Traffic light prompting method and device, vehicle and medium
By acquiring traffic light signals and recognizing driver intentions, and combining image recognition and machine learning technologies, the accuracy and positioning issues of traffic light recognition in autonomous driving have been solved, thereby improving driving safety and user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2026-03-24
AI Technical Summary
In Level 2 and below autonomous driving, the lack of high-precision map assistance leads to a decrease in the accuracy and reliability of traffic light recognition, environmental interference and the diversity of traffic lights increase the difficulty of recognition, and the lack of accurate positioning affects the judgment of traffic signals.
By acquiring traffic light signals in the direction of vehicle travel, identifying the signal type of each light and the driver's driving intention, and combining advanced image recognition and machine learning technologies, the traffic light status is fed back in real time to guide drivers to comply with traffic rules.
It improves the accuracy of traffic light signal recognition, reduces the risk of accidents, enhances driving safety and user experience, and optimizes traffic flow management.
Smart Images

Figure CN121725652A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of traffic light technology, and in particular to a traffic light prompting method, device, vehicle, and medium. Background Technology
[0002] In Level 2 and lower autonomous driving projects, given the lack of high-precision maps to assist in traffic light signal recognition, forward-facing cameras have become a key technology for identifying traffic signals. However, this technology often encounters multiple challenges in practical applications, including complex and variable weather conditions, fluctuations in light intensity, and occlusion by potential obstacles, all of which significantly reduce the accuracy and reliability of traffic light recognition.
[0003] Due to the diversity of traffic light designs—the positions, shapes, and numbers of straight, left-turn, and right-turn indicators vary—accurately distinguishing the direction of travel indicated by the current red light using only visual recognition technology is particularly difficult. Furthermore, the lack of high-precision map data support prevents vehicles from accurately locating themselves, thus hindering the precise matching of the recognized traffic light status with the vehicle's current lane. This undoubtedly exacerbates the decision-making complexity of autonomous driving systems when encountering traffic lights. Summary of the Invention
[0004] This application provides a traffic light prompting method, device, vehicle, and medium to solve problems in the prior art such as decreased recognition accuracy caused by environmental interference, the diversity of traffic lights and the lack of unified standards, and the impact of lack of precise positioning on traffic signal judgment.
[0005] The first aspect of this application provides a traffic light prompting method, including the following steps: acquiring traffic light signals in the direction of vehicle travel; identifying the signal type of each light in the traffic light signal and identifying the driver's driving intention; and providing traffic light prompts based on the signal type of each light and the driving intention.
[0006] Optionally, traffic light prompts can be provided based on the signal type and driving intention of each light, including: determining the target signal type that matches the driving intention; and displaying the current status of the light corresponding to the target signal type on the vehicle.
[0007] Optionally, the signal type includes at least one of left turn type, straight-ahead type and right turn type, and the driving intention includes at least one of left turn intention, straight-ahead intention and right turn intention.
[0008] Optionally, identifying the driver's driving intention includes: acquiring a turn signal, a steering wheel angle signal, and a vehicle yaw rate signal; and determining the driver's driving intention based on at least one of the turn signal, the steering wheel angle signal, and the vehicle yaw rate signal.
[0009] Optionally, identifying the signal type of each light in the traffic light signal includes: identifying the position of each light in the traffic light; and identifying the signal type of each light in the traffic light signal based on the position of each light in the traffic light.
[0010] Optionally, after identifying the signal type of each light in the traffic light signal based on the position of each light in the traffic light, the method includes: identifying the driver's intention to modify, and correcting the signal type of each light in the traffic light signal according to the driver's intention to modify.
[0011] Optionally, acquiring traffic light signals in the direction of vehicle travel includes: recognizing an image in front of the vehicle; and determining the traffic light signals in the direction of vehicle travel based on the image in front of the vehicle.
[0012] A second aspect of this application provides a traffic light prompting device, comprising: an acquisition module for acquiring traffic light signals in the direction of vehicle travel; an identification module for identifying the signal type of each light in the traffic light signals and identifying the driver's driving intention; and a prompting module for providing traffic light prompts based on the signal type of each light and the driving intention.
[0013] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the traffic light prompting method as described in the above embodiments.
[0014] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the traffic light prompting method as described in the above embodiments.
