A target lane traffic light screening method, screening device and computer readable storage medium

Abstract

The present application relates to a kind of target lane traffic light screening method, screening device and computer readable storage medium.The screening method includes: obtaining the signal light traffic light information in front of vehicle, identifies signal light traffic light information to obtain traffic light information, traffic light information is classified to generate the steering set, steering set includes left turn set, straight set and right turn set;According to the whole vehicle signal, the steering intention of driver is judged, steering intention includes left turn intention, straight intention or right turn intention;Based on steering intention, corresponding steering set is selected;According to the steering set selected, current light color is determined, and vehicle operation prompt is given based on current light color.The present application can solve the problem of multiple traffic light signal interference in complex intersection, improve the identification accuracy of target lane traffic light.

Description

Technical Field

[0001] This invention relates to the field of vehicle driver assistance technology, and in particular to a method, device and computer-readable storage medium for selecting target lane traffic lights. Background Technology

[0002] In complex urban intersections, there are often multiple lanes and traffic lights with various functions, such as left-turn arrow lights, straight-ahead arrow lights, right-turn arrow lights, or circular lights. Due to factors such as obstructed vision and driver distraction, drivers are prone to confusing the traffic light signals corresponding to different lanes. If a driver mistakenly interprets the red light of another lane as the signal for their current lane, they may stop when the light turns green, causing following vehicles to urge them on and reducing road efficiency. If a driver mistakenly interprets the red light of their current lane as a green light, they may run a red light, potentially leading to a serious traffic accident.

[0003] In existing vehicle driver assistance systems, the recognition of traffic lights in target lanes relies heavily on the perception results of a single camera. The system does not classify and filter traffic lights in conjunction with the vehicle's driving intention, nor does it arbitrate the validity and confidence of multiple traffic light signals. This makes it difficult to adapt to the multi-traffic light scenarios at complex intersections and fails to meet the driver's needs for traffic light prompts. Summary of the Invention

[0004] To address the aforementioned problems in the prior art, this invention proposes a method, device, and computer-readable storage medium for selecting target lane traffic lights. This method can solve the problem of interference from multiple traffic light signals at complex intersections, improve the accuracy of target lane traffic light identification, and ultimately enhance intersection traffic efficiency and reduce traffic accidents.

[0005] Specifically, this invention proposes a method for selecting target lane traffic lights, comprising the following steps: The system acquires traffic light information ahead of the vehicle, identifies the traffic light information to obtain traffic light information, and classifies the traffic light information to generate a turning set, which includes a left turn set, a straight go set, and a right turn set. The driver's steering intention is determined based on vehicle signals, including intention to turn left, intention to go straight, or intention to turn right. Based on the stated steering intention, the corresponding set of steering options is selected; Based on the selected set of turns, determine the current light color and provide vehicle operation prompts based on the current light color.

[0006] According to one embodiment of the present invention, the traffic light information obtained after identification is filtered according to the verification rules to obtain valid traffic light information, and the valid traffic light information is classified. The verification rules include all of the following conditions: The longitudinal distance between the traffic light and the vehicle is less than the maximum effective longitudinal distance threshold; The lateral distance between the traffic light and the vehicle is less than the maximum effective lateral distance threshold; The ground height of the traffic light is less than the maximum effective height threshold; The confidence level of the traffic light is greater than the minimum confidence threshold; The traffic light color is one of red, yellow, or green.

[0007] According to an embodiment of the present invention, classifying the valid traffic light information includes the following steps: If the valid traffic light information is a traffic light with a left-turn arrow, then the valid traffic light information is included in the left-turn set; If the valid traffic light information is a traffic light with a straight arrow, then the valid traffic light information is included in the straight-ahead set; If the valid traffic light information is a traffic light with a right-turn arrow, then the valid traffic light information is included in the right-turn set; If the valid traffic light information is a circular traffic light, then the valid traffic light information will be classified into the left turn set and the straight-ahead set.

