Signal lamp identification method and device, electronic equipment and readable storage medium

Abstract

The application discloses a signal lamp identification method and device, electronic equipment and a readable storage medium, which are applied to an augmented reality device. The signal lamp identification method comprises the following steps: when it is detected that a target user wearing the augmented reality device is located in a signal lamp identification area, a to-be-detected signal lamp image is acquired; whether the signal lamp identified by the target user exists occlusion is detected according to the to-be-detected signal lamp image; if the signal lamp exists occlusion, signal lamp prompt information corresponding to the signal lamp is displayed, so that the target user identifies the signal lamp according to the signal lamp prompt information. The application solves the technical problem that the signal lamp cannot be identified in real time in a driving scene.

Description

Technical Field

[0001] This application relates to the field of augmented reality technology, and in particular to a traffic light recognition method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] With the continuous development of technology, the level of vehicle intelligence has been comprehensively improved, and driving assistance equipment has gradually become an indispensable part of intelligent driving. At present, vehicles are usually equipped with driving assistance equipment such as cameras or radar sensors to help drivers get feedback on the driving environment around the vehicle. However, in some specific driving scenarios, it still relies on the driver's subjective judgment, such as driving at traffic light intersections.

[0003] Currently, when drivers approach traffic light intersections, they typically observe the status of the traffic lights with their naked eyes and then perform the corresponding driving operations. However, due to the limitations of human vision and the uncertainty of the driving environment, there are situations where drivers may not be able to observe the traffic lights. Therefore, real-time recognition of traffic lights is not currently possible in driving scenarios. Summary of the Invention

[0004] The main objective of this application is to provide a traffic light recognition method, device, electronic device, and readable storage medium, aiming to solve the technical problem in the prior art that traffic lights cannot be recognized in real time in driving scenarios.

[0005] To achieve the above objectives, this application provides a traffic light recognition method applied to an augmented reality device, the traffic light recognition method comprising:

[0006] When a target user wearing the augmented reality device is detected to be in the traffic light recognition area, an image of the traffic light to be detected is acquired;

[0007] Based on the image of the traffic light to be detected, detect whether the traffic light identified by the target user is obstructed;

[0008] If the traffic light is obstructed, the corresponding traffic light prompt information will be displayed so that the target user can identify the traffic light based on the traffic light prompt information.

[0009] Optionally, the step of detecting whether the traffic light identified by the target user is obstructed based on the traffic light image to be detected includes:

[0010] The image acquisition time for detecting whether the corresponding traffic light identifier of the traffic light does not appear in the image of the traffic light to be detected is greater than a preset acquisition time threshold.

[0011] If so, it is determined that the traffic light identified by the target user is obstructed;

[0012] If not, then it is determined that the traffic light identified by the target user is not obstructed.

[0013] Optionally, the step of detecting whether the traffic light identified by the target user is obstructed based on the traffic light image to be detected includes:

[0014] Determine the regional positional relationship between the target region and the field of view region in the image of the traffic light to be detected;

[0015] Based on the location relationship of the area, an occlusion coverage parameter is matched for the target user, wherein the occlusion coverage parameter is used to distinguish whether the occlusion object corresponding to the target area obstructs the target user from recognizing the traffic light;

[0016] Based on the occlusion coverage parameters, detect whether the traffic light identified by the target user is obstructed.

[0017] Optionally, the step of detecting whether the traffic light identified by the target user is obstructed based on the occlusion coverage parameter includes:

[0018] Obtain the occlusion coverage parameters between the target area and the field of view;

[0019] Based on the relationship between the occlusion coverage parameter and the occlusion coverage parameter threshold, it is detected whether the traffic light identified by the target user is obstructed.

[0020] Optionally, the step of matching occlusion coverage parameters for the target user based on the regional location relationship includes:

[0021] The relative distance between the target user and the traffic light is determined based on the first position of the target user and the second position of the traffic light.

[0022] Based on the relative distance and the regional location relationship, occlusion coverage parameters are matched for the target user.

[0023] Optionally, the step of matching occlusion coverage parameters for the target user based on the regional location relationship includes:

[0024] In a preset coordinate system, the first coordinate point of the target user and the second coordinate point of the traffic light are obtained, and the relative position axis between the target user and the traffic light is established based on the first coordinate point and the second coordinate point.

[0025] Determine the occlusion angle between the relative position axis and the reference axis in the preset coordinate system;

[0026] Based on the occlusion coverage angle, the relative position, and the regional positional relationship, occlusion coverage parameters are matched for the target user.

[0027] Optionally, after the step of displaying the traffic light prompt information corresponding to the traffic light, the traffic light identification method further includes:

[0028] Determine the dwell time of the vehicle carrying the target user within the traffic light recognition area;

[0029] Detect whether the dwell time is less than the traffic light transition time corresponding to the traffic light prompt information;

[0030] If the value is less than the specified value, a driving prompt message will be displayed indicating that the vehicle has left the traffic light recognition area.

[0031] If the time is not less than the time specified, vehicle start / stop information is generated at the traffic light transition time and sent to the vehicle so that the vehicle can perform the corresponding start / stop operation based on the vehicle start / stop information.

[0032] To achieve the above objectives, this application also provides a traffic light recognition device for use in augmented reality devices, the traffic light recognition device comprising:

[0033] The acquisition module is used to acquire an image of a traffic light to be detected when a target user wearing the augmented reality device is detected to be in the traffic light recognition area;

[0034] The detection module is used to detect whether the traffic light identified by the target user is obstructed based on the image of the traffic light to be detected;

[0035] The display module is used to display the corresponding traffic light prompt information if the traffic light is obstructed, so that the target user can identify the traffic light based on the traffic light prompt information.

[0036] Optionally, the detection module is further configured to:

[0037] The image acquisition time for detecting whether the corresponding traffic light identifier of the traffic light does not appear in the image of the traffic light to be detected is greater than a preset acquisition time threshold.