[0015] Therefore, this application has at least the following beneficial effects:
[0016] This application's embodiments accurately acquire traffic light signals and identify driver intentions, predicting driving operations in advance, reducing accident risks, and improving driving safety and user experience. Advanced image recognition and machine learning technologies are employed to ensure accurate traffic light signal recognition, and a real-time feedback mechanism guides drivers to comply with traffic rules. This solves the technical problems in existing technologies, such as decreased recognition accuracy due to environmental interference, the diversity of traffic lights, and the lack of unified standards, as well as the impact of insufficient precise positioning on traffic signal judgment.
[0017] Additional aspects and advantages of this 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 this application. Attached Figure Description
[0018] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:
[0019] Figure 1 This is a flowchart of a traffic light prompting method provided according to an embodiment of this application;
[0020] Figure 2 This is an example diagram of a traffic light warning device according to an embodiment of this application;
[0021] Figure 3 This is a structural schematic diagram of a vehicle according to an embodiment of this application. Detailed Implementation
[0022] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0023] The following description, with reference to the accompanying drawings, outlines a traffic light prompting method, apparatus, vehicle, and medium according to embodiments of this application. Addressing the problem of inaccurate traffic light recognition mentioned in the background section, this application provides a traffic light prompting method. This method accurately acquires traffic light signals and identifies the driver's driving intentions, predicting driving operations in advance, reducing accident risks, and improving driving safety and user experience. Advanced image recognition and machine learning technologies are employed to ensure accurate traffic light signal recognition, and a real-time feedback mechanism guides drivers to comply with traffic rules. This solves the problems in the prior art, such as decreased recognition accuracy due to environmental interference, the diversity of traffic lights, and the lack of unified standards, as well as the impact of insufficient precise positioning on traffic signal judgment.
[0024] Specifically, Figure 1 This is a flowchart illustrating the traffic light prompting method provided in an embodiment of this application.
[0025] like Figure 1 As shown, the traffic light prompting method includes the following steps:
[0026] In step S101, the traffic light signal in the vehicle's direction of travel is acquired.
[0027] Traffic light signals can be used to control the passage of vehicles and pedestrians.
[0028] It is understood that by acquiring the traffic light signal in the direction of vehicle travel in real time, the embodiments of this application can ensure that the driver is aware of the status of the traffic lights when approaching an intersection, so as to make the correct driving decision.
[0029] In this embodiment of the application, obtaining the traffic light signal in the direction of vehicle travel includes: identifying an image in front of the vehicle; and determining the traffic light signal in the direction of vehicle travel based on the image in front of the vehicle.
[0030] It is understood that the embodiments of this application determine the traffic light signal for driving direction by recognizing the image in front of the vehicle, providing key environmental perception capabilities for driving assistance and autonomous driving systems, and enhancing driving safety and convenience.
[0031] Specifically, using a forward-facing camera combined with traffic light signal information from a navigation map can significantly improve the accuracy of traffic light signal recognition. By combining the advantages of visual perception and map data, the confidence level of the forward-facing camera and navigation map signals can be flexibly adjusted in different scenarios, thereby more accurately identifying traffic light signals in the vehicle's direction of travel.
[0032] In step S102, the signal type of each light in the traffic light signal is identified, and the driver's driving intention is identified.
[0033] The signal type may include at least one of left turn type, straight type and right turn type, and the driving intention may include at least one of left turn intention, straight intention and right turn intention.
[0034] It is understood that the embodiments of this application provide corresponding driving assistance by accurately identifying the type of traffic light signal and the driver's driving intention, thereby improving the driver's driving experience and sense of security and optimizing traffic flow management.
[0035] In this embodiment of the application, identifying the driver's driving intention includes: acquiring a turn signal, a steering wheel angle signal, and a vehicle yaw rate signal; and determining the driver's driving intention based on at least one of the turn signal, the steering wheel angle signal, and the vehicle yaw rate signal.
[0036] Among them, the steering wheel angle signal can be the signal of the current rotation angle of the steering wheel, and the vehicle yaw rate signal can be the signal measured and generated by the yaw rate sensor on the vehicle.
[0037] It is understood that the embodiments of this application accurately determine the driver's driving intention by acquiring and analyzing turn signal, steering wheel angle and vehicle yaw rate signals, thereby improving driving safety and assistance capabilities, optimizing vehicle control, promoting the development of autonomous driving technology, enhancing user experience and promoting compliance with traffic rules.
