CN114475429B - Traffic light reminding method and system combined with user driving intention and automobile - Google Patents
Traffic light reminding method and system combined with user driving intention and automobile Download PDFInfo
- Publication number
- CN114475429B CN114475429B CN202210158508.9A CN202210158508A CN114475429B CN 114475429 B CN114475429 B CN 114475429B CN 202210158508 A CN202210158508 A CN 202210158508A CN 114475429 B CN114475429 B CN 114475429B
- Authority
- CN
- China
- Prior art keywords
- traffic light
- information
- traffic
- vehicle
- light
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 claims abstract description 89
- 238000001914 filtration Methods 0.000 claims abstract description 21
- 238000012805 post-processing Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 claims 1
- 230000008569 process Effects 0.000 description 7
- 230000003993 interaction Effects 0.000 description 3
- 238000012015 optical character recognition Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010065369 Burnout syndrome Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q11/00—Arrangement of monitoring devices for devices provided for in groups B60Q1/00 - B60Q9/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a traffic light reminding method, a traffic light reminding system and an automobile combined with the driving intention of a user, wherein the traffic light reminding method comprises the following steps: collecting pictures with traffic lights in real time; taking the region above the picture as a detection region; marking the traffic light position in the detection area image; filtering the background target and the false detection target; identifying the type, color, and number and color of the traffic light and the countdown light; outputting corresponding position information of the traffic light and the countdown light; carrying out real-time scene matching on traffic light information and countdown light information; acquiring vehicle navigation information or turn signal information; and obtaining traffic light instruction information to be followed by the vehicle in the running state and outputting the traffic light instruction information. According to the traffic light information reminding method and the traffic light information reminding device, the traffic information reminding device and the traffic light information reminding system can give the user a traffic information reminding in the direction to be driven according to the driving intention of the vehicle, and the problems that the traffic jam, the potential safety hazard and the like are caused by distraction or lack of attention of the user to the red light information when the traffic light is switched are prevented.
Description
Technical Field
The invention relates to the technical field of cabin interaction, in particular to a traffic light reminding method and system combined with a user driving intention and an automobile.
Background
Along with the continuous development of social economy, automobiles become vehicles for more and more people, meanwhile, along with the evolution of intelligent technology, more intelligent and humanized functions are given to the automobiles, the travel safety of people is greatly ensured, and the driving and riding convenience experience is improved. In the process of driving of the automobile, traffic light road conditions are frequently encountered scenes, and many drivers are distracted due to mental exhaustion or other things, so that the traffic light at the crossing is not seen to be out of order to brake, or in the process of waiting for the traffic light, the traffic light is converted into a green light due to the fact that the traffic light is not noticed when chatting with friends, processing mobile phone messages and the like, so that the situation of prompting a rear automobile, traffic jam and the like is caused, and even some novice drivers cannot see part of traffic light indication, so that the traffic light state and traffic indication can be intelligently reminded on the automobile by utilizing an intelligent technology, and the situation can be effectively improved.
At present, some vehicles are provided with traffic light identification reminding devices, and the identification technology is primarily combined and applied, for example, the patent application of the invention with the application number of CN201020664115.8 discloses an automatic red light sensing method and an automatic red light sensing device in an automatic red light stopping sensing device of a motor vehicle, the scheme is composed of a signal generating device and a signal receiving device, the signal generating device is arranged on the red light, the red light sends directional signals, the signal receiving device is arranged on the motor vehicle, when the motor vehicle is about to arrive at the red light, the signal receiving device on the vehicle receives the signals sent by the red light, and a corresponding control system is started, so that the aim of reminding and braking is fulfilled. Meanwhile, the scheme is not combined with an actual application scene, the actual running route of the vehicle can recognize and remind which traffic light, how the state of the traffic lights and the residual time are understood in a multi-signal light scene, and the like, and the scheme is not related.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to solve the technical problems that: how to provide a traffic light reminding method, a traffic light reminding system and an automobile which can give a user a traffic information reminding of a to-be-driven direction according to the driving intention of the automobile and prevent the problems of road congestion, traffic safety hidden danger and the like caused by the fact that the user is distracted or does not notice the red light information when the traffic light is switched.
