CN114128247A - Image processing method, device and storage medium - Google Patents

Image processing method, device and storage medium Download PDF

Info

Publication number
CN114128247A
CN114128247A CN202080025830.3A CN202080025830A CN114128247A CN 114128247 A CN114128247 A CN 114128247A CN 202080025830 A CN202080025830 A CN 202080025830A CN 114128247 A CN114128247 A CN 114128247A
Authority
CN
China
Prior art keywords
image
frame
size
photographic subject
determining
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202080025830.3A
Other languages
Chinese (zh)
Inventor
吴哲
周游
蔡剑钊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SZ DJI Technology Co Ltd
Original Assignee
SZ DJI Technology Co Ltd
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 SZ DJI Technology Co Ltd filed Critical SZ DJI Technology Co Ltd
Publication of CN114128247A publication Critical patent/CN114128247A/en
Pending legal-status Critical Current

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

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Studio Devices (AREA)

Abstract

An image processing method, apparatus and storage medium. The embodiment of the application can ensure that the shot object in the target video (70) generated based on the adjusted multi-frame image has the stability-enhancing effect in the picture by acquiring the multi-frame image (40), determining the shot object in each frame of the multi-frame image (40), adjusting the size of the shot object in each frame of the image according to the reference size of the shot object, and/or adjusting the position of the shot object in each frame of the image according to the reference position of the shot object, when the reference size and/or the reference position are fixed, the size and/or the position of the shot object in each frame of the adjusted multi-frame image can be kept stable, when the reference size and/or the reference position are smoothly changed or gradually changed, the picture quality of the target video is improved.