[0038] If so, it is determined that the traffic light identified by the target user is obstructed;

[0039] If not, then it is determined that the traffic light identified by the target user is not obstructed.

[0040] Optionally, the detection module is further configured to:

[0041] Determine the regional positional relationship between the target region and the field of view region in the image of the traffic light to be detected;

[0042] Based on the location relationship of the area, an occlusion coverage parameter is matched for the target user, wherein the occlusion coverage parameter is used to distinguish whether the occlusion object corresponding to the target area obstructs the target user from recognizing the traffic light;

[0043] Based on the occlusion coverage parameters, detect whether the traffic light identified by the target user is obstructed.

[0044] Optionally, the detection module is further configured to:

[0045] Obtain the occlusion coverage parameters between the target area and the field of view;

[0046] Based on the relationship between the occlusion coverage parameter and the occlusion coverage parameter threshold, it is detected whether the traffic light identified by the target user is obstructed.

[0047] Optionally, the detection module is further configured to:

[0048] The relative distance between the target user and the traffic light is determined based on the first position of the target user and the second position of the traffic light.

[0049] Based on the relative distance and the regional location relationship, occlusion coverage parameters are matched for the target user.

[0050] Optionally, the detection module is further configured to:

[0051] In a preset coordinate system, the first coordinate point of the target user and the second coordinate point of the traffic light are obtained, and the relative position axis between the target user and the traffic light is established based on the first coordinate point and the second coordinate point.

[0052] Determine the occlusion angle between the relative position axis and the reference axis in the preset coordinate system;

[0053] Based on the occlusion coverage angle, the relative position, and the regional positional relationship, occlusion coverage parameters are matched for the target user.

[0054] Optionally, the traffic light recognition device is further used for:

[0055] Determine the dwell time of the vehicle carrying the target user within the traffic light recognition area;

[0056] Detect whether the dwell time is less than the traffic light transition time corresponding to the traffic light prompt information;

[0057] If the value is less than the specified value, a driving prompt message will be displayed indicating that the vehicle has left the traffic light recognition area.

[0058] If the time is not less than the time specified, vehicle start / stop information is generated at the traffic light transition time and sent to the vehicle so that the vehicle can perform the corresponding start / stop operation based on the vehicle start / stop information.

[0059] This application also provides an electronic device, the electronic device comprising: at least one processor and a memory communicatively connected to the at least one processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the traffic light recognition method described above.

[0060] This application also provides a computer-readable storage medium storing a program for implementing a traffic light recognition method, wherein when the program for the traffic light recognition method is executed by a processor, it implements the steps of the traffic light recognition method as described above.

[0061] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the traffic light recognition method described above.

[0062] This application provides a traffic light recognition method, apparatus, electronic device, and readable storage medium, applied to an augmented reality device. Specifically, when a target user wearing the augmented reality device is detected to be in a traffic light recognition area, an image of a traffic light to be detected is acquired; based on the image of the traffic light to be detected, it is detected whether the traffic light to be recognized by the target user is obstructed; if the traffic light is obstructed, traffic light prompt information corresponding to the traffic light is displayed so that the target user can recognize the traffic light based on the traffic light prompt information.

[0063] When identifying traffic lights, this application first detects that a target user wearing an augmented reality device is located in the traffic light identification area. Then, it acquires an image of the traffic light to be detected through the augmented reality device. Next, it detects whether the traffic light being identified by the target user is obstructed based on the image of the traffic light to be detected. If an obstruction is detected, the corresponding traffic light prompt information is displayed through the augmented reality device. Since the target user is wearing an augmented reality device, the purpose of the target user identifying an obstructed traffic light can be achieved through the traffic light prompt information displayed by the augmented reality device.

[0064] Because augmented reality devices can project traffic light alerts onto the target user's retina, they can ensure that the target user receives the traffic light alerts in real time. When the target user is in the traffic light recognition area, the augmented reality device first detects whether the traffic light being recognized by the target user is obstructed. If the traffic light is obstructed, the corresponding traffic light recognition information is displayed on the target user's retina in real time. Since the traffic light can be easily recognized by the target user when there is no obstruction, the goal of real-time traffic light recognition by the target user is achieved.

[0065] Based on this, this application uses an augmented reality device to acquire an image of the traffic light to be detected when the target user is located in the traffic light recognition area. Then, if an obstruction is detected in the traffic light image, the augmented reality device displays the corresponding traffic light prompt information. Ultimately, the target user identifies the traffic light through the prompt information, thus achieving the goal of real-time traffic light recognition. This overcomes the technical shortcomings caused by the limitations of human field of vision and the uncertainty of the driving environment, which often lead to situations where drivers cannot observe traffic lights. Therefore, the target user can recognize traffic lights in real time, thus solving the problem of not being able to recognize traffic lights in real-time during driving scenarios. Attached Figure Description

[0066] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0067] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0068] Figure 1 This is a flowchart illustrating the traffic light recognition method provided in Embodiment 1 of this application;

[0069] Figure 2 This is a schematic diagram showing the regional positional relationship between the visual field area and the target area of ​​the traffic light recognition method provided in Embodiment 1 of this application;

[0070] Figure 3 This is a schematic diagram showing the location relationship of the target area of ​​the traffic light recognition method provided in Embodiment 1 of this application, which is entirely located within the field of view.

[0071] Figure 4 This is a flowchart illustrating the traffic light recognition method provided in Embodiment 2 of this application;

[0072] Figure 5 This is a schematic diagram illustrating the occlusion between a target user and a traffic light in different lanes for the traffic light recognition method provided in Embodiment 2 of this application.

