Traffic police gesture signal recognition method and device and augmented reality glasses

Abstract

The invention discloses a traffic police gesture signal recognition method and device and augmented reality glasses. The method is executed by augmented reality glasses, and comprises the following steps: when the augmented reality glasses are in a traffic police signal recognition mode, collecting a traffic environment image through an image collector of the augmented reality glasses, and determining whether a traffic police target exists on a current road according to the traffic environment image; when it is determined that the traffic police target exists on the current road, acquiring a traffic police gesture signal of the traffic police target; and carrying out augmented display and / or voice reminding on the gesture signal of the traffic police through the augmented reality glasses. According to the technical scheme, the user can be assisted in timely and accurately obtaining the current gesture signal of the traffic police through the augmented reality glasses.

Description

Technical Field

[0001] The present application relates to the field of augmented reality technology, and in particular to a method and device for identifying traffic police gesture signals and augmented reality glasses. Background Art

[0002] With the deepening of urbanization and the expansion of urban scale, more and more people are buying cars, which leads to the continuous increase in the number of vehicles, but the resulting road traffic pressure is also increasing. Although traditional traffic lights can control the passage of vehicles, the timetable and traffic mode are pre-set and cannot be adjusted in time according to the real-time situation, which will cause traffic congestion, especially during peak hours or when emergencies occur. In addition, traffic lights need regular maintenance and inspection to ensure normal operation. This requires a lot of human resources and capital investment, increasing the cost of urban management.

[0003] Traffic police signals are more flexible. Traffic police can adjust signals at any time according to actual conditions, such as increasing green light time or adjusting lane combinations in congested sections, so as to better manage traffic flow. At the same time, traffic police can direct traffic flow according to the needs of pedestrians and vehicles, such as increasing pedestrian passing time or simplifying turning rules at intersections during peak hours. However, since there are eight types of traffic police gestures at this stage, some gestures are relatively similar. It is difficult for drivers to accurately remember the meaning of each gesture, which can easily lead to confusion and misunderstandings and accidents, and may affect traffic efficiency. Summary of the invention

[0004] The embodiments of the present application provide a method, device and augmented reality glasses for identifying traffic police gesture signals to assist users in accurately interpreting the traffic meaning of traffic police gestures.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for identifying a traffic police hand gesture signal, the method being performed by augmented reality glasses, the method comprising:

[0007] When the augmented reality glasses are in the traffic police signal recognition mode, the image collector of the augmented reality glasses collects a traffic environment image, and determines whether there is a traffic police target on the current road according to the traffic environment image;

[0008] When it is determined that there is a traffic police target on the current road, obtaining a traffic police hand gesture signal of the traffic police target;

[0009] The traffic police gesture signal is enhanced by displaying and / or voice reminding through the augmented reality glasses.

[0010] In a second aspect, an embodiment of the present application further provides a traffic police hand gesture signal recognition device, the device being applied to augmented reality glasses, the traffic police hand gesture signal recognition device comprising:

[0011] A target detection unit, used for collecting a traffic environment image through the image collector of the augmented reality glasses when the augmented reality glasses are in a traffic police signal recognition mode, and determining whether there is a traffic police target on the current road according to the traffic environment image;

[0012] A signal recognition unit, used for obtaining a traffic police gesture signal of a traffic police target when it is determined that there is a traffic police target on the current road;

[0013] A signal display unit is used to enhance the display of the traffic police gesture signal through the augmented reality glasses and / or voice remind the traffic police gesture signal.

[0014] In a third aspect, the present application also provides an augmented reality glasses, including:

[0015] Processor; and

[0016] A memory is arranged to store computer executable instructions, which, when executed, cause the processor to perform a traffic police gesture signal recognition method.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs, and when the one or more programs are executed by augmented reality glasses including multiple application programs, the augmented reality glasses perform a traffic police gesture signal recognition method.

[0018] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0019] In the embodiment of the present application, the augmented reality glasses recognize traffic police gesture signals. When the augmented reality glasses are in the traffic police signal recognition mode, the image collector of the augmented reality glasses is first used to collect traffic environment images to determine whether there is a traffic police target on the current road based on the traffic environment image. When it is determined that there is a traffic police target on the current road, the traffic police gesture signal of the traffic police target is obtained to send the traffic police gesture signal to the user through at least one of the voice function and the enhanced display function of the augmented reality glasses, so that the user can promptly and accurately know the current gesture signal of the traffic police. Moreover, recognizing the traffic police gesture signal by the enhanced display glasses can not affect the user's forward line of sight, and can avoid safety hazards caused by line of sight diversion. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A flow chart of a method for identifying a traffic police hand gesture signal in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of a middle display area, a left display area, and a right display area of ​​an enhanced display interface in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of a C-shaped display area of ​​an enhanced display interface in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of an inverted H-shaped display area of ​​an enhanced display interface in an embodiment of the present application;

[0025] Figure 5 This is a schematic diagram of a traffic police gesture recognition process in a vehicle driving scenario in an embodiment of the present application;

[0026] Figure 6 This is a structural schematic diagram of a traffic police hand gesture signal recognition device in an embodiment of the present application;

[0027] Figure 7 This is a schematic diagram of the structure of an augmented reality glasses in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0029] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0030] The present application embodiment provides a method for identifying traffic police gesture signals, such as Figure 1 As shown, a flow chart of a method for identifying a traffic police hand gesture signal in an embodiment of the present application is provided, and the method at least includes the following steps S110 to S130:

[0031] Step S110, when the augmented reality glasses are in the traffic police signal recognition mode, the image collector of the augmented reality glasses collects a traffic environment image, and determines whether there is a traffic police target on the current road based on the traffic environment image.