[0008] According to one embodiment of the present invention, the vehicle signals include turn signal on / off status, steering wheel angle, vehicle speed, heading angle, and travel distance; the process of determining the driver's steering intention based on the vehicle signals includes the following steps: S21, determine whether the current lane allows the vehicle to turn left or right. If yes, determine the turning intention as a left turn or right turn based on the direction of the current lane, and proceed to step S27. If no, proceed to the next step. S22, determine whether the turn signal is on. If it is on, determine whether the turning intention is to turn left or right, and proceed to step S27. If it is off, proceed to the next step. S23, determine whether the steering setting conditions are met. If they are met, determine whether the steering intention is to turn left or right and proceed to step S27. If not, proceed to the next step. S24, determine whether the steering cancellation condition is met. If it is met, determine that the steering intention is to go straight and proceed to step S27. If it is not met, proceed to the next step. S25, determine whether the turning completion condition is met. If it is met, determine that the turning intention is to go straight and proceed to step S27. If it is not met, proceed to the next step. S26, determine that the steering intention is the direction of travel of the vehicle prior to the determination process; S27, End of steering intention judgment.

[0009] According to one embodiment of the present invention, the steering setting conditions are: the vehicle speed is greater than a speed threshold, the absolute value of the steering wheel angle is greater than a first angle threshold, and the change value of the heading angle is greater than a second angle threshold. The steering cancellation condition is: within n consecutive cycles, the change in steering wheel angle is greater than the third angle threshold, and the change in heading angle is less than the fourth angle threshold. Or, within n consecutive cycles, the steering wheel angle changes from greater than the fifth angle threshold to less than the sixth angle threshold; The steering completion condition is: within n consecutive cycles, the change value of the heading angle is greater than the seventh angle threshold, and the change value of the steering wheel angle is less than the eighth angle threshold. Or the turning distance exceeds the ninth threshold, and the steering wheel angle is less than the tenth angle threshold within n consecutive cycles; Where n is an integer greater than 2.

[0010] According to one embodiment of the present invention, if the turning intention is to turn left, then the left-turn set in the turning set is selected; if the turning intention is to go straight, then the straight set in the turning set is selected; if the turning intention is to turn right, then the right-turn set in the turning set is selected.

[0011] According to one embodiment of the present invention, the process of determining the current light color based on the selected turn signal set includes: Calculate the overall confidence level of each traffic light within the selected turn set; Count the number of each light color within the selected turn signal set; The current light color is determined based on the quantity and overall confidence level.

[0012] According to one embodiment of the present invention, the formula for calculating the overall confidence level of each traffic light is as follows: ; Where x is the lateral distance between the traffic light and the vehicle; y represents the longitudinal distance between the traffic light and the vehicle. c represents the confidence level of the traffic light; This is the maximum effective lateral distance threshold for this traffic light; This is the maximum effective longitudinal distance threshold for this traffic light; This is the weight value for the lateral distance of the traffic light, and its value is between 0 and 1; This is the weight value for the longitudinal distance of the traffic light, and its value is between 0 and 1; This is the confidence weight value for the traffic light, and its value is between 0 and 1. And satisfy .

[0013] According to one embodiment of the present invention, if there is only one current light color, the turn set with the highest overall confidence is selected and the current light color is output. If there are multiple possible current light colors, the color with the most occurrences is selected as the current light color. The traffic light with the highest overall confidence level is then chosen and the current light color is output.

[0014] The present invention also provides a screening device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the screening method described in any of the preceding claims.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the screening method as described in any of the preceding claims.

[0016] This invention provides a method, device, and computer-readable storage medium for filtering target lane traffic lights, which can solve the problem of interference from multiple traffic light signals in complex intersections and improve the accuracy of target lane traffic light identification. At the same time, by combining vehicle driving intention judgment, it avoids misjudgment of traffic light signals caused by drivers forgetting to use turn signals, ultimately improving intersection traffic efficiency and reducing traffic accidents.