[0073] Figure 6 This is a schematic diagram of the preset coordinate system of the traffic light recognition method provided in Embodiment 2 of this application;

[0074] Figure 7 This is a schematic diagram of the traffic light recognition device provided in Embodiment 3 of this application;

[0075] Figure 8 This is a schematic diagram of the structure of the electronic device provided in Embodiment 4 of this application.

[0076] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0077] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0078] Example 1

[0079] With the development of technology, more and more driver assistance devices are being applied to vehicles. Among them, AR (Augmented Reality) devices, with their immersive interactive experience, have become an important vehicle feature. However, there is still room for development in the driver assistance capabilities of AR devices. Taking the driving scenario at a traffic light intersection as an example, currently, cameras and radar are still used to monitor the driving environment around the vehicle. However, when the driver approaches a traffic light intersection, cameras and radar cannot accurately identify the traffic lights. For example, if the vehicle in front of the driver is a large truck, the driver's field of vision is obstructed, and the driver cannot identify the traffic lights at the intersection. If the driver follows the truck rashly, they may run a red light, meaning that driving safety cannot be guaranteed. Therefore, there is an urgent need for a method that allows drivers to identify traffic lights in real time. The applicant uses this as a technical concept fulcrum and, combined with the characteristics of AR devices, proposes a method that relies on AR devices to assist drivers in identifying traffic lights in real time.

[0080] This application provides a traffic light recognition method applied to an augmented reality device. In the first embodiment of the traffic light recognition method of this application, referring to... Figure 1 The traffic light recognition method includes:

[0081] Step S10: When a target user wearing the augmented reality device is detected to be in the traffic light recognition area, an image of the traffic light to be detected is acquired;

[0082] Step S20: Based on the image of the traffic light to be detected, detect whether the traffic light identified by the target user is obstructed;

[0083] Step S30: If the traffic light is obstructed, display the traffic light prompt information corresponding to the traffic light so that the target user can identify the traffic light based on the traffic light prompt information.

[0084] In this embodiment, it should be noted that, although Figure 1The logical order is shown, but in some cases, the steps shown or described may be performed in a different order than that shown here. The traffic light recognition method is performed in a scenario where a target user wearing an augmented reality device (AR device) passes through a traffic light intersection. Specifically, the scenario could be a target user driving a vehicle through a traffic light intersection while wearing an AR device, such as the target user waiting at a red light, or a target user walking to a crosswalk while waiting at a red light. The AR device could be AR glasses or an AR watch, etc. The target user is used to characterize the user who needs to recognize the traffic light. For example, in one possible implementation, assume there are four users (A, B, C, and D) in the vehicle, all wearing AR devices, and the vehicle is located at a traffic light intersection, where user A is the driver. Since the driver is responsible for controlling the vehicle, and therefore needs to recognize traffic lights, the target user is driver A. The traffic light recognition area is used to characterize the area where traffic light recognition is required. Specifically, the positional relationship between the target user and the traffic light recognition area can be used to determine whether any area is a traffic light recognition area. For example, in one feasible approach, the augmented reality device detects the location of the nearest traffic light intersection to the target user's current location and calculates the current distance between the target user and the traffic light based on the positional relationship. Then, when the current distance is detected to be no greater than a preset distance threshold, it is determined that the target user is located in the traffic light recognition area. The detection method can be real-time detection or periodic detection. The current location can be determined by GPS (Global Positioning System) of other positioning devices or by the positioning module carried by the augmented reality device. The preset distance threshold is set by the user according to the detection requirements. The recognition scenario corresponding to the traffic light recognition area can be the scenario of the target user wearing the augmented reality device driving a vehicle or the scenario of the target user wearing the augmented reality device crossing a zebra crossing. This application embodiment does not limit the above.

[0085] Additionally, it should be noted that the image of the traffic light to be detected, used to characterize the recognition status of the traffic light waiting to be detected, can be captured by a camera or depth camera configured in the augmented reality device. The camera's shooting angle covers the target user's field of vision. In the absence of obstructions, the traffic light can be captured normally. In the presence of obstructions, the relative position between the traffic light and the target user determines whether the traffic light has been captured. The relative angle between the camera and the traffic light is determined by the relative position between the camera and the augmented reality device. For example, in one feasible approach, the image of the traffic light to be detected is an image of the driving environment directly in front of the target user. The visibility of the image is determined by the camera's imaging accuracy. When a large truck obstructs the target user's field of vision in front of their vehicle, the driving environment image captured by the camera is the rear outline of the vehicle directly in front. In this case, the target user cannot know the operation of the traffic light in front of the truck. Therefore, if the target user easily follows the truck and performs start-stop operations, it could easily lead to unsafe driving behavior.

[0086] Additionally, it should be noted that the augmented reality device is equipped with an image recognition algorithm. Due to the special characteristics of the traffic light's color and installation device (cantilever or column type, etc.), pixel-level image recognition can identify whether the traffic light appears in the image to be detected, thus determining whether the traffic light is obstructed. During the detection process, the detection error caused by the difference in spatial position between the camera device and the target user is ignored. Therefore, if the augmented reality device detects a traffic light in the image, it determines that the traffic light identified by the target user is not obstructed; conversely, if the augmented reality device detects no traffic light in the image, it determines that the traffic light identified by the target user is obstructed. Once obstruction is detected, a traffic light prompt message can be displayed on a preset display interface. This prompt message represents information about the identified traffic light, specifically a countdown timer with accompanying text, such as "30 seconds left until the red light ends." The actual distance between the preset display interface and the user's retina is not limited in this embodiment.