[0032] At present, augmented reality (AR) devices mainly include glasses, head-mounted, and vehicle-mounted (such as Head up Display, HUD), etc. Among them, head-mounted is more suitable for indoor scenes, but not for complex traffic scenes; although the vehicle-mounted is set in the vehicle cockpit, it requires the driver to shift his sight from the road to the display screen of the vehicle-mounted AR device, which will affect the driver's observation of the road environment and pose certain safety hazards. However, the glasses type has no restrictions on the application scenarios, and the glasses type AR device is directly worn on the user's eyes, which does not affect the user's observation of the external environment. Especially in the vehicle driving scene, the driver does not need to shift his sight, which can improve driving safety to a certain extent.

[0033] In this way, the traffic police hand gesture signal recognition method of the embodiment of the present application is executed by the augmented reality glasses. The augmented reality glasses of the embodiment of the present application include multiple working modes, one of which is the traffic police signal recognition mode. When the augmented reality glasses are in the traffic police signal recognition mode, the embodiment of the present application starts the traffic police hand gesture signal recognition. During the recognition process, the traffic environment image is firstly collected by the image collector of the augmented reality glasses. The image collector can be a camera or other visual sensor. The traffic environment image can be an original image collected by a camera, or a spliced ​​image of the original images collected by multiple cameras.

[0034] In the embodiment of the present application, a target detection algorithm can be used to perform target detection on a traffic environment image, so as to determine whether there is a traffic police target on the current road based on the target detection result. The target detection algorithm can be a traditional target detection algorithm or a convolutional neural network model obtained by neural network training, such as a YOLOv3 model.

[0035] Step S120, when it is determined that there is a traffic police target on the current road, a traffic police gesture signal of the traffic police target is obtained.

[0036] When a traffic police target is detected on the current road, the traffic police target can be tracked and detected to obtain the traffic police gesture signal of the traffic police target. The traffic police gesture signal in the embodiment of the present application refers to one of the eight standard traffic police gesture signals: stop signal, straight signal, left turn signal, right turn signal, left turn waiting signal, lane change signal, slow down signal, and vehicle pull over signal.

[0037] Step S130, enhancing the display of the traffic police gesture signal through the augmented reality glasses and / or voice reminder.

[0038] When the traffic police hand gesture signal of the traffic police target is obtained, the recognized traffic police hand gesture signal can be sent to the user through at least one reminder method of voice reminder and enhanced display, so that the user can know the current hand gesture signal of the traffic police in a timely and accurate manner.

[0039] like Figure 1 It can be seen from the traffic police gesture signal recognition method shown that in the embodiment of the present application, the traffic police gesture signals are recognized by the augmented reality glasses. When the augmented reality glasses are in the traffic police signal recognition mode, the traffic environment image is first collected by the image collector of the augmented reality glasses to determine whether there is a traffic police target on the current road based on the traffic environment image. When it is determined that there is a traffic police target on the current road, the traffic police gesture signal of the traffic police target is obtained to send the traffic police gesture signal to the user through at least one of the voice function and enhanced display function of the augmented reality glasses, so that the user can timely and accurately know the current gesture signal of the traffic police, and the recognition of the traffic police gesture signal by the enhanced display glasses can also not affect the user's forward line of sight, and can avoid safety hazards caused by line of sight diversion.

[0040] In some embodiments of the present application, determining whether there is a traffic police target on the current road according to the traffic environment image includes:

[0041] Build the YOLOv3 model and test dataset;

[0042] The YOLOv3 model is trained using the test data set to obtain the target detection mode for detecting traffic police targets;

[0043] The target detection mode is used to perform target detection on the traffic environment image to obtain a target detection result, so as to determine whether there is a traffic police target on the current road according to the target detection result.

[0044] The test data set in this embodiment can be sample images including traffic police targets and excluding traffic police targets collected under different traffic environments, such as different road sections and different traffic conditions (for example, including unblocked traffic, congested traffic, heavy rain, blizzard, haze, water accumulation, snow accumulation, etc.). The sample images can be annotated using annotation tools or manually, and the YOLOv3 model can be trained based on the sample images and their annotation information, and the YOLOv3 model that achieves the training objectives can be used as the target detection model.

[0045] The loss function of the target detection model in this embodiment includes the target confidence loss L conf (o, c), target category loss L cla (O, C) and target localization loss L loc , where the target confidence loss L conf(o, c) is used to predict whether there is a real target in the i-th target detection box, and the target category loss L cla (O, C) is used to predict whether there is a j-th target in the i-th target detection box and the target positioning loss L loc It is the difference in position and size between the predicted box and the actual box.

[0046] The above three loss functions are specifically:

[0047] L conf(o，c) =-∑(o i ln(c i )+(1-o i )ln(1-c i )),

[0048] L cla (O, C) = -∑ iPos ∑ j∈cla (O ij In(c ij )+(1-O ij )ln(1-c ij )),

[0049]

[0050] In the above formula, o i ∈{0,1},o ij ∈{0, 1} represents the actual category value, c i 、c ij represents the network prediction value, P pre Represents the center point coordinates of the prediction box, P gt Indicates the center coordinates of the actual box, S pre Indicates the length and width of the prediction box, S gt represents the length and width of the actual frame, and λ is the tuning parameter.