[0038] For example, if the driver's driving intention is determined solely based on the turn signal: when the driver prepares to change lanes from the current lane to the right lane, the driver operates the turn signal switch, illuminating the right turn signal. Upon detecting the right turn signal, the driver's intention to change lanes to the right is immediately recognized;
[0039] If the driver's driving intention is determined by combining the steering wheel angle signal: When a driver is preparing to enter a ramp on a highway, slows down and turns right, the driver will turn on the right turn signal and turn the steering wheel to the right. When the change in the steering wheel angle signal and the turn signal are detected, it becomes more certain that the driver intends to turn right.
[0040] If multiple signals are combined to determine the driver's driving intention: When the driver is preparing to turn left at a complex intersection, the driver first turns on the left turn signal and turns the steering wheel to the left. As the steering action exceeds the set threshold, the vehicle's yaw rate also begins to increase significantly, thus indicating that the driver intends to turn left.
[0041] Determining Driver Intent Without Turn Signal: A driver approaches an intersection with a green traffic light, indicating passage is permitted. The driver intends to turn left but forgets to activate their turn signal. First, the camera detects the green light signal and continuously monitors it. Then, it detects that the steering wheel has turned left beyond a set threshold, and the yaw rate also indicates the vehicle is veering left. Even without a left turn signal, the system determines the driver's intention to turn left and displays a green left-turn arrow and warning message on the instrument panel, alerting the driver to traffic conditions. This provides necessary assistance and warnings even if the driver forgets to use their turn signal, ensuring driving safety.
[0042] In this embodiment of the application, identifying the signal type of each light in the traffic light signal includes: identifying the position of each light in the traffic light; and identifying the signal type of each light in the traffic light signal based on the position of each light in the traffic light.
[0043] It is understood that the embodiments of this application identify the signal type of each light in the traffic light signal based on the position of each light in the traffic light, so as to understand the current traffic light changes in real time, avoid traffic violations, and significantly improve driving safety.
[0044] In this embodiment of the application, after identifying the signal type of each light in the traffic light signal according to the position of each light in the traffic light, the method includes: identifying the driver's modification intention, and correcting the signal type of each light in the traffic light signal according to the driver's modification intention.
[0045] The driver's intention to modify the signal can be the driver's desire or need to adjust or correct the current traffic light signal status based on the current traffic conditions, personal judgment, or system prompts during the driving process, in order to deal with special situations such as traffic light misjudgment.
[0046] It is understood that the embodiments of this application improve driving flexibility and safety and enhance traffic management efficiency by recognizing the driver's intention to modify traffic signals and correcting them in real time.
[0047] Specifically, if a driver notices an error in a traffic light signal while driving, such as a misjudgment of a red light, they can send a modification request through the onboard device. After receiving and verifying the request, the intelligent traffic light system will assess the situation based on real-time traffic conditions. If the system confirms that the error is correct and safe, it will immediately correct the traffic light signal type, such as changing the red light to a green light, to improve driving flexibility and safety.
[0048] In step S103, traffic light prompts are given according to the signal type and driving intention of each light.
[0049] It is understood that the embodiments of this application can provide drivers with accurate traffic light status information in real time by recognizing the signal type of traffic lights in real time and combining it with the driving intention of vehicles. This helps drivers make correct judgments quickly in complex and ever-changing traffic environments. By adjusting the duration or sequence of traffic light signals, traffic flow distribution can be optimized, congestion and waiting time can be reduced, and traffic efficiency can be improved.
[0050] In this embodiment of the application, traffic light prompts are provided based on the signal type of each light and the driving intention, including: determining the target signal type that matches the driving intention; and displaying the current status of the light corresponding to the target signal type on the vehicle.
[0051] The current state of the light corresponding to the target signal type can be red, green, or yellow, etc.
[0052] It is understood that the embodiments of this application provide precise driving decision support by identifying the driver's driving intention and matching the target signal type, thereby improving driving safety and rationality. Simultaneously, real-time display of traffic light status enhances traffic information transparency and optimizes the driving experience and route planning.
[0053] The traffic light prompting method proposed in this application accurately acquires traffic light signals and identifies the driver's driving intentions, predicting driving operations in advance, reducing accident risks, and improving driving safety and user experience. It employs advanced image recognition and machine learning technologies to ensure accurate recognition of traffic light signals and guides drivers to comply with traffic rules through a real-time feedback mechanism. This solves the problems in existing technologies, such as decreased recognition accuracy due to environmental interference, the diversity of traffic lights, and the lack of unified standards, as well as the impact of insufficient precise positioning on traffic signal judgment.