[0087] As an example, steps S10 to S30 include: after detecting that a target user is wearing the augmented reality device, periodically acquiring the target user's current location and the location of the nearest traffic light to the target user; determining whether the target user is located in the traffic light recognition area based on the distance between the current location and the traffic light location, and according to the relationship between the distance and a preset distance threshold; when it is determined that the target user is located in the traffic light recognition area, acquiring an image of the traffic light to be detected using the camera device of the augmented reality device; detecting whether the traffic light to be recognized by the target user is obstructed by a preset image recognition algorithm; if the traffic light is obstructed, displaying a countdown timer corresponding to the traffic light on a preset display interface so that the target user can recognize the traffic light based on the countdown timer. When the traffic light being identified by the target user is obstructed due to external interference, the augmented reality device can display the corresponding traffic light information in front of the target user's retina, thus enabling the target user to identify the traffic light even when it is obstructed. At the same time, when the traffic light is not obstructed, the target user can autonomously capture the traffic light within their field of vision. Therefore, the target user can identify the traffic light in real time, thereby solving the problem that the target user cannot identify obstructed traffic lights while driving.

[0088] The step of detecting whether the traffic light identified by the target user is obstructed based on the image of the traffic light to be detected includes:

[0089] Step A10: Detect whether the image acquisition time for the traffic light image to be detected, where the traffic light identifier corresponding to the traffic light does not appear, is greater than a preset acquisition time threshold.

[0090] Step A20: If yes, then it is determined that the traffic light identified by the target user is obstructed;

[0091] Step A30: If not, then determine that the traffic light identified by the target user is not obstructed.

[0092] In this embodiment, it should be noted that, due to the high complexity of the preset image recognition algorithm and the high requirements for traffic light recognition efficiency in the target user's driving scenario, if the image recognition algorithm is used to identify whether the traffic light is obstructed, it may result in the traffic light recognition failing to meet the needs of the target user. Therefore, a simpler obstruction recognition method can be used to identify whether the traffic light is obstructed, that is, the image acquisition time is introduced to determine the obstruction of the traffic light.

[0093] Additionally, it should be noted that the image acquisition duration is used to characterize the total time for acquiring images of the traffic lights to be detected, and the traffic light identifier is used to identify the traffic lights, specifically the outline or color of the traffic lights. For example, in one feasible implementation, when a target user is driving a vehicle to a traffic light intersection, if the target user is detected to be in the traffic light recognition area, the camera device acquires images of the traffic lights to be detected, and simultaneously starts a traffic light image timing device to count the total time for acquiring images of the traffic lights to be detected. Then, based on the total time for which the traffic light identifier corresponding to the traffic light does not appear in the images of the traffic lights to be detected, it is determined whether it is greater than a preset acquisition duration threshold. If it is greater than the threshold, it is determined that the traffic light identified by the target user is obstructed; if it is less than the threshold, it is determined that the traffic light identified by the target user is not obstructed. The preset acquisition duration threshold is specifically set by the user based on the needs of the scenario. The image acquisition duration can be a continuous cumulative duration or an intermittent cumulative duration, and this application embodiment does not limit this.

[0094] As an example, steps A10 to A30 include: obtaining the image acquisition duration for which the traffic light identifier corresponding to the traffic light does not appear in the image of the traffic light to be detected, and detecting whether the image acquisition duration is greater than a preset acquisition duration threshold; if the image acquisition duration is detected to be greater than the preset acquisition duration threshold, it is determined that the traffic light identified by the target user is obstructed; if the image acquisition duration is detected to be less than the preset acquisition duration threshold, it is determined that the traffic light identified by the target user is not obstructed. Since it is only necessary to identify whether the traffic light identifier exists in the image of the traffic light to be detected when calculating the image acquisition duration, the purpose of identifying whether the traffic light identified by the target user is obstructed can be achieved. At the same time, since the shooting angle of the augmented reality device's camera can objectively reflect the target user's field of vision, the appearance of the traffic light identifier in the image of the traffic light to be detected can ensure a certain accuracy of the obstruction determination. Therefore, it avoids the situation where traffic light recognition cannot meet the target user's needs in specific scenarios, thus improving the recognition efficiency of traffic light recognition.

[0095] The step of detecting whether the traffic light identified by the target user is obstructed based on the image of the traffic light to be detected includes:

[0096] Step B10: Determine the regional positional relationship between the target area and the field of view area in the image of the traffic light to be detected;

[0097] Step B20: Match occlusion and coverage parameters for the target user based on the location relationship of the area, wherein the occlusion and coverage parameters are used to distinguish whether the occlusion object corresponding to the target area obstructs the target user from recognizing the traffic light;

[0098] Step B30: Based on the occlusion coverage parameters, detect whether the traffic light identified by the target user is obstructed.

[0099] In this embodiment, it should be noted that the positional relationship between the target user and the traffic light is quite complex in driving scenarios. If the traffic light is simply determined to be obstructed by statistically analyzing the image acquisition time, there will be some error when the target user's field of vision overlaps with the obstruction range of the vehicle in front of the target user. This can easily lead to unsafe driving situations due to recognition errors. Furthermore, the computational load of using a preset image recognition algorithm to recognize traffic lights in dynamic scenarios is too large, making it difficult to balance the accuracy and efficiency of traffic light recognition. Therefore, special processing is performed on the traffic light image to be detected to make it suitable for driving scenarios with high recognition complexity.

[0100] Additionally, it should be noted that after the imaging device captures the image of the traffic light to be detected, the edge detection algorithm built into the augmented reality device detects the target user's field of vision and the target area in front of the target user. The field of vision represents the area covering the target user's field of vision, specifically the outline of the windshield of the vehicle driven by the target user. The target area represents the area corresponding to an obstruction in front of the target user, specifically the outline of the obstruction in the image of the traffic light to be detected. The regional positional relationship represents the relative positional relationship between the field of vision and the target area, as described above. Figure 2 , Figure 2 This diagram illustrates the positional relationship between the visual field and the target area. In this diagram, 10 represents the image of the traffic light to be detected, 11 represents the visual field, and 12 represents the target area. The target area 12 can be completely located within the visual field 11, or it can be located on top of the visual field 11. Different occlusion / coverage parameters can be matched for different positional relationships. These parameters are used to determine whether an obstruction corresponding to the target area obstructs the target user's identification traffic light. The reference is... Figure 3 , Figure 3 This diagram illustrates the positional relationship of the target region completely within the field of view. Here, h1 represents the distance between the upper contour of the target region and the upper contour of the field of view; h2 represents the distance between the lower contour of the target region and the lower contour of the field of view; l1 represents the distance between the left contour of the target region and the left contour of the field of view; and l2 represents the distance between the right contour of the target region and the right contour of the field of view. h1, h2, l1, and l2 are all occlusion parameters. During the matching process, all four can be used as matching occlusion parameters, or only one of them can be used.

