating the actual risk rating of the current vehicle includes: acquiring the severity and the controllability of the identification error type; and obtaining the actual risk rating according to the severity and the controllability.
According to the technical means, the embodiment of the application can obtain the actual risk rating according to the severity and the controllability of the error type.
An embodiment of a second aspect of the present application provides a signal lamp identification device, including: the identifying module is used for acquiring the running information of the vehicle of at least one other lane while identifying the current signal lamp state of the current intersection; the calculation module is used for calculating the theoretical signal lamp state of the current intersection according to the running information of the vehicles of the at least one other lane and judging whether the current signal lamp state is consistent with the theoretical signal lamp state or not; and the first control module is used for judging that the current signal lamp state is wrong in recognition if the current signal lamp state is inconsistent with the theoretical signal lamp state, generating a target running state according to the theoretical signal lamp state and running information of the opposite same-lane vehicles, and controlling the current vehicle to pass through the current intersection according to the target running state.
Optionally, in one embodiment of the present application, further includes: the generating module is used for generating an error prompt of the current signal lamp state and acquiring the error type of the current signal lamp state; the reminding module is used for matching an optimal error reminding mode according to the error type and sending the error reminding to a vehicle terminal or a preset terminal according to the optimal error reminding mode.
Optionally, in one embodiment of the present application, further includes: the rating module is used for calculating the actual risk rating of the current vehicle when the error type is the identification error type; and the second control module is used for controlling the current vehicle to move according to a preset safety strategy when the actual risk rating is larger than a preset rating.
Optionally, in one embodiment of the present application, the evaluation module includes: an obtaining unit, configured to obtain severity and controllability of the identification error type; and the rating unit is used for obtaining the actual risk rating according to the severity and the controllability.
An embodiment of a third aspect of the present application provides a vehicle, including: the signal lamp identification system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize the signal lamp identification method according to the embodiment.
A fourth aspect of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the signal identification method as above.
The beneficial effects of the embodiment of the application are that:
(1) According to the method and the device, the theoretical signal lamp state of the current intersection can be judged based on the running information of vehicles in other lanes, the recognized current signal lamp state is compared with the theoretical signal lamp state, whether recognition is accurate or not is confirmed, and then the target running state is generated, so that the vehicles can be controlled to pass through the current intersection, the accuracy of the generated target running state is guaranteed in the aspect of expected functional safety, and therefore safety of drivers and pedestrians is effectively guaranteed;
(2) The embodiment of the application can classify the identification errors of the signal lamps and correspondingly remind different types, so that the subsequent technicians can maintain the signal lamps conveniently;
(3) According to the method and the device for grading the risk, the risk grading can be carried out, and the vehicles are controlled to execute the corresponding safety strategy based on the risk grading, so that the traffic safety of the vehicle at the intersection is guaranteed.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flowchart of a signal lamp identification method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of the correct identification of a left-turn signal lamp according to a signal lamp identification method according to one embodiment of the present application;
FIG. 3 is a left turn signal lamp error identification schematic diagram of a signal lamp identification method according to one embodiment of the present application;
FIG. 4 is a schematic diagram of the right identification of a straight signal according to a signal identification method according to one embodiment of the present application;
FIG. 5 is a schematic diagram of straight-going signal error identification of a signal identification method according to one embodiment of the present application;
FIG. 6 is a right turn signal lamp proper identification schematic diagram of a signal lamp identification method according to one embodiment of the present application;
FIG. 7 is a right-turn signal lamp error identification schematic diagram of a signal lamp identification method according to one embodiment of the present application;
fig. 8 is a schematic structural diagram of a signal lamp identification device according to an embodiment of the present application;
fig. 9 is a schematic structural view of a vehicle according to an embodiment of the present application.
Wherein, 10-signal lamp recognition device; 100-identification module, 200-calculation module, 300-first control module.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.