[0017] It should be understood that the above general description and the following detailed description of the invention are exemplary and illustrative, and are intended to provide further explanation of the invention as described in the claims. Attached Figure Description

[0018] The accompanying drawings are included to provide further explanation of the invention; they are incorporated into and constitute a part of this application. The drawings illustrate embodiments of the invention and, together with this specification, serve to explain the principles of the invention. In the drawings: Figure 1 A flowchart illustrating a method for selecting target lane traffic lights according to an embodiment of the present invention is shown.

[0019] Figure 2 A system block diagram of a target lane traffic light screening device according to an embodiment of the present invention is shown. Detailed Implementation

[0020] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this application or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0022] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0023] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0024] In the description of this application, it should be understood that the orientation or positional relationship indicated by directional terms such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" is usually based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing this application and simplifying the description. Unless otherwise stated, these directional terms do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the scope of protection of this application; the directional terms "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself.

[0025] Furthermore, it should be noted that the use of terms such as "first" and "second" to define components is merely for the purpose of distinguishing the corresponding components. Unless otherwise stated, these terms have no special meaning and therefore should not be construed as limiting the scope of protection of this application. In addition, although the terminology used in this application is selected from commonly known and used terms, some terms mentioned in this application's specification may have been chosen by the applicant according to his or her judgment, and their detailed meanings are explained in the relevant sections of this description. Moreover, this application should be understood not only through the actual terms used, but also through the meaning implied by each term.

[0026] Figure 1 A flowchart illustrating a target lane traffic light filtering method according to an embodiment of the present invention is shown. As shown, this filtering method is an identification scheme designed to address the problem of interference from multiple traffic lights at complex intersections and the ease with which drivers misjudge traffic lights, and includes the following steps: First, acquiring and classifying traffic light information ahead of the vehicle is fundamental to selecting traffic lights for the target lane. Complex intersections often contain multiple traffic lights with varying functions and locations. Directly using the raw information from cameras may result in invalid signals, such as those that are too far away or installed at the wrong height. Therefore, the validity of the identified traffic light information must be verified first. By limiting longitudinal and lateral distances, installation height, recognition confidence levels, and light color types, valid information strongly relevant to the current intersection is filtered out, avoiding irrelevant signals from interfering with subsequent judgments. Based on this, the valid traffic light information is divided into three sets: left-turn, straight-ahead, and right-turn. In other words, the valid traffic light information is categorized into these three turning sets.

[0027] Secondly, determining the driver's steering intention based on overall vehicle signals is a prerequisite for ensuring that traffic lights match actual driving needs. Relying solely on turn signal signals to determine intention has significant limitations; drivers may inadvertently forget to activate their turn signals. Therefore, a comprehensive judgment must be made based on overall vehicle signals, including turn signal on / off status, steering wheel angle, vehicle speed, heading angle changes, and distance traveled. For example, prioritizing lane restrictions to determine intention is suitable for scenarios involving dedicated lanes; considering turn signal status covers situations requiring standard operation; and judging steering setting, cancellation, and completion conditions allows for capturing the driver's actual driving actions when the turn signal is not activated. Ultimately, this ensures that the determined steering intention matches the vehicle's actual driving direction, providing a reliable basis for subsequently matching the correct set of traffic lights.

[0028] Next, selecting the corresponding turn set based on the turning intention is a crucial step in connecting driving needs with traffic light signals. Different turning intentions correspond to traffic lights with different functions at the intersection. By matching left-turn intentions to left-turn sets, straight-ahead intentions to straight-ahead sets, and right-turn intentions to right-turn sets, traffic light signals irrelevant to the current driving direction can be filtered out, focusing on the traffic lights that the current lane actually needs to refer to, further narrowing down the effective range of traffic lights and avoiding interference from multiple traffic lights.