[0101] As an example, steps B10 to B30 include: detecting the regional positional relationship between the occlusion area and the field of view area based on the pixel coverage between the occlusion area and the field of view area in the traffic light image to be detected; matching occlusion coverage parameters for the target user based on the regional positional relationship, wherein the occlusion coverage parameters are used to distinguish whether the occlusion area corresponding to the occlusion area obstructs the target user's recognition of the traffic light; and detecting whether the traffic light recognized by the target user is obstructed based on the occlusion coverage parameters. Since the target user's field of view and the occlusion range of the occlusion object overlap, the occlusion coverage parameters used to distinguish whether the occlusion area obstructs the target user's recognition of the traffic light can be matched based on the regional positional relationship between the occlusion area and the field of view area. Therefore, the occlusion coverage parameters can be used to identify whether the traffic light recognized by the target user is obstructed. That is, the goal of recognizing traffic light occlusion in a driving scenario by matching occlusion coverage parameters that conform to the regional positional relationship between the occlusion area and the field of view area is achieved. Therefore, both recognition accuracy and recognition efficiency are considered when performing traffic light recognition.

[0102] In one feasible approach, the target region can also be the region outside the occlusion region within the overall region formed by the field of view and the occlusion region in the image of the traffic light to be detected. Then, based on the regional positional relationship between the target region and the field of view, the corresponding occlusion coverage parameter is matched to determine whether the traffic light identified by the target user is occluded. Here, the occlusion coverage parameter used for the target region and the occlusion region is different, that is, the specific value of h1 used for the target region and the specific value of h1 used for the occlusion region are different.

[0103] The step of detecting whether the traffic light identified by the target user is obstructed based on the occlusion coverage parameter includes:

[0104] Step C10: Obtain the occlusion coverage parameters between the target area and the field of view area;

[0105] Step C20: Based on the relationship between the occlusion coverage parameter and the occlusion coverage parameter threshold, detect whether the traffic light identified by the target user is obstructed.

[0106] As an example, steps C10 to C20 include: obtaining occlusion coverage parameters between the target area and the field of view; if the occlusion coverage parameters are detected to be less than a preset occlusion coverage parameter threshold, it is determined that the traffic light identified by the target user is occluded; if the occlusion coverage parameters are detected to be not less than the preset occlusion coverage parameter threshold, it is determined that the traffic light identified by the target user is not occluded.

[0107] The step of matching occlusion coverage parameters for the target user based on the regional location relationship includes:

[0108] Step D10: Determine the relative distance between the target user and the traffic light based on the first position of the target user and the second position of the traffic light;

[0109] Step D20: Match occlusion and coverage parameters for the target user based on the relative distance and the regional location relationship.

[0110] In this embodiment, it should be noted that the occlusion coverage parameters in dynamic driving scenarios are dynamically matched and involve complex influencing factors. For example, the relative position difference between the target user and the traffic light will affect the size of the occlusion area in the field of vision. For example, in one feasible approach, if the positions of the occlusion and the traffic light are fixed, the relative position between the target user and the traffic light changes as the target user drives the vehicle closer to the occlusion. Consequently, the occlusion coverage parameters used to determine whether the occlusion obstructs the target user's identification of the traffic light also change. Therefore, in the process of matching the occlusion coverage parameters, it is necessary to combine the relative distance between the target user and the traffic light as well as the regional position relationship.

[0111] As an example, steps D10 to D20 include: obtaining the first location of the target user and the second location of the traffic light; calculating the relative distance between the target user and the traffic light based on the first and second locations; and querying a preset mapping table to obtain the occlusion coverage parameters of the target user, using the relative distance and the regional position relationship as indexes. The preset mapping table stores the mapping relationship between the occlusion coverage parameters and occlusion determination conditions, where the occlusion determination conditions can specifically be regional position relationships, or the relative distance and the regional position relationship. By combining the relative distance between the target user and the traffic light when matching the occlusion coverage parameters, the matched occlusion coverage parameters can be perfectly adapted to the scenario of the target user driving their vehicle to the traffic light intersection. That is, in dynamic driving scenarios, the goal of accurately matching occlusion coverage parameters based on the relative positions of the target user and the traffic light is achieved, thus laying the foundation for improving the accuracy of traffic light recognition.

[0112] The traffic light identification method further includes, after the step of displaying the traffic light prompt information corresponding to the traffic light:

[0113] Step E10: Determine the dwell time of the vehicle carrying the target user within the traffic light recognition area;

[0114] Step E20: Detect whether the dwell time is less than the traffic light switching time corresponding to the traffic light prompt information;

[0115] Step E30: If the value is less than the threshold, then display a driving prompt message indicating that the vehicle has left the traffic light recognition area.

[0116] In step E40, if the time is not less than the traffic light transition time, vehicle start-stop information is generated and sent to the vehicle so that the vehicle can perform the corresponding start-stop operation based on the vehicle start-stop information.

