WO2021258249A1 - 图像获取方法、电子设备和可移动设备 - Google Patents

图像获取方法、电子设备和可移动设备 Download PDF

Info

Publication number
WO2021258249A1
WO2021258249A1 PCT/CN2020/097444 CN2020097444W WO2021258249A1 WO 2021258249 A1 WO2021258249 A1 WO 2021258249A1 CN 2020097444 W CN2020097444 W CN 2020097444W WO 2021258249 A1 WO2021258249 A1 WO 2021258249A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
target object
pose
person
head
Prior art date
Application number
PCT/CN2020/097444
Other languages
English (en)
French (fr)
Inventor
朱超
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2020/097444 priority Critical patent/WO2021258249A1/zh
Priority to CN202080006208.8A priority patent/CN113170050A/zh
Publication of WO2021258249A1 publication Critical patent/WO2021258249A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/63—Control of cameras or camera modules by using electronic viewfinders
    • H04N23/631—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
    • H04N23/632—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80—Camera processing pipelines; Components thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Definitions

  • the present disclosure relates to the field of image processing, and in particular, to an image acquisition method, electronic equipment and movable equipment.
  • ID photos or photo stickers are a very important scene in the camera usage scene.
  • ID photos have high requirements for image quality and specifications, and the shooting of ID photos is often restricted by the shooting location and shooting equipment.
  • a professional SLR camera is required, a special flash, a flash stand, blue, white and red background cloth, etc. are required.
  • the shooting process is very cumbersome and affects the user experience. For example, in camera scenes where shooting conditions are simple, shooting time is tight, and repeated shooting is difficult, the pose of the target object in the image may not fully meet the composition requirements, which will also affect the imaging effect.
  • the embodiments of the present disclosure provide an image acquisition method, an electronic device, and a movable device, which can adjust the working parameters of the camera by recognizing the pose of the target object in the image, so that the image acquired by the adjusted camera is The pose of the target object meets the composition requirements, and there is no need to preset the pose of the target object, the operation is convenient, and the user experience in the imaging process is improved.
  • an embodiment of the present disclosure provides an image acquisition method, including: acquiring a first image; identifying the pose of a target object in the first image; adjusting the acquisition based on the pose of the target object in the first image Working parameters in the second image; and acquiring the second image with the adjusted working parameters, so that the pose of the target object in the second image meets the preset condition.
  • the target object includes a person.
  • the recognizing the pose of the target object in the first image includes recognizing the posture of the shoulder of the person in the first image.
  • the pose of the target object in the second image satisfies a preset condition, including: the shoulder reference line of the person in the second image is parallel to the preset reference line.
  • the recognizing the pose of the target object in the first image includes: recognizing the positions of the head and shoulders of the person in the first image;
  • the pose of the target object in the second image satisfies a preset condition, including: the head and shoulders of the person in the second image are located in the central area of the second image.
  • the recognizing the pose of the target object in the first image includes recognizing the ratio between the size of the person in the first image and the size of the first image.
  • the adjustment of the working parameters when acquiring the second image, so that the pose of the target object in the second image meets the preset condition, and the pose of the target object in the second image meets the preset condition includes: adjusting the angle of view when the second image is acquired, so that the ratio between the size of the person in the image and the size of the second image when the second image is acquired meets the threshold.
  • the acquiring the second image using the adjusted operating parameters includes: in response to a user instruction, acquiring the second image using the adjusted operating parameters.
  • the user instruction includes at least one of the following: user operation instruction; user voice instruction; user behavior instruction.
  • the acquiring the second image with the adjusted working parameters includes: in response to satisfying the acquiring condition, acquiring the second image with the adjusted working parameters.
  • the satisfying the acquisition condition includes at least one of the following: satisfying a preset duration; and the pose of the target object in the second image already satisfies the preset condition.
  • the method further includes: processing the second image; and storing the processed image.
  • the method further includes: processing the second image; and displaying the processed image.
  • the processing the second image includes at least one of the following: processing the face of the person in the second image; rendering the background in the second image; Or correct the inclination angle of the head of the person in the second image relative to the shoulder.
  • the correcting the inclination angle of the head of the person in the second image with respect to the shoulder includes: determining the difference between the symmetry line of the head and the reference line of the shoulder Adjust the position of the head based on the included angle to correct the inclination angle of the head relative to the shoulder.
  • the method further includes: in the process of processing the second image, displaying the second image and the processing progress; in response to the completion of the processing, storing the processed image And display the stored images.
  • the method further includes: determining whether the first image contains a target object; in a case where the first image does not contain the target object, outputting prompt information.
  • an embodiment of the present disclosure provides an electronic device including an image acquisition device, a processor, and a controller.
  • the image acquisition device is used to acquire an image.
  • the processor is connected to the image acquisition device, and the processor is configured to identify the pose of the target object in the first image acquired by the image acquisition device, and determine the image acquisition based on the pose of the target object in the first image Working parameters when the device acquires the second image.
  • the controller is connected to the processor and the image acquisition device, and the controller is used to control the image acquisition device to acquire the second image with the adjusted working parameters, so that the pose of the target object in the second image meets the preset requirements. Set conditions.
  • embodiments of the present disclosure provide a movable device, including an image acquisition device, a pan-tilt, a processor, and a controller.
  • the image acquisition device is used to acquire an image.
  • the pan-tilt is used to fix the image acquisition device.
  • the processor is connected to the image acquisition device, and the processor is configured to identify the pose of the target object in the first image acquired by the image acquisition device, and determine the image acquisition based on the pose of the target object in the first image Working parameters when the device acquires the second image.
  • the controller is connected to the processor and the pan/tilt, and the controller is used to adjust the pose of the pan/tilt, so that the image acquisition device acquires the second image with the adjusted working parameters, so that the second The pose of the target object in the image satisfies the preset condition.
  • embodiments of the present disclosure provide a computer system, including: one or more processors; a computer-readable storage medium for storing one or more programs, wherein when the one or more programs are When the one or more processors execute, the one or more processors implement the method described above.
  • embodiments of the present disclosure provide a computer-readable storage medium having executable instructions stored thereon, and when the instructions are executed by a processor, the processor implements the method described above.
  • embodiments of the present disclosure provide a computer program product, including computer-readable instructions, where the computer-readable instructions are used to execute the above-mentioned method when executed.
  • Fig. 1 schematically shows an application scenario of an image acquisition method according to an embodiment of the present disclosure
  • Fig. 2 schematically shows a flowchart of an image acquisition method according to an embodiment of the present disclosure
  • 3A-3D schematically show schematic diagrams of making the pose of a target object in an image satisfy a preset condition according to an embodiment of the present disclosure
  • Fig. 4 schematically shows a flowchart of an image acquisition method according to another embodiment of the present disclosure
  • Fig. 5 schematically shows a block diagram of an electronic device according to an embodiment of the present disclosure
  • Fig. 6 schematically shows a block diagram of a movable device according to an embodiment of the present disclosure.
  • Fig. 7 schematically shows a block diagram of a computer system according to an embodiment of the present disclosure.
  • An embodiment of the present disclosure provides an image acquisition method, which includes acquiring a first image through an image acquisition device, and recognizing the pose of a target object in the first image. Then, based on the pose of the target object in the first image, the operating parameters of the image acquisition device when acquiring the second image are adjusted. And, controlling the image acquisition device to acquire the second image with the adjusted working parameters, so that the pose of the target object in the second image meets the preset condition, so that the directly acquired second image can meet the needs of the user. It avoids the cumbersome operations brought about by first taking pictures and then processing in related technologies, and improves the user experience.
  • Fig. 1 schematically shows an application scenario 100 of an image acquisition method according to an embodiment of the present disclosure.
  • an application scenario 100 may include an electronic device 110 and a pan-tilt 120.
  • the electronic device 110 may include an image acquisition device.
  • the electronic device 110 may be a camera including a camera, a smart phone, a tablet computer, and so on.
  • the image acquisition device of the electronic device 110 may be used to acquire an image including the user 130.
  • the pan-tilt 120 may be used to change the operating parameters of the image acquisition device of the electronic device 110.
  • the electronic device 110 may be detachably connected to the pan-tilt 120.
  • the pan-tilt 120 may be installed outside the electronic device 110 for fixing the electronic device 110.
  • the electronic device 110 may be used to control the spatial layout (posture) of the pan-tilt 120.
  • the electronic device 110 may send a control signal to the pan-tilt 120 to control the pan-tilt 120 to change the posture in three degrees of freedom, so as to drive the electronic device 110 to change the posture, so as to realize the operating parameters of the image acquisition device of the electronic device 110 Adjustment.
  • the pan-tilt 120 may be installed inside the electronic device 110.
  • the pan-tilt 120 may be directly connected to the image acquisition device inside the electronic device.
  • the electronic device 110 can control the pan-tilt 120 to change the posture of the internal image acquisition device while remaining still, so as to realize the adjustment of the working parameters of the image acquisition device of the electronic device 110.
  • the first image including the user 130 can be acquired through the image acquisition device of the electronic device 110.
  • the processor of the electronic device 110 may recognize the pose of the user 130 in the acquired first image, and determine the working parameters of the image capturing apparatus based on the pose of the user 130.
  • the pan/tilt head 120 is controlled to change the posture in the three degrees of freedom to adjust the working parameters of the image acquisition device.
  • the image acquisition device can capture the second image with the adjusted working parameters, so that the directly acquired second image can meet the needs of the user 130.
  • the image acquisition method provided by the embodiments of the present disclosure is easy to operate, can directly capture images that meet user needs, and avoids the need to adjust the pose of the target object during shooting in the related art, or the need to first shoot and store the image and then adjust the image
  • the cumbersome process improves the user experience.
  • FIG. 1 is only an example of an application scenario where the image acquisition method of the embodiment of the present disclosure can be applied to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiment of the present disclosure cannot Used in other equipment, systems, environments or scenarios.
  • Fig. 2 schematically shows a flowchart of an image acquisition method according to an embodiment of the present disclosure.
  • the method includes operations S201 to S204.
  • acquiring the first image may be, for example, acquiring the first image through an image acquisition device of an electronic device.
  • the first image can be acquired through the image sensor of the camera.
  • acquiring the first image may be, for example, turning on the image sensor and acquiring the image, and the image saving operation may not be performed in this process.
  • Obtaining the first image may also be obtaining the first image stored in advance.
  • the first image may be a real scene, or a scene virtualized by artificial intelligence and other methods.
  • the image acquisition device of the electronic device in response to receiving a user's start instruction, can be switched to a working state, and the acquired image can be acquired and displayed for the user to preview.
  • the acquired first image can be identified, whether the first image contains the target object, and if the first image does not contain the target object, the operation is suspended or terminated, or a prompt message is output.
  • a prompt message can be output.
  • the prompt information may be used, for example, to prompt the user that the user's image cannot be obtained in the current viewing range, and the user is requested to move to the current viewing range. If the first image contains people, you can continue to perform subsequent operations.
  • the target object may be a person, for example.
  • the recognized person is the target object.
  • a person meeting the condition can be selected as the target object.
  • the satisfying condition may be, for example, the person selected by the person for the user, or the proportion of the person satisfying the condition, and so on.
  • recognizing the pose of the target object in the first image may be recognizing the posture of the shoulders of the person in the first image.
  • the angle of inclination between the reference line of the shoulder of the person and the preset reference line can be recognized.
  • a head and shoulder level detection algorithm can be run through an ISP (Image Signal Processing, image signal processing unit) chip to identify the inclination angle of the shoulder reference line relative to the horizontal line of the image sensor.
  • ISP Image Signal Processing, image signal processing unit
  • the embodiment of the present disclosure does not limit the algorithm of the shoulder reference line, and those skilled in the art can set it according to the actual situation.
  • the shoulder reference line may be the line between the highest points of the shoulders on both sides.
  • recognizing the pose of the target object in the first image may also be recognizing the positions of the head and shoulders of the person in the first image. For example, the offset distance of a person's head and shoulders relative to the center of the image can be recognized.
  • the head and shoulders detection algorithm can be run through the ISP chip to detect the position of the head and shoulders in the image framing range. It can be understood that the embodiments of the present disclosure do not limit the specific algorithm for head and shoulder detection, and those skilled in the art can set it according to actual conditions. For example, the position of the shoulder can be directly determined by detecting the position of the head.
  • recognizing the pose of the target object in the first image may also be recognizing the ratio between the size of the person in the first image and the size of the first image. For example, the ratio between the area occupied by a person and the area of an image can be recognized. Alternatively, the ratio between the width/height of the person and the width/height of the image can also be identified.