In order to solve the technical problems, the invention adopts the following technical scheme:
a traffic light reminding method combining with a user driving intention comprises the following steps:
step 1), acquiring and acquiring pictures with traffic lights in front of the running of a vehicle in real time;
step 2) taking the area, above the picture in the step 1), as a detection area, and intercepting an image of the detection area as an image input for traffic light detection;
step 3) marking the position of the traffic light in the image of the detection area in the step 2) by using a detection frame, and detecting and acquiring traffic light information of the motor vehicle lane;
step 4) filtering the background target and the false detection target from the traffic light information obtained in the step 3);
step 5) identifying the type of the traffic light, the color of the traffic light and the number and the color of the countdown light in the traffic light information subjected to the filtering treatment in the step 4);
step 6) respectively outputting corresponding position information of the traffic light and the countdown light according to the position of the detection frame in the step 3);
step 7) carrying out real-time scene matching on the traffic light information obtained in the step 5) and the step 6) and the countdown light information to obtain the residual duration of the traffic lights in all directions;
step 8) acquiring vehicle navigation information or turn signal information to judge the running intention of the vehicle;
step 9), according to the remaining duration of the traffic lights in all directions obtained in the step 7), combining the vehicle driving intention obtained in the step 8) to obtain traffic light instruction information to be followed by the vehicle in the driving state;
step 10), outputting traffic light instruction information to be followed by the vehicle obtained in the step 9) in the running state;
step 11) ends.
The working principle of the invention is as follows: in the scheme, in the running process of a vehicle, a picture with a traffic light in front of the vehicle is acquired and acquired in real time, according to the characteristic that the traffic light is generally installed above, an area, close to the picture, is taken as a detection area of a traffic light image, then the position of the traffic light in the detection area is marked by utilizing a detection frame, the traffic light information of a motor vehicle lane is acquired, the accuracy of a subsequent identification result is ensured by carrying out filtering processing on a background target and a false detection target on the acquired traffic light information of the motor vehicle lane, then the type, the color and the number and the color of a countdown light in the filtered traffic light information are identified, the corresponding position information of the traffic light and the countdown light is respectively output according to the position of the detection frame, the residual duration information of the traffic light in all directions can be obtained by carrying out real-time scene matching on the traffic light information and the countdown light information, then the running intention of the vehicle is judged by the navigation information or the turn light information of the vehicle, the instruction information of the traffic light in the running intention of the vehicle is obtained, and finally the purpose of reminding a user of the traffic light is achieved by outputting the obtained traffic light instruction information in the running intention direction. Therefore, the scheme can give the traffic information reminding of the direction to be driven to the user according to the driving intention of the vehicle, and the problems of road congestion, traffic safety hidden danger and the like caused by distraction or unnoticed red light information when the traffic light is switched are prevented.
Preferably, in step 1), a road video of a vehicle advancing direction is obtained in real time through a camera installed on the vehicle, a frame-by-frame picture is obtained for the obtained road video in a frame extraction mode, and distortion correction processing is performed for the obtained picture.
Preferably, in step 2), the vanishing point is detected by the graying process, and a region above the horizontal line where the vanishing point is located is taken as a detection region.
Preferably, in step 3), setting a traffic light detection model, adjusting parameters of the traffic light detection model by using training data, and iteratively completing training of the traffic light detection model;
inputting the image in the step 2) into a traffic light detection model, detecting traffic light information of a motor vehicle lane in the traffic light detection model through a real-time target detection network, outputting a detection frame, marking the traffic light detection frame in the input image in the image by the traffic light detection model, and outputting the target position of the detection frame.