[0117] In this embodiment, it should be noted that, under normal circumstances, the target user can judge the situation at the traffic light intersection through the traffic light prompts displayed by the augmented reality device and take corresponding actions, such as driving away from the traffic light intersection at the current speed or waiting for the next sign that the vehicle can leave. However, in some extreme cases, the target user is at a critical point and cannot react to the changes in the traffic light signs in time, thus failing to make the most correct judgment quickly. This may lead to unsafe driving behavior at the traffic light intersection. Therefore, after displaying the traffic light prompts, the user can actively intervene in the vehicle's start and stop to avoid unsafe driving behavior.

[0118] Additionally, it should be noted that the dwell time of the target user's vehicle within the traffic light recognition area refers to the absolute value of the difference between the time the target user enters the traffic light recognition area and the time the target user leaves the traffic light recognition area. This can be obtained through the timer statistics of the augmented reality device. The traffic light transition time is used to represent the remaining time for the traffic light to maintain its current state. After the remaining time expires, the traffic light will transition to a different state, which can be red, green, or yellow. The driving prompt information is used to prompt the target user to drive, specifically "Please maintain your current speed and leave the traffic light intersection". The vehicle start-stop information is used to represent the vehicle's start or stop (braking) information, which can trigger the vehicle's terminal to perform the corresponding start or braking operation on the target user's vehicle.

[0119] As an example, steps E10 to E40 include: based on the timer of the augmented reality device, calculating the dwell time of the vehicle carrying the target user within the traffic light recognition area; detecting whether the dwell time is less than the traffic light transition time corresponding to the traffic light prompt information; if the dwell time is less than the traffic light transition time corresponding to the traffic light prompt information, displaying a driving prompt information indicating that the vehicle has left the traffic light recognition area; if the dwell time is not less than the traffic light transition time corresponding to the traffic light prompt information, generating vehicle start-stop information at the traffic light transition time point, and sending the vehicle start-stop information to the vehicle so that the vehicle can perform the corresponding start-stop operation according to the vehicle start-stop information.

[0120] In one feasible approach, assuming the target user drives into the traffic light recognition area and a green light countdown begins, the system can calculate the time required for the target user to leave the traffic light intersection (i.e., the time the target user's vehicle remains within the traffic light recognition area) by combining the current vehicle speed and the vehicle's position relative to the stop line at the intersection. This time is then compared with the remaining countdown time of the current traffic light (traffic light transition time), and an output is given indicating whether the target user can maintain the current speed to leave the traffic light intersection. If the system detects that the current vehicle speed is too high and the remaining time for the target user's vehicle to leave the traffic light intersection at that speed is insufficient, to avoid problems caused by the driver's delayed reaction, the augmented reality device can feed back the relevant results (vehicle start-stop information) to the vehicle's infotainment system, allowing the infotainment system to intervene in the target user's driving behavior, for example, by applying emergency braking.

[0121] This application provides a traffic light recognition method applied to an augmented reality device. Specifically, when a target user wearing the augmented reality device is detected to be in the traffic light recognition area, an image of a traffic light to be detected is acquired; based on the image of the traffic light to be detected, it is detected whether the traffic light to be recognized by the target user is obstructed; if the traffic light is obstructed, traffic light prompt information corresponding to the traffic light is displayed so that the target user can recognize the traffic light based on the traffic light prompt information.

[0122] In this embodiment of the application, when identifying traffic lights, firstly, when a target user wearing an augmented reality device is detected to be in the traffic light identification area, an image of the traffic light to be detected is acquired through the augmented reality device. Then, based on the image of the traffic light to be detected, it is detected whether the traffic light to be identified by the target user is obstructed. If an obstruction is detected, the traffic light prompt information corresponding to the traffic light is displayed through the augmented reality device. Since the target user is wearing an augmented reality device, the target user can identify the obstructed traffic light through the traffic light prompt information displayed by the augmented reality device.

[0123] Because augmented reality devices can project traffic light alerts onto the target user's retina, they can ensure that the target user receives the traffic light alerts in real time. When the target user is in the traffic light recognition area, the augmented reality device first detects whether the traffic light being recognized by the target user is obstructed. If the traffic light is obstructed, the corresponding traffic light recognition information is displayed on the target user's retina in real time. Since the traffic light can be easily recognized by the target user when there is no obstruction, the goal of real-time traffic light recognition by the target user is achieved.

[0124] Based on this, this application uses an augmented reality device to acquire an image of the traffic light to be detected when the target user is located in the traffic light recognition area. Then, if an obstruction is detected in the traffic light image, the augmented reality device displays the corresponding traffic light prompt information. Ultimately, the target user identifies the traffic light through the prompt information, thus achieving the goal of real-time traffic light recognition. This overcomes the technical shortcomings caused by the limitations of human field of vision and the uncertainty of the driving environment, which often lead to situations where drivers cannot observe traffic lights. Therefore, the target user can recognize traffic lights in real time, thus solving the problem of not being able to recognize traffic lights in real-time during driving scenarios.

[0125] Example 2

[0126] Furthermore, referring to Figure 4 In another embodiment of this application, content that is the same as or similar to that in Embodiment 1 described above can be referred to the above description and will not be repeated hereafter. Based on this, the step of matching occlusion coverage parameters for the target user according to the regional location relationship includes:

[0127] Step F10: Obtain the first coordinate point of the target user and the second coordinate point of the traffic light in a preset coordinate system, and establish the relative position axis between the target user and the traffic light based on the first coordinate point and the second coordinate point;

[0128] Step F20: Determine the occlusion / coverage angle between the relative position axis and the reference axis in the preset coordinate system;

[0129] Step F30: Match occlusion and coverage parameters for the target user based on the occlusion and coverage angle, the relative position, and the regional positional relationship.