[0051] In other embodiments of the present application, when collecting traffic environment images through the image collector of the augmented reality glasses, the method further includes:

[0052] Performing target detection on the traffic environment image to obtain target detection results about traffic participants;

[0053] Obtain virtual information corresponding to the target detection result of each traffic participant;

[0054] Each traffic participant is enhanced and displayed based on the target detection results and virtual information of each traffic participant.

[0055] For example, the U-Net semantic segmentation model can be used to perform semantic segmentation on the traffic environment image regarding traffic participants, and target detection information such as location information and pixel information of each traffic participant can be obtained based on the semantic segmentation result. Traffic participants include, for example, pedestrians, traffic police, vehicles, traffic lights, obstacles (obstacles such as buildings, etc.), and any other targets of interest that may appear in the traffic scene. In addition, the embodiment of the present application also obtains virtual information corresponding to each traffic participant, and the virtual information includes, for example, color effects, brightness effects, etc.

[0056] Then, based on the target detection result of each traffic participant and in combination with the first augmented display interface and the second augmented display interface of the augmented reality glasses and the calibration parameters of its camera, the pixel position of each traffic participant in the first augmented display interface and the second augmented display interface is determined, and the traffic participant is enhanced displayed by controlling virtual information such as the color effect and / or brightness effect of the pixel point at the pixel position.

[0057] Exemplarily, taking the traffic police as an example, the RGB values ​​of the pixels of the detected traffic police targets at the relevant pixel positions on the first enhanced display interface and the second enhanced display interface are simultaneously increased by γ, and the γ value can be adjusted according to weather information and / or traffic status information. Then, when the user observes the real environment through the augmented reality glasses, the observed real environment image will be superimposed with virtual information about the traffic police, that is, the background color in the observed real environment image is approximately the color of the real environment, and the color of the traffic police, the target of interest, is different from the real environment due to the superposition of virtual information. In this way, the traffic police targets can be enhanced and displayed through the augmented reality glasses to remind users to pay attention to such targets.

[0058] When it is determined that there is a traffic police target on the current road, the traffic police gesture signal recognition method of the embodiment of the present application further includes:

[0059] Determining whether the traffic police target is facing the augmented reality glasses;

[0060] When the traffic police target faces the augmented reality glasses, a traffic police gesture signal of the traffic police target is obtained.

[0061] In actual applications, the direction of the traffic police's face is the direction of the traffic police's command. When the traffic police is not facing the augmented reality glasses, it can be determined that the traffic police's hand gesture signal is not to direct the vehicle or pedestrian in the direction of the user, and there is no need to recognize the traffic police's hand gesture signal and send it to the user. Therefore, before recognizing the traffic police's hand gesture signal, the embodiment of the present application first determines whether the traffic police's target is facing the user. The determination method includes, for example:

[0062] Performing facial detection on the traffic police target to obtain a facial detection result, wherein the facial detection result includes detecting complete facial features and not detecting complete facial features;

[0063] If the facial detection result is that complete facial features are detected, determining that the traffic police target is facing the augmented reality glasses;

[0064] If the facial detection result is that no complete facial features are detected, it is determined that the traffic police target is not facing the augmented reality glasses.

[0065] It should be noted that the “complete facial features” in the embodiments of the present application can be understood as when the facial features of at least one of the eyes, mouth, and nose are detected, it is determined that the complete facial features are detected.

[0066] In some scenarios of actual applications, due to the user's head turning and other actions, the detection results determined based on the facial feature detection method may not be accurate. For example, when the user turns his head to the right significantly, the detection result obtained based on the facial feature detection method is that the traffic police target is facing the augmented reality glasses, but because the user turns his head significantly, the direction of the traffic police's current gesture action may not be the user's driving direction. In other words, the traffic police's gesture signal in this case is not the traffic police gesture signal that the user is interested in.

[0067] In order to prevent irrelevant traffic police gesture signals from interfering with the user's perception of the real environment, the embodiment of the present application addresses the above problem. Before performing facial detection on the traffic police target, posture information of the augmented reality glasses is also obtained, and the posture information includes a head-on posture and a non-head-on posture; when the posture information of the augmented reality glasses is a head-on posture, facial detection is performed on the traffic police target. In this way, based on the facial detection result, it can be determined that the traffic police target is facing the user's driving direction, and the traffic police gesture signal can be further identified and sent to the user.

[0068] In practical applications, the augmented reality glasses of the embodiments of the present application can obtain their posture information through relevant sensors such as an inertial measurement unit (IMU), where the "head-up posture" can be understood as a state where the angle between the optical axis direction of the augmented reality glasses and the user's driving direction is less than a preset angle value, and the preset angle value can be flexibly set according to needs.

[0069] Thus, the conditions for the augmented reality glasses of the embodiment of the present application to detect the traffic police hand gesture signal can be determined through the above embodiment. When the above relevant conditions are met, the embodiment of the present application can obtain the traffic police hand gesture signal of the traffic police target through the following steps:

[0070] Acquire the sub-image where the traffic police target is located from the traffic environment image to prevent non-target images from interfering with the recognition of traffic police gesture signals;

[0071] Performing human body reconstruction detection on the sub-image through a pre-constructed human body posture reconstruction model to obtain a reconstructed human body point cloud, wherein the human body posture reconstruction model includes, for example, an Hs-Net human body posture reconstruction model. Of course, those skilled in the art may also use other human body posture reconstruction models, which are not specifically limited in the present embodiment of the application;

[0072] Extracting feature points from the human body point cloud according to the three-dimensional coordinates of the human body point cloud to obtain a feature point extraction result, such as extracting feature points of the upper body;

[0073] The feature point extraction result is classified and detected by a multi-layer perceptron to obtain a classification detection result, so as to obtain the traffic police hand gesture signal of the traffic police target according to the classification detection result. When the traffic police hand gesture signal includes the eight standard traffic police hand gesture signals mentioned above, any one of the above standard traffic police hand gesture signals can be detected by the multi-layer perceptron of the embodiment of the present application.