Preferably, in step 5), a traffic light identification model is constructed through a convolutional neural network, and the traffic light type, the traffic light color and the countdown light color in the traffic light information after the filtering treatment in step 4) are identified through the traffic light identification model;
the number of the countdown light is identified by an optical character recognition technique.
Preferably, in step 7), when only one group of traffic lights and the countdown lights have the same color, judging that the number of the countdown lights represents the remaining duration of the traffic lights;
when the colors of the traffic lights and the countdown lights are consistent, judging that the group with the nearest relative position is the actual matching condition according to the positions of the traffic lights and the countdown lights output in the step 6) so as to obtain the residual duration of the traffic lights in all directions.
Preferably, in step 8), when the vehicle has navigation information, the driving intention of the vehicle is determined according to the navigation information; when the vehicle has no navigation information, the driving intention of the vehicle is judged according to the information of the vehicle turn signal lamp.
Preferably, in step 10), the traffic light instruction information is output to a vehicle machine of the vehicle for display, and the traffic light instruction information is voice-broadcast.
The invention also provides a system for realizing the traffic light reminding method combined with the user driving intention, which comprises the following steps:
the image acquisition module is used for acquiring and acquiring pictures with traffic lights in front of the vehicle in real time;
the image intercepting module is used for intercepting an area above the picture to be used as a detection area;
the traffic light detection module is used for marking the traffic light position in the detection area image intercepted by the image interception module, and detecting and acquiring traffic light information of the motor vehicle lane;
the target filtering module is used for filtering the background target and the false detection target of the traffic light information acquired by the traffic light detection module;
the traffic light identification module is used for identifying the type of the traffic light, the color of the traffic light and the number and the color of the countdown light in the traffic light information filtered and processed by the target filtering module, and identifying the corresponding position information of the traffic light and the countdown light;
the matching module is used for performing real-time scene matching on the information of the traffic lights and the countdown lights identified by the traffic light identification module so as to obtain the residual duration of the traffic lights in all directions;
the navigation module is used for judging the driving intention of the vehicle;
the post-processing module is used for obtaining traffic light instruction information to be followed by the vehicle in the running state according to the information of the matching module and the navigation module;
the vehicle-mounted display module is used for displaying the traffic light instruction information obtained by the post-processing module;
and the voice broadcasting module is used for carrying out voice broadcasting on the traffic light instruction information obtained by the post-processing module.
The invention further provides an automobile, which adopts the traffic light reminding method combining the user driving intention.
Compared with the prior art, the invention has the following advantages:
1. according to the invention, the traffic light image data captured by the camera in the driving process is classified, the traffic light state and the corresponding residual time length are identified, and the traffic information reminding of the direction to be driven is given to the user by combining the vehicle navigation and steering information, so that the problems of road congestion, traffic safety hidden danger and the like caused by distraction or lack of attention of the red light information when the traffic light is switched are prevented, and meanwhile, the cabin interaction mode is more intelligent and more friendly.
2. According to the invention, on the basis of independently identifying the basic traffic light state and the residual time without adding additional hardware devices, the signal light identification and reminding which are actually observed by the user are given by combining the user navigation information and the vehicle turn light information, and meanwhile, the signal light state and the second number are intelligently matched according to the signal light color and the position, so that the user is reminded of the residual waiting time.