The following describes a signal lamp identification method, a device, a vehicle and a storage medium according to the embodiments of the present application with reference to the accompanying drawings. Aiming at the technical problems that in the related technology mentioned in the background technology center, the identification of the intersection signal lamp is in a function implementation level, the research on an expected function safety level is lacking, and the safety of drivers and pedestrians is difficult to effectively guarantee, the application provides a signal lamp identification method. Therefore, the technical problems that in the related technology, the identification of the intersection signal lamp is in the function implementation level, the research on the expected function safety level is lacking, and the safety of drivers and pedestrians is difficult to effectively guarantee are solved.
Specifically, fig. 1 is a schematic flow chart of a signal lamp identification method provided in an embodiment of the present application.
As shown in fig. 1, the signal lamp identification method includes the following steps:
in step S101, the driving information of the vehicle in at least one other lane is acquired while the current signal lamp state of the current intersection is identified.
In the actual execution process, the embodiment of the application can realize correct cognition to the external environment through sensing fusion based on sensors such as a front-view camera, a front millimeter wave radar, a peripheral-view camera, an angle radar, an ultrasonic radar and the like, wherein the front view is mainly responsible for identifying signal lamp information, including the identification of information such as the color, the shape, the state and the countdown of the signal lamp.
The embodiment of the application can also obtain the running information of the vehicles of at least one other lane, such as passing, parking, steering and the like through the sensor while identifying the current signal lamp state of the current intersection.
In step S102, a theoretical signal light state of the current intersection is calculated according to the traveling information of the vehicles in at least one other lane, and it is determined whether the current signal light state and the theoretical signal light state are consistent.
As a possible implementation manner, the embodiment of the present application may calculate, according to the driving information of the vehicle in at least one other lane, a theoretical signal lamp state of the current intersection, that is, determine, based on the driving states of the vehicles in different lanes, the signal lamp state corresponding to the lane, so as to obtain the theoretical signal lamp state, so as to determine whether the identified current signal lamp state identifies an error.
In step S103, if the current traffic light state and the theoretical traffic light state are inconsistent, it is determined that the current traffic light state is misidentified, a target running state is generated according to the theoretical traffic light state and running information of the oncoming vehicle, and the current vehicle is controlled to pass through the current intersection according to the target running state.
In some embodiments, if the current signal light state is inconsistent with the theoretical signal light state, the embodiment of the application may determine that the identified current signal light state has an error, so the current signal light state cannot be used as a reference for a running state of a current vehicle passing through a current intersection.
Optionally, in one embodiment of the present application, after determining that the current signal lamp status has a recognition error, the method further includes: obtaining the error type of the current signal lamp state while generating the error prompt of the current signal lamp state; and matching the optimal error reminding mode according to the error type, and sending error reminding to the vehicle terminal or a preset terminal according to the optimal error reminding mode.
It can be understood that, under the interference of the external complex environment, the signal lamp signal of the forward looking detection may change abnormally, and specific error types may include: the signal lamp color signal misrecognition, the signal lamp shape information misrecognition, the signal lamp countdown information misrecognition and the signal lamp information can be summarized as the recognition error and the signal lamp information which cannot be recognized.
Further, the above-mentioned identification errors may cause unacceptable vehicle-level hazard, and according to the SOTIF process, the cause of the above-mentioned functional deficiency, i.e. the hazard triggering condition, needs to be identified.
The signal lamp identification belongs to a sensing function, the sensed triggering condition mainly comes from input and a model, and the problem of the input end is often caused by the increase of data noise, limitation of the principle of the sensor or the limitation of the visual field of the sensor caused by the external environment and the sensor, such as severe environment; the problem with the model comes from the algorithm itself.
In the related art, most of automatic driving perception algorithms are based on deep learning technology, training of a deep learning model depends on a large amount of labeling data, and when the perception algorithm faces an unknown object or special gesture and form, false detection, missing detection and false detection often occur, and the limitation of the perception algorithm is triggered.
Thus, identifying false trigger conditions may include:
light and shadow interference: the method mainly comprises direct irradiation of sunlight to the front view, the direct irradiation of the sunlight to the signal lamp causes the front view to be difficult to identify, and the like.