[0130] In this embodiment, it should be noted that, since the longitudinal distance between the traffic light and the target user's vehicle in a driving scenario can be characterized by relative distance—that is, the size of the field of vision covered by the obstruction area can, to some extent, reflect the distance between the target user's vehicle and the obstruction—and since the positional relationship between the lane and the traffic light is also involved in the driving scenario, it will also affect the determination of the traffic light obstruction situation. For example, in one feasible approach, referring to... Figure 5 , Figure 5 To illustrate the obstruction between the target user and the traffic light in different lanes, since the position of the traffic light is fixed, if the target user is in the lane directly facing the traffic light, the target user will not be able to recognize the traffic light due to obstruction. If the target user is not in the lane directly facing the traffic light, the target user shown in Figures (a) and (d) will not be able to recognize the traffic light due to obstruction. The target user shown in Figures (b) and (c) can recognize the traffic light normally when the traffic light is unobstructed.

[0131] Additionally, it should be noted that to dynamically match occlusion coverage parameters for different lanes at the same lateral position, a preset coordinate system can be established using the target user as the reference point, the horizontal direction of the target user as the X-axis, and the vertical direction between the target user and the traffic light as the Y-axis. The reference axis can be either the X-axis or the Y-axis, as shown in the reference diagram. Figure 6 , Figure 6 To illustrate the preset coordinate system, p is the occlusion angle, and the line connecting the target user 21 and the traffic light 22 is the relative position axis. The occlusion parameters can be dynamically matched by comprehensively considering the occlusion angle, relative position, and regional position relationship.

[0132] As an example, steps F10 to F30 include: obtaining the first coordinate point of the target user and the second coordinate point of the traffic light in a preset coordinate system; establishing a relative position axis between the target user and the traffic light based on the first coordinate point and the second coordinate point; determining the occlusion coverage angle between the relative position axis and the reference axis in the preset coordinate system; and querying the occlusion coverage parameters of the target user in a preset mapping table using the occlusion coverage angle, the relative position, and the regional position relationship as indexes.

[0133] This application provides a method for matching occlusion coverage parameters. Specifically, it involves obtaining a first coordinate point of the target user and a second coordinate point of the traffic light in a preset coordinate system; establishing a relative position axis between the target user and the traffic light based on the first and second coordinate points; determining the occlusion coverage angle between the relative position axis and a reference axis in the preset coordinate system; and matching occlusion coverage parameters for the target user based on the occlusion coverage angle, the relative position, and the regional positional relationship. In the process of matching occlusion coverage parameters, this application establishes a preset coordinate system and determines the occlusion coverage angle within that system. Then, it uses the occlusion coverage angle, relative position, and regional positional relationship to jointly match the target user's occlusion coverage parameters. This means that the matching process considers the impact of different lanes on the occlusion of traffic lights by obstructions, thus laying the foundation for improving the accuracy of traffic light recognition.

[0134] Example 3

[0135] This application also provides a traffic light recognition device, applied to an augmented reality device, see reference. Figure 7 The traffic light recognition device includes:

[0136] The acquisition module 101 is used to acquire an image of a traffic light to be detected when it detects that a target user wearing the augmented reality device is located in the traffic light recognition area;

[0137] The detection module 102 is used to detect whether the traffic light identified by the target user is obstructed based on the image of the traffic light to be detected.

[0138] The display module 103 is used to display the corresponding traffic light prompt information if the traffic light is obstructed, so that the target user can identify the traffic light based on the traffic light prompt information.

[0139] Optionally, the detection module 102 is further configured to:

[0140] The image acquisition time for detecting whether the corresponding traffic light identifier of the traffic light does not appear in the image of the traffic light to be detected is greater than a preset acquisition time threshold.

[0141] If so, it is determined that the traffic light identified by the target user is obstructed;

[0142] If not, then it is determined that the traffic light identified by the target user is not obstructed.

[0143] Optionally, the detection module 102 is further configured to:

[0144] Determine the regional positional relationship between the target region and the field of view region in the image of the traffic light to be detected;

[0145] Based on the location relationship of the area, an occlusion coverage parameter is matched for the target user, wherein the occlusion coverage parameter is used to distinguish whether the occlusion object corresponding to the target area obstructs the target user from recognizing the traffic light;

[0146] Based on the occlusion coverage parameters, detect whether the traffic light identified by the target user is obstructed.

[0147] Optionally, the detection module 102 is further configured to:

[0148] Obtain the occlusion coverage parameters between the target area and the field of view;

[0149] Based on the relationship between the occlusion coverage parameter and the occlusion coverage parameter threshold, it is detected whether the traffic light identified by the target user is obstructed.

[0150] Optionally, the detection module 102 is further configured to:

[0151] The relative distance between the target user and the traffic light is determined based on the first position of the target user and the second position of the traffic light.

[0152] Based on the relative distance and the regional location relationship, occlusion coverage parameters are matched for the target user.

[0153] Optionally, the detection module 102 is further configured to:

[0154] In a preset coordinate system, the first coordinate point of the target user and the second coordinate point of the traffic light are obtained, and the relative position axis between the target user and the traffic light is established based on the first coordinate point and the second coordinate point.

[0155] Determine the occlusion angle between the relative position axis and the reference axis in the preset coordinate system;

[0156] Based on the occlusion coverage angle, the relative position, and the regional positional relationship, occlusion coverage parameters are matched for the target user.

[0157] Optionally, the traffic light recognition device is further used for:

[0158] Determine the dwell time of the vehicle carrying the target user within the traffic light recognition area;

[0159] Detect whether the dwell time is less than the traffic light transition time corresponding to the traffic light prompt information;

[0160] If the value is less than the specified value, a driving prompt message will be displayed indicating that the vehicle has left the traffic light recognition area.

[0161] If the time is not less than the time specified, vehicle start / stop information is generated at the traffic light transition time and sent to the vehicle so that the vehicle can perform the corresponding start / stop operation based on the vehicle start / stop information.