Drawings
FIG. 1 is a flow chart of a traffic light reminding method combining with the user driving intention;
fig. 2 is a system block diagram of the traffic light reminding system combining with the user driving intention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
As shown in fig. 1, a traffic light reminding method combined with a user driving intention comprises the following steps:
step 1), acquiring and acquiring pictures with traffic lights in front of the running of a vehicle in real time;
step 2) taking the area, above the picture in the step 1), as a detection area, and intercepting an image of the detection area as an image input for traffic light detection;
step 3) marking the position of the traffic light in the image of the detection area in the step 2) by using a detection frame, and detecting and acquiring traffic light information of the motor vehicle lane;
step 4) filtering the background target and the false detection target from the traffic light information obtained in the step 3);
step 5) identifying the type of the traffic light, the color of the traffic light and the number and the color of the countdown light in the traffic light information subjected to the filtering treatment in the step 4);
step 6) respectively outputting corresponding position information of the traffic light and the countdown light according to the position of the detection frame in the step 3);
step 7) carrying out real-time scene matching on the traffic light information obtained in the step 5) and the step 6) and the countdown light information to obtain the residual duration of the traffic lights in all directions;
step 8) acquiring vehicle navigation information or turn signal information to judge the running intention of the vehicle;
step 9), according to the remaining duration of the traffic lights in all directions obtained in the step 7), combining the vehicle driving intention obtained in the step 8) to obtain traffic light instruction information to be followed by the vehicle in the driving state;
step 10), outputting traffic light instruction information to be followed by the vehicle obtained in the step 9) in the running state;
step 11) ends.
The working principle of the invention is as follows: in the scheme, in the running process of a vehicle, a picture with a traffic light in front of the vehicle is acquired and acquired in real time, according to the characteristic that the traffic light is generally installed above, an area, close to the picture, is taken as a detection area of a traffic light image, then the position of the traffic light in the detection area is marked by utilizing a detection frame, the traffic light information of a motor vehicle lane is acquired, the accuracy of a subsequent identification result is ensured by carrying out filtering processing on a background target and a false detection target on the acquired traffic light information of the motor vehicle lane, then the type, the color and the number and the color of a countdown light in the filtered traffic light information are identified, the corresponding position information of the traffic light and the countdown light is respectively output according to the position of the detection frame, the residual duration information of the traffic light in all directions can be obtained by carrying out real-time scene matching on the traffic light information and the countdown light information, then the running intention of the vehicle is judged by the navigation information or the turn light information of the vehicle, the instruction information of the traffic light in the running intention of the vehicle is obtained, and finally the purpose of reminding a user of the traffic light is achieved by outputting the obtained traffic light instruction information in the running intention direction. Therefore, the scheme can give the traffic information reminding of the direction to be driven to the user according to the driving intention of the vehicle, and the problems of road congestion, traffic safety hidden danger and the like caused by distraction or unnoticed red light information when the traffic light is switched are prevented.
In this embodiment, in step 1), a road video in the forward direction of the vehicle is acquired in real time by a camera installed in front of a rearview mirror in the vehicle, an RGB picture of one frame is acquired for the acquired road video in a frame-extracting manner, and distortion correction processing is performed on the acquired RGB picture as an input of a subsequent step.
In the embodiment, in step 2), the vanishing point is detected through graying processing, the area above the horizontal line where the vanishing point is located is taken as the detection area, and the image of the part of the detection area is intercepted to be taken as the image input of traffic light detection, so that the calculated amount is reduced and the false detection rate is reduced.
In the embodiment, in step 3), a traffic light detection model is set, parameters of the traffic light detection model are adjusted by using training data, and training of the traffic light detection model is completed iteratively;
inputting the image in the step 2) into a traffic light detection model, detecting traffic light information (including indicator lights and seconds) of a motor vehicle lane in the traffic light detection model through a real-time target detection network (in the specific embodiment, YOLO V5 is selected as the real-time target detection network), outputting a detection frame, marking the traffic light detection frame in the input image in the image by the traffic light detection model, outputting the target position of the detection frame, and otherwise, reacquiring road data for detection.
In this embodiment, in step 4), background traffic lights, background targets such as vehicle indicator lights, and false detection targets obtained in step 3) are filtered out, so as to ensure accuracy of subsequent recognition results, and the filtered detection targets are input into step 5) for recognition.