Dirt shielding class: the device comprises a camera shielded by rain and snow or a signal lamp shielded by snow.
View blocking class: including the shielding of the camera view by the other vehicle.
Identifying algorithm classes: the training set for identifying the signal lamp is incomplete, and full coverage cannot be realized without the signal lamp state.
Therefore, the embodiment of the application can match the optimal error reminding mode according to the error type, and send the error reminding to the vehicle terminal or the preset terminal according to the optimal error reminding mode, for example, when the error type of the identification signal is the identification error and the triggering condition of the error type is the dirt shielding type, the embodiment of the application can send the error reminding to the traffic management department, so that related personnel can conveniently clean the surface of the signal lamp in time; when the error type of the identification signal is identification error or signal lamp information cannot be identified and the triggering condition for causing the error type is identification algorithm type, the embodiment of the application can send error reminding to the vehicle enterprise terminal, so that technicians can update an algorithm model conveniently; when the error type of the identification signal is the signal lamp information which cannot be identified and the triggering condition of the error type is the view shielding type, the embodiment of the application can send the error prompt to the vehicle terminal, so that a driver can conveniently pick up the vehicle for control.
Optionally, in one embodiment of the present application, after obtaining the error type of the current signal lamp state, the method further includes: 5, calculating the actual risk rating of the current vehicle when the error type is the identification error type; when the actual risk rating is greater than a preset
And when the vehicle is rated, controlling the current vehicle to move according to a preset safety strategy.
In the actual implementation process, when the error type is the identification error type, the embodiment of the application calculates the actual risk rating of the current vehicle, and controls the current vehicle to move by a preset safety strategy when the actual risk rating is greater than the preset rating, for example
If the actual risk rating is smaller than the preset rating, the embodiment of the application can control the current vehicle to decelerate, and then the vehicle passes through the intersection according to the state of the signal lamp of theory 0, and a prompt can be sent to the driver, so that the driver can conveniently pick up the vehicle for control; when the wind is actual
When the risk rating is larger than the preset rating, the vehicle can be controlled to be decelerated, the vehicle stops at the roadside to wait for maintenance, and the driving state of the vehicle can be stopped through emergency braking.
It should be noted that the preset rating may be set by those skilled in the art according to the actual situation, and is not particularly limited herein.
5 optionally, in one embodiment of the present application, calculating an actual risk rating for the current vehicle includes: acquisition identification
Severity and controllability of the error type; and obtaining the actual risk rating according to the severity and the controllability.
As one possible implementation manner, the embodiment of the application may determine whether the risk is acceptable according to identifying the possible vehicle-level hazard and evaluating the risk of the hazard event, and according to the requirements of the SOTIF, the risk evaluation may be measured based on the severity S and the controllability C, and when S >0 or C >0, the risk is not acceptable.
0, wherein the hazard of the whole vehicle layer surface can comprise: unexpected start of vehicle, unexpected brake of vehicle
Straight, unintended left turn of the vehicle, and unintended right turn of the vehicle.
For example: when a vehicle is at a crossing or the like, the perception layer erroneously recognizes a red light as a green light, and the vehicle can be started unexpectedly; when the vehicle erroneously recognizes a green light as a red light, unintended braking of the vehicle may occur; during the crossing, the vehicle will
If the red light is identified as a green light, the straight line is not expected; when the vehicle erroneously recognizes the red light of the left turn light and the right turn light as a green light, unexpected left turn and right turn behaviors may occur at 5.
The above-mentioned unexpected start at the intersection, unexpected left/right turns, both of which result in a dangerous event of collision with his car, is an unacceptable risk of either S >0 or C > 0.
The working principle of the signal lamp identification method according to the embodiment of the present application will be described in detail with reference to fig. 2 to 7.
0 an embodiment of the present application may include the steps of:
s1: the current signal lamp state of the current intersection is identified. In the actual execution process, the embodiment of the application can realize correct cognition to the external environment through sensing fusion based on sensors such as a front-view camera, a front millimeter wave radar, a peripheral-view camera, an angle radar, an ultrasonic radar and the like, wherein the front view is mainly responsible for identifying signal lamp information, including the identification of information such as the color, the shape, the state and the countdown of the signal lamp.