  • the above-described method or other methods can be used to identify whether the pose of the user in the first image meets the needs of the ID photo.
  • the operating parameters for acquiring the second image are adjusted based on the pose of the target object in the first image.
  • the operating parameters of the image acquisition device can be adjusted based on the pose of the target object in the first image.
  • the internal parameters and/or external parameters of the image acquisition device can be adjusted.
  • the posture of the image acquisition device in three degrees of freedom can be adjusted.
  • the focal length, exposure time, etc. of the image acquisition device can also be adjusted.
  • the working parameters of the image acquisition device when acquiring the second image can be adjusted so that the reference line of the person's shoulder in the second image is consistent with the preset The reference line is parallel.
  • the image acquisition device 330 may acquire the first image 310 with original operating parameters. It is recognized that there is an inclination angle between the shoulder reference line L1 of the person in the first image 310 and the horizontal line L2 of the image acquisition device 330. Then, based on the tilt angle, the image acquisition device 330 can be controlled to rotate the first angle relative to the z axis, so that the shoulder reference line L1 of the person in the second image 320 acquired by the adjusted image acquisition device 330 and the image acquisition device 330 The horizontal line L2 is parallel.
  • the working parameters of the image acquisition device when acquiring the second image can be adjusted so that the head and shoulders of the person in the second image The part is located in the central area of the second image.
  • the image acquisition device 330 may acquire the first image 330 with original operating parameters.
  • the offset distance of the head and shoulders of the person in the first image 330 relative to the center position of the image is recognized. Then, based on the offset distance, the image acquisition device 330 can be controlled to rotate a second angle with respect to the x-axis and a third angle with respect to the y-axis, so that the head of the person in the second image 340 acquired by the adjusted image acquisition device 330 can be controlled.
  • the shoulders and shoulders are located in the central area of the image.
  • the operating parameters of the image acquisition device when acquiring the second image can be adjusted, so that the image The ratio between the size of the middle character and the size of the second image satisfies the threshold.
  • the image acquisition device 330 may acquire the first image 350 with the original operating parameters.
  • the ratio between the area of the person in the first image 350 and the area of the first image is recognized.
  • the angle of view of the image acquisition device 330 can be adjusted based on the ratio.
  • the adjustment of the angle of view of the image acquisition device 330 can be achieved by changing the focal length of the image acquisition device 330. Therefore, the ratio between the area of the person in the second image 330 acquired by the adjusted image acquisition device 330 and the area of the second image satisfies the threshold.
  • the threshold of the embodiment of the present disclosure may be, for example, a threshold range, and the ratio between the area of the person in the second image 330 acquired by the adjusted image acquisition device and the area of the second image should be higher than the minimum threshold and lower than The highest threshold.
  • the embodiment of the present disclosure does not limit the adjustment sequence of the working parameters of the image acquisition device, and those skilled in the art can set it according to actual needs. For example, you can first adjust the ratio between the size of the person in the second image and the size of the second image to meet the working parameters corresponding to the threshold, and then adjust so that the head and shoulders of the person in the second image are located in the second image. The working parameters in the central area are finally adjusted to make the reference line of the person's shoulder in the second image parallel to the preset reference line.
  • adjusting the working parameters when acquiring the second image may also be performing stretching processing on the acquired second image by the image acquiring device, so as to scale up or reduce the original image.
  • distortion processing may be performed on the acquired second image to adjust the proportion of the original image that is distorted. For example, when the user's shoulders are unbalanced or asymmetric, the distortion processing may be used to adjust.
  • a second image is acquired with the adjusted working parameters, so that the pose of the target object in the second image meets a preset condition.
  • the second image can be captured with adjusted operating parameters in response to user instructions.
  • the user instruction may include at least one of a user operation instruction, a user voice instruction, or a user behavior instruction.
  • the user can control the image acquisition device to capture the second image by pressing a button.
  • the user can also control the image acquisition device to capture the second image by issuing a voice command of "photograph”.
  • the user can also control the image acquisition device to capture the second image through a specific gesture.
  • the second image may also be acquired with adjusted working parameters in response to satisfying the acquisition condition. Satisfying the acquisition condition may include at least one of satisfying a preset time period or the pose of the target object in the second image has satisfied a preset condition. For example, it is possible to detect the length of time the target object enters the shooting mode at the current moment, and if the length of time reaches the time length threshold, the image acquisition device can be controlled to capture the second image. Alternatively, it can also be detected whether the posture of the person in the image acquired by the image acquisition device has met the requirements of the ID photo, and if so, the image acquisition device can be controlled to capture the second image.
  • the acquired second image may also be processed.
  • the face of the person in the second image may be processed.
  • the face of the person in the second image is subjected to processing such as dermabrasion, whitening, freckle removal, acne removal, face-lifting, or highlighting.
  • the background in the second image may also be rendered. For example, based on the background color selected by the user or determined according to the ID photo scene or the default background color, the background other than the character in the second image is rendered. Or, the second image is rendered based on a filter selected by the user or determined according to the ID photo scene or a default filter.
  • the inclination angle of the head of the person in the second image relative to the shoulder can also be corrected.
  • the angle between the symmetry line of the character's head and the reference line of the shoulder is determined, and the posture of the head is adjusted based on the angle to correct the inclination angle of the head relative to the shoulder.
  • the angle between the line of symmetry L3 of the head of the person and the reference line L1 of the shoulder can be identified, and when the angle exceeds the threshold range (for example, 85 degrees to 95 degrees), The inclination angle of the head relative to the shoulder is corrected so that the angle between the corrected head symmetry line L3 and the shoulder reference line L1 meets the threshold range.
  • the threshold range for example 85 degrees to 95 degrees
  • the second image before processing and the current processing progress can be displayed.
  • the second image acquired in response to a user instruction may be displayed, and the current progress of processing the second image may be displayed in the form of a floating window.
  • the current progress of processing the second image may be displayed in the form of a floating window.
  • it can be displayed in the form of a progress bar.
  • the processed image in response to the completion of the processing, the processed image can be stored and the stored image can be displayed.
  • the image can be acquired in real-time in the acquisition mode by the image acquisition device, but the image is not stored.
  • the first image may be acquired in the acquisition mode through the image acquisition device, and the working parameters of the image acquisition device may be adjusted based on the pose of the target object in the first image, and the image acquisition device may then acquire the second image with the adjusted working parameters to
  • the shoulder reference line of the character in the second image can be parallel to the preset reference line, and/or the head and shoulders are located in the central area, and/or the character size ratio meets the condition.
  • the embodiments of the present disclosure can display the acquired image to the user in a preview mode, and the user can instruct the image acquisition device to shoot and capture the current image according to the preview effect.
  • the embodiments of the present disclosure may further process the captured image, for example, correct the head and shoulder tilt angle, and/or beautify, and/or background rendering, etc., and store and display the processed image to the user.
  • the embodiments of the present disclosure simplifies the tedious process of repeated operations by the user, and the user can Directly shoot and obtain the desired image to improve user experience.
  • Fig. 4 schematically shows a flowchart of an image acquisition method according to another embodiment of the present disclosure.
  • the method includes operations S401 to S415.
  • the user can control the camera to start through the start instruction. For example, in the scene of holding a pan-tilt camera, the user can start the camera by pressing the power button.
  • the user can preview the camera's viewfinder image through a GUI (Graphical User Interface) built into the camera or an external application APP.
  • GUI Graphic User Interface
  • the GUI or APP selects the ID photo mode.
  • a user can perform mode selection operations through GUI or APP. For example, you can select the camera's shooting mode as ID photo mode.
  • the pan/tilt when the shooting mode of the camera is switched to the ID photo mode, the pan/tilt may also enter the ID photo shooting mode.
  • the yaw axis (Yaw axis) of the pan/tilt can be controlled to rotate 180° to enter the self-portrait state, and the viewing range of the camera faces the direction of the user.
  • the face recognition and head-and-shoulders detection algorithms can be run through the ISP chip of the camera to detect the position of the face and the head-and-shoulders in the viewing range.
  • the pan-tilt can also be controlled to adjust and track the face or head and shoulders, so that the face and head and shoulders are kept within the viewing range.
  • a rectangular ROI (Region Of Interest) area can be formed according to the positions of the detected face and head and shoulders in the viewing range.
  • the pan/tilt adjusts its posture so that the head and shoulders are centered and level.
  • the ISP chip of the camera can run the head and shoulders level detection algorithm for the ROI area, and identify the inclination angle of the shoulder reference line relative to the camera's image sensor horizontal line, the position difference of the head and shoulders relative to the center point of the viewfinder, And the tilt angle of the head relative to the shoulder.
  • the roll axis (Roll) is controlled to eliminate the inclination angle of the shoulder reference line relative to the horizontal line of the camera's image sensor, make the shoulder reference line parallel to the horizontal line of the camera's image sensor, and eliminate the head and shoulders relative to the center point of the viewfinder.
  • the position is poor, so that the head and shoulders are in the center area of the viewfinder, so as to achieve the effect that the head and shoulders of the person in the acquired image are centered and shoulders are level.
  • the face is beautified.
  • the beauty algorithm can be run through the ISP chip of the camera to enter the portrait beauty mode, and the face in the acquired image can be processed for skin resurfacing, skin beautification, freckle removal, acne removal, and highlighting.
  • the optical zoom or digital zoom adjusts the viewing range.
  • optical zoom or digital zoom can be performed according to the ratio between the size of the ROI area and the size of the viewing area, so that the imaging size of the head and shoulders meets the requirements of the ID photo.
  • a background color or filter is selected.
  • the user can select the desired background color and filter through the GUI or APP according to the previewable real-time ID photo effect on the LCD of the handheld pan/tilt camera.
  • the background color may include a background color such as white, blue, or red.
  • the filter may include, for example, a frame, a rendering or an animal form filter, and so on.
  • the ISP chip can obtain the raw image in rggb format from the image sensor, and form a rough YUV image of the ID photo after a series of filtering processing and format conversion processing.
  • the head and shoulders area is cropped according to the position of the head and shoulders frame.
  • the head and shoulders in the YUV diagram can be cut out, and the tilt angle of the head relative to the shoulder can be eliminated through the head correction algorithm.
  • the LCD prompts the user to have an incorrect head in real time, so that the user can move the head position according to the prompt information on the LCD to eliminate the head The angle of inclination relative to the shoulder.
  • the background area other than the head and shoulders area can be rendered according to the background color and filter selected by the user in operation S409.
  • the ISP generates a photo.
  • the ISP chip can perform Jpeg encoding on the rendered YUV image to generate a photo.
  • the generated photos can be stored in storage devices such as SD cards.
  • the LCD or APP displays that the photo is taken.
  • the camera's LCD or APP can display the completion animation of the photo, which can be used to playback, preview, and download the ID photo through the GUI and APP.
  • the image acquisition method of the embodiment of the present disclosure can use image processing algorithms such as face detection, head and shoulder detection, pan-tilt tracking, pan-tilt leveling, optical zoom or digital zoom, portrait beautification, smart cropping, background rendering, etc., and are integrated in
  • image processing algorithms such as face detection, head and shoulder detection, pan-tilt tracking, pan-tilt leveling, optical zoom or digital zoom, portrait beautification, smart cropping, background rendering, etc.
  • image processing algorithms such as face detection, head and shoulder detection, pan-tilt tracking, pan-tilt leveling, optical zoom or digital zoom, portrait beautification, smart cropping, background rendering, etc.
  • FIG. 5 schematically shows a block diagram of an electronic device 500 according to an embodiment of the present disclosure.
  • the electronic device 500 of the embodiment of the present disclosure may include an image acquisition device 510, a processor 520, and a controller 530.
  • the image acquisition device 510 may be used to acquire an image.
  • the processor 520 may be used to identify the pose of the target object in the first image obtained by the image obtaining device 510, and determine the working parameters of the image obtaining device 510 when obtaining the second image based on the pose of the target object in the first image.
  • the controller 530 may be used to control the image acquisition device 510 to acquire the second image with the adjusted working parameters, so that the pose of the target object in the second image meets a preset condition.
  • the electronic device 500 may be various electronic devices having image acquisition devices, such as a camera, a mobile phone, and a tablet computer.
  • the electronic device 500 may be provided with an image acquisition device 510, a processor 520, and a controller 530.
  • the processor 520 may be connected to the image acquisition device 510.
  • the processor 520 may obtain an image obtained by the image obtaining device 510.
  • the controller 530 may be connected with the processor 520 and the image acquisition device 510.
  • the controller 530 may receive a control instruction from the processor 520, and control and adjust the operating parameters of the image acquisition device 510 based on the control instruction.
  • the image acquisition device 510 may be, for example, various camera components capable of acquiring images.
  • it may be an image sensor or the like.