[0029] Finally, the current traffic light color is determined based on the selected turn set, and an operation prompt is provided. The selected turn set may contain multiple traffic lights. Calculating the overall confidence level of each traffic light is crucial to comprehensively consider the distance between the traffic light and the vehicle, as well as the recognition confidence level, ensuring the selected traffic light has high reference value. Counting the number of traffic light colors and combining this with confidence levels to determine the current color addresses the situation of multiple colors within the turn set. By using a dominant color and a high-confidence traffic light, the impact of misidentification of a single traffic light is reduced, improving the accuracy of color judgment. Providing operation prompts based on the color, such as voice prompts or color displays, directly assists the driver, resolving traffic light misjudgments caused by obstructed vision or distraction, ultimately achieving the invention's objective of improving intersection traffic efficiency and reducing traffic accidents.

[0030] In some examples, to avoid interference from irrelevant traffic lights in the filtering results, the validity of the identified traffic light information must first be verified before classification based on the functional attributes of the traffic lights. The core purpose of validity verification is to filter out traffic light information that is strongly related to the current vehicle driving scenario. Complex intersections may contain traffic lights that are too far away, have abnormal installation heights, or have low recognition reliability. If such signals are used in subsequent judgments, they are prone to misjudgment; therefore, multiple verification conditions must be met simultaneously. Verification conditions include: The limits for longitudinal and lateral distances include: the longitudinal distance between the traffic light and the vehicle must be less than the maximum effective longitudinal distance threshold, and the lateral distance between the traffic light and the vehicle must be less than the maximum effective lateral distance threshold. This ensures that the traffic light is within the effective perception range of the vehicle's current direction of travel. Ground height restrictions include: the ground height of traffic lights must be less than the maximum effective height threshold. This is used to exclude non-intersection control traffic lights that are too high or too low. The confidence level is limited to: the confidence level of the traffic light is greater than the minimum confidence threshold. This is used to ensure the reliability of the traffic light recognition results. The color of traffic lights is limited to one of three colors: red, yellow, or green. This is used to eliminate interference from non-standard traffic lights (such as warning lights).

[0031] After valid traffic light information is obtained through verification, it is classified into left-turn set, straight-ahead set, and right-turn set according to functional attributes to adapt to the signal light control requirements of different driving directions.

[0032] In some examples, the classification of valid traffic light information includes the following steps: If the valid traffic light information is a traffic light with a left-turn arrow, it is categorized into the left-turn set; if it is a traffic light with a straight-ahead arrow, it is categorized into the straight-ahead set; if it is a traffic light with a right-turn arrow, it is categorized into the right-turn set; and if it is a circular traffic light, it is categorized into both the left-turn and straight-ahead sets. Categorizing circular traffic lights into both the left-turn and straight-ahead sets aligns with the actual traffic rules where circular lights typically control both left-turn and straight-ahead traffic flows, ensuring coverage of these common traffic scenarios and avoiding omissions due to incorrect signal light types.

[0033] In some examples, by integrating lane restrictions, turn signal status, and actual vehicle driving actions such as speed, steering wheel angle, and heading angle, it is ensured that the final determined steering intention matches the vehicle's actual driving needs. This determination process includes the following steps: S21: Determine whether the current lane allows vehicles to turn left or right. If yes, determine the turning intention as a left or right turn based on the current lane's direction, and proceed to step S27. If not, proceed to the next step. This step prioritizes determining whether the current lane allows left or right turns because dedicated lanes have clearly defined vehicle directions according to traffic rules; a left-turn lane always indicates a left-turn intention, and a right-turn lane always indicates a right-turn intention. This allows for direct identification of the turning intention without relying on other signals, improving efficiency and avoiding misjudgments of intentions conflicting with lane restrictions. S22, determine whether the turn signal is on. If on, determine whether the turning intention is a left turn or a right turn, and proceed to step S27. If off, proceed to the next step. Prioritizing the on / off status of the turn signal is because the turn signal is a direct signal from the driver to express their driving intention and covers most standard driving scenarios. A left turn signal on indicates a left turn intention, and a right turn signal on indicates a right turn intention. S23, determine whether the steering setting conditions are met. If they are met, determine whether the steering intention is to turn left or right and proceed to step S27. If not, proceed to the next step. S24, determine whether the steering cancellation condition is met. If it is met, determine that the steering intention is to go straight and proceed to step S27. If it is not met, proceed to the next step. S25, determine whether the turning completion condition is met. If it is met, determine that the turning intention is to go straight and proceed to step S27. If it is not met, proceed to the next step. S26, Determine the steering intention as the vehicle's direction of travel before the judgment process; S27, End of steering intention judgment.