S2: performance limitation identification. Under the interference of an external complex environment, the signal lamp signal of forward looking detection can be abnormally changed, and specific error types can comprise: the signal lamp color signal misrecognition, the signal lamp shape information misrecognition, the signal lamp countdown information misrecognition and the signal lamp information can be summarized as the recognition error and the signal lamp information which cannot be recognized.
S3: and (5) triggering condition identification. The above-mentioned identification error may cause unacceptable vehicle-level hazard, and according to the SOTIF process, the cause of the above-mentioned functional deficiency, i.e. the hazard triggering condition, needs to be identified.
The signal lamp identification belongs to a sensing function, the sensed triggering condition mainly comes from input and a model, and the problem of the input end is often caused by the increase of data noise, limitation of the principle of the sensor or the limitation of the visual field of the sensor caused by the external environment and the sensor, such as severe environment; the problem with the model comes from the algorithm itself.
In the related art, most of automatic driving perception algorithms are based on deep learning technology, training of a deep learning model depends on a large amount of labeling data, and when the perception algorithm faces an unknown object or special gesture and form, false detection, missing detection and false detection often occur, and the limitation of the perception algorithm is triggered.
Thus, identifying false trigger conditions may include:
light and shadow interference: the method mainly comprises direct irradiation of sunlight to the front view, the direct irradiation of the sunlight to the signal lamp causes the front view to be difficult to identify, and the like.
Dirt shielding class: the device comprises a camera shielded by rain and snow or a signal lamp shielded by snow.
View blocking class: including the shielding of the camera view by the other vehicle.
Identifying algorithm classes: the training set for identifying the signal lamp is incomplete, and full coverage cannot be realized without the signal lamp state.
S4: hazard analysis and risk assessment. According to the embodiment of the application, the risk of a hazard event can be determined according to the identification of the possible vehicle-level hazard and the evaluation of the risk, whether the risk is acceptable or not can be determined, according to the SOTIF requirement, the risk evaluation can be measured based on the severity S and the controllability C, and when S >0 or C >0, the risk is unacceptable.
Wherein, the harm of whole car aspect can include: unexpected start of the vehicle, unexpected brake of the vehicle, unexpected straight-ahead of the vehicle, unexpected left turn of the vehicle, and unexpected right turn of the vehicle.
For example: when a vehicle is at a crossing or the like, the perception layer erroneously recognizes a red light as a green light, and the vehicle can be started unexpectedly; when the vehicle erroneously recognizes a green light as a red light, unintended braking of the vehicle may occur; during the passing of the road, the vehicle recognizes the red light as a green light, and then the vehicle can go straight unexpectedly; when the vehicle erroneously recognizes the red light of the left turn light and the right turn light as a green light, unexpected left turn and right turn behaviors may occur.
The above-mentioned unexpected start at the intersection, unexpected left/right turns, both of which result in a dangerous event of collision with his car, is an unacceptable risk of either S >0 or C > 0.
S5: and (5) improving functions. For the above identified hazard events and trigger conditions, embodiments of the present application may purposefully formulate functional improvements to ensure that, upon encountering similar trigger conditions, hazard events due to unexpected behavior of the vehicle are no longer occurring.
Embodiments of the present application may be designed functional improvements for unintended starting, unintended straight running, unintended left-hand and unintended right-hand turns of the vehicle, and not for unintended braking designs.
Because the speed of the vehicles at the intersection can be reduced to be less than 30km/h, and all the vehicles entering the road section of the intersection can enter a deceleration state no matter whether the signal lamp is a red light or a green light, the unexpected braking is more similar to the excessive braking, and most drivers can timely react and cannot cause unacceptable risks under the conditions of low-speed running and unexpected braking of the front vehicle.