  • the processor 520 may be, for example, various processors 520 such as a general-purpose processor CPU, an image processor GPU, an image signal processing unit ISP chip, and so on.
  • processors 520 such as a general-purpose processor CPU, an image processor GPU, an image signal processing unit ISP chip, and so on.
  • the processor 520 may be an ISP chip of the camera or other processing modules.
  • the processor 520 may also be the CPU or other processing modules of the smart phone.
  • the target object may include a person.
  • recognizing the pose of the target object in the first image includes: recognizing the posture of the shoulder of the person in the first image.
  • the pose of the target object in the second image satisfies a preset condition, including: the shoulder reference line of the person in the second image is parallel to the preset reference line.
  • recognizing the pose of the target object in the first image includes recognizing the positions of the head and shoulders of the person in the first image.
  • the pose of the target object in the second image satisfies a preset condition, including: the head and shoulders of the person in the second image are located in the central area of the second image.
  • recognizing the pose of the target object in the first image includes recognizing the ratio between the size of the person in the first image and the size of the first image.
  • the image acquisition device is controlled to acquire the second image with the adjusted working parameters, so that the pose of the target object in the second image meets the preset condition, and the pose of the target object in the second image meets the preset condition
  • the method includes: adjusting the angle of view when the image acquisition device acquires the second image, so that the ratio between the size of the person in the image and the size of the second image when the second image is acquired meets the threshold.
  • acquiring the second image with the adjusted operating parameters includes: in response to a user instruction, acquiring the second image with the adjusted operating parameters.
  • the user instruction includes at least one of the following: a user operation instruction, a user voice instruction, or a user behavior instruction.
  • acquiring the second image with the adjusted operating parameters includes: in response to satisfying the acquisition condition, acquiring the second image with the adjusted operating parameters.
  • satisfying the acquisition condition includes at least one of the following: satisfying a preset duration or the pose of the target object in the second image has satisfied the preset condition.
  • the processor 520 is further configured to process the second image.
  • the electronic device 500 further includes a memory for storing processed images.
  • the processor 520 is further configured to process the second image.
  • the electronic device 500 further includes: a display device for displaying the processed image.
  • the display device may be various display devices such as LCD, LED, GUI, ink screen, or projector.
  • the display device may be a GUI of the camera or a display screen of an external APP.
  • the display device may be a display screen of the smart phone.
  • processing the second image includes at least one of the following: processing the face of the person in the second image, rendering the background in the second image, or correcting the character in the second image The tilt angle of the head relative to the shoulders.
  • correcting the inclination angle of the head of the person in the second image with respect to the shoulder includes: determining the angle between the symmetry line of the head and the reference line of the shoulder, and adjusting the head based on the angle To correct the tilt angle of the head relative to the shoulders.
  • the display device is also used to display the second image and the processing progress during the process of processing the second image.
  • the memory is also used to store the processed image in response to the completion of the processing.
  • the display device is also used to display the processed image stored in the memory.
  • the processor is further configured to determine whether the target object is included in the first image, and output prompt information if the target object is not included in the first image. For example, output prompt information through a display device.
  • the electronic device 500 in the embodiment of the present disclosure integrates an image acquisition device 510, a processor 520, and a controller 530.
  • the processor 520 can use image processing algorithms such as face detection, head and shoulder detection, pan-tilt tracking, pan-tilt leveling, optical zoom or digital zoom, portrait beautification, smart cropping, background rendering, etc., and be integrated in the electronic device, thereby
  • a control instruction may be sent to the controller 530 based on the pose of the person in the first image acquired by the image acquiring device 510.
  • the controller 530 may control the image acquisition device 510 to adjust working parameters, so that the adjusted image acquisition device 510 can directly acquire an image that meets a preset condition.
  • the electronic device 500 has the ability to shoot ID photos or photo stickers, and process portraits in real time during the shooting process, without post-processing, high degree of intelligence, one-click filming, smart shooting, shooting complexity and post-processing professionalism are also greatly Reduced, the shooting time is greatly shortened, and the user's sense of shooting experience is improved.
  • FIG. 6 schematically shows a block diagram of a movable device 600 according to an embodiment of the present disclosure.
  • the mobile device 600 may include an image acquisition device 610, a pan-tilt 620, a processor 630, and a controller 640.
  • the movable device 600 may be a camera including a camera, a smart phone, a tablet computer, or the like.
  • the movable device 600 may be a handheld pan-tilt camera, for example.
  • the mobile device 600 may include two parts: a camera and a pan/tilt, and the camera may be detachably connected to the pan/tilt.
  • the camera may be provided with an image acquisition device 610 (for example, an image sensor) and a processing 630 (for example, an ISP chip).
  • a controller 640 may be provided in the pan-tilt.
  • the pan/tilt can be set outside the camera to fix the camera.
  • the processor 630 of the camera can send control signals to the controller 640 of the pan/tilt (for example, the MCU of the pan/tilt), and the controller 640 can drive the motor to control the pan/tilt on the yaw axis (Yaw), roll axis (Roll) and pitch axis. (Pitch) Three-axis adjustment posture, so as to drive the camera to adjust working parameters.
  • the movable device 600 may be a smart phone, for example.
  • the mobile device 600 may be provided with an image acquisition device 610, a pan-tilt 620, a processor 630, and a controller 640 inside.
  • the pan-tilt can be directly connected internally with the image acquisition device of the mobile device.
  • the movable device can control the pan-tilt to change the posture of the image acquisition device inside it while keeping itself still.
  • the image acquisition device 610 can be used to acquire an image.
  • the pan/tilt 620 can be used to fix the image acquisition device 610.
  • the processor 630 is connected to the image acquisition device 610.
  • the processor 630 may be used to identify the pose of the target object in the first image obtained by the image obtaining device 610, and determine the working parameters of the image obtaining device 610 when obtaining the second image based on the pose of the target object in the first image.
  • the controller 640 is connected to the processor 630 and the pan-tilt 620.
  • the controller 640 may be used to adjust the pose of the pan-tilt 620, so that the image acquisition device 610 obtains the second image with the adjusted working parameters, so that the pose of the target object in the second image meets the preset condition.
  • the target object includes a person.
  • recognizing the pose of the target object in the first image includes: recognizing the posture of the shoulder of the person in the first image.
  • adjusting the pose of the pan/tilt so that the image acquisition device acquires the second image with the adjusted working parameters includes: controlling the pan/tilt to rotate by a first angle relative to the first axis, So that the reference line of the shoulder of the person in the second image is parallel to the preset reference line.
  • recognizing the pose of the target object in the first image includes recognizing the positions of the head and shoulders of the person in the first image.
  • adjusting the pose of the pan/tilt so that the image acquisition device acquires the second image with the adjusted working parameters includes: controlling the pan/tilt to rotate a second angle relative to a second axis and Rotate a third angle with respect to the third axis, so that the head and shoulders of the person in the second image are located in the central area of the second image.
  • recognizing the pose of the target object in the first image includes: recognizing the ratio between the size of the person in the first image and the size of the first image.
  • controlling the image acquisition device to acquire the second image with adjusted operating parameters includes: adjusting the angle of view when the image acquisition device acquires the second image, so that the image is The ratio between the size of the person and the size of the second image satisfies the threshold.
  • acquiring the second image with the adjusted operating parameters includes: in response to a user instruction, acquiring the second image with the adjusted operating parameters.
  • the user instruction includes at least one of the following: a user operation instruction, a user voice instruction, or a user behavior instruction.
  • acquiring the second image with the adjusted operating parameters includes: in response to satisfying the acquisition condition, acquiring the second image with the adjusted operating parameters.
  • satisfying the acquisition condition includes at least one of the following: satisfying a preset duration or the pose of the target object in the second image has satisfied a preset condition.
  • the processor 630 is further configured to process the second image.
  • the mobile device 600 also includes a memory for storing processed images.
  • the processor 630 is further configured to process the second image.
  • the mobile device 600 also includes: a display device for displaying the processed image.
  • the display device may be various display devices such as LCD, LED, GUI, ink screen, or projector.
  • the display device may be a GUI of the camera or a display screen of an external APP.
  • the display device may be a display screen of the smart phone.
  • processing the second image includes at least one of the following: processing the face of the person in the second image, rendering the background in the second image, or correcting the character in the second image The tilt angle of the head relative to the shoulders.
  • correcting the inclination angle of the person's head relative to the shoulder in the second image includes: determining the angle between the symmetry line of the head and the reference line of the shoulder, and adjusting the head based on the angle To correct the tilt angle of the head relative to the shoulders.
  • the display device is also used to display the second image and the processing progress during the process of processing the second image.
  • the memory is also used to store the processed image in response to the completion of the processing.
  • the display device is also used to display the processed image stored in the memory.
  • the processor is further configured to determine whether the target object is included in the first image, and output prompt information if the target object is not included in the first image. For example, output prompt information through a display device.
  • the mobile device 600 in the embodiment of the present disclosure integrates an image acquisition device 610, a pan-tilt 620, a processor 630, and a controller 640.
  • the processor 630 can use image processing algorithms such as face detection, head and shoulder detection, pan-tilt tracking, pan-tilt leveling, optical zoom or digital zoom, portrait beautification, smart cropping, background rendering, etc., and it is integrated into the electronic device, thereby A control instruction may be sent to the controller 640 based on the posture of the person in the first image acquired by the image acquiring device 610.
  • the controller 640 can drive the motor to control the pan/tilt 620 to adjust the attitude on the yaw axis (Yaw), roll axis (Roll) and pitch axis (Pitch), thereby driving the image acquisition device 610 to adjust the working parameters to make the adjusted image
  • the acquiring device 610 can directly acquire an image that meets the preset condition.
  • the mobile device 600 has the ability to shoot ID photos or photo stickers, and process portraits in real time during the shooting process, without post-processing, high degree of intelligence, one-click filming, smart shooting, shooting complexity and post-processing expertise Greatly reduce, the shooting time is greatly shortened, and the user's sense of shooting experience is improved.
  • FIG. 7 schematically shows a block diagram of a computer system 700 according to an embodiment of the present disclosure.
  • the computer system shown in FIG. 7 is only an example, and should not bring any limitation to the function and use range of the embodiments of the present disclosure.
  • an electronic device 700 includes a processor 701, which can be loaded into a random access memory (RAM) 703 according to a program stored in a read only memory (ROM) 702 or from a storage part 708 The program executes various appropriate actions and processing.
  • the processor 701 may include, for example, a general-purpose microprocessor (for example, a CPU), an instruction set processor and/or a related chipset and/or a special-purpose microprocessor (for example, an application specific integrated circuit (ASIC)), and so on.
  • the processor 701 may also include on-board memory for caching purposes.
  • the processor 701 may include a single processing unit or multiple processing units for performing different actions of a method flow according to an embodiment of the present disclosure.
  • the processor 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704.
  • the processor 701 executes various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 702 and/or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703.
  • the processor 701 may also execute various operations of the method flow according to the embodiments of the present disclosure by executing programs stored in the one or more memories.
  • the system 700 may further include an input/output (I/O) interface 705, and the input/output (I/O) interface 705 is also connected to the bus 704.
  • the system 700 may also include one or more of the following components connected to the I/O interface 705: an input part 706 including a keyboard, a mouse, etc.; including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker
  • the output section 707 including the hard disk and the like; the storage section 708 including the hard disk and the like; and the communication section 709 including the network interface card such as a LAN card, a modem, and the like.
  • the communication section 709 performs communication processing via a network such as the Internet.
  • the drive 710 is also connected to the I/O interface 705 as needed.
  • a removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that the computer program read therefrom is installed into the storage portion 708 as needed.
  • the method flow according to the embodiment of the present disclosure may be implemented as a computer software program.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication part 709, and/or installed from the removable medium 711.
  • the computer program executes the above-mentioned functions defined in the system of the embodiment of the present disclosure.
  • the systems, devices, devices, modules, units, etc. described above may be implemented by computer program modules.
  • the present disclosure also provides a computer-readable storage medium.
  • the computer-readable storage medium may be included in the device/device/system described in the above embodiment; or it may exist alone without being assembled into the device/ In the device/system.
  • the aforementioned computer-readable storage medium carries one or more programs, and when the aforementioned one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium.
  • it can include but not limited to: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD- ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable storage medium may include one or more memories other than ROM 702 and/or RAM 703 and/or ROM 702 and RAM 703 described above.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the above-mentioned module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two blocks shown one after the other can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by It is realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Studio Devices (AREA)