[0074] Among them, the multilayer perceptron (Multilayer Perceptron, MLP) is a forward structure artificial neural network, including an input layer, an output layer and multiple hidden layers. The embodiment of the present application does not limit the specific network structure of the multilayer perceptron, and those skilled in the art can flexibly set it. In other embodiments of the present application, other classifiers can also be used to classify and detect the feature point extraction results, and the embodiments of the present application are not illustrated one by one here.

[0075] The augmented reality glasses of the embodiment of the present application may be optical perspective type, that is, this type of augmented reality glasses places an optical combiner in front of the user's eyes, a part of the optical combiner is light-transmissive and used to display the picture of the real environment, and the other part is reflective and used to display virtual information. The projection device of the augmented reality glasses projects the virtual information onto the optical combiner, and the optical combiner reflects the virtual information to the user's eyes, realizing the superposition of the real picture and the virtual information, and realizing the augmented reality of the real information. Of course, the augmented reality glasses of the embodiment of the present application may also be video perspective type, mirror reflection type, etc. No matter what kind of augmented reality display method is used, the augmented reality glasses include a first augmented display interface for the left eye and a second augmented display interface for the right eye, wherein the augmented display interface is used to display virtual information.

[0076] Accordingly, in some embodiments of the present application, the traffic police hand gesture signal may be enhanced and displayed through the following steps:

[0077] Acquire enhanced display information corresponding to the traffic police hand gesture signal, wherein the enhanced display information includes a target enhanced display interface, a target display area on the target enhanced display interface, and a display effect of the target display area; optionally, the target enhanced display interface is a first enhanced display interface or a second enhanced display interface, and performing augmented reality of the traffic police hand gesture signal on one enhanced display interface instead of two enhanced display interfaces simultaneously can minimize the interference of virtual information with external real information;

[0078] The target display area on the target enhanced display interface is controlled to display with the display effect corresponding to the traffic police gesture signal.

[0079] like Figures 2 to 4 As shown, the target display area of ​​the embodiment of the present application includes at least one of a middle display area, a left display area and a right display area, a C-shaped display area, and an inverted H-shaped display area. The display effect of the target display area includes a color effect and a brightness effect. The color effect includes a green filter effect and a red filter effect. The brightness effect includes a constant brightness effect and a non-constant brightness effect.

[0080] Specifically, the embodiment of the present application can pre-set an enhanced display information table of various types of traffic police hand gesture signals, so that the enhanced display information corresponding to the traffic police hand gesture signals can be obtained through the table. Specifically, the display areas and display effects of the above eight standard traffic police hand gesture signals in the enhanced display information table are as follows:

[0081] If the current traffic police hand signal is a stop signal, the middle display area of ​​the target enhanced display interface is used as the target display area, the color effect of the middle display area is set to a red filter effect, and the brightness effect is set to a constant brightness effect. The constant brightness effect means that the brightness curve of the target display area is the same as the brightness curve of the non-target display area, both of which are linear brightness curves. Figure 2 The middle area shown.

[0082] If the current traffic police hand signal is a straight ahead signal, the middle display area of ​​the target enhanced display interface is used as the target display area, the color effect of the middle display area is set to a green filter effect, and the brightness effect is set to a constant brightness effect.

[0083] If the current traffic police gesture signal is a slow-down signal, the middle display area, the left display area, and the right display area of ​​the target enhanced display interface are simultaneously used as the target display area (that is, the entire target enhanced display interface is used as the target display area). At this time, the color effect of the entire target enhanced display interface is set to a green filter effect, and the brightness effect is set to a non-constant brightness effect. The non-constant brightness effect means that the brightness curve of the target display area is different from the brightness curve of the non-target display area. The brightness curve of the target display area is, for example, a periodic curve such as a sawtooth or triangle. Optionally, the non-constant brightness effect of the embodiment of the present application can be a gradually brightening and dimming effect of a breathing light. Among them, the entire target enhanced display interface is, for example, Figure 2 The entire area shown.

[0084] If the current traffic police hand signal is a left turn signal (or a right turn signal), the left display area (or the right display area) of the target enhanced display interface is used as the target display area, and the color effect of the left display area (or the right display area) is set to a green filter effect, and the brightness effect is set to a constant brightness effect. Figure 2 The left area shown, the right display area is for example Figure 2 The right area shown.

[0085] If the current traffic police hand signal is a left turn waiting signal, the left display area of ​​the target enhanced display interface is used as the target display area, the color effect of the left display area is set to a green filter effect, and the brightness effect is set to a non-constant brightness effect.

[0086] If the current traffic police hand signal is a lane change signal, the C-shaped display area of ​​the target enhancement display interface is used as the target display area, the color effect of the C-shaped display area is set to a green filter effect, and the brightness effect is set to a constant brightness effect. Figure 3 The display area shown.

[0087] If the current traffic police hand signal is a vehicle pull-over signal, the inverted H-shaped display area of ​​the target enhancement display interface is used as the target display area, the color effect of the inverted H-shaped display area is set to a red filter effect, and the brightness effect is set to a non-constant brightness effect. Figure 4 The display area shown.

[0088] It should be noted that the embodiment of the present application sets the display area and display effect of various traffic police hand gesture signals based on the method of "seeing the shape and knowing the meaning", that is, when the user views the display area and its display effect, he can quickly understand the traffic police hand gesture signal corresponding to the display area with the display effect. Because, in actual traffic scenes, green is usually used to indicate passage and red is used to indicate stop, the embodiment of the present application sets the color effect to a green filter effect and a red filter effect, and then distinguishes different traffic police hand gesture signals in the same display area based on the constant brightness effect and the non-constant brightness effect (the non-constant brightness effect is, for example, the gradual brightening and dimming effect of the breathing light). It should be understood that those skilled in the art can also set other forms of display areas and display effects for each traffic police hand gesture signal.

[0089] In some embodiments of the present application, the above steps control the display area on the target enhanced display interface to display the display effect corresponding to the traffic police gesture signal, specifically including:

[0090] Acquire an R channel target value or a G channel target value of the target display area, wherein the R channel target value or the G channel target value is different from a current R channel value or a current G channel value of a non-target display area on the target enhanced display interface; and acquire a target brightness curve of the target display area, wherein the target brightness curve is linear or non-linear, and the brightness value of the linear brightness curve is the same as the current brightness value of the non-target display area;

[0091] The R channel value of the target display area is modified to the R channel target value or the G channel value is modified to the G channel target value, and the display brightness of the target display area is controlled according to the target brightness curve, and the RGB value of the non-target display area and the brightness curve of the non-target display area are kept unchanged.

[0092] For example, it is assumed that the brightness value of the non-target display area is L.

[0093] For the stop signal, the augmented reality glasses set the R channel value of the middle display area of ​​the first augmented reality interface (or the second augmented reality interface) to α and the brightness value to L, so that the virtual information displayed by the first augmented reality interface is superimposed on the real environment image observed by the user through the augmented reality glasses. In the embodiment of the present application, the virtual information at this time is specifically the red filter effect of the middle display area, so the user can know from the information observed that the current traffic police gesture signal is a stop signal.

[0094] For the straight-ahead signal, the augmented reality glasses set the G-channel value of the middle display area of the first augmented reality interface (or the second augmented reality interface) to β and the brightness value to L. In this way, the virtual information displayed on the first augmented reality interface is superimposed on the real environment image observed by the user through the augmented reality glasses. In the embodiment of the present application, the virtual information at this time is specifically the green filter effect in the middle display area. Therefore, the user can know that the current traffic police gesture signal is the straight-ahead signal through the information observed by him / her.

[0095] For the slow down signal, the augmented reality glasses set the G-channel value of the entire display area of the first augmented reality interface (or the second augmented reality interface) to β, and the brightness curve is set, for example, as a sawtooth periodic curve from L to N, where N < L. In this way, the virtual information displayed on the first augmented reality interface is superimposed on the real environment image observed by the user through the augmented reality glasses. In the embodiment of the present application, the virtual information at this time is specifically the green filter effect in the entire display area and the breathing light effect of gradually brightening and dimming. Therefore, the user can know that the current traffic police gesture signal is the slow down signal through the information observed by him / her.

[0096] For the left turn signal (or right turn signal), the augmented reality glasses set the G-channel value of the left display area (or right display area) of the first augmented reality interface (or the second augmented reality interface) to β and the brightness value to L. In this way, the virtual information displayed on the first augmented reality interface is superimposed on the real environment image observed by the user through the augmented reality glasses. In the embodiment of the present application, the virtual information at this time is specifically the green filter effect in the left display area (or right display area). Therefore, the user can know that the current traffic police gesture signal is the left turn signal through the information observed by him / her.

[0097] For the left turn waiting signal, the augmented reality glasses set the G-channel value of the left display area of the first augmented reality interface (or the second augmented reality interface) to β, and the brightness curve is set, for example, as a sawtooth periodic curve from L to N. In this way, the virtual information displayed on the first augmented reality interface is superimposed on the real environment image observed by the user through the augmented reality glasses. In the embodiment of the present application, the virtual information at this time is specifically the green filter effect in the left display area and the breathing light effect of gradually brightening and dimming. Therefore, the user can know that the current traffic police gesture signal is the left turn waiting signal through the information observed by him / her.

[0098] For lane change signals, the augmented reality glasses set the G channel value of the C-shaped display area of ​​the first augmented reality interface (or the second augmented reality interface) to β and the brightness value to L. In this way, the virtual information displayed by the first augmented reality interface is superimposed on the real environment image observed by the user through the augmented reality glasses. In the embodiment of the present application, the virtual information at this time is specifically the green filter effect of the C-shaped display area. Therefore, the user can know from the information observed that the current traffic police gesture signal is a lane change signal.

[0099] For the vehicle pull-over parking signal, the augmented reality glasses set the G channel value of the inverted H-shaped display area of ​​the first augmented reality interface (or the second augmented reality interface) to β, and set the brightness curve to a sawtooth periodic curve from L to N. In this way, the virtual information displayed by the first augmented reality interface is superimposed on the real environment image observed by the user through the augmented reality glasses. In the embodiment of the present application, the virtual information at this time is specifically the green filter effect of the inverted H-shaped display area and the gradual brightening and dimming effect of the breathing light. Therefore, the user can know from the information observed that the current traffic police gesture signal is a vehicle pull-over parking signal.

[0100] Among them, α, β, and L in the above embodiments of the present application can be adjusted according to weather information and / or traffic status information. For example, the light brightness in the current real environment is collected in real time and the light brightness is used as L, or the value of L is set based on the current weather information. Similarly, the values ​​of α and β can also be set.

[0101] In addition, in some application scenarios, the augmented reality glasses may recognize multiple traffic police gesture signals in sequence in a short period of time. In this case, the multiple traffic police gesture signals can be merged and the merged gesture signal can be displayed.

[0102] Specifically, before controlling the target display area on the target enhanced display interface to display the display effect corresponding to the traffic police gesture signal, the method further includes:

[0103] Determine whether the current traffic police hand signal and the previous traffic police hand signal meet the combined display condition, for example, determine whether the time interval between the current traffic police hand signal and the previous traffic police hand signal is less than the preset time threshold, whether the current traffic police hand signal and the previous traffic police hand signal can be displayed on the same screen, for example, the straight signal and the left turn waiting signal mentioned above can be displayed on the same screen, the straight signal and the right turn signal (or left turn signal) mentioned above can also be displayed on the same screen, and the straight signal and the slow down signal mentioned above can also be displayed on the same screen. When the time interval between the current traffic police hand signal and the previous traffic police hand signal is less than the preset time threshold, and the current traffic police hand signal and the previous traffic police hand signal can be displayed on the same screen, it is determined that the two meet the combined display condition. The preset time threshold here can be a time value in seconds, such as 3 seconds or other values; "display on the same screen" can be determined according to the gesture actions generated by the traffic police in the actual traffic scene, and this embodiment will not be illustrated one by one here.

[0104] If the current traffic police hand gesture signal and the previous traffic police hand gesture signal meet the combined display condition, then the enhanced display information corresponding to the combined hand gesture signal obtained by combining the current traffic police hand gesture signal and the previous traffic police hand gesture signal is obtained, and the target display area on the target enhanced display interface is controlled to display with the display effect corresponding to the combined hand gesture signal; otherwise, the target display area on the target enhanced display interface is controlled to display with the display effect corresponding to the current traffic police hand gesture signal. The enhanced display information corresponding to the combined hand gesture signal may be a combination of the enhanced display information of the two traffic police hand gesture signals, or may be enhanced display information set separately.

[0105] In order to facilitate the understanding of the various embodiments of the present application, Figure 5 As shown, a schematic diagram of the traffic police gesture recognition process in a vehicle driving scene in an embodiment of the present application is provided. First, a traffic environment image is collected using the camera of the augmented reality glasses, and target detection is performed on the traffic environment image to obtain a target detection result including a traffic police target; then a sub-image where the traffic police target is located is cropped from the traffic environment image, and the size of the sub-image can be cropped according to the size required by the human posture reconstruction model, or it can be cropped based on the target detection frame, and then the cropped image is resized to obtain the size required by the human posture reconstruction model. The sub-image where the traffic police target is located is input into the human posture estimation model, which specifically includes a human posture reconstruction model, a feature extraction network, and a multi-layer perceptron. The traffic police gesture signal of the traffic police target is obtained through the classification detection result of the multi-layer perceptron; the traffic police gesture signal is sent to the user through voice and enhanced display.

[0106] It can be seen that in the embodiment of the present application, in traffic congestion or complex road scenes, various traffic police gesture signals made by traffic police targets are identified through augmented reality glasses, and different virtual information is generated for different traffic police gesture signals, so as to display traffic police gesture signals to users through real environment images superimposed with corresponding virtual information, thereby helping drivers to quickly and accurately understand the gesture signals made by traffic police, and avoid traffic congestion and safety hazards caused by misinterpretation of traffic police gesture signals.

[0107] The present application embodiment also provides a traffic police hand gesture signal recognition device 600, such as Figure 6 As shown, a schematic diagram of the structure of a traffic police hand gesture signal recognition device in an embodiment of the present application is provided, wherein the device 600 comprises: a target detection unit 610, a signal recognition unit 620 and a signal display unit 630, wherein:

[0108] The target detection unit 610 is used to collect a traffic environment image through the image collector of the augmented reality glasses when the augmented reality glasses are in the traffic police signal recognition mode, and determine whether there is a traffic police target on the current road according to the traffic environment image;

[0109] The signal recognition unit 620 is used to obtain the traffic police gesture signal of the traffic police target when it is determined that there is a traffic police target on the current road;

[0110] The signal display unit 630 is used to enhance the display and / or voice remind the traffic police gesture signal through the augmented reality glasses.

[0111] In some embodiments of the present application, the signal recognition unit 620 is also used to determine whether a traffic police target is facing the augmented reality glasses when it is determined that there is a traffic police target on the current road; when the traffic police target is facing the augmented reality glasses, obtain the traffic police gesture signal of the traffic police target.

[0112] In some embodiments of the present application, the signal recognition unit 620 is specifically used to perform facial detection on the traffic police target to obtain a facial detection result, wherein the facial detection result includes detecting complete facial features and not detecting complete facial features; if the facial detection result is detecting complete facial features, it is determined that the traffic police target is facing the augmented reality glasses; if the facial detection result is not detecting complete facial features, it is determined that the traffic police target is not facing the augmented reality glasses.

[0113] In some embodiments of the present application, the signal recognition unit 620 is also used to obtain posture information of the augmented reality glasses before performing facial detection on the traffic police target, and the posture information includes a head-on posture and a non-head-on posture; when the posture information of the augmented reality glasses is a head-on posture, performing facial detection on the traffic police target.

[0114] In some embodiments of the present application, the signal recognition unit 620 is specifically used to obtain a sub-image where the traffic police target is located from the traffic environment image; perform human body reconstruction detection on the sub-image through a pre-constructed human body posture reconstruction model to obtain a reconstructed human body point cloud; extract feature points of the human body point cloud according to the three-dimensional coordinates of the human body point cloud to obtain a feature point extraction result; perform classification detection on the feature point extraction result through a multi-layer perceptron to obtain a classification detection result, so as to obtain the traffic police gesture signal of the traffic police target according to the classification detection result.

[0115] In some embodiments of the present application, the augmented reality glasses include a first enhanced display interface for the left eye and a second enhanced display interface for the right eye, and the signal display unit 630 is specifically used to obtain enhanced display information corresponding to the traffic police gesture signal, the enhanced display information including a target enhanced display interface, a target display area on the target enhanced display interface, and a display effect of the target display area; the target display area on the target enhanced display interface is controlled to display with the display effect corresponding to the traffic police gesture signal.

[0116] In some embodiments of the present application, the signal display unit 630 is specifically used to determine whether the current traffic police gesture signal and the previous traffic police gesture signal meet the combined display condition before controlling the target display area on the target enhanced display interface to display the display effect corresponding to the traffic police gesture signal;

[0117] If the current traffic police gesture signal and the previous traffic police gesture signal meet the combined display conditions, then obtain the enhanced display information corresponding to the combined gesture signal obtained by combining the current traffic police gesture signal and the previous traffic police gesture signal, and control the target display area on the target enhanced display interface to display with the display effect corresponding to the combined gesture signal; otherwise, control the target display area on the target enhanced display interface to display with the display effect corresponding to the current traffic police gesture signal.

[0118] In some embodiments of the present application, the target enhanced display interface adopts an RGB color mode, and the signal display unit 630 is specifically used to obtain an R channel target value or a G channel target value of the target display area, wherein the R channel target value or the G channel target value is different from a current R channel value or a current G channel value of a non-target display area on the target enhanced display interface; and, to obtain a target brightness curve of the target display area, wherein the target brightness curve is linear or non-linear, and the brightness value of the linear brightness curve is the same as the current brightness value of the non-target display area; the R channel value of the target display area is modified to the R channel target value or the G channel value is modified to the G channel target value, and the display brightness of the target display area is controlled according to the target brightness curve, and the RGB value of the non-target display area and the brightness curve of the non-target display area are kept unchanged.

[0119] In some embodiments of the present application, the target detection unit is further used to perform target detection on the traffic environment image to obtain target detection results about traffic participants; obtain virtual information corresponding to each traffic participant;

[0120] Correspondingly, the signal display unit 630 is also used to enhance the display of each traffic participant according to the target detection result and virtual information of each traffic participant.

[0121] It can be understood that the above-mentioned traffic police gesture signal recognition device can implement the various steps of the traffic police gesture signal recognition method provided in the aforementioned embodiment, and the relevant explanations about the traffic police gesture signal recognition method are applicable to the traffic police gesture signal recognition device and will not be repeated here.

[0122] Figure 7 This is a schematic diagram of the structure of an augmented reality glasses in one embodiment of the present application. Please refer to Figure 7 At the hardware level, the augmented reality glasses include a processor, and optionally an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the augmented reality glasses may also include hardware required for other services.

[0123] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0124] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0125] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a traffic police hand gesture signal recognition device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0126] When the augmented reality glasses are in the traffic police signal recognition mode, the image collector of the augmented reality glasses collects a traffic environment image, and determines whether there is a traffic police target on the current road according to the traffic environment image;

[0127] When it is determined that there is a traffic police target on the current road, obtaining a traffic police hand gesture signal of the traffic police target;

[0128] The traffic police gesture signal is enhanced by displaying and / or voice reminding the traffic police through the augmented reality glasses.

[0129] The above application Figure 1The method performed by the traffic police gesture signal recognition device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0130] The augmented reality glasses can also perform Figure 1 The method for executing the traffic police hand gesture signal recognition device in the Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0131] The embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by augmented reality glasses including multiple application programs, enable the augmented reality glasses to execute Figure 1 The method performed by the traffic police hand gesture signal recognition device in the illustrated embodiment is specifically used to perform:

[0132] When the augmented reality glasses are in the traffic police signal recognition mode, the image collector of the augmented reality glasses collects a traffic environment image, and determines whether there is a traffic police target on the current road according to the traffic environment image;

[0133] When it is determined that there is a traffic police target on the current road, obtaining a traffic police hand gesture signal of the traffic police target;

[0134] The traffic police gesture signal is enhanced by displaying and / or voice reminding through the augmented reality glasses.

[0135] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0137] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0139] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0140] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0141] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0142] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0143] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0144] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for identifying traffic police hand gesture signals, characterized in that: The method is performed by augmented reality glasses, and the traffic police gesture signal recognition method includes: When the augmented reality glasses are in the traffic police signal recognition mode, the image collector of the augmented reality glasses collects a traffic environment image, and determines whether there is a traffic police target on the current road according to the traffic environment image; When it is determined that there is a traffic police target on the current road, obtaining a traffic police hand gesture signal of the traffic police target; The traffic police gesture signal is enhanced by displaying and / or voice reminding the traffic police through the augmented reality glasses.

2. The method for identifying traffic police hand gesture signals according to claim 1, characterized in that: When it is determined that there is a traffic police target on the current road, the method further includes: Determining whether the traffic police target is facing the augmented reality glasses; When the traffic police target faces the augmented reality glasses, a traffic police gesture signal of the traffic police target is obtained.

3. The method for identifying traffic police hand gesture signals as claimed in claim 2, characterized in that: The determining whether the traffic police target is facing the augmented reality glasses includes: Performing facial detection on the traffic police target to obtain a facial detection result, wherein the facial detection result includes detecting complete facial features and not detecting complete facial features; If the facial detection result is that complete facial features are detected, determining that the traffic police target is facing the augmented reality glasses; If the facial detection result is that no complete facial features are detected, it is determined that the traffic police target is not facing the augmented reality glasses.

4. The method for identifying traffic police hand gesture signals as claimed in claim 3, characterized in that: Before performing facial detection on the traffic police target, the method further includes: Acquire posture information of the augmented reality glasses, wherein the posture information includes a head-up posture and a non-head-up posture; When the posture information of the augmented reality glasses is a head-on posture, face detection is performed on the traffic police target.

5. The method for identifying traffic police hand gesture signals according to claim 1, characterized in that: When it is determined that there is a traffic police target on the current road, obtaining the traffic police gesture signal of the traffic police target includes: Acquire a sub-image where the traffic police target is located from the traffic environment image; Performing human body reconstruction detection on the sub-image using a pre-built human body posture reconstruction model to obtain a reconstructed human body point cloud; Extracting feature points from the human body point cloud according to the three-dimensional coordinates of the human body point cloud to obtain a feature point extraction result; The feature point extraction result is classified and detected by a multi-layer perceptron to obtain a classification detection result, so as to obtain the traffic police gesture signal of the traffic police target according to the classification detection result.

6. The method for identifying traffic police hand gesture signals according to claim 1, characterized in that: The augmented reality glasses include a first augmented display interface for the left eye and a second augmented display interface for the right eye, and the traffic police hand gesture signal is enhanced and displayed through the following steps: Acquire enhanced display information corresponding to the traffic police hand gesture signal, wherein the enhanced display information includes a target enhanced display interface, a target display area on the target enhanced display interface, and a display effect of the target display area; The target display area on the target enhanced display interface is controlled to display with the display effect corresponding to the traffic police gesture signal.

7. The method for identifying traffic police hand gesture signals as claimed in claim 6, characterized in that: Before controlling the target display area on the target enhanced display interface to display the display effect corresponding to the traffic police gesture signal, the method further includes: Determine whether the current traffic police hand signal and the previous traffic police hand signal meet the combined display condition; If the current traffic police hand gesture signal and the previous traffic police hand gesture signal meet the combined display condition, then obtaining enhanced display information corresponding to the combined hand gesture signal obtained by combining the current traffic police hand gesture signal and the previous traffic police hand gesture signal, and controlling the target display area on the target enhanced display interface to display with the display effect corresponding to the combined hand gesture signal; Otherwise, the target display area on the target enhanced display interface is controlled to display with the display effect corresponding to the current traffic police gesture signal.

8. The method for identifying traffic police hand gesture signals according to claim 6, characterized in that: The traffic police hand signal includes a plurality of eight standard traffic police hand signals: stop signal, straight signal, left turn signal, right turn signal, left turn waiting signal, lane change signal, slow down signal, and vehicle pull over signal; The target display area includes at least one of a middle display area, a left display area, a right display area, a C-shaped display area, and an inverted H-shaped display area; The display effect includes a color effect and a brightness effect. The color effect includes a green filter effect and a red filter effect. The brightness effect includes a constant brightness effect and a non-constant brightness effect.

9. The method for identifying traffic police hand gesture signals as claimed in claim 8, characterized in that: The target enhancement display interface adopts RGB color mode, and the control of the display area on the target enhancement display interface to display the display effect corresponding to the traffic police gesture signal includes: Acquire an R channel target value or a G channel target value of the target display area, wherein the R channel target value or the G channel target value is different from a current R channel value or a current G channel value of a non-target display area on the target enhanced display interface; and acquire a target brightness curve of the target display area, wherein the target brightness curve is linear or non-linear, and the brightness value of the linear brightness curve is the same as the current brightness value of the non-target display area; The R channel value of the target display area is modified to the R channel target value or the G channel value is modified to the G channel target value, and the display brightness of the target display area is controlled according to the target brightness curve, and the RGB value of the non-target display area and the brightness curve of the non-target display area are kept unchanged.

10. The method for identifying traffic police hand gesture signals according to any one of claims 1 to 9, characterized in that: When collecting the traffic environment image by the image collector of the augmented reality glasses, the method further includes: Performing target detection on the traffic environment image to obtain target detection results about traffic participants; Obtain virtual information corresponding to each traffic participant; Each traffic participant is enhanced and displayed based on the target detection results and virtual information of each traffic participant.

11. A traffic police hand gesture signal recognition device, characterized in that: The device is applied to augmented reality glasses, and the traffic police hand gesture signal recognition device comprises: A target detection unit, used for collecting a traffic environment image through the image collector of the augmented reality glasses when the augmented reality glasses are in a traffic police signal recognition mode, and determining whether there is a traffic police target on the current road according to the traffic environment image; A signal recognition unit, used for obtaining a traffic police gesture signal of a traffic police target when it is determined that there is a traffic police target on the current road; A signal display unit is used to enhance the display of the traffic police gesture signal through the augmented reality glasses and / or voice remind the traffic police gesture signal.

12. An augmented reality glasses, characterized in that: The augmented reality glasses include: Processor; and A memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the method for identifying traffic police gesture signals as claimed in any one of claims 1 to 10.

Images