In the embodiment, in step 5), a traffic light identification model is constructed through a Convolutional Neural Network (CNN), and the traffic light type, the traffic light color and the countdown light color in the traffic light information after the filtering processing in step 4) are identified through the traffic light identification model, wherein the traffic light type specifically comprises signals such as a straight arrow, a left-turn arrow, a right-turn arrow, a turning around, a disc, a number and the like, and the traffic light color and the countdown light color comprise red and green;
the number of the countdown light is recognized by Optical Character Recognition (OCR).
In the embodiment, in step 7), when only one group of traffic lights and the countdown lights have the same color, determining that the number of the countdown light indicates the remaining duration of the traffic lights;
when the colors of the traffic lights and the countdown lights are consistent, judging that the group with the nearest relative position is the actual matching condition according to the positions of the traffic lights and the countdown lights output in the step 6) so as to obtain the residual duration of the traffic lights in all directions.
In the embodiment, in step 8), vehicle navigation information and turn signal information are obtained through internet of vehicles data, and when the vehicle has navigation information, the driving intention of the vehicle is judged according to the navigation information, such as the vehicle is about to turn left/turn right/go straight/drop head; when the vehicle does not have navigation information, the running intention of the vehicle is judged according to the information of the vehicle steering lamp, such as the left steering lamp/right steering lamp/no steering lamp of the vehicle, and the running intention of the vehicle is judged according to the information.
In this embodiment, in step 9), the vehicle driving intention information in step 8) and the traffic light and remaining time information in each direction in step 7) are combined, and matching is performed through post-processing, when the vehicle navigation information or the turn light signal is left turn and there is a left turn signal light in the traffic light identification result, the left turn traffic light state and the count-down seconds (such as count-down) are output, otherwise, the corresponding information of the traffic light is output, and similarly, the result output post-processing rule can be formulated, and finally the traffic light result instruction to be followed in the driving state of the vehicle is output, including type, color and count-down.
In this embodiment, in step 10), the traffic light instruction information is output to the vehicle machine of the vehicle for displaying, and the traffic light instruction information is voice-broadcast, for example, the prompting information in step 9) is displayed on the vehicle machine, for example, the user is prompted to notice the green light (or red light), please notice the traffic, and the user is reminded to be able to pass after 5 seconds are predicted (stop after 5 seconds are predicted, etc.), and simultaneously, the voice broadcast is performed, and the prompt tone is waited for reminding.
As shown in fig. 2, the present invention further provides a system for implementing the traffic light reminding method combined with the user driving intention, which includes:
the image acquisition module is used for acquiring and acquiring pictures with traffic lights in front of the vehicle in real time;
the image intercepting module is used for intercepting an area above the picture to be used as a detection area;
the traffic light detection module is used for marking the traffic light position in the detection area image intercepted by the image interception module, and detecting and acquiring traffic light information of the motor vehicle lane;
the target filtering module is used for filtering the background target and the false detection target of the traffic light information acquired by the traffic light detection module;
the traffic light identification module is used for identifying the type of the traffic light, the color of the traffic light and the number and the color of the countdown light in the traffic light information filtered and processed by the target filtering module, and identifying the corresponding position information of the traffic light and the countdown light;
the matching module is used for performing real-time scene matching on the information of the traffic lights and the countdown lights identified by the traffic light identification module so as to obtain the residual duration of the traffic lights in all directions;
the navigation module is used for judging the driving intention of the vehicle;
the post-processing module is used for obtaining traffic light instruction information to be followed by the vehicle in the running state according to the information of the matching module and the navigation module;
the vehicle display module is used for displaying the traffic light instruction information obtained by the post-processing module;
and the voice broadcasting module is used for voice broadcasting the traffic light instruction information obtained by the post-processing module.
The invention further provides an automobile, which adopts the traffic light reminding method combining the user driving intention.