Abstract

一种图像获取方法，包括：获取第一图像；识别所述第一图像中目标对象的位姿；基于所述第一图像中目标对象的位姿调整获取第二图像时的工作参数；以及以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。

Description

图像获取方法、电子设备和可移动设备 技术领域
本公开涉及图像处理领域，具体地，涉及一种图像获取方法、电子设备和可移动设备。
背景技术
随着数码技术和网络技术的蓬勃发展，相机已经成为记录生活片段的重要工具和方式。例如，证件照或大头贴是相机使用场景中非常重要的一个场景。然而，证件照对图像质量和规格要求较高，拍摄证件照往往受到拍摄场地和拍摄器材的限制。例如，需要专业单反相机，需要专用闪光灯，闪光灯架，蓝白红三色背景布等，拍摄过程十分繁琐，影响用户体验。例如，在拍摄条件简陋，拍摄时间紧张，重复拍摄难度较高的相机使用场景中，图像中目标对象的位姿可能出现不能完全符合构图需求的情况，同样也会影响成像效果。
发明内容
有鉴于此，本公开实施例提供了一种图像获取方法、电子设备和可移动设备，可以通过识别图像中目标对象的位姿调整相机的工作参数，以使调整后的相机获取到的图像中的目标对象的位姿满足构图要求，无需预设目标对象位姿，操作方便，提升用户在成像过程中的体验感。
第一方面，本公开实施例提供了一种图像获取方法，包括：获取第一图像；识别所述第一图像中目标对象的位姿；基于所述第一图像中目标对象的位姿调整获取第二图像时的工作参数；以及以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
在本公开的一些实施例中，所述目标对象包括人物。
在本公开的一些实施例中，所述识别所述第一图像中目标对象的位姿，包括：识别所述第一图像中人物的肩部的姿态。
在本公开的一些实施例中，所述第二图像中目标对象的位姿满足预 设条件，包括：所述第二图像中人物的肩部基准线与预设的参考线平行。
在本公开的一些实施例中，所述识别所述第一图像中目标对象的位姿，包括：识别所述第一图像中人物的头部和肩部的位置；
在本公开的一些实施例中，所述第二图像中目标对象的位姿满足预设条件，包括：所述第二图像中人物的头部和肩部位于第二图像的中心区域内。
在本公开的一些实施例中，所述识别所述第一图像中目标对象的位姿，包括：识别所述第一图像中人物的尺寸与所述第一图像的尺寸之间的比例。
在本公开的一些实施例中，所述调整获取第二图像时的工作参数，以使第二图像中目标对象的位姿满足预设条件第二图像中目标对象的位姿满足预设条件，包括：调整获取第二图像时的视场角，以使获取第二图像时图像中人物的尺寸与所述第二图像的尺寸之间的比例满足阈值。
在本公开的一些实施例中，所述以调整后的工作参数获取第二图像，包括：响应于用户指令，以调整后的工作参数获取第二图像。
在本公开的一些实施例中，所述用户指令包括以下至少一个：用户操作指令；用户语音指令；用户行为指令。
在本公开的一些实施例中，所述以调整后的工作参数获取第二图像，包括：响应于满足获取条件，以调整后的工作参数获取第二图像。
在本公开的一些实施例中，所述满足获取条件，包括以下至少一个：满足预设时长；所述第二图像中目标对象的位姿已满足预设条件。
在本公开的一些实施例中，所述方法还包括：对所述第二图像进行处理；以及将处理后的图像进行存储。
在本公开的一些实施例中，所述方法还包括：对所述第二图像进行处理；以及展示处理后的图像。
在本公开的一些实施例中，所述对第二图像进行处理，包括以下至少一种：对所述第二图像中人物的面部进行处理；对所述第二图像中的背景进行渲染处理；或者校正所述第二图像中的人物的头部相对于肩部的倾斜角度。
在本公开的一些实施例中，所述校正所述第二图像中的人物的头部 相对于肩部的倾斜角度，包括：确定所述头部的对称线与所述肩部的基准线之间的夹角；基于所述夹角调整所述头部的位姿，以校正所述头部相对于所述肩部的倾斜角度。
在本公开的一些实施例中，所述方法还包括：在对所述第二图像进行处理的过程中，展示所述第二图像和处理进度；响应于处理完成，将处理后的图像进行存储并展示存储的图像。
在本公开的一些实施例中，所述方法还包括：确定所述第一图像中是否包含目标对象；在所述第一图像中不包含目标对象的情况下，输出提示信息。
第二方面，本公开实施例提供了一种电子设备，包括图像获取装置、处理器和控制器。其中，图像获取装置用于获取图像。处理器与所述图像获取装置连接，所述处理器用于识别所述图像获取装置获取的第一图像中目标对象的位姿，基于所述第一图像中目标对象的位姿确定所述图像获取装置获取第二图像时的工作参数。控制器与所述处理器和所述图像获取装置连接，所述控制器用于控制所述图像获取装置以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
第三方面，本公开实施例提供了一种可移动设备，包括图像获取装置、云台、处理器和控制器。其中，图像获取装置用于获取图像。云台用于固定所述图像获取装置。处理器与所述图像获取装置连接，所述处理器用于识别所述图像获取装置获取的第一图像中目标对象的位姿，基于所述第一图像中目标对象的位姿确定所述图像获取装置获取第二图像时的工作参数。控制器与所述处理器和所述云台连接，所述控制器用于调整所述云台的位姿，以使所述图像获取装置以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
第四方面，本公开实施例提供了一种计算机***，包括：一个或多个处理器；计算机可读存储介质，用于存储一个或多个程序，其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现如上所述的方法。
第五方面，本公开实施例提供了一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器实现如上所述的方法。
第六方面，本公开实施例提供了一种计算机程序产品，包括计算机可读指令，其中，所述计算机可读指令被执行时用于执行如上所述的方法。
附图说明
附图是用来提供对本公开的进一步理解，并且构成说明书的一部分，与下面的具体实施方式一起用于解释本发明，但并不构成对本公开的限制。在附图中：
图1示意性示出了本公开实施例的图像获取方法的应用场景；
图2示意性示出了本公开实施例的图像获取方法的流程图；
图3A-图3D示意性示出了本公开实施例的使图像中目标对象位姿满足预设条件的示意图；
图4示意性示出了本公开另一实施例的图像获取方法的流程图；
图5示意性示出了本公开实施例的电子设备的框图；
图6示意性示出了本公开实施例的可移动设备的框图；以及
图7示意性示出了本公开实施例的计算机***的框图。
具体实施方式
为使本公开的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本公开进一步详细说明。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
本公开实施例提供了一种图像获取方法，该方法包括通过图像获取装置获取第一图像，识别第一图像中目标对象的位姿。然后，基于该第一图像中目标对象的位姿调整该图像获取装置获取第二图像时的工作参数。以及，控制该图像获取装置以调整后的工作参数获取第二图像，以 使第二图像中目标对象的位姿满足预设条件，从而可以实现直接获取到的第二图像即可满足用户需求，避免了相关技术中先拍照后处理带来的繁琐操作，提高了用户体验感。
图1示意性示出了本公开实施例的图像获取方法的应用场景100。
如图1所示，根据本公开实施例的应用场景100可以包括电子设备110和云台120。
根据本公开实施例，电子设备110可以包括图像获取装置。例如，电子设备110可以是包含摄像头的相机、智能手机、平板电脑等等。
在本公开实施例中，电子设备110的图像获取装置可以用于获取包含用户130在内的图像。
根据本公开实施例，云台120可以用于改变电子设备110的图像获取装置的工作参数。
例如，电子设备110可以可拆卸地连接至云台120。例如，云台120可以设置于电子设备110的外部，用于固定电子设备110。电子设备110可以用于控制云台120的空间布局(姿态)。例如，电子设备110可以向云台120发送控制信号，以控制云台120改变三个自由度上的姿态，从而可以带动电子设备110改变姿态，以实现对电子设备110的图像获取装置的工作参数的调整。
又例如，云台120可以设置于电子设备110的内部。例如，云台120可以直接在电子设备的内部与图像获取装置连接。电子设备110可以在自身保持不动的情况下，控制云台120改变内部图像获取装置的姿态，从而实现对电子设备110的图像获取装置的工作参数的调整。
根据本公开实施例，可以通过电子设备110的图像获取装置获取包含用户130的第一图像。电子设备110的处理器可以识别获取到的第一图像中的用户130的位姿，并基于用户130的位姿确定该图像获取装置的工作参数。然后，控制云台120改变三个自由度上的姿态，以调整该图像获取装置的工作参数。该图像获取装置可以以调整后的工作参数捕获第二图像，从而可以实现直接获取到的第二图像即可满足用户130的需求的目的。本公开实施例提供的图像获取方法操作方便，可以直接捕获满足用户需要的图像，避免了相关技术中拍摄时目标对象位姿需要多 次调整，或是需要先拍摄存储图像后对图像进行调整的繁琐过程，提高用户体验感。
需要注意的是，图1所示仅为可以应用本公开实施例的图像获取方法的应用场景示例，以帮助本领域技术人员理解本公开的技术内容，但并不意味着本公开实施例不可以用于其他设备、***、环境或场景。
图2示意性示出了本公开实施例的图像获取方法的流程图。
如图2所示，该方法包括操作S201～S204。
在操作S201，获取第一图像。
根据本公开实施例，获取第一图像例如可以是通过电子设备的图像采集装置获取第一图像。例如，可以通过相机的图像传感器获取第一图像。
在本公开实施例，获取第一图像例如可以是开启图像传感器并采集图像，该过程可以不执行图像保存操作。获取第一图像也可以是获取预先存储的第一图像。第一图像可以是真实的场景，也可以是通过人工智能等方法虚拟出来的场景等。
根据本公开实施例，可以响应于接收到用户的启动指令，将电子设备的图像获取装置切换为工作状态，获取并展示获取到的图像，以便用户预览。
在本公开实施例中，可以识别获取到的第一图像，确定第一图像中是否包含目标对象，在第一图像中不包含目标对象的情况下，暂停或终止操作，或是输出提示信息。例如，可以识别获取到的图像中是否包含人物，若不包含则可以输出提示信息。提示信息例如可以用于提示用户当前取景范围内获取不到用户的图像，请用户移动至当前取景范围内。若第一图像中包含人物，则可以继续执行后续操作。
在操作S202，识别第一图像中目标对象的位姿。
根据本公开实施例，目标对象例如可以是人物。例如，在第一图像中识别到一个人物的情况下，识别到的人物即是目标对象。又例如，在第一图像中识别到多个人物的情况下，可以选择满足条件的人物作为目标对象。满足条件例如可以是该人物为用户选定的人物、或者该人物的占比满足条件等等。
在本公开一实施例中，识别第一图像中的目标对象的位姿可以是识别第一图像中人物的肩部的姿态。例如，可以识别人物的肩部基准线与预设参考线之间的倾斜角度。例如，可以通过ISP(Image Signal Processing，图像信号处理单元)芯片运行头肩水平检测算法，识别出肩部基准线相对于图像传感器水平线的倾斜角度。可以理解，本公开实施例不限定肩部基准线的算法，本领域技术人员可以根据实际情况进行设定，例如，肩部准线可以是两侧肩部最高点之间的连线等。
在本公开另一实施例中，识别第一图像中的目标对象的位姿也可以是识别第一图像中人物的头部和肩部的位置。例如，可以识别人物的头部和肩部相对于图像中心位置的偏移距离。例如，可以通过ISP芯片运行头肩检测算法，检测出头肩在图像取景范围中的位置。可以理解，本公开实施例不限定头肩检测的具体算法，本领域技术人员可以根据实际情况进行设定，例如，可以通过检测头部的位置直接确定肩部的位置等等。
在本公开又一实施例中，识别第一图像中的目标对象的位姿还可以是识别第一图像中人物的尺寸与第一图像的尺寸之间的比例。例如，可以识别人物所占的面积与图像的面积之间的比例。或者，也可以识别人物的宽度/高度与图像的宽度/高度之间的比例。
本公开实施例可以通过以上描述的方法或者其他方法来识别用户在第一图像中的位姿是否满足证件照的需要。
在操作S203，基于第一图像中目标对象的位姿调整获取第二图像时的工作参数。
根据本公开实施例，可以基于第一图像中目标对象的位姿调整图像获取装置的工作参数。例如，可以调整图像获取装置的内参和/或外参。例如，可以调整图像获取装置在三个自由度上的姿态。或者也可以调整图像获取装置的焦距、曝光时间等等。
在本公开一实施例中，可以基于第一图像中人物的肩部的姿态，调整图像获取装置获取第二图像时的工作参数，以使第二图像中人物的肩部基准线与预设的参考线平行。