Description

Image processing method, device and storage medium Technical Field
The embodiment of the application relates to the technical field of image processing, in particular to an image processing method, an image processing device and a storage medium.
Background
In the prior art, time-lapse photography is also called time-lapse photography and time-lapse video recording, and is a shooting technology for compressing time, specifically, a group of photos or videos can be shot through a shooting device, and the processes of minutes, hours or even days and years are compressed in a short time through a photo series connection or video frame extraction technology in the later period and are played in a video mode. So that the process of slowly changing objects or scenes can be compressed to a shorter time and present a singularly wonderful scene that is not normally perceived by the naked eye.
However, in the process of performing wide-range moving time-lapse photographing with respect to a photographic subject, the photographing device needs to move for a long distance, and the distance or position of the photographing device with respect to the photographic subject may vary, thereby causing a large shake of the photographic subject in the time-lapse video to affect the picture quality of the time-lapse video.
Disclosure of Invention
The embodiment of the application provides an image processing method, an image processing device and a storage medium, which are used for improving the picture quality of a target video.
A first aspect of embodiments of the present application provides an image processing method, including:
acquiring a multi-frame image;
determining a shooting object in each frame of image in the multiple frames of images;
adjusting the size of the shot object in each frame of image according to the reference size of the shot object; and/or adjusting the position of the shooting object in each frame of image according to the reference position of the shooting object so as to generate a target video based on the adjusted multi-frame image.
A second aspect of the embodiments of the present application provides an image processing apparatus, including:
a memory and a processor;
the memory is used for storing program codes;
the processor, invoking the program code, when executed, is configured to:
acquiring a multi-frame image;
determining a shooting object in each frame of image in the multiple frames of images;
adjusting the size of the shot object in each frame of image according to the reference size of the shot object; and/or adjusting the position of the shooting object in each frame of image according to the reference position of the shooting object so as to generate a target video based on the adjusted multi-frame image.
A third aspect of embodiments of the present application is to provide a computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the method of the first aspect.
The image processing method, the image processing device and the storage medium provided by the embodiment can adjust the size of the photographic object in each frame of image in accordance with the reference size of the photographic object by acquiring the multi-frame image and determining the photographic object in each frame of image in the multi-frame image, and/or adjust the position of the photographic object in each frame of image in accordance with the reference position of the photographic object, when the reference size and/or the reference position are fixed, the size and/or the position of the photographic object in each frame of image in the adjusted multi-frame image can be kept stable, and when the reference size and/or the reference position change smoothly or gradually, the size and/or the position of the photographic object in each frame of image in the adjusted multi-frame image can be changed stably, so that the photographic object in the target video generated based on the adjusted multi-frame image has the stability increasing effect in the picture, the picture quality of the target video is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application;
fig. 2 is a flowchart of an image processing method according to an embodiment of the present application;
fig. 3 is a schematic diagram of a joint point of a photographic subject according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a multi-frame image provided in an embodiment of the present application;
FIG. 5 is a flowchart of another image processing method provided in the embodiments of the present application;
FIG. 6 is a flowchart of another image processing method provided in the embodiments of the present application;
FIG. 7 is a schematic diagram of an adjusted image according to an embodiment of the present application;
FIG. 8 is a schematic illustration of a reference position provided by an embodiment of the present application;
FIG. 9 is a schematic diagram of an adjusted image according to an embodiment of the present application;
fig. 10 is a block diagram of an image processing apparatus according to an embodiment of the present application.
Reference numerals:
10: an unmanned aerial vehicle; 11: a target object; 12: a ground control end;
101: a photographing device; 102: a support device; 103: a communication device;
0: a joint point; 1: a joint point; 2: a joint point;
3: a joint point; 4: a joint point; 5: a joint point;
6: a joint point; 7: a joint point; 8: a joint point;
9: a joint point; 10: a joint point; 11: a joint point;
12: a joint point; 13: a joint point; 14: a joint point;
15: a joint point; 16: a joint point; 17: a joint point;
40: a plurality of frames of images; 41: an image; 42: an image; 43: an image;
4 n: an image; 70: a target video; 71: an image;
72: an image; 7 n: an image; 80: an arc;
100: an image processing device; 101: a memory; 102: a processor;
103: a communication interface; 73: an image; 74: an image;
75: an image; 76: an image; 77: and (4) an image.
Detailed Description
The technical solutions in the embodiments of the present application will be described below clearly with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When a component is referred to as being "connected" to another component, it can be directly connected to the other component or intervening components may also be present.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
The embodiment of the present application provides an image processing method, which may be applied to various scenes, as shown in fig. 1, a camera 101 is mounted on an unmanned aerial vehicle 10, specifically, the camera 101 is mounted on a body of the unmanned aerial vehicle 10 through a support device 102, the support device 102 may be a pan-tilt, and the camera 101 is configured to capture a target object 11, where this embodiment does not limit the target object 11, and may be a person or another movable object, for example. Further, the unmanned aerial vehicle 10 may send the multi-frame image or the video shot by the shooting device 101 to the ground control end 12 through the communication device 103, and the ground control end 12 may specifically be a remote controller (for example, a remote controller with a screen) of the unmanned aerial vehicle 10, a mobile phone, a tablet computer, a notebook computer, and other devices. Further, the ground control end 12 may process multiple frames of images or videos by using the image processing method described in this embodiment. Optionally, the image processing method described in this embodiment may also be executed by the unmanned aerial vehicle 10, and the unmanned aerial vehicle 10 sends the processed target video to the ground control end 12.
In another possible scenario, a user may shoot a target object 11 through a handheld shooting device, where the handheld shooting device may specifically be a handheld cradle head, and the handheld cradle head may carry the shooting device thereon, and further, the handheld cradle head may process a plurality of frames of images or videos collected by the shooting device by using the image processing method described in this embodiment.
In some other scenarios, the unmanned aerial vehicle or the handheld cradle head as described above may further send the multiple frames of images or videos collected by the shooting device to another device, for example, a remote server, and the remote server processes the multiple frames of images or videos by using the image processing method described in this embodiment.