Compared with the prior art, the traffic light information prompting method based on the traffic light image data has the advantages that the traffic light image data captured by the camera in the driving process are classified, the traffic light state and the corresponding residual duration are identified, the vehicle navigation and steering information are combined, the traffic information prompting of the direction to be driven is given to the user, the problems that the traffic light information is distracted or not noticed by the user when the traffic light is switched to cause road congestion, potential traffic safety hazards and the like are prevented, and meanwhile, the cabin interaction mode is intelligent and friendly. According to the invention, on the basis of independently identifying the basic traffic light state and the residual time without adding additional hardware devices, the signal light identification and reminding which are actually observed by the user are given by combining the user navigation information and the vehicle turn light information, and meanwhile, the signal light state and the second number are intelligently matched according to the signal light color and the position, so that the user is reminded of the residual waiting time.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the technical solution, and those skilled in the art should understand that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the present invention, and all such modifications and equivalents are included in the scope of the claims.
Claims (6)
1. The red and green lamp reminding method combined with the user driving intention is characterized by comprising the following steps of:
step 1), acquiring and acquiring pictures with traffic lights in front of the running of a vehicle in real time;
step 2) taking the area, above the picture in the step 1), as a detection area, and intercepting an image of the detection area as an image input for traffic light detection;
step 3) marking the position of the traffic light in the image of the detection area in the step 2) by using a detection frame, and detecting and acquiring traffic light information of the motor vehicle lane;
step 4) filtering the background target and the false detection target from the traffic light information obtained in the step 3);
step 5) identifying the type of the traffic light, the color of the traffic light and the number and the color of the countdown light in the traffic light information subjected to the filtering treatment in the step 4);
step 6) respectively outputting corresponding position information of the traffic light and the countdown light according to the position of the detection frame in the step 3);
step 7) carrying out real-time scene matching on the traffic light information obtained in the step 5) and the step 6) and the countdown light information to obtain the residual duration of the traffic lights in all directions;
step 8) acquiring vehicle navigation information or turn signal information to judge the running intention of the vehicle;
step 9), according to the remaining duration of the traffic lights in all directions obtained in the step 7), combining the vehicle driving intention obtained in the step 8) to obtain traffic light instruction information to be followed by the vehicle in a driving state;
step 10), outputting traffic light instruction information to be followed by the vehicle obtained in the step 9) in the running state;
ending the step 11);
in the step 1), a road video in the advancing direction of a vehicle is obtained in real time through a camera arranged on the vehicle, a frame-by-frame picture is obtained from the obtained road video in a frame extraction mode, and distortion correction processing is carried out on the obtained picture;
in the step 3), a traffic light detection model is set, parameters of the traffic light detection model are adjusted by using training data, and training of the traffic light detection model is completed in an iteration mode;
inputting the image in the step 2) into a traffic light detection model, detecting traffic light information of a motor vehicle lane in the traffic light detection model through a real-time target detection network, outputting a detection frame, marking the traffic light detection frame in the input image in the image by the traffic light detection model, and outputting a target position of the detection frame;
in the step 5), a traffic light identification model is built through a convolutional neural network, and the traffic light type, the traffic light color and the countdown light color in the traffic light information subjected to filtering in the step 4) are identified through the traffic light identification model;
identifying the number of the countdown lamp by an optical character identification technology;
in the step 7), when only one group of traffic lights is consistent with the countdown lights in color, judging that the number of the countdown lights represents the residual duration of the traffic lights;
when the colors of the traffic lights and the countdown lights are consistent, judging that the group with the nearest relative position is the actual matching condition according to the positions of the traffic lights and the countdown lights output in the step 6) so as to obtain the residual duration of the traffic lights in all directions.
2. The method according to claim 1, wherein in step 2), the vanishing point is detected by graying processing, and a region above a horizontal line where the vanishing point is located is taken as a detection region.
3. The method for reminding a user of a driving intention by a red and green lamp according to claim 1, wherein in the step 8), when the vehicle has navigation information, the driving intention of the vehicle is judged according to the navigation information; when the vehicle has no navigation information, the driving intention of the vehicle is judged according to the information of the vehicle turn signal lamp.