例如，如图3A所示，图像获取装置330可以以原始工作参数获取 第一图像310。识别到第一图像310中人物的肩部基准线L1与图像获取装置330的水平线L2之间存在倾斜角度。则可以基于该倾斜角度控制图像获取装置330相对于z轴旋转第一角度，以使调整后的图像获取装置330获取到的第二图像320中人物的肩部基准线L1与图像获取装置330的水平线L2平行。
在本公开另一实施例中，可以基于第一图像中人物的头部和肩部的位置，调整图像获取装置获取第二图像时的工作参数，以使第二图像中人物的头部和肩部位于第二图像的中心区域内。
例如，如图3B所示，图像获取装置330可以以原始工作参数获取第一图像330。识别第一图像330中人物的头部和肩部相对于图像中心位置的偏移距离。则可以基于该偏移距离控制图像获取装置330相对于x轴旋转第二角度以及相对于y轴旋转第三角度，以使调整后的图像获取装置330获取到的第二图像340中人物的头部和肩部位于图像的中心区域内。
在本公开再一实施例中，可以基于第一图像中人物的尺寸与第一图像的尺寸之间的比例，调整图像获取装置获取第二图像时的工作参数，以使获取第二图像时图像中人物的尺寸与第二图像的尺寸之间的比例满足阈值。
例如，如图3C所示，图像获取装置330可以以原始工作参数获取第一图像350。识别第一图像350中人物的面积与第一图像的面积之间的比例。则可以基于该比例调整图像获取装置330的视场角，例如，可以通过改变图像获取装置330的焦距实现对图像获取装置330的视场角的调整。从而调整后的图像获取装置330获取到的第二图像330中人物的面积与第二图像的面积之间的比例满足阈值。可以理解，本公开实施例的阈值例如可以是阈值范围，调整后的图像获取装置获取到的第二图像330中人物的面积与第二图像的面积之间的比例应高于最低阈值且低于最高阈值。
本公开实施例不限定图像获取装置的各工作参数的调整顺序，本领域技术人员可以根据实际需要进行设定。例如，可以先调整使第二图像中人物的尺寸与第二图像的尺寸之间的比例满足阈值所对应的工作参数， 再调整使第二图像中人物的头部和肩部位于第二图像的中心区域内的工作参数，最后调整使第二图像中人物的肩部基准线与预设的参考线平行的工作参数。
根据本公开实施例，调整获取第二图像时的工作参数还可以是通过图像获取装置对获取的第二图像进行拉伸处理，以对原始图像按比例进行放大或者缩小。或者，也可以对获取的第二图像进行畸变处理，以对原始图像比例失真的部分进行调节，例如，用户的肩部不平衡或者不对称时，可以通过畸变处理调整。或者，还可以对获取的第二图像进行裁切处理，以对原始图像的部分进行剪切等等。
在操作S204，以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
根据本公开实施例，可以响应于用户指令，以调整后的工作参数捕获第二图像。用户指令可以包括用户操作指令、用户语音指令或者用户行为指令中的至少一个。例如，用户可以通过按键控制图像获取装置捕获第二图像。或者，用户也可以通过发出“拍照”的语音指令，控制图像获取装置捕获第二图像。或者，用户还可以通过特定的手势，控制图像获取装置捕获第二图像。
根据本公开实施例，也可以响应于满足获取条件，以调整后的工作参数获取第二图像。满足获取条件可以包括满足预设时长或者第二图像中目标对象的位姿已满足预设条件中的至少一个。例如，可以检测到当前时刻距离目标对象进入拍摄模式的时长，若该时长达到时长阈值，则可以控制图像获取装置捕获第二图像。或者，也可以检测图像获取装置所获取的图像中人物的位姿是否已满足证件照的要求，若满足，则可以控制图像获取装置捕获第二图像。
在本公开实施例中，还可以对获取到的第二图像进行处理。
在本公开一实施例中，可以对第二图像中人物的面部进行处理。例如，对第二图像中人物的面部进行磨皮、美白、祛斑、祛痘、瘦脸或者高光等处理。
在本公开另一实施例中，还可以对第二图像中的背景进行渲染处理。例如，基于用户选择的或者根据证件照场景确定的或者默认的背景颜色 对第二图像中除人物外的背景进行渲染处理。或者，基于用户选择的或者根据证件照场景确定的或者默认的滤镜对第二图像进行渲染处理。
在本公开又一实施例中，还可以校正第二图像中的人物的头部相对于肩部的倾斜角度。例如，确定人物头部的对称线与肩部的基准线之间的夹角，基于夹角调整头部的位姿，以校正头部相对于肩部的倾斜角度。
例如，如图3D所示，可以识别人物头部的对称线L3与肩部的基准线L1之间的夹角，在该夹角超过阈值范围(例如，85度至95度)的情况下，校正头部相对于肩部的倾斜角度，以使校正后的头部对称线L3与肩部基准线L1之间的夹角满足阈值范围。
根据本公开实施例，可以在对第二图像进行处理的过程中，展示处理前的第二图像和当前处理进度。例如，可以展示响应于用户指令获取的第二图像，并通过浮窗的形式展示当前对第二图像处理的进度。例如，可以通过进度条的形式进行展示。
根据本公开实施例，可以响应于处理完成，将处理后的图像进行存储并展示存储的图像。
本公开实施例可以通过图像获取装置先以获取模式实时获取图像，但不进行存储。例如，可以通过图像获取装置以获取模式获取第一图像，并基于第一图像中目标对象的位姿调整图像获取装置的工作参数，图像获取装置继而以调整后的工作参数获取第二图像，以使第二图像中的人物的肩部基准线可以与预设参考线平行，和/或头部和肩部位于中心区域内，和/或人物尺寸占比符合条件。本公开实施例可以将获取到的图像以预览模式展示给用户，用户可以根据预览效果指示图像获取装置对当期图像进行拍摄捕获。本公开实施例可以对捕获到的图像进一步进行处理，例如，校正头肩倾斜角度，和/或美颜处理，和/或背景渲染处理等，并将处理后的图像存储并展示给用户。相对于相关技术中需要多次调整目标对象位姿以满足构图需求，或是需要用户拍摄存储图像后再导入应用程序中进行后期处理，本公开实施例简化了用户反复操作的繁琐过程，用户可以直接拍摄并获得想要的图像，提高用户体验感。
图4示意性示出了本公开另一实施例的图像获取方法的流程图。
如图4所示，该方法包括操作S401～S415。
在操作S401，启动相机。
根据本公开实施例，用户可以通过启动指令控制相机启动。例如，在手持云台相机的场景中，用户可以通过按动开机键启动相机。
在本公开实施例中，在启动相机后，用户可以通过相机内置的GUI(Graphical User Interface，图形用户界面)或者外接应用程序APP预览相机的取景图像。
在操作S402，GUI或APP选择证件照模式。
根据本公开实施例，用户可以通过GUI或者APP进行模式选择的操作。例如，可以选择相机的拍摄模式为证件照模式。
在操作S403，云台旋转至自拍位置。
根据本公开实施例，在相机的拍摄模式切换为证件照模式时，云台也可以随之进入证件照拍摄模式。例如，可以控制云台的偏航轴(Yaw轴)旋转180°进入自拍状态，相机的取景范围朝向用户方向。
在操作S404，开启人脸识别和头肩识别。
根据本公开实施例，可以通过相机的ISP芯片运行人脸识别和头肩检测算法，检测出人脸和头肩在取景范围的位置。
在本公开实施例中，若未检测到人脸，则可以在GUI或者APP上提示用户。例如，“证件照模式需将人脸置于取景范围”等提示内容。在本公开实施例中，若检测到人脸或头肩移动，还可控制云台调整追踪人脸或头肩，使人脸和头肩保持在取景范围内。
在操作S405，锁定人脸和头肩ROI区域。
根据本公开实施例，可以根据检测到的人脸和头肩在取景范围的位置，形成矩形的ROI(Region Of Interest)区域。
在操作S406，云台调整姿态使头肩居中且水平。
根据本公开实施例，相机的ISP芯片可以针对ROI区域运行头肩水平检测算法，识别出肩部基准线相对于相机的图像传感器水平线的倾斜角度、头肩相对于取景范围中心点的位置差、以及头部相对于肩部的倾斜角度。进而向云台发送指令，通知云台的MCU(Microcontroller Unit，微控制单元)驱动电机控制偏航轴(Yaw)、滚动轴(Roll)和俯仰轴(Pitch)三轴调整姿态，特别是可以对滚动轴(Roll)进行控制以消除肩部基准 线相对于相机的图像传感器水平线的倾斜角度，使得肩部基准线相对于相机的图像传感器的水平线平行，以及消除头肩相对于取景范围中心点的位置差，使得头肩处于取景范围的中心区域，从而实现获取到的图像中的人物头肩居中且肩部水平的效果。在操作S407，人脸美颜。
根据本公开实施例，可以通过相机的ISP芯片运行美颜算法，进入人像美颜模式，对获取到的图像中的人脸进行磨皮、美肤、祛斑、祛痘、高光等处理。
在操作S408，光学变焦或数码变焦调节取景范围。
根据本公开实施例，根据ROI区域的尺寸与取景范围尺寸之间的比例，可以进行光学变焦或数码变焦，使得头肩的成像大小符合证件照的要求。
在操作S409，选择背景颜色或滤镜。
根据本公开实施例，用户可以根据手持云台相机的LCD上可预览的实时证件照效果，通过GUI或者APP选择想要的背景颜色和滤镜。背景颜色例如可以包括白色、蓝色或者红色等底色。滤镜例如可以包括边框、渲染或者动物形态类滤镜等等。
在操作S410，开始拍照。
根据本公开实施例，可以响应于用户按下快门键，开始拍照。ISP芯片可以从图像传感器获取rggb格式的生图，经过一系列的滤波处理和格式转换处理，形成粗略的证件照YUV图。
在操作S411，根据头肩框位置剪裁出头肩区域。
根据本公开实施例，可以将YUV图中的头肩剪裁出来，通过头部校正算法，消除头部相对于肩部的倾斜角度。
或者，也可以在检测出来的头部相对肩部倾斜角度大于一定幅度时，在LCD上实时提示用户头部不正，以使用户可以根据LCD上的提示信息，挪动头部位置，以消除头部相对于肩部的倾斜角度。
在操作S412，非头肩区域进行背景渲染。
根据本公开实施例，可以根据操作S409中用户选定的背景颜色和滤镜，对非头肩区域的背景区域进行渲染处理。
在操作S413，ISP生成照片。
根据本公开实施例，ISP芯片可以将渲染后的YUV图，进行Jpeg编码，生成照片。
在操作S414，存储照片。
根据本公开实施例，可以将生成的照片存储至SD卡等存储设备中。
在操作S415，LCD或APP显示拍照完成。
根据本公开实施例，相机的LCD或APP上可以显示拍照完成动画，可以用于通过GUI和APP对证件照进行回放预览和下载。
可以理解，上述图像获取方法应用于手持云台相机仅是本公开示例性实施例，本公开对此不做限定，上述图像获取方法也可以应用于手机、运动相机或者其他电子设备中。
本公开实施例的图像获取方法可以使用人脸检测、头肩检测、云台跟踪、云台调平、光学变焦或数码变焦、人像美颜、智能裁剪、背景渲染等图像处理算法，并集成在相机芯片内部，使得家庭常用小相机或手机就能具备证件照或大头贴拍摄能力，在拍摄过程中对人像进行实时处理，无需后处理，智能化程度高，一键成片，智能拍摄，拍摄复杂度和后处理专业程度也大大降低，拍摄时间大大缩短，提高用户拍摄体验感。
图5示意性示出了本公开实施例的电子设备500的框图。
如图5所示，本公开实施例的电子设备500可以包括图像获取装置510、处理器520和控制器530。
图像获取装置510可以用于获取图像。
处理器520可以用于识别图像获取装置510获取的第一图像中目标对象的位姿，基于第一图像中目标对象的位姿确定图像获取装置510获取第二图像时的工作参数。
控制器530可以用于控制图像获取装置510以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
根据本公开实施例，电子设备500可以是相机、手机、平板电脑等各种具有图像获取装置的电子设备。电子设备500可以设置有图像获取装置510、处理器520和控制器530。处理器520可以与图像获取装置510连接。例如，处理器520可以获取到图像获取装置510获取的图像。控制器530可以与处理器520和图像获取装置510连接。例如，控制器 530可以接收来自处理器520的控制指令，并基于控制指令控制调整图像获取装置510的工作参数。
根据本公开实施例，图像获取装置510例如可以是能够获取图像的各种摄像组件。例如，可以是图像传感器等。
根据本公开实施例，处理器520例如可以是通用处理器CPU、图像处理器GPU、图像信号处理单元ISP芯片等各种处理器520。例如，当电子设备500为相机时，处理器520可以是相机的ISP芯片或者其他处理模块。又例如，当电子设备500为智能手机时，处理器520也可以是智能手机的CPU或者其他处理模块。
根据本公开实施例，目标对象可以包括人物。
根据本公开实施例，识别第一图像中目标对象的位姿，包括：识别第一图像中人物的肩部的姿态。
根据本公开实施例，第二图像中目标对象的位姿满足预设条件，包括：第二图像中人物的肩部基准线与预设的参考线平行。
根据本公开实施例，识别第一图像中目标对象的位姿，包括：识别第一图像中人物的头部和肩部的位置。
根据本公开实施例，第二图像中目标对象的位姿满足预设条件，包括：第二图像中人物的头部和肩部位于第二图像的中心区域内。
根据本公开实施例，识别第一图像中目标对象的位姿，包括：识别第一图像中人物的尺寸与第一图像的尺寸之间的比例。
根据本公开实施例，控制图像获取装置以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件第二图像中目标对象的位姿满足预设条件，包括：调整图像获取装置获取第二图像时的视场角，以使获取第二图像时图像中人物的尺寸与所述第二图像的尺寸之间的比例满足阈值。