[0162] The traffic light recognition device provided by this invention, employing the traffic light recognition method described in the above embodiments, solves the technical problem of the inability to perform real-time recognition of traffic lights in driving scenarios. Compared with the prior art, the beneficial effects of the traffic light recognition device provided by this invention are the same as those of the traffic light recognition method described in the above embodiments, and other technical features of this traffic light recognition device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0163] Example 4

[0164] This invention provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the traffic light recognition method in Embodiment 1 above.

[0165] The following is for reference. Figure 8 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0166] like Figure 8 As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus.

[0167] Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication devices allow electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although electronic devices with various systems are shown in the figures, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0168] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1009, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of embodiments of this disclosure.

[0169] The electronic device provided by this invention, employing the traffic light recognition method described in the above embodiments, solves the technical problem of the inability to perform real-time recognition of traffic lights in driving scenarios. Compared with the prior art, the beneficial effects of the electronic device provided by this invention are the same as those of the traffic light recognition method described in the above embodiments, and other technical features of this electronic device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0170] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0171] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0172] Example 5

[0173] This embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon, which are used to execute the traffic light recognition method described in the above embodiment.

[0174] The computer-readable storage medium provided in this embodiment of the invention may be, for example, a USB flash drive, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0175] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0176] The aforementioned computer-readable storage medium carries one or more programs that, when executed by an electronic device, cause the electronic device to: acquire an image of a traffic light to be detected when it detects that a target user wearing the augmented reality device is located in a traffic light recognition area; detect whether the traffic light to be recognized by the target user is obstructed based on the image of the traffic light to be detected; and if the traffic light is obstructed, display traffic light prompt information corresponding to the traffic light so that the target user can recognize the traffic light based on the traffic light prompt information.

[0177] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0178] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0179] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0180] The computer-readable storage medium provided by this invention stores computer-readable program instructions for executing the above-described traffic light recognition method, solving the technical problem of the inability to recognize traffic lights in real time during driving scenarios. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this invention are the same as those of the traffic light recognition method provided in the above-described embodiments, and will not be repeated here.

[0181] Example 6

[0182] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the traffic light recognition method described above.

[0183] The computer program product provided in this application solves the technical problem of the inability to recognize traffic lights in real time during driving scenarios. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiments of this invention are the same as the beneficial effects of the traffic light recognition method provided in the above embodiments, and will not be repeated here.

[0184] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A traffic light recognition method, characterized in that, The traffic light recognition method, applied to augmented reality devices, includes: When a target user wearing the augmented reality device is detected to be in the traffic light recognition area, an image of the traffic light to be detected is acquired; Based on the image of the traffic light to be detected, detect whether the traffic light identified by the target user is obstructed; If the traffic light is obstructed, the corresponding traffic light prompt information is displayed so that the target user can identify the traffic light based on the traffic light prompt information; The step of detecting whether the traffic light identified by the target user is obstructed based on the image of the traffic light to be detected includes: Determine the regional positional relationship between the target region and the field of view region in the image of the traffic light to be detected; Based on the location relationship of the area, an occlusion coverage parameter is matched for the target user, wherein the occlusion coverage parameter is used to distinguish whether the occlusion object corresponding to the target area obstructs the target user from recognizing the traffic light; If the detected occlusion coverage parameter is less than the preset occlusion coverage parameter threshold, it is determined that the traffic light identified by the target user is obstructed. If the detected occlusion coverage parameter is not less than the preset occlusion coverage parameter threshold, it is determined that the traffic light identified by the target user is not obstructed. The step of matching occlusion coverage parameters for the target user based on the regional location relationship includes: The relative distance between the target user and the traffic light is determined based on the first position of the target user and the second position of the traffic light. Using the relative distance and the regional location relationship as indexes, the occlusion and coverage parameters of the target user are obtained by querying a preset mapping table.

2. The traffic light recognition method as described in any one of claims 1, characterized in that, After the step of displaying the traffic light prompt information corresponding to the traffic light, the traffic light identification method further includes: Determine the dwell time of the vehicle carrying the target user within the traffic light recognition area; Detect whether the dwell time is less than the traffic light transition time corresponding to the traffic light prompt information; If the value is less than the specified value, a driving prompt message will be displayed indicating that the vehicle has left the traffic light recognition area. If the time is not less than the time specified, vehicle start / stop information is generated at the traffic light transition time and sent to the vehicle so that the vehicle can perform the corresponding start / stop operation based on the vehicle start / stop information.

3. A traffic light recognition device, characterized in that, The traffic light recognition device, used in augmented reality devices, includes: The acquisition module is used to acquire an image of a traffic light to be detected when a target user wearing the augmented reality device is detected to be in the traffic light recognition area; A detection module is used to detect whether a traffic light identified by a target user is obstructed based on the traffic light image to be detected. The detection includes: determining the positional relationship between a target area and a field of view in the traffic light image; matching an occlusion coverage parameter to the target user based on the positional relationship, wherein the occlusion coverage parameter is used to distinguish whether an obstruction corresponding to the target area obstructs the target user's identification of the traffic light; if the occlusion coverage parameter is less than a preset occlusion coverage parameter threshold, it is determined that the traffic light identified by the target user is obstructed; if the occlusion coverage parameter is not less than the preset occlusion coverage parameter threshold, it is determined that the traffic light identified by the target user is not obstructed. Matching the occlusion coverage parameter to the target user based on the positional relationship includes: determining the relative distance between the target user and the traffic light based on a first position of the target user and a second position of the traffic light; and querying a preset mapping table using the relative distance and the positional relationship as indexes to obtain the occlusion coverage parameter for the target user. The display module is used to display the corresponding traffic light prompt information if the traffic light is obstructed, so that the target user can identify the traffic light based on the traffic light prompt information.

4. An electronic device, characterized in that, The electronic device includes: At least one processor; A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the steps of the traffic light recognition method according to any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for implementing a traffic light recognition method, which is executed by a processor to implement the steps of the traffic light recognition method as described in any one of claims 1 to 2.

Images