[0034] In some examples, the steering settings are: vehicle speed greater than a speed threshold, absolute value of steering wheel angle greater than a first angle threshold, and change in yaw angle greater than a second angle threshold. This design eliminates non-steering interference through multi-dimensional motion characteristics. The speed threshold filters out minor steering wheel adjustments during low-speed maneuvering, the steering wheel angle threshold ensures a clear steering operation, and the yaw angle change threshold verifies that the vehicle body has actually turned with the steering wheel operation. Only the combination of these three factors can determine that the driver has a genuine steering intention. For example, setting the speed threshold to 2 m / s, the first angle threshold to 40°, and the second angle threshold to 5°; The steering cancellation condition is: within n consecutive cycles, the change in steering wheel angle is greater than the third angle threshold, and the change in heading angle is less than the fourth angle threshold. For example, within 5 consecutive cycles, if the change in steering wheel angle is greater than 5° and the change in heading angle is less than 10°, it corresponds to a situation where the driver temporarily adjusts the steering wheel but does not cause a significant steering of the vehicle. Or, within n consecutive cycles, the steering wheel angle changes from greater than the fifth angle threshold to less than the sixth angle threshold. For example, within 5 consecutive cycles, if the steering wheel angle change is greater than 10° and the heading angle change is less than 3°, it corresponds to the driver actively straightening the steering wheel. The steering completion condition is: within n consecutive cycles, the change in heading angle is greater than the seventh angle threshold, and the change in steering wheel angle is less than the eighth angle threshold. For example, within 5 consecutive cycles, if the change in heading angle is greater than 50° and the steering wheel angle is less than 5°, it corresponds to the vehicle steering amplitude meeting the standard and the steering wheel returning to center. Alternatively, the turning distance exceeds the ninth threshold, and the steering wheel angle is less than the tenth angle threshold for n consecutive cycles. For example, if the turning distance exceeds 50m, and the steering wheel angle is less than 5° for 5 consecutive cycles, this corresponds to the situation where the turning distance meets the standard and the steering wheel returns to center.

[0035] It should be noted that n is an integer greater than 2. The limitation of n consecutive cycles in various conditions is intended to filter out transient signal interference. During vehicle operation, transient abnormal signals such as steering wheel vibration and slight fluctuations in heading angle may occur. Continuous judgment over multiple cycles can improve the reliability of condition triggering and avoid misjudgment caused by abnormal signals in a single cycle.

[0036] In some examples, the corresponding turning set is selected based on the determined turning intention. If the turning intention is to turn left, the left-turn set in the turning set is selected; if the turning intention is to go straight, the straight set in the turning set is selected; and if the turning intention is to turn right, the right-turn set in the turning set is selected.

[0037] In some examples, a combination of comprehensive confidence-based quantitative assessment and statistical arbitration of light color counts ensures that the final output light color matches the actual control requirements of the current lane. The process of determining the current light color based on the selected set of turns includes: First, calculate the overall confidence level of each traffic light within the selected turn signal set, because a single dimension of distance or recognition confidence level cannot fully reflect the correlation between the traffic light and the current lane, as well as the reliability of recognition. Looking only at distance might lead to the mistaken selection of a nearby but poorly recognized traffic light; looking only at confidence level might lead to the mistaken selection of a clearly identifiable but distant traffic light belonging to another lane. The number of each color of traffic light within the selected turn signal set is counted to address conflicting scenarios where multiple traffic lights of different colors exist within the same turn signal set. When multiple colors coexist, the risk of misidentification of a single traffic light is higher. By counting the number of colors, the impact of individual misidentification can be reduced through group consistency, thereby improving the reliability of color determination. The current light color is determined based on the quantity and overall confidence level.