根据本公开实施例，以调整后的工作参数获取第二图像，包括：响应于用户指令，以调整后的工作参数获取第二图像。
根据本公开实施例，用户指令包括以下至少一个：用户操作指令，用户语音指令，或者用户行为指令。
根据本公开实施例，以调整后的工作参数获取第二图像，包括：响 应于满足获取条件，以调整后的工作参数获取第二图像。
根据本公开实施例，满足获取条件，包括以下至少一个：满足预设时长或者第二图像中目标对象的位姿已满足预设条件。
根据本公开实施例，处理器520还用于对第二图像进行处理。电子设备500还包括：存储器，用于存储处理后的图像。
根据本公开实施例，处理器520还用于对第二图像进行处理。电子设备500还包括：展示装置，用于展示处理后的图像。展示装置例如可以LCD、LED、GUI、墨水屏或者投影仪等各种展示装置。例如，当电子设备500为相机时，展示装置可以是相机的GUI或者外界APP的显示屏。又例如，当电子设备500为智能手机时，展示装置可以是智能手机的显示屏。
根据本公开实施例，对第二图像进行处理，包括以下至少一种：对第二图像中人物的面部进行处理、对第二图像中的背景进行渲染处理、或者校正第二图像中的人物的头部相对于肩部的倾斜角度。
根据本公开实施例，校正第二图像中的人物的头部相对于肩部的倾斜角度，包括：确定头部的对称线与肩部的基准线之间的夹角，基于夹角调整头部的位姿，以校正头部相对于肩部的倾斜角度。
根据本公开实施例，展示装置还用于在对第二图像进行处理的过程中，展示第二图像和处理进度。存储器还用于响应于处理完成，存储处理后的图像。展示装置还用于展示存储器中存储的处理后的图像。
根据本公开实施例，处理器还用于确定第一图像中是否包含目标对象，在第一图像中不包含目标对象的情况下，输出提示信息。例如，通过展示装置输出提示信息。
本公开实施例中的电子设备500集成有图像获取装置510、处理器520和控制器530。处理器520可以使用人脸检测、头肩检测、云台跟踪、云台调平、光学变焦或数码变焦、人像美颜、智能裁剪、背景渲染等图像处理算法，并集成在电子设备内部，从而可以基于图像获取装置510获取的第一图像中人物的位姿向控制器530发送控制指令。控制器530可以控制图像获取装置510调整工作参数，以使调整后的图像获取装置510可以直接获取到满足预设条件的图像。使得电子设备500具备证件 照或大头贴拍摄能力，在拍摄过程中对人像进行实时处理，无需后处理，智能化程度高，一键成片，智能拍摄，拍摄复杂度和后处理专业程度也大大降低，拍摄时间大大缩短，提高用户拍摄体验感。
图6示意性示出了本公开实施例的可移动设备600的框图。
如图6所示，可移动设备600可以包括图像获取装置610、云台620、处理器630和控制器640。
根据本公开实施例，可移动设备600可以是包含摄像头的相机、智能手机、平板电脑等等。
在本公开一实施例中，可移动设备600例如可以是手持云台相机。例如，可移动设备600可以包括相机和云台两个部分，相机可以可拆卸地连接至云台。相机内可以设置有图像获取装置610(例如，图像传感器)和处理630(例如，ISP芯片)。云台中可以设置有控制器640。例如，云台可以设置于相机的外部，用于固定相机。相机的处理器630可以向云台的控制器640(例如，云台的MCU)发送控制信号，控制器640可以驱动电机控制云台在偏航轴(Yaw)、滚动轴(Roll)和俯仰轴(Pitch)三轴调整姿态，从而带动相机调整工作参数。
在本公开另一实施例中，可移动设备600例如可以是智能手机。例如，可移动设备600内部可以设置有图像获取装置610、云台620、处理器630和控制器640。例如，云台可以直接在内部与可移动设备的图像获取装置连接。可移动设备可以在自身保持不动的情况下，控制云台改变其内部的图像获取装置的姿态。
图像获取装置610可以用于获取图像。
云台620可以用于固定图像获取装置610。
处理器630与图像获取装置610连接。处理器630可以用于识别图像获取装置610获取的第一图像中目标对象的位姿，基于第一图像中目标对象的位姿确定图像获取装置610获取第二图像时的工作参数。
控制器640与处理器630和云台620连接。控制器640可以用于调整云台620的位姿，以使图像获取装置610以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
根据本公开实施例，目标对象包括人物。
根据本公开实施例，识别所述第一图像中目标对象的位姿，包括：识别所述第一图像中人物的肩部的姿态。
根据本公开实施例，调整所述云台的位姿，以使所述图像获取装置以调整后的工作参数获取第二图像，包括：控制所述云台相对于第一轴旋转第一角度，以使所述第二图像中人物的肩部基准线与预设的参考线平行。
根据本公开实施例，识别所述第一图像中目标对象的位姿，包括：识别所述第一图像中人物的头部和肩部的位置。
根据本公开实施例，调整所述云台的位姿，以使所述图像获取装置以调整后的工作参数获取第二图像，包括：控制所述云台相对于第二轴旋转第二角度且相对于第三轴旋转第三角度，以使所述第二图像中人物的头部和肩部位于第二图像的中心区域内。
根据本公开实施例，识别所述第一图像中目标对象的位姿，包括：识别所述第一图像中人物的尺寸与所述第一图像的尺寸之间的比例。
根据本公开实施例，控制所述图像获取装置以调整后的工作参数获取第二图像，包括：调整所述图像获取装置获取第二图像时的视场角，以使获取第二图像时图像中人物的尺寸与所述第二图像的尺寸之间的比例满足阈值。
根据本公开实施例，以调整后的工作参数获取第二图像，包括：响应于用户指令，以调整后的工作参数获取第二图像。
根据本公开实施例，用户指令包括以下至少一个：用户操作指令、用户语音指令、或者用户行为指令。
根据本公开实施例，以调整后的工作参数获取第二图像，包括：响应于满足获取条件，以调整后的工作参数获取第二图像。
根据本公开实施例，满足获取条件，包括以下至少一个：满足预设时长或者所述第二图像中目标对象的位姿已满足预设条件。
根据本公开实施例，处理器630还用于对所述第二图像进行处理。可移动设备600还包括：存储器，用于存储处理后的图像。
根据本公开实施例，处理器630还用于对所述第二图像进行处理。可移动设备600还包括：展示装置，用于展示处理后的图像。
展示装置例如可以LCD、LED、GUI、墨水屏或者投影仪等各种展示装置。例如，当电子设备500为相机时，展示装置可以是相机的GUI或者外界APP的显示屏。又例如，当电子设备500为智能手机时，展示装置可以是智能手机的显示屏。
根据本公开实施例，对第二图像进行处理，包括以下至少一种：对第二图像中人物的面部进行处理、对第二图像中的背景进行渲染处理、或者校正第二图像中的人物的头部相对于肩部的倾斜角度。
根据本公开实施例，校正第二图像中的人物的头部相对于肩部的倾斜角度，包括：确定头部的对称线与肩部的基准线之间的夹角，基于夹角调整头部的位姿，以校正头部相对于肩部的倾斜角度。
根据本公开实施例，展示装置还用于在对第二图像进行处理的过程中，展示第二图像和处理进度。存储器还用于响应于处理完成，存储处理后的图像。展示装置还用于展示存储器中存储的处理后的图像。
根据本公开实施例，处理器还用于确定第一图像中是否包含目标对象，在第一图像中不包含目标对象的情况下，输出提示信息。例如，通过展示装置输出提示信息。
本公开实施例中的可移动设备600集成有图像获取装置610、云台620、处理器630和控制器640。处理器630可以使用人脸检测、头肩检测、云台跟踪、云台调平、光学变焦或数码变焦、人像美颜、智能裁剪、背景渲染等图像处理算法，并集成在电子设备内部，从而可以基于图像获取装置610获取的第一图像中人物的位姿向控制器640发送控制指令。控制器640可以驱动电机控制云台620在偏航轴(Yaw)、滚动轴(Roll)和俯仰轴(Pitch)三轴调整姿态，从而带动图像获取装置610调整工作参数，以使调整后的图像获取装置610可以直接获取到满足预设条件的图像。使得可移动设备600具备证件照或大头贴拍摄能力，在拍摄过程中对人像进行实时处理，无需后处理，智能化程度高，一键成片，智能拍摄，拍摄复杂度和后处理专业程度也大大降低，拍摄时间大大缩短，提高用户拍摄体验感。
图7示意性示出了本公开实施例的计算机***700的框图。图7示出的计算机***仅仅是一个示例，不应对本公开实施例的功能和使用范 围带来任何限制。
如图7所示，根据本公开实施例的电子设备700包括处理器701，其可以根据存储在只读存储器(ROM)702中的程序或者从存储部分708加载到随机访问存储器(RAM)703中的程序而执行各种适当的动作和处理。处理器701例如可以包括通用微处理器(例如CPU)、指令集处理器和/或相关芯片组和/或专用微处理器(例如，专用集成电路(ASIC))，等等。处理器701还可以包括用于缓存用途的板载存储器。处理器701可以包括用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。
在RAM 703中，存储有***700操作所需的各种程序和数据。处理器701、ROM 702以及RAM 703通过总线704彼此相连。处理器701通过执行ROM 702和/或RAM 703中的程序来执行根据本公开实施例的方法流程的各种操作。需要注意，所述程序也可以存储在除ROM 702和RAM 703以外的一个或多个存储器中。处理器701也可以通过执行存储在所述一个或多个存储器中的程序来执行根据本公开实施例的方法流程的各种操作。
根据本公开的实施例，***700还可以包括输入/输出(I/O)接口705，输入/输出(I/O)接口705也连接至总线704。***700还可以包括连接至I/O接口705的以下部件中的一项或多项：包括键盘、鼠标等的输入部分706；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分707；包括硬盘等的存储部分708；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分709。通信部分709经由诸如因特网的网络执行通信处理。驱动器710也根据需要连接至I/O接口705。可拆卸介质711，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器710上，以便于从其上读出的计算机程序根据需要被安装入存储部分708。
根据本公开的实施例，根据本公开实施例的方法流程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读存储介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程 序可以通过通信部分709从网络上被下载和安装，和/或从可拆卸介质711被安装。在该计算机程序被处理器701执行时，执行本公开实施例的***中限定的上述功能。根据本公开的实施例，上文描述的***、设备、装置、模块、单元等可以通过计算机程序模块来实现。
本公开还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施例中描述的设备/装置/***中所包含的；也可以是单独存在，而未装配入该设备/装置/***中。上述计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被执行时，实现根据本公开实施例的方法。
根据本公开的实施例，计算机可读存储介质可以是非易失性的计算机可读存储介质。例如可以包括但不限于：便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。
例如，根据本公开的实施例，计算机可读存储介质可以包括上文描述的ROM 702和/或RAM 703和/或ROM 702和RAM 703以外的一个或多个存储器。
附图中的流程图和框图，图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图或流程图中的每个方框、以及框图或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。
本领域技术人员可以理解，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合，即使这样的组合或结合没有明确记载于本公开中。特别地，在不脱离本公开精神和教导的情况下，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合。所有这些组合和/或结合均落入本公开的范围。
以上对本公开的实施例进行了描述。但是，这些实施例仅仅是为了说明的目的，而并非为了限制本公开的范围。尽管在以上分别描述了各实施例，但是这并不意味着各个实施例中的措施不能有利地结合使用。本公开的范围由所附权利要求及其等同物限定。不脱离本公开的范围，本领域技术人员可以做出多种替代和修改，这些替代和修改都应落在本公开的范围之内。