Unexpected straight going/left turning/right turning is caused by misidentification of signal light information (red light is identified as green light) or misidentification of signal light countdown (countdown of identification > true countdown), and since the results caused by the deficiency of both identifications are the same, merging can be performed, therefore, the embodiment of the application can only improve on misidentification of signal light information (red light is identified as green light).
According to the embodiment of the application, the running information of the vehicles facing the same kind of lanes and the running information of the vehicles vertical to the same kind of lanes can be taken into the running decision of the current vehicle, and the specific decision logic is as follows:
when the vehicle is in straight or left turn, besides the identified signal lamp signals, the current vehicle also identifies the running information of the vehicle facing the straight/left turn lane and the running information of the vehicle vertical to the straight/left turn lane, and the running states of the vehicles are determined by combining the information.
Taking left turn as an example, as shown in fig. 2 and 3, the a car recognizes the left turn red light as a green light, and the a car collects driving information of the opposite lane C car and the vertical lanes B and D car. If the C vehicle stops at the left-turn lane and the B vehicle and the D vehicle (more than two vehicles) perform left-turn operation, the A vehicle is judged to enter a left-turn waiting state at the moment, and the A vehicle is stopped and waits.
The straight-line logic is similar to a left turn, as shown in fig. 4 and 5.
The driving condition of the vehicle facing the same kind of lane is only included in the driving decision of the current vehicle in the right turn, as shown in fig. 6 and 7. When the current vehicle recognizes the right turn red light as a green light and two or more vehicles C and E are waiting on the right turn lane, the current vehicle stops waiting, and when the vehicles C and E start to turn right, the current vehicle starts to turn right and reminds a driver of abnormal functions.
According to the signal lamp identification method provided by the embodiment of the application, the theoretical signal lamp state of the current intersection can be calculated according to the running information of vehicles of at least one other lane, whether the current signal lamp state is consistent with the theoretical signal lamp state or not is judged, when the current signal lamp state is inconsistent with the theoretical signal lamp state, the identification error is judged to occur in the current signal lamp state, the target running state is generated according to the theoretical signal lamp state and the running information of vehicles facing the same lane, so that the current vehicles can be controlled to pass through the current intersection, the safety of the vehicles passing through the intersection is guaranteed in the expected functional safety level, and the traffic safety of the intersection of a driver and pedestrians is effectively guaranteed. Therefore, the technical problems that in the related technology, the identification of the intersection signal lamp is in the function implementation level, the research on the expected function safety level is lacking, and the safety of drivers and pedestrians is difficult to effectively guarantee are solved.
Next, a signal lamp recognition device according to an embodiment of the present application will be described with reference to the accompanying drawings.
Fig. 8 is a block schematic diagram of a signal lamp identification device according to an embodiment of the present application.
As shown in fig. 8, the signal lamp recognition apparatus 10 includes: an identification module 100, a calculation module 200 and a first control module 300.
Specifically, the identifying module 100 is configured to identify a current signal lamp state of a current intersection and obtain driving information of a vehicle in at least one other lane.
The calculating module 200 is configured to calculate a theoretical signal lamp state of the current intersection according to the driving information of the vehicle in at least one other lane, and determine whether the current signal lamp state is consistent with the theoretical signal lamp state.
The first control module 300 is configured to determine that an identification error occurs in the current signal lamp state if the current signal lamp state is inconsistent with the theoretical signal lamp state, generate a target driving state according to the theoretical signal lamp state and driving information of the opposite lane vehicle, and control the current vehicle to pass through the current intersection according to the target driving state.
Optionally, in one embodiment of the present application, the signal lamp identification device 10 further includes: the system comprises a generating module and a reminding module.
The generating module is used for generating the error prompt of the current signal lamp state and simultaneously acquiring the error type of the current signal lamp state.
The reminding module is used for matching the optimal error reminding mode according to the error type and sending error reminding to the vehicle terminal or the preset terminal according to the optimal error reminding mode.
Optionally, in one embodiment of the present application, the signal lamp identification device 10 further includes: a rating module and a second control module.