[0038] In some examples, the formula for calculating the overall confidence level for each traffic light is: ; Where x is the lateral distance between the traffic light and the vehicle; y represents the longitudinal distance between the traffic light and the vehicle; c represents the confidence level of the traffic light; its value is between 0 and 1, directly reflecting the reliability of the recognition result. This is the maximum effective lateral distance threshold for this traffic light; It can be set to 10m; This is the maximum effective longitudinal distance threshold for this traffic light; It can be set to 100m; set horizontal and vertical distance thresholds to achieve a quantitative mapping where the closer the distance, the higher the score, which is consistent with the actual traffic scenario where a nearby traffic light is more likely to correspond to the current lane. This is the weight value for the lateral distance of the traffic light, and its value is between 0 and 1; This is the weight value for the longitudinal distance of the traffic light, and its value is between 0 and 1; This is the confidence weight value for the traffic light, and its value is between 0 and 1. And satisfy This design aims to avoid distorting results by giving too much weight to any one dimension, ensuring that the evaluation weights of the three dimensions are balanced and reasonable. For example, a preset weighting can be used. , , The weight allocation takes into account both distance correlation and the reliability of identification.

[0039] In some examples, if the current light color of the determined turn set is only one, it means that there is no light color conflict. In this case, the turn set (traffic lights) with the highest overall confidence is directly selected to output the light color, ensuring that the most reliable signal in the set is selected. If there are multiple possible current light colors, the color with the most occurrences is selected as the current light color to avoid individual misjudgments by leveraging the advantage of the group's numbers. Then, the traffic light with the highest overall confidence level is selected from the candidate light colors and the current light color is output.

[0040] The implementation process of the present invention will be described in detail below with reference to the accompanying drawings and specific parameters: 1. Acquisition and classification of traffic light information After the vehicle-mounted forward-facing camera captures images of the intersection, it identifies information from three traffic lights: Traffic light A: with a left-turn arrow, longitudinal distance 50m, lateral distance 3m, height 4m, confidence level 0.9, light color red; Traffic light B: Circular light, longitudinal distance 45m, lateral distance 2m, height 4m, confidence level 0.95, light color green; Traffic light C: with a right turn arrow, longitudinal distance 55m, lateral distance 4m, height 4m, confidence level 0.85, light color yellow.

[0041] Preset verification thresholds: maximum effective longitudinal distance 100m, maximum effective lateral distance 10m, maximum effective height 5m, minimum confidence level 0.8. Verification shows that A, B, and C are all valid traffic lights.

[0042] Classification results: Traffic light A is assigned to the left-turn group; Traffic light B is included in both the left-turn set and the straight-ahead set; Traffic light C is classified as a right turn.

[0043] 2. Judging the driver's steering intention

[0044] The vehicle signals are as follows: turn signal off, vehicle speed 3m / s (>2m / s), steering wheel angle -45° (absolute value >40°), heading angle change 6° (>5°), which meets the steering setting conditions. Therefore, the steering intention is determined to be a left turn.

[0045] 3. Selection of the turning set

[0046] Since the intention to turn is to turn left, the left-turn set is selected, which includes traffic light A and traffic light B.

[0047] 4. Determining the current light color

[0048] Preset weights: , , ; , .

[0049] Calculate the overall confidence level: Overall confidence level of traffic light A: 0.2×(10-3) / 10+0.3×(100-50) / 100+0.5×0.9=0.14+0.15+0.45=0.74; Overall confidence level of traffic light B: 0.2×(10-2) / 10+0.3×(100-45) / 100+0.5×0.95=0.16+0.165+0.475=0.8.

[0050] Count the number of light colors: Signal light A has 1 red light and signal light B has 1 green light.

[0051] Since there are multiple light colors, it is necessary to compare the number of light colors. If both are 1, select signal light B with higher overall confidence, output green light color, and give the driver an auditory prompt that the driver can start driving on a green light.