Claims (57)

  1. 一种图像获取方法，包括：
    获取第一图像；
    识别所述第一图像中目标对象的位姿；
    基于所述第一图像中目标对象的位姿调整获取第二图像时的工作参数；以及
    以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
  2. 根据权利要求1所述的方法，其中，所述目标对象包括人物。
  3. 根据权利要求2所述的方法，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的肩部的姿态。
  4. 根据权利要求3所述的方法，其中，所述第二图像中目标对象的位姿满足预设条件，包括：
    所述第二图像中人物的肩部基准线与预设的参考线平行。
  5. 根据权利要求2所述的方法，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的头部和肩部的位置。
  6. 根据权利要求5所述的方法，其中，所述第二图像中目标对象的位姿满足预设条件，包括：
    所述第二图像中人物的头部和肩部位于第二图像的中心区域内。
  7. 根据权利要求2所述的方法，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的尺寸与所述第一图像的尺寸之间的比例。
  8. 根据权利要求7所述的方法，其中，所述调整获取第二图像时的工作参数，以使第二图像中目标对象的位姿满足预设条件第二图像中目标对象的位姿满足预设条件，包括：
    调整获取第二图像时的视场角，以使获取第二图像时图像中人物的尺寸与所述第二图像的尺寸之间的比例满足阈值。
  9. 根据权利要求1所述的方法，其中，所述以调整后的工作参数获取第二图像，包括：
    响应于用户指令，以调整后的工作参数获取第二图像。
  10. 根据权利要求9所述的方法，其中，所述用户指令包括以下至少一个：
    用户操作指令；
    用户语音指令；
    用户行为指令。
  11. 根据权利要求1所述的方法，其中，所述以调整后的工作参数获取第二图像，包括：
    响应于满足获取条件，以调整后的工作参数获取第二图像。
  12. 根据权利要求11所述的方法，其中，所述满足获取条件，包括以下至少一个：
    满足预设时长；
    所述第二图像中目标对象的位姿已满足预设条件。
  13. 根据权利要求1所述的方法，还包括：
    对所述第二图像进行处理；以及
    将处理后的图像进行存储。
  14. 根据权利要求1所述的方法，还包括：
    对所述第二图像进行处理；以及
    展示处理后的图像。
  15. 根据权利要求13或14所述的方法，其中，所述对第二图像进行处理，包括以下至少一种：
    对所述第二图像中人物的面部进行处理；
    对所述第二图像中的背景进行渲染处理；或者
    校正所述第二图像中的人物的头部相对于肩部的倾斜角度。
  16. 根据权利要求15所述的方法，其中，所述校正所述第二图像中的人物的头部相对于肩部的倾斜角度，包括：
    确定所述头部的对称线与所述肩部的基准线之间的夹角；
    基于所述夹角调整所述头部的位姿，以校正所述头部相对于所述肩部的倾斜角度。
  17. 根据权利要求13或14所述的方法，还包括：
    在对所述第二图像进行处理的过程中，展示所述第二图像和处理进度；
    响应于处理完成，将处理后的图像进行存储并展示存储的图像。
  18. 根据权利要求1所述的方法，还包括：
    确定所述第一图像中是否包含目标对象；
    在所述第一图像中不包含目标对象的情况下，输出提示信息。
  19. 一种电子设备，包括：
    图像获取装置，用于获取图像；
    处理器，与所述图像获取装置连接，所述处理器用于识别所述图像获取装置获取的第一图像中目标对象的位姿，基于所述第一图像中目标对象的位姿确定所述图像获取装置获取第二图像时的工作参数；以及
    控制器，与所述处理器和所述图像获取装置连接，所述控制器用于控制所述图像获取装置以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
  20. 根据权利要求19所述的电子设备，其中，所述目标对象包括人物。
  21. 根据权利要求20所述的电子设备，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的肩部的姿态。
  22. 根据权利要求21所述的电子设备，其中，所述第二图像中目标对象的位姿满足预设条件，包括：
    所述第二图像中人物的肩部基准线与预设的参考线平行。
  23. 根据权利要求20所述的电子设备，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的头部和肩部的位置。
  24. 根据权利要求23所述的电子设备，其中，所述第二图像中目标对象的位姿满足预设条件，包括：
    所述第二图像中人物的头部和肩部位于第二图像的中心区域内。
  25. 根据权利要求20所述的电子设备，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的尺寸与所述第一图像的尺寸之间的比例。
  26. 根据权利要求25所述的电子设备，其中，所述控制所述图像获取装置以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件第二图像中目标对象的位姿满足预设条件，包括：
    调整所述图像获取装置获取第二图像时的视场角，以使获取第二图像时图像中人物的尺寸与所述第二图像的尺寸之间的比例满足阈值。
  27. 根据权利要求19所述的电子设备，其中，所述以调整后的工作参数获取第二图像，包括：
    响应于用户指令，以调整后的工作参数获取第二图像。
  28. 根据权利要求27所述的电子设备，其中，所述用户指令包括以下至少一个：
    用户操作指令；
    用户语音指令；
    用户行为指令。
  29. 根据权利要求19所述的电子设备，其中，所述以调整后的工作参数获取第二图像，包括：
    响应于满足获取条件，以调整后的工作参数获取第二图像。
  30. 根据权利要求29所述的电子设备，其中，所述满足获取条件，包括以下至少一个：
    满足预设时长；
    所述第二图像中目标对象的位姿已满足预设条件。
  31. 根据权利要求19所述的电子设备，其中，
    所述处理器还用于：对所述第二图像进行处理；
    所述电子设备还包括：存储器，用于存储处理后的图像。
  32. 根据权利要求19所述电子设备，其中，
    所述处理器还用于：对所述第二图像进行处理；
    所述电子设备还包括：展示装置，用于展示处理后的图像。
  33. 根据权利要求31或32所述的电子设备，其中，所述对第二图像进行处理，包括以下至少一种：
    对所述第二图像中人物的面部进行处理；
    对所述第二图像中的背景进行渲染处理；或者
    校正所述第二图像中的人物的头部相对于肩部的倾斜角度。
  34. 根据权利要求33所述的电子设备，其中，所述校正所述第二图像中的人物的头部相对于肩部的倾斜角度，包括：
    确定所述头部的对称线与所述肩部的基准线之间的夹角；
    基于所述夹角调整所述头部的位姿，以校正所述头部相对于所述肩部的倾斜角度。
  35. 根据权利要求32所述的电子设备，其中：
    所述展示装置还用于：在对所述第二图像进行处理的过程中，展示所述第二图像和处理进度；
    所述存储器还用于：响应于处理完成，存储处理后的图像；
    所述展示装置还用于：展示所述存储器中存储的处理后的图像。
  36. 根据权利要求19所述的电子设备，所述处理器还用于：
    确定所述第一图像中是否包含目标对象；
    在所述第一图像中不包含目标对象的情况下，输出提示信息。
  37. 一种可移动设备，包括：
    图像获取装置，用于获取图像；
    云台，用于固定所述图像获取装置；
    处理器，与所述图像获取装置连接，所述处理器用于识别所述图像获取装置获取的第一图像中目标对象的位姿，基于所述第一图像中目标对象的位姿确定所述图像获取装置获取第二图像时的工作参数；以及
    控制器，与所述处理器和所述云台连接，所述控制器用于调整所述云台的位姿，以使所述图像获取装置以调整后的工作参数获取第二图像，以使第二图像中目标对象的位姿满足预设条件。
  38. 根据权利要求37所述的可移动设备，其中，所述目标对象包括人物。
  39. 根据权利要求38所述的可移动设备，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的肩部的姿态。
  40. 根据权利要求39所述的可移动设备，其中，所述调整所述云台的位姿，以使所述图像获取装置以调整后的工作参数获取第二图像，包括：
    控制所述云台相对于第一轴旋转第一角度，以使所述第二图像中人物的肩部基准线与预设的参考线平行。
  41. 根据权利要求38所述的可移动设备，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的头部和肩部的位置。
  42. 根据权利要求41所述的可移动设备，其中，所述调整所述云台的位姿，以使所述图像获取装置以调整后的工作参数获取第二图像，包括：
    控制所述云台相对于第二轴旋转第二角度且相对于第三轴旋转第三角度，以使所述第二图像中人物的头部和肩部位于第二图像的中心区域内。
  43. 根据权利要求38所述的可移动设备，其中，所述识别所述第一图像中目标对象的位姿，包括：
    识别所述第一图像中人物的尺寸与所述第一图像的尺寸之间的比例。
  44. 根据权利要求43所述的可移动设备，其中，所述控制所述图像获取装置以调整后的工作参数获取第二图像，包括：
    调整所述图像获取装置获取第二图像时的视场角，以使获取第二图像时图像中人物的尺寸与所述第二图像的尺寸之间的比例满足阈值。
  45. 根据权利要求37所述的可移动设备，其中，所述以调整后的工作参数获取第二图像，包括：
    响应于用户指令，以调整后的工作参数获取第二图像。
  46. 根据权利要求45所述的可移动设备，其中，所述用户指令包括以下至少一个：
    用户操作指令；
    用户语音指令；
    用户行为指令。
  47. 根据权利要求37所述的可移动设备，其中，所述以调整后的工作参数获取第二图像，包括：
    响应于满足获取条件，以调整后的工作参数获取第二图像。
  48. 根据权利要求47所述的可移动设备，其中，所述满足获取条件，包括以下至少一个：
    满足预设时长；
    所述第二图像中目标对象的位姿已满足预设条件。
  49. 根据权利要求37所述的可移动设备，其中，
    所述处理器还用于：对所述第二图像进行处理；
    所述可移动设备还包括：存储器，用于存储处理后的图像。
  50. 根据权利要求37所述的可移动设备，其中，
    所述处理器还用于：对所述第二图像进行处理；
    所述可移动设备还包括：展示装置，用于展示处理后的图像。
  51. 根据权利要求49或50所述的可移动设备，其中，所述对第二图像进行处理，包括以下至少一种：
    对所述第二图像中人物的面部进行处理；
    对所述第二图像中的背景进行渲染处理；或者
    校正所述第二图像中的人物的头部相对于肩部的倾斜角度。
  52. 根据权利要求51所述的可移动设备，其中，所述校正所述第二图像中的人物的头部相对于肩部的倾斜角度，包括：
    确定所述头部的对称线与所述肩部的基准线之间的夹角；
    基于所述夹角调整所述头部的位姿，以校正所述头部相对于所述肩部的倾斜角度。
  53. 根据权利要求49或50所述的可移动设备，其中：
    所述展示装置还用于：在对所述第二图像进行处理的过程中，展示所述第二图像和处理进度；
    所述存储器还用于：响应于处理完成，存储处理后的图像；
    所述展示装置还用于：展示所述存储器中存储的处理后的图像。
  54. 根据权利要求37所述的可移动设备，所述处理器还用于：
    确定所述第一图像中是否包含目标对象；
    在所述第一图像中不包含目标对象的情况下，输出提示信息。
  55. 一种计算机***，包括：
    一个或多个处理器；
    计算机可读存储介质，用于存储一个或多个程序，
    其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现权利要求1至18中任一项所述的方法。
  56. 一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器实现权利要求1至18中任一项所述的方法。
  57. 一种计算机程序产品，包括计算机可读指令，其中，所述计算机可读指令被执行时用于执行根据权利要求1-18中任一项所述的方法。
PCT/CN2020/097444 2020-06-22 2020-06-22 图像获取方法、电子设备和可移动设备 WO2021258249A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/097444 WO2021258249A1 (zh) 2020-06-22 2020-06-22 图像获取方法、电子设备和可移动设备
CN202080006208.8A CN113170050A (zh) 2020-06-22 2020-06-22 图像获取方法、电子设备和可移动设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/097444 WO2021258249A1 (zh) 2020-06-22 2020-06-22 图像获取方法、电子设备和可移动设备