[0054] Next, the traffic light prompting device according to the embodiments of this application is described with reference to the accompanying drawings.
[0055] Figure 2 This is a block diagram of a traffic light warning device according to an embodiment of this application.
[0056] like Figure 2As shown, the traffic light warning device 10 includes: an acquisition module 100, an identification module 200, and a warning module 300.
[0057] The acquisition module 100 is used to acquire traffic light signals in the direction of vehicle travel; the identification module 200 is used to identify the signal type of each light in the traffic light signal and identify the driver's driving intention; and the prompting module 300 is used to provide traffic light prompts based on the signal type of each light and the driving intention.
[0058] It should be noted that the foregoing explanation of the traffic light prompting method embodiment also applies to the traffic light prompting device of this embodiment, and will not be repeated here.
[0059] The traffic light warning device proposed in this application accurately acquires traffic light signals and identifies the driver's driving intentions, predicting driving operations in advance, reducing accident risks, and improving driving safety and user experience. It employs advanced image recognition and machine learning technologies to ensure accurate recognition of traffic light signals and guides drivers to comply with traffic rules through a real-time feedback mechanism. This solves the problems in existing technologies, such as decreased recognition accuracy due to environmental interference, the diversity of traffic lights, and the lack of unified standards, as well as the impact of insufficient precise positioning on traffic signal judgment.
[0060] Figure 3 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:
[0061] The memory 301, the processor 302, and the computer program stored on the memory 301 and capable of running on the processor 302.
[0062] When the processor 302 executes the program, it implements the traffic light prompting method provided in the above embodiments.
[0063] Furthermore, the vehicle also includes:
[0064] Communication interface 303 is used for communication between memory 301 and processor 302.
[0065] The memory 301 is used to store computer programs that can run on the processor 302.
[0066] The memory 301 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.
[0067] If the memory 301, processor 302, and communication interface 303 are implemented independently, then the communication interface 303, memory 301, and processor 302 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0068] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.
[0069] Processor 302 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.
[0070] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the traffic light prompting method described above.
[0071] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0072] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0073] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0074] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.
[0075] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.
[0076] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.
Claims
1. A traffic light prompting method, characterized in that, Includes the following steps: Obtain traffic light signals indicating the direction of vehicle travel; Identify the signal type of each light in the traffic light signals and identify the driver's driving intention; Traffic light prompts are provided based on the signal type of each light and the driving intention.
2. The traffic light prompting method according to claim 1, characterized in that, The step of providing traffic light prompts based on the signal type of each light and the driving intention includes: Determine the target signal type that matches the driving intention; The current status of the light corresponding to the target signal type is displayed on the vehicle.
3. The traffic light prompting method according to claim 1 or 2, characterized in that, The signal type includes at least one of left turn type, straight type and right turn type, and the driving intention includes at least one of left turn intention, straight intention and right turn intention.
4. The traffic light prompting method according to claim 1, characterized in that, The process of identifying the driver's driving intention includes: Acquire turn signal, steering wheel angle signal, and vehicle yaw rate signal; The driver's driving intention is determined based on at least one of the turn signal signal, the steering wheel angle signal, and the vehicle yaw rate signal.
5. The traffic light prompting method according to claim 1, characterized in that, The identification of the signal type of each light in the traffic light signals includes: Identify the position of each light in the traffic light system; The signal type of each light in the traffic light signal is identified based on the position of each light in the traffic light.
6. The traffic light prompting method according to claim 5, after identifying the signal type of each light in the traffic light signal based on the position of each light in the traffic light, includes: Identify the driver's intention to modify the signal, and adjust the signal type of each light in the traffic light signal accordingly.
7. The traffic light prompting method according to claim 1, characterized in that, The acquisition of traffic light signals indicating the vehicle's direction of travel includes: Identify the image in front of the vehicle; Traffic light signals that determine the vehicle's direction of travel based on an image of what's in front of the vehicle.
8. A traffic light warning device, characterized in that, include: The acquisition module is used to acquire traffic light signals indicating the direction of vehicle travel; The identification module is used to identify the signal type of each light in the traffic light signal and to identify the driver's driving intention; The prompt module is used to provide traffic light prompts based on the signal type of each light and the driving intention.
9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the traffic light prompting method as described in any one of claims 1-7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the traffic light prompting method as described in any one of claims 1-7.