And the rating module is used for calculating the actual risk rating of the current vehicle when the error type is the identification error type.
And the second control module is used for controlling the current vehicle to move according to a preset safety strategy when the actual risk rating is larger than the preset rating.
Optionally, in one embodiment of the present application, the rating module includes: an acquisition unit and a rating unit.
The acquisition unit is used for acquiring the severity and the controllability of the type of the identification error.
And the rating unit is used for obtaining the actual risk rating according to the severity and the controllability.
It should be noted that the foregoing explanation of the signal lamp identification method embodiment is also applicable to the signal lamp identification device of this embodiment, and will not be repeated here.
According to the signal lamp identification device provided by the embodiment of the application, the theoretical signal lamp state of the current intersection can be calculated according to the running information of vehicles of at least one other lane, whether the current signal lamp state is consistent with the theoretical signal lamp state or not is judged, when the current signal lamp state is inconsistent with the theoretical signal lamp state, the identification error is judged to occur in the current signal lamp state, the target running state is generated according to the theoretical signal lamp state and the running information of vehicles facing the same lane, so that the current vehicles can be controlled to pass through the current intersection, the safety of the vehicles passing through the intersection is guaranteed in the expected functional safety level, and the traffic safety of the intersection of a driver and pedestrians is effectively guaranteed. Therefore, the technical problems that in the related technology, the identification of the intersection signal lamp is in the function implementation level, the research on the expected function safety level is lacking, and the safety of drivers and pedestrians is difficult to effectively guarantee are solved.
Fig. 9 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle may include:
memory 901, processor 902, and a computer program stored on memory 901 and executable on processor 902.
The signal lamp recognition method provided in the above embodiment is implemented when the processor 902 executes a program.
Further, the vehicle further includes:
a communication interface 903 for communication between the memory 901 and the processor 902.
Memory 901 for storing a computer program executable on processor 902.
Memory 901 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (Peripheral Component, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 901, the processor 902, and the communication interface 903 are integrated on a chip, the memory 901, the processor 902, and the communication interface 903 may communicate with each other through internal interfaces.
The processor 902 may be a central processing unit (Central Processing Unit, abbreviated as CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or one or more integrated circuits configured to implement embodiments of the present application.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the signal lamp identification method as above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims (10)

1. A signal lamp identification method, comprising the steps of:
acquiring the running information of vehicles of at least one other lane while identifying the current signal lamp state of the current intersection;
calculating a theoretical signal lamp state of the current intersection according to the running information of the vehicles of the at least one other lane, and judging whether the current signal lamp state is consistent with the theoretical signal lamp state;
if the current signal lamp state is inconsistent with the theoretical signal lamp state, judging that the current signal lamp state is wrong in recognition, generating a target running state according to the theoretical signal lamp state and running information of the opposite lane vehicles, and controlling the current vehicle to pass through the current intersection according to the target running state.
2. The method of claim 1, further comprising, after determining that the current signal condition has an identification error:
obtaining the error type of the current signal lamp state while generating the error prompt of the current signal lamp state;
and matching an optimal error reminding mode according to the error type, and sending the error reminding to a vehicle terminal or a preset terminal according to the optimal error reminding mode.
3. The method of claim 2, further comprising, after obtaining the error type for the current signal status:
calculating an actual risk rating of the current vehicle when the error type is an identified error type;
and when the actual risk rating is larger than a preset rating, controlling the current vehicle to move according to a preset safety strategy.
4. A method according to claim 3, wherein said calculating an actual risk rating for the current vehicle comprises:
acquiring the severity and the controllability of the identification error type;
and obtaining the actual risk rating according to the severity and the controllability.
5. A signal lamp identification device, comprising:
the identifying module is used for acquiring the running information of the vehicle of at least one other lane while identifying the current signal lamp state of the current intersection;
the calculation module is used for calculating the theoretical signal lamp state of the current intersection according to the running information of the vehicles of the at least one other lane and judging whether the current signal lamp state is consistent with the theoretical signal lamp state or not;
and the first control module is used for judging that the current signal lamp state is wrong in recognition if the current signal lamp state is inconsistent with the theoretical signal lamp state, generating a target running state according to the theoretical signal lamp state and running information of the opposite same-lane vehicles, and controlling the current vehicle to pass through the current intersection according to the target running state.