4. The method for reminding a user of a traffic light according to claim 1, wherein in step 10), traffic light instruction information is output to a vehicle body of a vehicle to be displayed, and the traffic light instruction information is voice-broadcast.
5. A system for implementing the traffic light reminding method according to claim 1 and combined with the user's driving intention, comprising:
the image acquisition module is used for acquiring and acquiring pictures with traffic lights in front of the vehicle in real time;
the image intercepting module is used for intercepting an area above the picture to be used as a detection area;
the traffic light detection module is used for marking the traffic light position in the detection area image intercepted by the image interception module, and detecting and acquiring traffic light information of the motor vehicle lane;
the target filtering module is used for filtering the background target and the false detection target of the traffic light information acquired by the traffic light detection module;
the traffic light identification module is used for identifying the type of the traffic light, the color of the traffic light and the number and the color of the countdown light in the traffic light information filtered and processed by the target filtering module, and identifying the corresponding position information of the traffic light and the countdown light;
the matching module is used for performing real-time scene matching on the information of the traffic lights and the countdown lights identified by the traffic light identification module so as to obtain the residual duration of the traffic lights in all directions;
the navigation module is used for judging the driving intention of the vehicle;
the post-processing module is used for obtaining traffic light instruction information to be followed by the vehicle in the running state according to the information of the matching module and the navigation module;
the vehicle-mounted display module is used for displaying the traffic light instruction information obtained by the post-processing module;
and the voice broadcasting module is used for carrying out voice broadcasting on the traffic light instruction information obtained by the post-processing module.
6. An automobile, characterized in that a traffic light reminding method according to any one of claims 1 to 5 combined with the user's intention is adopted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210158508.9A CN114475429B (en) | 2022-02-21 | 2022-02-21 | Traffic light reminding method and system combined with user driving intention and automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210158508.9A CN114475429B (en) | 2022-02-21 | 2022-02-21 | Traffic light reminding method and system combined with user driving intention and automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114475429A CN114475429A (en) | 2022-05-13 |
| CN114475429B true CN114475429B (en) | 2024-03-22 |
Family
ID=81482432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210158508.9A Active CN114475429B (en) | 2022-02-21 | 2022-02-21 | Traffic light reminding method and system combined with user driving intention and automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114475429B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115465295B (en) * | 2022-09-14 | 2024-07-23 | 重庆长安汽车股份有限公司 | Method and device for predicting future track of intersection vehicle, vehicle and storage medium |
| CN115752441B (en) * | 2022-11-25 | 2024-09-13 | 重庆长安汽车股份有限公司 | Traffic light construction method for high-precision map |
| CN118736870A (en) * | 2024-09-02 | 2024-10-01 | 安徽蔚来智驾科技有限公司 | Traffic light countdown timing sequence tracking reporting method, storage medium and intelligent device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107826036A (en) * | 2017-01-26 | 2018-03-23 | 问众智能信息科技（北京）有限公司 | Automobile intelligent auxiliary drives traffic lights safety prompt function method |
| CN108734976A (en) * | 2018-05-28 | 2018-11-02 | 汤庆佳 | A kind of communication navigation reminding method and its system |
| WO2018201835A1 (en) * | 2017-05-03 | 2018-11-08 | 腾讯科技（深圳）有限公司 | Signal light state recognition method, device and vehicle-mounted control terminal and motor vehicle |
| WO2020098004A1 (en) * | 2018-11-13 | 2020-05-22 | 惠州市德赛西威汽车电子股份有限公司 | Lane traffic status reminder method and device |