[0052] Figure 2 A system block diagram of a screening device according to an embodiment of the present invention is shown. As shown, the screening device 200 may include an internal communication bus 201, a processor 202, a read-only memory (ROM) 203, a random access memory (RAM) 204, and a communication port 205. When applied to a personal computer, the screening device 200 may also include a hard disk 206. The internal communication bus 201 enables data communication between the components of the screening device 200. The processor 202 can perform judgments and issue prompts. In some embodiments, the processor 202 may consist of one or more processors. The communication port 205 enables data communication between the screening device 200 and external devices. In some embodiments, the screening device 200 can send and receive information and data from a network through the communication port 205. The screening device 200 may also include different forms of program storage units and data storage units, such as the hard disk 206, the read-only memory (ROM) 203, and the random access memory (RAM) 204, capable of storing various data files used for computer processing and / or communication, as well as possible program instructions executed by the processor 202. Processor 202 executes these instructions to implement the main part of the method. The results processed by processor 202 are transmitted to the user equipment via communication port 205 and displayed on the user interface.

[0053] The above-described screening method can be implemented as a computer program, stored in the hard disk 206, and loaded into the processor 202 for execution to implement the screening method of this application.

[0054] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the aforementioned screening methods.

[0055] The specific implementation methods and technical effects of the screening equipment and computer-readable storage medium can be found in the embodiments of the target lane traffic light screening method provided by the present invention, and will not be repeated here.

[0056] The present invention provides a method, device, and computer-readable storage medium for selecting target lane traffic lights, which has the following advantages: 1. Precise judgment of steering intention: It does not rely on a single turn signal, but combines vehicle information such as vehicle speed and steering wheel angle to solve the problem of misjudging traffic lights caused by the driver forgetting to use the turn signal; 2. More reliable traffic light filtering: Through multiple processing steps including validity verification, classification, and confidence arbitration, the interference problem of multiple traffic lights at complex intersections is solved, ensuring that the identification result is the traffic light corresponding to the current lane; 3. Improve driving experience and safety: Accurate light color prompts can prevent situations such as running red lights or stopping at green lights, which not only improves the efficiency of intersection traffic but also reduces the risk of traffic accidents.

[0057] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above in a generalized manner in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the invention.

[0058] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or performed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor may be a microprocessor, but in alternatives, it may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0059] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor such that the processor can read and write information to / from the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside as discrete components in the user terminal.

[0060] In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functionality may be stored or transmitted as one or more instructions or code on or via a computer-readable medium. A computer-readable medium includes both computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium accessible to a computer. By way of example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and is accessible to a computer. Any connection is also legitimately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of a medium. As used in this article, disk and disc include compact discs (CDs), laser discs, optical discs, digital multi-purpose discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of these should also be included within the scope of computer-readable media.

[0061] It will be apparent to those skilled in the art that various modifications and variations can be made to the exemplary embodiments described above without departing from the spirit and scope of the invention. Therefore, it is intended that this invention cover modifications and variations falling within the scope of the appended claims and their equivalents.

Claims

1. A method for selecting target lane traffic lights, comprising the following steps: The system acquires traffic light information ahead of the vehicle, identifies the traffic light information to obtain traffic light information, and classifies the traffic light information to generate a turning set, which includes a left turn set, a straight go set, and a right turn set. The driver's steering intention is determined based on vehicle signals, including intention to turn left, intention to go straight, or intention to turn right. Based on the stated steering intention, the corresponding set of steering options is selected; Based on the selected set of turns, determine the current light color and provide vehicle operation prompts based on the current light color; The process of determining the current light color based on the selected turn signal set includes: Calculate the overall confidence level of each traffic light within the selected turn set; Count the number of each light color within the selected turn signal set; The current light color is determined based on the quantity and overall confidence level. Specifically, the traffic light information obtained after identification is filtered according to the verification rules to obtain valid traffic light information, and the valid traffic light information is classified. The verification rules include all of the following conditions: The longitudinal distance between the traffic light and the vehicle is less than the maximum effective longitudinal distance threshold; The lateral distance between the traffic light and the vehicle is less than the maximum effective lateral distance threshold; The ground height of the traffic light is less than the maximum effective height threshold; The confidence level of the traffic light is greater than the minimum confidence threshold; The traffic light is one of the colors red, yellow, or green; The classification of the valid traffic light information includes the following steps: If the valid traffic light information is a traffic light with a left-turn arrow, then the valid traffic light information is included in the left-turn set; If the valid traffic light information is a traffic light with a straight arrow, then the valid traffic light information is included in the straight-ahead set; If the valid traffic light information is a traffic light with a right-turn arrow, then the valid traffic light information is included in the right-turn set; If the valid traffic light information is a circular traffic light, then the valid traffic light information will be classified into the left turn set and the straight-ahead set.