6. The apparatus as recited in claim 5, further comprising:
the generating module is used for generating an error prompt of the current signal lamp state and acquiring the error type of the current signal lamp state;
the reminding module is used for matching an optimal error reminding mode according to the error type and sending the error reminding to a vehicle terminal or a preset terminal according to the optimal error reminding mode.
7. The apparatus as recited in claim 6, further comprising:
the rating module is used for calculating the actual risk rating of the current vehicle when the error type is the identification error type;
and the second control module is used for controlling the current vehicle to move according to a preset safety strategy when the actual risk rating is larger than a preset rating.
8. The apparatus of claim 7, wherein the evaluation module comprises:
an obtaining unit, configured to obtain severity and controllability of the identification error type;
and the rating unit is used for obtaining the actual risk rating according to the severity and the controllability.
9. A vehicle, characterized by comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the traffic light identification method according to any one of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing the signal identification method as claimed in any one of claims 1-4.
CN202310002871.6A 2023-01-03 2023-01-03 Signal lamp identification method and device, vehicle and storage medium Pending CN116563815A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310002871.6A CN116563815A (en) 2023-01-03 2023-01-03 Signal lamp identification method and device, vehicle and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310002871.6A CN116563815A (en) 2023-01-03 2023-01-03 Signal lamp identification method and device, vehicle and storage medium

Publications (1)

Publication Number Publication Date
CN116563815A true CN116563815A (en) 2023-08-08

Family

ID=87497155

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310002871.6A Pending CN116563815A (en) 2023-01-03 2023-01-03 Signal lamp identification method and device, vehicle and storage medium

Country Status (1)

Country Link
CN (1) CN116563815A (en)

Similar Documents

Publication Publication Date Title
US9415718B2 (en) Vehicular headlight apparatus
US8493195B2 (en) Method for detecting an environment of a vehicle
CN111547053B (en) Automatic driving control method and system based on vehicle-road cooperation
US11518374B2 (en) Vehicle braking support device and braking support control method
CN108615383B (en) Automobile traffic intersection auxiliary passing system based on workshop communication and control method thereof
KR20140107629A (en) Method and control unit for monitoring traffic
US11348463B2 (en) Travel control device, travel control method, and storage medium storing program
CN107139921B (en) A kind of steering collision-proof method and system for vehicle
CN111879360B (en) Automatic driving auxiliary safety early warning system in dark scene and early warning method thereof
US20220258731A1 (en) Collision avoidance assist apparatus
CN112606831A (en) Anti-collision warning information external interaction method and system for passenger car
CN113053165A (en) Vehicle and collision recognition method, device and equipment thereof
CN113650607B (en) Low-speed scene automatic driving method, system and automobile
CN115817522A (en) Vehicle driving assisting method and device, vehicle and storage medium
CN113246978A (en) Vehicle rearview mirror blind area detection method and detection device
JPH02287799A (en) Collision preventing device for vehicle
CN116563815A (en) Signal lamp identification method and device, vehicle and storage medium
CN116148860A (en) Method and device for identifying static obstacle, vehicle and storage medium
JP6069081B2 (en) Vehicle driving support device
CN113753067B (en) Lane departure intervention control method and device
US20210284148A1 (en) Travel control apparatus, vehicle, travel control method, and non-transitory computer-readable storage medium
KR20210108307A (en) Method for detecting wrong way driving situations of vehicle, method for detecting one way street driving situations of vehicle, and vehicle
CN115556722A (en) Control method and device of vehicle active emergency braking system, vehicle and medium
JPH09156437A (en) Warning device
US20230242140A1 (en) Driving assistance device, vehicle, driving assistance method, and storage medium

Legal Events

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