| CN111862635A (en) * | 2020-02-28 | 2020-10-30 | 重庆长安汽车股份有限公司 | Traffic signal lamp-based vehicle speed control method and device and automobile |
| CN112580571A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Vehicle running control method and device and electronic equipment |
| CN113212300A (en) * | 2021-05-10 | 2021-08-06 | 首约科技(北京)有限公司 | Vehicle-mounted traffic light identification system |
| CN113781808A (en) * | 2021-08-30 | 2021-12-10 | 东风汽车集团股份有限公司 | Method and system for passing internet-connected automatic driving vehicle at traffic light intersection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665719A (en) * | 2017-03-28 | 2018-10-16 | 比亚迪股份有限公司 | Traffic lights based reminding method, device and vehicle |
-
2022
- 2022-02-21 CN CN202210158508.9A patent/CN114475429B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107826036A (en) * | 2017-01-26 | 2018-03-23 | 问众智能信息科技（北京）有限公司 | Automobile intelligent auxiliary drives traffic lights safety prompt function method |
| WO2018201835A1 (en) * | 2017-05-03 | 2018-11-08 | 腾讯科技（深圳）有限公司 | Signal light state recognition method, device and vehicle-mounted control terminal and motor vehicle |
| CN108734976A (en) * | 2018-05-28 | 2018-11-02 | 汤庆佳 | A kind of communication navigation reminding method and its system |
| WO2020098004A1 (en) * | 2018-11-13 | 2020-05-22 | 惠州市德赛西威汽车电子股份有限公司 | Lane traffic status reminder method and device |
| CN111862635A (en) * | 2020-02-28 | 2020-10-30 | 重庆长安汽车股份有限公司 | Traffic signal lamp-based vehicle speed control method and device and automobile |
| CN112580571A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Vehicle running control method and device and electronic equipment |
| CN113212300A (en) * | 2021-05-10 | 2021-08-06 | 首约科技(北京)有限公司 | Vehicle-mounted traffic light identification system |
| CN113781808A (en) * | 2021-08-30 | 2021-12-10 | 东风汽车集团股份有限公司 | Method and system for passing internet-connected automatic driving vehicle at traffic light intersection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114475429A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114475429B (en) | Traffic light reminding method and system combined with user driving intention and automobile | |
| CN105825696B (en) | Drive assist system based on signal information prompting | |
| US10322674B2 (en) | Display control method and display control device | |
| JP5198835B2 (en) | Method and system for presenting video images | |
| US10887568B2 (en) | Image processing apparatus, and image processing method | |
| CN104875681A (en) | Dynamic vehicle-mounted camera control method based on application scenarios | |
| EP3518205A1 (en) | Vehicle control device, vehicle control method, and moving body | |
| US9227563B2 (en) | Backward movement indicator apparatus for a vehicle | |
| CN106985819B (en) | Method and device for judging vehicle driving intention | |
| EP3517384B1 (en) | Vehicle control device, vehicle control method, and moving body | |
| CN108482367B (en) | Method, device and system for assisting driving based on intelligent rearview mirror | |
| CN104842874A (en) | Emergency Vehicle Detection Using Digital Image Sensors | |
| CN107972674A (en) | It is a kind of to merge navigation and the drive assist system and method for intelligent vision | |
| CN110533945B (en) | Early warning method and system of traffic signal lamp, vehicle and storage medium | |
| US20230174091A1 (en) | Motor-vehicle driving assistance in low meteorological visibility conditions, in particular with fog | |
| JP4984844B2 (en) | Merge guidance apparatus and merge guidance method | |
| KR101601500B1 (en) | System and Method for assisting vehicle driving for using smartphone | |
| JP4986070B2 (en) | Ambient monitoring device for vehicles | |
| CN114582146A (en) | Traffic light remaining duration intelligent reminding method and system, storage medium and automobile | |
| CN109987025B (en) | Vehicle driving assistance system and method for night environment | |
| US11548505B2 (en) | Vehicular speed control system with automatic setting parameters | |
| CN112406705B (en) | Vehicle-mounted panoramic radar monitoring system | |
| US11052822B2 (en) | Vehicle control apparatus, control method, and storage medium for storing program | |
| JPH01281600A (en) | Traveling vehicle recognizing device | |
| CN115447600B (en) | Vehicle anti-congestion method based on deep learning, controller and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |