Shooting method based on intelligent robot and intelligent robot

Abstract

The embodiments of the present application provide a shooting method based on an intelligent robot and the intelligent robot, which are applied to the field of artificial intelligence technology. By responding to the received shooting instruction, the intelligent robot is controlled to go to the target shooting location where the shooting picture is not backlit; play the audio information for guiding the user to the target shooting location; when the user arrives at the target shooting location, obtain the facial center position of the user in the shooting picture; adjust the facial center position of the user in the shooting picture until the facial center position meets the shooting requirements, and then shoot the user. In this way, the influence of backlight on the shooting effect can be avoided, and by playing the audio information to guide the user to the shooting location, the interaction between the user and the intelligent robot can be increased, so as to provide better services for the user. At the same time, by adjusting the facial center position of the user in the shooting picture, a better shooting effect can be obtained, making the quality of the taken photos higher.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and particularly to a shooting method based on an intelligent robot and an intelligent robot. Background Art

[0002] Currently, with the popularization of intelligent devices, taking pictures or shooting things using a camera has also become mainstream. At the same time, more and more venues will provide users with various interactive experiences. For example, shopping malls, exhibition halls, etc. will set up intelligent robots to interact with users for taking pictures.

[0003] In related technologies, when an intelligent robot receives a shooting instruction, it performs face detection on a user through a camera, and takes a picture of the user when the user is detected. However, in this case, the shooting effect of the intelligent robot is greatly affected by surrounding environmental factors, resulting in poor photo-taking effects. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a shooting method based on an intelligent robot and an intelligent robot, which can solve the problem of poor photo-taking effects of intelligent robots in the prior art.

[0005] The embodiments of the present application provide a shooting method based on an intelligent robot, and the method includes:

[0006] In response to the received shooting instruction, control the intelligent robot to go to a target shooting location where the shooting picture is not backlit;

[0007] Play audio information for guiding the user to the target shooting location;

[0008] When the user arrives at the target shooting location, obtain the facial center position of the user in the shooting picture;

[0009] Adjust the facial center position of the user in the shooting picture until the facial center position meets the shooting requirements, and then take a picture of the user.

[0010] The embodiments of the present application provide an intelligent robot, which includes a first camera, a second camera, a chassis motor, a speaker, and a processor. The focal length of the first camera is less than the focal length of the second camera;

[0011] The processor is configured to, in response to the received shooting instruction, control the chassis motor to drive the intelligent robot to the target shooting location;

[0012] The first camera is configured to shoot the target shooting location to obtain a to-be-detected image;

[0013] The processor is further configured to perform backlight detection on the image to be detected; when the backlight detection result of the image to be detected is backlight, control the chassis motor to drive the intelligent robot to the next target shooting location until the backlight detection result of the next target shooting location is non-backlight;

[0014] The audio playback module is configured to play audio information for guiding the user to the target shooting location;

[0015] The first camera is further configured to, when the user reaches the target shooting location, capture the user at the target shooting location to obtain a user image;

[0016] The processor is further configured to obtain the facial center position of the user in the shooting frame based on the user image; control the chassis motor to drive the intelligent robot to adjust the facial center position of the user in the shooting frame until the facial center position meets the shooting requirements;

[0017] The second camera is configured to capture the user.

[0018] An embodiment of the present application discloses a shooting device based on an intelligent robot, the device includes:

[0019] A first control module, configured to, in response to a received shooting instruction, control the intelligent robot to go to a target shooting location where the shooting frame is non-backlight;

[0020] A first playback module, configured to play audio information for guiding the user to the target shooting location;

[0021] A first acquisition module, configured to, when the user reaches the target shooting location, acquire the facial center position of the user in the shooting frame;

[0022] A first shooting module, configured to adjust the facial center position of the user in the shooting frame until the facial center position meets the shooting requirements, and capture the user.

[0023] An embodiment of the present application discloses an electronic device, including: one or more processors; and one or more machine-readable media storing instructions thereon, which when executed by the one or more processors, cause the device to execute the intelligent robot-based shooting method as described in any one of the above.

[0024] An embodiment of the present application discloses a computer-readable storage medium, the computer program stored thereon causes a processor to execute the intelligent robot-based shooting method as described in any one of the above.

[0025] In the embodiments of the present application, in response to a received shooting instruction, the intelligent robot is controlled to go to a target shooting location where the shooting scene is not backlit; audio information for guiding the user to the target shooting location is played; when the user arrives at the target shooting location, the central position of the user's face in the shooting scene is obtained; the central position of the user's face in the shooting scene is adjusted until the central position of the face meets the shooting requirements, and then the user is photographed. In this way, the intelligent robot can take pictures in a non-backlit environment, avoiding the influence of backlight on the shooting effect. And by playing audio information to guide the user to the shooting location, the interaction between the user and the intelligent robot can be increased, thereby providing better services for the user. At the same time, by adjusting the central position of the user's face in the shooting scene, a better shooting effect can be obtained, and the quality of the taken photos is higher, further improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0027] Figure 1 is a flowchart of the steps of a shooting method based on an intelligent robot provided by an embodiment of the present application;

[0028] Figure 2 is a flowchart of the steps of backlight detection and face detection provided by an embodiment of the present application;

[0029] Figure 3 is a specific schematic diagram of a shooting method of an intelligent robot provided by an embodiment of the present application;

[0030] Figure 4 is a structural block diagram of a shooting device based on an intelligent robot provided by an embodiment of the present invention;

[0031] Figure 5 is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0033] Figure 1 FIG. 0 is a flowchart of steps of a shooting method based on an intelligent robot provided by an embodiment of the present application. This method can be applied to an intelligent robot, such as an intelligent robot with a display screen. The intelligent robot is equipped with a camera that has functions such as taking pictures or videos. The intelligent robot can be applied to any indoor or outdoor venue, such as a service hall, an event site, etc.

[0034] The intelligent robot may include an application layer, a platform layer, an Application Programming Interface (API) layer, and a hardware layer. Among them, the applications in the application layer can be implemented using the TypeScript language and run in the environment provided by the React Native framework and the platform. The API layer mainly provides the ability for applications to communicate with the underlying hardware. The API layer may include a motion ability interface, a vision ability interface, a speaker interface, a pick-up interface, and a sensor interface, etc. The application calls the API layer to call and control the underlying hardware of the robot (such as the chassis motor of the intelligent robot, the camera, the microphone array, the pick-up array, the pan-tilt, the laser sensor, the touch screen, the acceleration sensor, the ultrasonic sensor, etc.), so as to implement functions such as face detection, portrait shooting, motion control, speech recognition, and voice playback.

[0035] The intelligent robot can perform data interaction with the background server. The background server provides an object storage service, such as a software backend service that can be used for photo storage. The photos obtained by the application will be transmitted to the background server side for object storage (storing the photo name, the photo file, and the shooting date) by means of a network request. At the same time, the Uniform Resource Locator (URL) of the picture can also be obtained by sending a network request. The URL will be generated by the front-end program for the user to scan the QR code to obtain the photo.

[0036] As Figure 1 shown, the method may include:

[0037] Step 101, in response to the received shooting instruction, control the intelligent robot to go to a target shooting location where the shooting scene is not backlit.

[0038] In the embodiments of the present application, the shooting instruction can be triggered by the user, and the triggering methods can include click triggering, voice triggering, etc. In response to the shooting instruction, the intelligent robot is controlled to go to the target shooting location. The intelligent robot can detect backlight for the shooting screen at the location where it is located, and determine whether the current location of the intelligent robot is backlit. A non-backlit location indicates that the current location is a suitable location for shooting, and this location is taken as the target shooting location. Among them, the shooting screen can include all the scenes that can be shot within the field of view in the direction the current intelligent robot is facing. Exemplarily, the intelligent robot can be controlled to move through the driving component in the intelligent robot, and the driving component can be a chassis motor.

[0039] Step 102: Play the audio information for guiding the user to the target shooting location.

[0040] In the embodiments of the present application, the intelligent robot can play the audio information to the user by voice through the audio playback module of the intelligent robot. For example, the audio information for guiding the user to the target shooting location. The intelligent robot can play the audio information for guiding the user to the target shooting location after arriving at the target shooting location. This audio information can be preset, and the embodiments of the present application do not limit this.

[0041] In a possible implementation manner, the intelligent robot can play a guiding word before starting to move to guide the user to the shooting location, such as: "Please follow me."

[0042] Step 103: When the user arrives at the target shooting location, obtain the facial center position of the user in the shooting screen.

[0043] In the embodiments of the present application, when the user arrives at the target shooting location according to the content of the audio information, the facial center position of the user in the captured shooting screen is obtained through the camera. Among them, the facial center position can include the facial center positions of one or more users. Among them, the user can be a user whose entire face is exposed in the shooting screen of the camera. Exemplarily, it can be a user with all facial features exposed, or a user with clear facial information. The embodiments of the present application do not limit this.

[0044] Step 104: Adjust the facial center position of the user in the shooting screen until the facial center position meets the shooting requirements, and then take a photo of the user.

[0045] In the embodiments of the present application, the position of the intelligent robot or the shooting angle of the camera can be adjusted based on the chassis motor and the pan-tilt of the intelligent robot, and by continuously judging the position of the user's face center in the shooting screen until the position of the user's face center in the shooting screen meets the shooting requirements. When the position of the user's face center in the shooting screen meets the shooting requirements, it indicates that the current shooting conditions can obtain good shooting effects. Therefore, the camera of the intelligent robot is controlled to shoot the user.

[0046] In summary, in the embodiments of the present application, in response to the received shooting instruction, the intelligent robot is controlled to go to the target shooting location where the shooting screen is not backlit; the audio information for guiding the user to the target shooting location is played; when the user arrives at the target shooting location, the position of the user's face center in the shooting screen is obtained; the position of the user's face center in the shooting screen is adjusted until the face center position meets the shooting requirements, and the user is shot. In this way, the intelligent robot can shoot in a non-backlit environment, avoiding the influence of backlight on the shooting effect, and by playing audio information to guide the user to the shooting location, the interaction between the user and the intelligent robot can be increased, thereby providing better services for the user. At the same time, by adjusting the position of the user's face center in the shooting screen, better shooting effects can be obtained, the quality of the taken photos is higher, and the user experience is further improved.

[0047] Optionally, step 101 may include the following steps:

[0048] Step 1011, when detecting a shooting instruction triggered by voice, query the target shooting location closest to the current position of the intelligent robot from the candidate shooting location list.

[0049] In the embodiments of the present application, the shooting instruction can be triggered by voice input by the user. Exemplarily, the shooting instruction can be triggered when detecting keywords input by the user's voice. For example, the keywords can include "shoot", "take a photo", "take pictures", etc., or the shooting instruction can be triggered when detecting a target sentence. For example, the target sentence can include "Take a photo of us" or "I want to take a photo". When the microphone array of the intelligent robot detects a shooting instruction triggered by the user's voice, the candidate shooting location list is obtained, and the target shooting location closest to the current position of the intelligent robot is queried. Among them, the candidate shooting location list includes at least two candidate shooting locations, and the candidate shooting locations can be pre-set locations with good positions or representative shooting locations in the venue.

[0050] Step 1012, control the intelligent robot to go to the target shooting location and perform backlight detection on the shooting screen of the target shooting location.

[0051] In the embodiments of the present application, after determining the target shooting location, the coordinates of the target shooting location are obtained, and based on the preset map built in the intelligent robot, the intelligent robot is controlled to go to the target shooting location. After arriving at the target shooting location, the shooting environment where the target shooting point is located is detected for backlight through a camera. The purpose of backlight detection is to detect whether there is insufficient exposure in the field of view captured by the camera based on the current camera orientation. Exemplarily, backlight detection can be achieved by detecting whether the subject to be photographed is between the light source and the camera.

[0052] It can be understood that the initial orientation of the camera of the intelligent robot can be fixed. For example, it can be a preset orientation and camera angle.

[0053] Step 1013, when the captured image is backlit, query the remaining candidate shooting locations closest to the current location from the candidate shooting location list, and use the remaining candidate shooting locations as the target shooting location to perform backlight detection again until the captured image is not backlit.

[0054] Since the captured image being backlit will cause insufficient exposure of the subject to be photographed, resulting in a poor shooting effect. For example, when the user's back is facing the direction of sunlight, there will be a large brightness difference between the portrait and the background, resulting in a poor shooting effect. Therefore, when it is detected that the captured image at the target shooting location is backlit, the position of the intelligent robot is adjusted to avoid the impact of backlight on the shooting effect.

[0055] In the embodiments of the present application, when it is detected that the captured image is backlit, it indicates that the current shooting location is not suitable for taking pictures. Then, query the remaining candidate shooting locations closest to the shooting location where the intelligent robot is currently located from the candidate shooting location list. The remaining candidate shooting locations can be shooting locations that have not undergone backlight detection. The shooting location that is closest to the current location and has not undergone backlight detection is used as the target shooting location, and the intelligent robot is controlled to go to the target shooting location to perform backlight detection on the captured image of the target shooting location until it is detected that the captured image at the target shooting location where the intelligent robot is located is not backlit.

[0056] In the embodiments of the present application, by performing backlight detection on the target shooting location and actively adjusting the position of the intelligent robot until the captured image at the target shooting location is not backlit, it can be ensured that the light intensity and the irradiation direction of the light of the captured image of the intelligent robot will not affect the shooting effect, thereby avoiding the problem of poor shooting effect caused by backlight and improving the shooting effect and shooting quality.

[0057] Optionally, step 1022 may include the following steps:

[0058] Step 1022a, obtain the image to be detected at the target shooting location.

[0059] In an embodiment of the present application, after the intelligent robot reaches the target shooting location, a to-be-detected image can be captured based on the initial orientation of the camera. The to-be-detected image includes the shooting scene of the target shooting location, that is, all the scenes that can be captured within the field of view of the initial orientation of the camera.

[0060] Step 1022b: Determine the number of black pixel points and the number of white pixel points based on the gray values of the pixel points in the to-be-detected image; the number of black pixel points is the number of pixel points whose gray values are within the first gray threshold range, and the number of white pixel points is the number of pixel points whose gray values are within the second gray threshold range. The gray values in the first gray threshold range are less than the gray values in the second gray threshold range.

[0061] In an embodiment of the present application, the principle of backlight detection can be achieved by performing numerical operations according to the gray value distribution of image pixel points. Obtain the gray values of the pixel points in the to-be-detected image. Exemplarily, the gray values of the pixel points in the to-be-detected image can be calculated by methods such as the floating-point method, the shift method, and the average value method. Based on the obtained gray values of the pixel points, count the number of black pixel points and white pixel points in the to-be-detected image. Take the pixel points whose gray values are within the first gray threshold range as black pixel points and count the number of black pixel points. Take the pixel points whose gray values are within the second gray threshold range as white pixel points and count the number of white pixel points. Among them, the gray values in the first gray threshold range are less than the gray values in the second gray threshold range, that is, the image scene represented by the white pixel points is brighter, and the image scene represented by the black pixel points is darker. The first gray threshold range and the second gray threshold range can be pre-set threshold ranges. For example, the first gray threshold range can be a range of gray values between 0 and 60, and the second gray threshold range can be a range of gray values between 225 and 255.

[0062] Step 1022c: Calculate the pixel ratios of the number of black pixel points and the number of white pixel points to the total number of pixel points in the to-be-detected image.

[0063] Step 1022d: When the pixel ratio is less than the pixel ratio threshold, determine that the shooting scene of the target shooting location is not backlit.

[0064] Step 1022e: When the pixel ratio is greater than or equal to the pixel ratio threshold, determine that the shooting scene of the target shooting location is backlit.

[0065] In an embodiment of the present application, when the pixel ratio of the number of black pixel points and the number of white pixel points to the total number of pixel points is greater than the pixel ratio threshold, it indicates that the proportion of over-bright or over-dark scenes in the image to be detected in the entire captured image is large. Therefore, it is determined that the image to be detected is captured in a backlight state or the current target shooting location is in a backlight environment, and the effect of the captured image is poor, which is not suitable for taking pictures of users. When the pixel ratio is less than the pixel ratio threshold, it indicates that the proportion of over-bright or over-dark scenes in the image to be detected in the entire captured image is small and will not affect the overall shooting effect. Therefore, it is determined that the image to be detected is captured in a non-backlight state or the current target shooting location is not in a backlight environment, and pictures can be taken of users. Among them, the pixel ratio threshold can be set according to requirements, such as 40%.

[0066] In an embodiment of the present application, by judging the gray values of each pixel point in the image to be detected, it can be judged whether the captured image at the target shooting location is backlit. Therefore, determining whether the captured image is backlit through the gray values of the pixel points can ensure the shooting effect of the captured image while making the judgment more simple and effective, and improving the speed of backlight detection.

[0067] Optionally, step 103 may include the following steps:

[0068] Step 1031: Obtain the user image at the target shooting location.

[0069] In an embodiment of the present application, when it is determined that the captured image at the target shooting location is not backlit, the captured image at the target shooting location is obtained through a camera. The captured image includes a user image, and the user image includes at least one user's face image.

[0070] Step 1032: Extract the gradient feature data in the user image.

[0071] In an embodiment of the present application, in order to facilitate feature extraction, the user image can be preprocessed first. The preprocessing steps may include normalizing the user image to obtain a normalized image. The so-called image normalization is to convert the original image to be processed into a corresponding unique standard form through a series of transformations (the standard form image has invariant characteristics for affine transformations such as translation, rotation, and scaling). The gradient feature data is extracted based on the processed normalized image. Among them, the gradient feature data can be statistical information of the gradient, such as Histogram of Oriented Gradient (HOG) features. Specifically, the HOG features can be formed by calculating and statistically analyzing the gradient direction histogram of the local area of the image. The HOG features have strong robustness to lighting factors. In this way, based on the characteristics of the HOG features, the false detection problem caused by lighting and shadows to the face detection result can be reduced.

[0072] Step 1033: Input the gradient feature data into a face detection model to obtain an external rectangular frame of the user's face.

[0073] In the embodiments of the present application, the face detection model can be a face detection model that has been trained and is used for face detection. For example, the face detection model can be a face detection model based on a linear support vector machine provided by the Dlib library, or a face detection model based on a linear support vector machine provided by the Dlib library can be used as a pre-trained model, and then combined with a training set to train a model. The training set can include a certain amount of non-face images and face images taken in backlight and dark environments as negative samples. The embodiments of the present application do not limit this. Input the gradient feature data into the face detection model, and the face detection can output relevant information of one or more external rectangular frames of the user's face in the form of a list. The relevant information can include the vertex coordinates of the external rectangular frame of the user's face, as well as the length information and width information of the external rectangular frame, etc. Based on the external rectangular frame of the user's face and the user image, the position of the external rectangular frame in the user image can be determined.

[0074] Step 1034: Use the position where the center of the external rectangular frame is located in the captured image as the center position of the user's face.

[0075] In the embodiments of the present application, the center coordinates of the external rectangular frame can be calculated based on the vertex coordinates of the external rectangular frame, and the position of the center coordinates in the captured image is the center position of the user's face. Exemplarily, the center coordinates can be obtained with the lower left corner of the captured image as the origin.

[0076] In the embodiments of the present application, based on the gradient feature data and the face detection model, the number and position of faces in the user image can be accurately and quickly identified. At the same time, compared with the face detection method based on a convolutional neural network, the face detection method in the embodiments of the present application can be more lightweight and have a lower computational complexity while ensuring the accuracy of face detection. Further, in the case where the computing power of the intelligent robot is limited by hardware, this method can also save costs and ensure the speed of face detection, consuming less computing resources.

[0077] Exemplarily, Figure 2 shows a flowchart of steps for backlight detection and face detection provided by the embodiments of the present application, as Figure 2As shown, the intelligent robot performs backlight detection on the current shooting location. When the shooting scene is under backlight conditions, it moves to other shooting locations; when the shooting scene is not under backlight conditions, it obtains the image to be detected through the camera, extracts the HOG features in the image to be detected, and inputs them into the face detection model. According to the output of the face detection model, the face center point, that is, the center position of the user's face, is calculated. The coordinate values of this face center point will be used in the subsequent shooting process of automatic position adjustment.

[0078] Optionally, the face center position at least includes: the vertical coordinate of the face and the horizontal coordinate of the face.

[0079] In the case where the face center position includes the face center position of one user, step 104 may include the following steps:

[0080] Step 1041: Obtain the vertical coordinate difference between the vertical coordinate of the face and the vertical coordinate of the center of the shooting scene, and the horizontal coordinate difference between the horizontal coordinate of the face and the horizontal coordinate of the center of the shooting scene.

[0081] In the embodiment of the present application, in the case where the face center position includes the face center position of one user, that is, only one user is included in the shooting scene of the camera. Correspondingly, only one user's face image is included in the user image. Obtain the center coordinates of the shooting scene, which include the center horizontal coordinate and the center vertical coordinate. Based on the vertical coordinate of the face and the center vertical coordinate, calculate the vertical coordinate difference, which represents the vertical distance between the center of the user's face and the center of the shooting scene in the shooting scene. Based on the horizontal coordinate of the face and the center horizontal coordinate, calculate the horizontal coordinate difference, which represents the horizontal distance between the center of the user's face and the center of the shooting scene in the shooting scene.

[0082] Step 1042: In the case where the vertical coordinate difference is greater than or equal to the vertical coordinate difference threshold, or the horizontal coordinate difference is greater than or equal to the horizontal coordinate difference threshold, adjust the shooting position and shooting angle of the intelligent robot until the vertical coordinate difference is less than the vertical coordinate difference threshold and the horizontal coordinate difference is less than the horizontal coordinate difference threshold.

[0083] In the embodiments of the present application, when the vertical coordinate difference is greater than or equal to the vertical coordinate difference threshold, it indicates that the central pixel point of the user's face is too high or too low relative to the central pixel point of the captured image. Specifically, if the user is far from the robot, the central pixel point of the face will be lower than the central pixel point of the captured image in this case; if the user is close to the robot, the central pixel point of the face will be higher than the central pixel point of the captured image in this case. When the central pixel point of the user's face is too high or too low relative to the central pixel point of the captured image, there may be a phenomenon that the proportion of the user's image in the captured image is too large or too small, which cannot well display the captured content and affects the shooting effect. Therefore, the intelligent robot can be controlled to move forward and backward by the chassis motor to adjust the position of the intelligent robot, or the angle of the camera of the intelligent robot in the vertical direction can be adjusted by the pan-tilt head until the vertical coordinate difference is less than the vertical coordinate difference threshold. When the vertical coordinate difference is less than the vertical coordinate difference threshold, the proportion of the user's image in the captured image is suitable for shooting and framing, and the intelligent robot is in a shooting position suitable for shooting. The vertical coordinate difference threshold can be set according to requirements. In a possible implementation, the vertical coordinate difference threshold can be 0, that is, when the vertical coordinate of the user's face coincides with the central vertical coordinate of the captured image, the intelligent robot is in a shooting position suitable for shooting.

[0084] When the horizontal coordinate difference is greater than or equal to the horizontal coordinate difference threshold, it indicates that the central pixel point of the user's face deviates from the central pixel point of the captured image. The angle of the camera of the intelligent robot in the horizontal direction can be adjusted by the pan-tilt head to adjust the shooting angle of the intelligent robot, or the intelligent robot can be controlled to move left and right by the chassis motor to adjust the shooting position of the intelligent robot until the horizontal coordinate difference is less than the horizontal coordinate difference threshold. When the horizontal coordinate difference is less than the horizontal coordinate difference threshold, the user's image is centered relative to the captured image and is suitable for shooting and framing, and the intelligent robot is in a shooting angle suitable for shooting. The horizontal coordinate difference threshold can be set according to requirements. In a possible implementation, the horizontal coordinate difference threshold can be 0, that is, when the horizontal coordinate of the user's face coincides with the central horizontal coordinate of the captured image, the intelligent robot is in a shooting angle suitable for shooting.

[0085] In a possible implementation, when the vertical coordinate difference is greater than or equal to the vertical coordinate difference threshold and the horizontal coordinate difference is greater than or equal to the horizontal coordinate difference threshold, first, the intelligent robot is controlled to move forward and backward by the chassis motor to make the vertical coordinate difference less than the vertical coordinate difference threshold, that is, the vertical coordinate of the user's face is at the same height as the central vertical coordinate of the captured image, and then the camera of the intelligent robot is controlled by the pan-tilt head to make the horizontal coordinate difference less than the horizontal coordinate difference threshold, that is, the user's face is centered relative to the captured image, so as to adjust the intelligent robot to a shooting position and shooting angle suitable for taking pictures.

[0086] It can be understood that during the process of adjusting the shooting position and shooting angle of the intelligent robot, face detection can be continuously performed on the user image in the shooting screen, and the position relationship between the user and the intelligent robot can be judged according to the vertical coordinate and horizontal coordinate of the face in the face detection result, so as to actively adjust the intelligent robot to an ideal shooting position and shooting angle, thereby achieving the purpose of optimizing the shooting effect.

[0087] Step 1043: Shoot the user according to the shooting position and the shooting angle.

[0088] In the embodiment of the present application, the user is shot according to the shooting position and shooting angle of the adjusted intelligent robot.

[0089] In the embodiment of the present application, according to the distances between the vertical coordinate and horizontal coordinate of the face and the center of the shooting screen, adjusting the shooting position and shooting angle of the intelligent robot can enable the intelligent robot to autonomously adjust its position and provide a better experience for the user. Moreover, by adjusting the position of the user's face part in the shooting screen, the captured image can be made more beautiful and the shooting quality can be improved.

[0090] Optionally, when the face center position includes the face center positions of at least two users, step 104 may include the following steps:

[0091] Step 104a: Obtain the vertical coordinate distance value between the vertical coordinate of the face of each user and the vertical coordinate of the center of the shooting screen.

[0092] In the embodiment of the present application, when the face center position includes the face center positions of at least two users, that is, the shooting screen of the camera contains at least two users. Correspondingly, the user image also contains the face images of at least two users. Calculate the vertical coordinate distance value between the vertical coordinate of the face of each user and the vertical coordinate of the center of the shooting screen respectively, and obtain at least two vertical coordinate distance values.

[0093] Step 104b: Calculate the average value of the vertical coordinate distances of at least two of the vertical coordinate distance values.

[0094] In the embodiment of the present application, calculate the average value of at least two vertical coordinate distance values to obtain the average value of the vertical coordinate distances corresponding to the vertical coordinates of the faces of at least two users.

[0095] Step 104c: When the average value of the vertical coordinate distances is greater than or equal to the vertical coordinate distance average value threshold, adjust the shooting angle and shooting position of the intelligent robot until the average value of the vertical coordinate distances is less than the vertical coordinate distance average value threshold.

[0096] In the embodiments of the present application, when the vertical coordinate distance mean value is greater than or equal to the vertical coordinate distance threshold value, it indicates that the central pixel points of the faces of at least two users are too high or too low relative to the central pixel point of the captured image. Therefore, the intelligent robot can be controlled to move forward and backward by the chassis motor to adjust the position of the intelligent robot, or the angle of the camera of the intelligent robot in the vertical direction can be adjusted by the pan-tilt head to adjust the shooting angle of the intelligent robot until the vertical coordinate distance mean value is greater than or equal to the vertical coordinate distance mean value threshold value. When the vertical coordinate distance mean value is greater than or equal to the vertical coordinate distance mean value threshold value, the proportion of at least two user images in the captured image is suitable for shooting and framing, and the intelligent robot is in a shooting position suitable for shooting. Among them, the vertical coordinate difference threshold value can be set according to requirements.

[0097] Alternatively, step 104 may further include the following steps:

[0098] Step 104d, obtain the horizontal coordinate distance value between the horizontal coordinate of the face of each user and the central horizontal coordinate of the captured image.

[0099] In the embodiments of the present application, when the central position of the face includes the central positions of the faces of at least two users, that is, the captured image of the camera includes at least two users. Correspondingly, the user image also includes the face images of at least two users. Calculate the horizontal coordinate distance value between the horizontal coordinate of the face of each user and the central horizontal coordinate of the captured image respectively, and obtain at least two horizontal coordinate distance values.

[0100] Step 104e, when the minimum horizontal coordinate distance value is greater than or equal to the horizontal coordinate distance value threshold, adjust the shooting angle and shooting position of the intelligent robot until the minimum horizontal coordinate distance value is less than the horizontal coordinate distance value threshold.

[0101] In the embodiments of the present application, determine the minimum horizontal coordinate distance value among at least two horizontal coordinate distance values. When the minimum horizontal coordinate distance value is greater than or equal to the horizontal coordinate distance value threshold, control the camera of the intelligent robot through the pan-tilt head to adjust the shooting angle of the intelligent robot, or control the intelligent robot to move left and right through the chassis motor to adjust the shooting position of the intelligent robot until the minimum horizontal coordinate distance value is less than the horizontal coordinate distance value threshold. Among them, the horizontal coordinate distance value threshold can be set according to requirements. In a possible implementation manner, the horizontal coordinate distance value threshold can be 0, that is, when the central position of the user face corresponding to the minimum horizontal coordinate distance value coincides with the central horizontal coordinate of the captured image, the intelligent robot is in a shooting angle suitable for shooting.

[0102] Step 104f, shoot the user according to the shooting position and the shooting angle.

[0103] In the embodiments of the present application, when the central position of the face includes the central positions of at least two users' faces, adjusting the shooting position and shooting angle of the intelligent robot can present a better shooting effect in the case of multi-person shooting and improve the user experience.

[0104] Optionally, step 103 may include the following steps:

[0105] Step 201: Use the first camera of the intelligent robot to obtain the central position of the user's face in the shooting screen.

[0106] In the embodiments of the present application, the camera may include a first camera. Among them, the first camera may be a wide-angle camera for face detection to obtain the central position of the user's face in the shooting screen.

[0107] Correspondingly, step 104 may include the following steps:

[0108] Step 202: Use the second camera of the intelligent robot to shoot the user; the focal length of the first camera is less than the focal length of the second camera.

[0109] In the embodiments of the present application, the camera may further include a second camera. Among them, the second camera may be a high-definition camera. Since the high-definition camera has a higher resolution than the wide-angle camera, it can be used to shoot the user to optimize the shooting effect. In a possible implementation manner, when the shooting position and shooting angle of the intelligent robot are adjusted, the first camera can be switched to the second camera to shoot the user.

[0110] In the embodiments of the present application, by using the first camera to obtain the central position of the user's face in the shooting screen, a larger field of view can be obtained to more accurately detect the number and position of human faces in the user image. And by using the second camera to shoot the user, a clearer shooting image can be obtained, providing a better shooting experience for the user.

[0111] Optionally, to ensure a better shooting effect, when the central position of the face includes the central positions of more than three users' faces, the intelligent robot can play a voice to prompt the user to shoot in batches.

[0112] Optionally, during the process of the intelligent robot moving away from and approaching the user, a laser sensor (for detecting obstacles in front of the robot) and an ultrasonic sensor (for detecting obstacles behind the robot) can be used to detect obstacles or other users, and when an obstacle is found during the movement, the robot will immediately stop moving to avoid it. In this way, the safety of the robot during automatic position adjustment can be ensured.

[0113] Optionally, after the user is photographed by the camera, the photographed photo can be decompressed and then displayed on the display screen of the intelligent robot. The user can choose to preview and select a satisfactory photo, and the selected photo will be uploaded to the server and the URL address of the picture will be returned. The front-end shooting program will generate a QR code through the returned picture URL and render and display it on the display screen of the intelligent robot. The user can scan the QR code with the mobile phone to view the photo and download and save it for memory.

[0114] Exemplarily, Figure 3 shows a specific schematic diagram of a shooting method of an intelligent robot, as Figure 3 shown. The intelligent robot can be applied to specific business scenarios, such as the institution service hall. The intelligent robot will continuously activate the wide-angle camera to determine whether there is anyone in front of the robot. After discovering a customer or an agent visiting the venue, the intelligent robot will display a welcome message on the touch screen and activate the speaker to play the voice obtained by text-to-speech (TTS), such as: "Nice to meet you all. Do you want me to take a group photo for you?" If the customer needs to take a photo, they can click on the touch screen of the intelligent robot to enter the shooting application, or enter the shooting application by saying sentences such as: "Take a photo for us" or "I want to take a photo". After the voice is collected by the microphone array of the intelligent robot, it is handed over to the processing program for speech recognition, and then the shooting application will be triggered. After the application program is started, the robot will start the chassis motor and go to the preset photo-taking point according to the digital map. At the same time, it will play a guiding word through the speaker: "Please follow me" to guide the user to the target photo-taking point. After arriving at the photo-taking point, the program will first perform backlight detection to determine whether the current position is in a backlight position. If it is in a backlight position, it will play a guiding word and lead the customer or agent to other candidate photo-taking points. The application program will use the wide-angle camera for face detection and perform position adjustment and automatic framing according to the results of face detection. After the position adjustment is completed, the application program will switch the wide-angle camera to a high-definition camera for continuous shooting and display it on the touch screen after decompression processing. Subsequently, the customer and the agent can click on the touch screen to select a satisfactory photo. After the photo is selected, it will be handed over to the application program for uploading. The picture will be uploaded to the background object storage server, and the front-end program will generate and render a QR code according to the URL returned by the network request. Subsequently, the generated QR code will be displayed on the touch screen. At the same time, the application program will activate the speaker and play the voice: "Your photo is ready. Please use your mobile phone to scan the QR code to get the photo" to guide the customer to scan the QR code. The customer can use the mobile phone to scan the QR code displayed on the touch screen of the robot to obtain the photo selected by the user, and the photo can be downloaded to the mobile phone for viewing, editing, downloading and other operations.

[0115] The embodiments of the present application can make up for the deficiencies of the lack of interactive photography and other services in specific scenarios, and integrate visual interaction, voice interaction, and click interaction, providing diversified interaction methods, which can directly increase the interaction frequency with terminals such as intelligent robots, thereby increasing the usage rate and exposure of terminals such as intelligent robots. The shooting method provided by the embodiments of the present application can enrich and enrich the content of experiential services, achieving the purpose of increasing user traffic. And the embodiments of the present application automatically provide shooting services for users through intelligent robots, which can reduce labor consumption and lower labor costs while ensuring user experience when the passenger flow is large. In addition, the shooting method provided by the embodiments of the present application can provide a channel for users to take group photos with staff, and can also play a potential role in enhancing customer viscosity at the business level.

[0116] The present application also provides an intelligent robot, which includes a first camera, a second camera, a chassis motor, a speaker, and a processor. The focal length of the first camera is less than that of the second camera;

[0117] The processor is configured to control the chassis motor to drive the intelligent robot to a target shooting location in response to a received shooting instruction.

[0118] The first camera is configured to shoot the target shooting location to obtain a to-be-detected image.

[0119] The processor is further configured to perform backlight detection on the to-be-detected image; when the backlight detection result of the to-be-detected image is backlight, control the chassis motor to drive the intelligent robot to the next target shooting location until the backlight detection result of the next target shooting location is non-backlight.

[0120] The audio playback module is configured to play audio information for guiding the user to the target shooting location.

[0121] The first camera is further configured to shoot the user in the target shooting location when the user reaches the target shooting location to obtain a user image.

[0122] The processor is further configured to obtain the facial center position of the user in the shooting screen based on the user image; control the chassis motor to drive the intelligent robot to adjust the facial center position of the user in the shooting screen until the facial center position meets the shooting requirements.

[0123] The second camera is configured to shoot the user.

[0124] Optionally, the intelligent robot further includes a laser sensor and an ultrasonic sensor,

[0125] The laser sensor is used to detect obstacles in front of the intelligent robot; the ultrasonic sensor is used to detect obstacles behind the intelligent robot.

[0126] Optionally, the intelligent robot further includes a microphone array;

[0127] The microphone array is used to collect the triggering voice of the user and perform speech recognition on the voice; the triggering voice is used to trigger the shooting instruction.

[0128] Optionally, the intelligent robot further includes a pan-tilt head, which is used to adjust the shooting angles of the first camera and the second camera in the intelligent robot.

[0129] Referring to Figure 4 , a structural block diagram of a shooting device based on an intelligent robot according to the present application is shown. The shooting device 30 specifically includes the following modules:

[0130] A first control module 301, configured to control the intelligent robot to go to a target shooting location where the shooting picture is not backlit in response to a received shooting instruction;

[0131] A first playback module 302, configured to play audio information for guiding the user to the target shooting location;

[0132] A first acquisition module 303, configured to acquire the facial center position of the user in the shooting picture when the user arrives at the target shooting location;

[0133] A first shooting module 304, configured to adjust the facial center position of the user in the shooting picture until the facial center position meets the shooting requirements, and then shoot the user.

[0134] Optionally, the first control module 301 may include:

[0135] A first query module, configured to query, from a candidate shooting location list, a target shooting location that is closest to the current position of the intelligent robot when detecting a voice-triggered shooting instruction;

[0136] A first detection module, configured to control the intelligent robot to go to the target shooting location and perform backlight detection on the shooting picture of the target shooting location;

[0137] When the shooting picture is backlit, query, from the candidate shooting location list, a remaining candidate shooting location that is closest to the current position, and use the remaining candidate shooting location as the target shooting location to perform backlight detection again until the shooting picture is not backlit.

[0138] Optionally, the first detection module may include:

[0139] A second acquisition module, configured to acquire a to-be-detected image of the target shooting location;

[0140] A first determination module, configured to determine the number of black pixel points and the number of white pixel points based on the gray values of the pixel points in the to-be-detected image; the number of black pixel points is the number of pixel points whose gray values are within a first gray threshold range, and the number of white pixel points is the number of pixel points whose gray values are within a second gray threshold range, and the gray values in the first gray threshold range are less than the gray values in the second gray threshold range;

[0141] A first calculation module, configured to calculate the pixel ratios of the number of black pixel points and the number of white pixel points to the total number of pixel points in the to-be-detected image;

[0142] A second determination module, configured to determine that the shooting picture of the target shooting location is not backlit when the pixel ratio is less than a pixel ratio threshold;

[0143] A third determination module, configured to determine that the shooting picture of the target shooting location is backlit when the pixel ratio is greater than or equal to the pixel ratio threshold.

[0144] Optionally, the first acquisition module 303 may include:

[0145] A first acquisition sub-module, configured to acquire a user image in the target shooting location;

[0146] A first extraction module, configured to extract gradient feature data from the user image;

[0147] A second acquisition sub-module, configured to input the gradient feature data into a face detection model to obtain an outer circumscribed rectangle of the user's face;

[0148] A first determination sub-module, configured to use the position where the center of the outer circumscribed rectangle is located in the shooting picture as the center position of the user's face.

[0149] Optionally, the center position of the face at least includes: the vertical coordinate of the face and the horizontal coordinate of the face; in the case where the center position of the face includes the center position of a user's face, the first shooting module 304 may include:

[0150] A third acquisition module, configured to acquire the vertical coordinate difference between the vertical coordinate of the face and the vertical coordinate of the center of the shooting picture, and the horizontal coordinate difference between the horizontal coordinate of the face and the horizontal coordinate of the center of the shooting picture;

[0151] The first adjustment module is used to adjust the shooting position and shooting angle of the intelligent robot when the vertical coordinate difference is greater than or equal to the vertical coordinate difference threshold, or the horizontal coordinate difference is greater than or equal to the horizontal coordinate difference threshold, until the vertical coordinate difference is less than the vertical coordinate difference threshold and the horizontal coordinate difference is less than the horizontal coordinate difference threshold;

[0152] The first shooting sub-module is used to shoot the user according to the shooting position and the shooting angle.

[0153] Optionally, the facial center position at least includes: facial vertical coordinate, facial horizontal coordinate; when the facial center position includes the facial center positions of at least two users, the first shooting module 304 may include:

[0154] The fourth acquisition module is used to acquire the vertical coordinate distance value between the facial vertical coordinate of each user and the vertical coordinate of the center of the shooting screen;

[0155] The second calculation module is used to calculate the average vertical coordinate distance of at least two of the vertical coordinate distance values;

[0156] The second adjustment module is used to adjust the shooting angle and shooting position of the intelligent robot when the average vertical coordinate distance is greater than or equal to the average vertical coordinate distance threshold, until the average vertical coordinate distance is less than the average vertical coordinate distance threshold;

[0157] Alternatively, the fifth acquisition module is used to acquire the horizontal coordinate distance value between the facial horizontal coordinate of each user and the horizontal coordinate of the center of the shooting screen;

[0158] The third calculation module is used to adjust the shooting angle and shooting position of the intelligent robot when the minimum horizontal coordinate distance value is greater than or equal to the horizontal coordinate distance threshold, until the minimum horizontal coordinate distance value is less than the horizontal coordinate distance threshold;

[0159] The second shooting sub-module is used to shoot the user according to the shooting position and the shooting angle.

[0160] Optionally, the first acquisition module 303 includes:

[0161] The third acquisition sub-module is used to acquire the facial center position of the user in the shooting screen by using the first camera of the intelligent robot;

[0162] Correspondingly, the first shooting module 304 includes:

[0163] The third shooting sub-module is used to shoot the user by using the second camera of the intelligent robot; the focal length of the first camera is less than the focal length of the second camera.

[0164] For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For related parts, please refer to the corresponding descriptions in the method embodiments.

[0165] This application also provides an electronic device. Refer to Figure 5 , including: a processor 401, a memory 402, and a computer program 4021 stored on the memory and executable on the processor. When the processor executes the program, it implements the shooting method based on an intelligent robot in the foregoing embodiments.

[0166] This application also provides a readable storage medium. When the instructions in the storage medium are executed by the processor of an electronic device, the electronic device can execute the shooting method based on an intelligent robot in the foregoing embodiments.

[0167] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings provided herein. The structure required to construct such systems will be apparent from the above description. In addition, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the descriptions of specific languages above are for disclosing the best mode of this application.

[0168] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that the embodiments of this application can be practiced without these specific details. In some instances, well-known methods, structures, and technologies have not been shown in detail so as not to obscure the understanding of this specification.

[0169] Similarly, it should be understood that, in order to streamline this application and assist in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of this application, the various features of this application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed subject matter of this application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.

[0170] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be adopted to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0171] Each component embodiment of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present application. The present application can also be implemented as a device or device program for executing some or all of the methods described herein. Such a program for implementing the present application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0172] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a properly programmed computer. In a unit claim listing several devices, several of these devices can be embodied by the same hardware item. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0173] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0174] It should be noted that all actions of obtaining signals, information or data in this application are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where it is located and with the authorization given by the owner of the corresponding device.

[0175] The above are only the preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included in the protection scope of this application.

[0176] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or replacements, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A shooting method based on an intelligent robot, characterized in that, The method includes: In response to a received shooting instruction, controlling the intelligent robot to go to a target shooting location where the shooting scene is not backlit; Playing audio information for guiding the user to the target shooting location; When the user arrives at the target shooting location, obtaining the center position of the user's face in the shooting scene; Adjusting the center position of the user's face in the shooting scene until the center position meets the shooting requirements, and shooting the user; The step of, in response to a received shooting instruction, controlling the intelligent robot to go to a target shooting location where the shooting scene is not backlit includes: When detecting a voice-triggered shooting instruction, querying the target shooting location closest to the current position of the intelligent robot from a list of candidate shooting locations; Controlling the intelligent robot to go to the target shooting location and performing backlight detection on the shooting scene of the target shooting location; When the shooting scene is backlit, querying the remaining candidate shooting location closest to the current position from the list of candidate shooting locations, and using the remaining candidate shooting location as the target shooting location to perform backlight detection again until the shooting scene is not backlit.

2. The method according to claim 1, characterized in that, The step of performing backlight detection on the shooting scene of the target shooting location includes: Obtaining a to-be-detected image of the target shooting location; Based on the gray values of the pixel points in the to-be-detected image, determining the number of black pixel points and the number of white pixel points; the number of black pixel points is the number of pixel points whose gray values are within a first gray threshold range, the number of white pixel points is the number of pixel points whose gray values are within a second gray threshold range, and the gray values in the first gray threshold range are less than the gray values in the second gray threshold range; Calculating the pixel ratios of the number of black pixel points and the number of white pixel points to the total number of pixel points in the to-be-detected image; When the pixel ratio is less than a pixel ratio threshold, determining that the shooting scene of the target shooting location is not backlit; When the pixel ratio is greater than or equal to the pixel ratio threshold, determining that the shooting scene of the target shooting location is backlit.

3. The method according to claim 1, characterized in that, The step of obtaining the center position of the user's face in the shooting scene includes: Obtaining an image of the user at the target shooting location; Extracting gradient feature data from the user image; Inputting the gradient feature data into a face detection model to obtain an outer circumscribed rectangle of the user's face; Taking the position where the center of the outer circumscribed rectangle is located in the shooting scene as the center position of the user's face.

4. The method according to claim 1, characterized in that, The center position of the face at least includes: the vertical coordinate of the face and the horizontal coordinate of the face; In the case where the center position of the face includes the center position of one user's face, the step of adjusting the center position of the user's face in the shooting scene until the center position meets the shooting requirements and shooting the user includes: Obtaining the vertical coordinate difference between the vertical coordinate of the face and the vertical coordinate of the center of the shooting scene, and the horizontal coordinate difference between the horizontal coordinate of the face and the horizontal coordinate of the center of the shooting scene; When the vertical coordinate difference is greater than or equal to the vertical coordinate difference threshold, or the horizontal coordinate difference is greater than or equal to the horizontal coordinate difference threshold, adjust the shooting position and shooting angle of the intelligent robot until the vertical coordinate difference is less than the vertical coordinate difference threshold and the horizontal coordinate difference is less than the horizontal coordinate difference threshold; Shoot the user according to the shooting position and the shooting angle.

5. The method according to claim 1, characterized in that, The facial center position at least includes: facial vertical coordinate, facial horizontal coordinate; When the facial center position includes the facial center positions of at least two users, adjust the facial center position of the user in the shooting screen until the facial center position meets the shooting requirements, and shoot the user, including: Obtain the vertical coordinate distance value between the facial vertical coordinate of each user and the vertical coordinate of the center of the shooting screen; Calculate the average vertical coordinate distance of at least two of the vertical coordinate distance values; When the average vertical coordinate distance is greater than or equal to the average vertical coordinate distance threshold, adjust the shooting angle and shooting position of the intelligent robot until the average vertical coordinate distance is less than the average vertical coordinate distance threshold; Alternatively, obtain the horizontal coordinate distance value between the facial horizontal coordinate of each user and the horizontal coordinate of the center of the shooting screen; When the minimum horizontal coordinate distance value is greater than or equal to the horizontal coordinate distance value threshold, adjust the shooting angle and shooting position of the intelligent robot until the minimum horizontal coordinate distance value is less than the horizontal coordinate distance value threshold; Shoot the user according to the shooting position and the shooting angle.

6. The method according to claim 1, wherein The obtaining the facial center position of the user in the shooting screen includes: Use the first camera of the intelligent robot to obtain the facial center position of the user in the shooting screen; The shooting the user includes: Use the second camera of the intelligent robot to shoot the user; The focal length of the first camera is less than the focal length of the second camera.

7. An intelligent robot, characterized in that, The intelligent robot includes a first camera, a second camera, a chassis motor, a speaker, and a processor, and the focal length of the first camera is less than the focal length of the second camera; The processor is configured to, in response to a received shooting instruction, control the chassis motor to drive the intelligent robot to a target shooting location; the target shooting location is determined based on querying the candidate shooting location list for the candidate shooting location closest to the current location of the intelligent robot when a voice-triggered shooting instruction is detected; The first camera is configured to shoot the target shooting location to obtain a to-be-detected image; The processor is further configured to perform backlight detection on the to-be-detected image; when the backlight detection result of the to-be-detected image is backlight, control the chassis motor to drive the intelligent robot to the next target shooting location until the backlight detection result of the next target shooting location is non-backlight; the next target shooting location is determined based on the remaining candidate shooting location closest to the current location queried from the candidate shooting location list; The audio playback module is configured to play audio information for guiding the user to the target shooting location; The first camera is further configured to, when the user reaches the target shooting location, shoot the user in the target shooting location to obtain a user image; The processor is further configured to obtain the facial center position of the user in the shooting frame based on the user image; control the chassis motor to drive the intelligent robot to adjust the facial center position of the user in the shooting frame until the facial center position meets the shooting requirements; The second camera is configured to shoot the user.

8. The intelligent robot according to claim 7, wherein The intelligent robot further includes a laser sensor and an ultrasonic sensor; The laser sensor is configured to detect obstacles in front of the intelligent robot; the ultrasonic sensor is configured to detect obstacles behind the intelligent robot.

9. The intelligent robot according to claim 7, wherein The intelligent robot further includes a microphone array; The microphone array is configured to collect the trigger voice of the user and perform voice recognition on the voice; the trigger voice is used to trigger the shooting instruction.

10. A shooting device based on an intelligent robot, characterized in that, The device includes: A first control module, configured to, in response to a received shooting instruction, control the intelligent robot to go to a target shooting location where the shooting frame is not backlit; A first playback module, configured to play audio information for guiding the user to the target shooting location; A first acquisition module, configured to, when the user reaches the target shooting location, obtain the facial center position of the user in the shooting frame; A first shooting module, configured to adjust the facial center position of the user in the shooting frame until the facial center position meets the shooting requirements, and shoot the user; The first control module may include: A first query module, configured to, when detecting a shooting instruction triggered by voice, query from a list of candidate shooting locations the target shooting location that is closest to the current position of the intelligent robot; A first detection module, configured to control the intelligent robot to go to the target shooting location and perform backlight detection on the shooting frame of the target shooting location; When the shooting frame is backlit, query from the list of candidate shooting locations the remaining candidate shooting location that is closest to the current position, and use the remaining candidate shooting location as the target shooting location to perform backlight detection again until the shooting frame is not backlit.

11. An electronic device, characterized in that, Includes: One or more processors; And One or more machine-readable media storing instructions that, when executed by the one or more processors, cause the processors to execute the shooting method based on an intelligent robot according to any one of claims 1 to 6.

12. A computer-readable storage medium, characterized in that, The computer program stored therein causes the processor to execute the shooting method based on an intelligent robot according to any one of claims 1 to 6.

Images