Publications (1)

Publication Number Publication Date
WO2021258249A1 true WO2021258249A1 (zh) 2021-12-30

Family

ID=76879235

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/097444 WO2021258249A1 (zh) 2020-06-22 2020-06-22 图像获取方法、电子设备和可移动设备

Country Status (2)

Country Link
CN (1) CN113170050A (zh)
WO (1) WO2021258249A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114466140B (zh) * 2022-02-09 2023-10-24 维沃移动通信有限公司 图像拍摄方法及装置

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8072491B2 (en) * 2002-10-18 2011-12-06 Sony Corporation Information processing system and method, information processing apparatus, image-capturing device and method, recording medium, and program
US20120019620A1 (en) * 2010-07-20 2012-01-26 Hon Hai Precision Industry Co., Ltd. Image capture device and control method
CN104243832A (zh) * 2014-09-30 2014-12-24 北京金山安全软件有限公司 通过移动终端进行拍摄的方法、装置及移动终端
CN106210507A (zh) * 2016-06-27 2016-12-07 联想(北京)有限公司 图像调整方法及电子设备
CN107749947A (zh) * 2017-09-28 2018-03-02 努比亚技术有限公司 拍照方法、移动终端及计算机可读存储介质
CN110633629A (zh) * 2019-08-02 2019-12-31 广东电网有限责任公司清远供电局 基于人工智能的电网巡检方法、装置、设备及存储介质
CN110830705A (zh) * 2018-08-08 2020-02-21 深圳市优必选科技有限公司 机器人拍照方法、机器人、终端设备及存储介质
CN111147749A (zh) * 2019-12-31 2020-05-12 宇龙计算机通信科技(深圳)有限公司 拍摄方法、拍摄装置、终端及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105554285B (zh) * 2015-12-22 2020-11-17 努比亚技术有限公司 拍摄人物照片的处理方法、智能移动终端
CN111311729B (zh) * 2020-01-18 2022-03-11 西安电子科技大学 一种基于双向投影网络的自然场景三维人体姿态重建方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8072491B2 (en) * 2002-10-18 2011-12-06 Sony Corporation Information processing system and method, information processing apparatus, image-capturing device and method, recording medium, and program
US20120019620A1 (en) * 2010-07-20 2012-01-26 Hon Hai Precision Industry Co., Ltd. Image capture device and control method
CN104243832A (zh) * 2014-09-30 2014-12-24 北京金山安全软件有限公司 通过移动终端进行拍摄的方法、装置及移动终端
CN106210507A (zh) * 2016-06-27 2016-12-07 联想(北京)有限公司 图像调整方法及电子设备
CN107749947A (zh) * 2017-09-28 2018-03-02 努比亚技术有限公司 拍照方法、移动终端及计算机可读存储介质
CN110830705A (zh) * 2018-08-08 2020-02-21 深圳市优必选科技有限公司 机器人拍照方法、机器人、终端设备及存储介质
CN110633629A (zh) * 2019-08-02 2019-12-31 广东电网有限责任公司清远供电局 基于人工智能的电网巡检方法、装置、设备及存储介质
CN111147749A (zh) * 2019-12-31 2020-05-12 宇龙计算机通信科技(深圳)有限公司 拍摄方法、拍摄装置、终端及存储介质

Also Published As

Publication number Publication date
CN113170050A (zh) 2021-07-23

Similar Documents

Publication Publication Date Title
US9712751B2 (en) Camera field of view effects based on device orientation and scene content
US9578260B2 (en) Digital photographing apparatus and method of controlling the digital photographing apparatus
JP5409189B2 (ja) 撮像装置及びその制御方法
TWI411970B (zh) 攝像裝置、臉部檢測方法及記錄媒體
US8704929B2 (en) System and method for user guidance of photographic composition in image acquisition systems
JP2012199675A (ja) 画像処理装置、画像処理方法及びプログラム
JP5930245B1 (ja) 画像処理装置、画像処理方法及びプログラム
US10348958B2 (en) Image processing apparatus for performing predetermined processing on a captured image
WO2019214574A1 (zh) 图像拍摄方法、装置及电子终端
CN108270959B (zh) 全景成像的方法、终端设备和全景成像装置
JP6206542B2 (ja) 画像処理装置、画像処理方法及びプログラム
CN106791390B (zh) 广角自拍实时预览方法及用户终端
JP2020053774A (ja) 撮像装置および画像記録方法
TWI520604B (zh) 攝像裝置及其影像預覽系統及影像預覽方法
JP2007336411A (ja) 撮像装置、オートブラケティング撮影方法、およびプログラム
US20160292842A1 (en) Method and Apparatus for Enhanced Digital Imaging
WO2021258249A1 (zh) 图像获取方法、电子设备和可移动设备
JP2009089220A (ja) 撮像装置
WO2018196854A1 (zh) 一种拍照方法、拍照装置及移动终端
CN113302908B (zh) 控制方法、手持云台、***及计算机可读存储介质
US8971636B2 (en) Image creating device, image creating method and recording medium
JP2011239267A (ja) 撮像装置及び画像処理装置
US9600735B2 (en) Image processing device, image processing method, program recording medium
JPWO2019065820A1 (ja) 撮影装置とその制御方法および制御プログラム
JP2009253925A (ja) 撮像装置及び撮像方法と、撮影制御プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20942130

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20942130

Country of ref document: EP

Kind code of ref document: A1