2. The screening method as described in claim 1, characterized in that, The vehicle signals include turn signal on / off status, steering wheel angle, vehicle speed, heading angle, and distance traveled; the process of determining the driver's steering intention based on the vehicle signals includes the following steps: S21, determine whether the current lane allows the vehicle to turn left or right. If yes, determine the turning intention as a left turn or right turn based on the direction of the current lane, and proceed to step S27. If no, proceed to the next step. S22, determine whether the turn signal is on. If it is on, determine whether the turning intention is to turn left or right, and proceed to step S27. If it is off, proceed to the next step. S23, determine whether the steering setting conditions are met. If they are met, determine whether the steering intention is to turn left or right and proceed to step S27. If not, proceed to the next step. S24, determine whether the steering cancellation condition is met. If it is met, determine that the steering intention is to go straight and proceed to step S27. If it is not met, proceed to the next step. S25, determine whether the turning completion condition is met. If it is met, determine that the turning intention is to go straight and proceed to step S27. If it is not met, proceed to the next step. S26, determine that the steering intention is the direction of travel of the vehicle prior to the determination process; S27, End of steering intention judgment.

3. The screening method as described in claim 2, characterized in that, The steering setting conditions are: the vehicle speed is greater than the speed threshold, the absolute value of the steering wheel angle is greater than the first angle threshold, and the change value of the heading angle is greater than the second angle threshold. The steering cancellation condition is: within n consecutive cycles, the change in steering wheel angle is greater than the third angle threshold, and the change in heading angle is less than the fourth angle threshold. Or, within n consecutive cycles, the steering wheel angle changes from greater than the fifth angle threshold to less than the sixth angle threshold; The steering completion condition is: within n consecutive cycles, the change value of the heading angle is greater than the seventh angle threshold, and the change value of the steering wheel angle is less than the eighth angle threshold. Or the turning distance exceeds the ninth threshold, and the steering wheel angle is less than the tenth angle threshold within n consecutive cycles; Where n is an integer greater than 2.

4. The screening method as described in claim 1, characterized in that, If the steering intention is to turn left, then the left-turn set in the steering set is selected; if the steering intention is to go straight, then the straight set in the steering set is selected. If the intended turn is a right turn, then the right turn set in the intended turn set is selected.

5. The screening method as described in claim 1, characterized in that, The formula for calculating the overall confidence level of each traffic light is as follows: ； Where x is the lateral distance between the traffic light and the vehicle; y represents the longitudinal distance between the traffic light and the vehicle. c represents the confidence level of the traffic light; This is the maximum effective lateral distance threshold for this traffic light; This is the maximum effective longitudinal distance threshold for this traffic light; This is the weight value for the lateral distance of the traffic light, and its value is between 0 and 1; This is the weight value for the longitudinal distance of the traffic light, and its value is between 0 and 1; This is the confidence weight value for the traffic light, and its value is between 0 and 1. And satisfy .

6. The screening method as described in claim 5, characterized in that, If there is only one possible current light color, then select the turning set with the highest overall confidence and output the current light color. If there are multiple possible current light colors, the color with the most occurrences is selected as the current light color. The traffic light with the highest overall confidence level is then chosen and the current light color is output.

7. A screening device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the filtering method as described in any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the screening method as described in any one of claims 1-6.

Images