The image processing method according to the present embodiment can be described in detail below with reference to the application scenario shown in fig. 1.
Fig. 2 is a flowchart of an image processing method according to an embodiment of the present application. As shown in fig. 2, the method in this embodiment may include:
s201, acquiring a multi-frame image.
In a possible manner, as shown in fig. 1, the ground control end 12 may receive multiple frames of images sent by the unmanned aerial vehicle 10, where the multiple frames of images may be continuously captured by the capturing device or discontinuously captured by the capturing device, for example, the capturing time interval of two adjacent frames of images in the multiple frames of images is a preset time interval.
In another possible manner, the acquiring the multi-frame image includes: acquiring a video shot by a shooting device; and extracting the multi-frame image from the video.
As shown in fig. 1, the shooting device 101 shoots a target object 11 to form a video, the unmanned aerial vehicle 10 sends the video to the ground control end 12, and after receiving the video, the ground control end 12 performs frame extraction processing on the video, and extracts a plurality of frame images from the video.
S202, determining a shooting object in each frame of image in the multi-frame images.
The ground control terminal 12 further determines the photographic subject in each frame of the multiple frames of images, and the photographic subject is specifically the target subject 11 as described above. The ground control end 12 may determine the shooting object in each frame of the multiple frames of images by using various methods. For example, the ground control end 12 may determine the photographic subject in each frame of image by using a neural network algorithm. When the photographic subject is a person, a local association field (PAFs) may also be used to determine the photographic subject in each frame of image.
Optionally, the determining the photographic subject in each frame of image in the multiple frames of images includes: and determining the joint point of the shooting object in each frame of image in the plurality of frames of images. For example, when the ground control terminal 12 determines a photographic subject in each frame image using PAFs, the joint point of the photographic subject in each frame image can be specifically determined. As shown in fig. 3, joint points of a person in a certain frame image, for example, joint points (0,1,2, … …, 17), can be determined by using PAFs.
S203, adjusting the size of the shot object in each frame of image according to the reference size of the shot object; and/or adjusting the position of the shooting object in each frame of image according to the reference position of the shooting object so as to generate a target video based on the adjusted multi-frame image.
It is understood that, as shown in fig. 1, during the shooting of the target object 11 by the shooting device 101, the position and/or distance of the drone 10 relative to the target object 11 is continuously changed, that is, the position and/or distance of the shooting device 101 relative to the target object 11 is continuously changed, so that the size and/or position of the target object 11 in each frame of image is also continuously changed. In order to keep the size and/or position of the target object 11 stable or stably varying in the multi-frame images as described above, the size of the photographic subject in each frame image may be adjusted according to the reference size of the photographic subject; and/or adjusting the position of the shooting object in each frame of image according to the reference position of the shooting object. The reference size and/or the reference position may be fixed or may be variable.
Optionally, the adjusting the size of the photographic object in each frame of image includes: and adjusting the size of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
Optionally, the adjusting the position of the photographic object in each frame of image includes: and adjusting the position of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
When the reference size and/or the reference position are/is fixed, the size of the photographic subject adjusted according to the reference size in each frame image is similar to the reference size, for example, the difference between the size of the photographic subject adjusted in each frame image and the reference size is within a preset difference range, so that the size of the photographic subject in each frame image in the multiple frame images adjusted can be kept stable. Similarly, the position of the photographic subject adjusted according to the reference position in each frame of image is close to the reference position, for example, the difference between the position of the photographic subject adjusted in each frame of image and the reference position is within a preset difference range, so that the position of the photographic subject in each frame of image in the adjusted multi-frame image can be kept stable.
In some other embodiments, the reference size and/or the reference position may also be changed smoothly or gradually, so that the size of the subject adjusted according to the reference size in each frame of image changes smoothly or gradually, and the position of the subject adjusted according to the reference position in each frame of image changes smoothly or gradually.
Further, the target video may be generated based on the adjusted multi-frame images, so that the photographic subject in the target video has a stability-increasing effect in the picture, for example, the size and/or position of the photographic subject in the target video remains stable or changes stably. The target video may be specifically a delayed video or may not be a delayed video. For example, when the plurality of frames of images as described above are continuous, the target video is not a delayed video; when the multi-frame images as described above are discontinuous and the shooting time interval between two adjacent frames of the multi-frame images is large, the target video is a delayed video.
The embodiment obtains a plurality of frame images, determines a photographic object in each frame image in the plurality of frame images, adjusting the size of the photographic subject in each frame of image according to the reference size of the photographic subject, and/or adjusting the position of the photographic subject in each frame of image according to the reference position of the photographic subject, when the reference size and/or the reference position are fixed, the size and/or position of the photographic subject in each frame of the adjusted multi-frame images can be kept stable, and when the reference size and/or the reference position change smoothly or gradually, the size and/or position of the photographic subject in each frame of image in the adjusted multi-frame image can be stably changed, therefore, the shot object in the target video generated based on the adjusted multi-frame image has the stability increasing effect in the picture, and the picture quality of the target video is improved.
In the above embodiment, the ground control end 12 may determine the photographic subject in each frame of image by using PAFs, for example, may determine the joint point of the photographic subject in each frame of image. In the embodiment of the present application, the position of the photographic subject in each frame of image is determined according to the position of the joint point of the photographic subject in each frame of image.
As shown in fig. 3, the joint point (0,1,2, … …, 17) is a joint point of a person in a certain frame image, and the position of the person in the image can be determined according to the position of the joint point of the person in the frame image. The position of the joint point of the person in the frame image may specifically be a two-dimensional coordinate of the joint point of the person in the frame image, and the position of the person in the image may specifically be a two-dimensional coordinate of a center point of the person in the frame image, where the center point of the person is specifically a five-pointed star shown in fig. 3. The two-dimensional coordinates of the center point of the person in the frame image are recorded as centerkWherein k represents the sequence number of the frame image in the multi-frame image. centerkCan be calculated by the following formula (1):
center k＝∑w iJ i (1)
wherein i represents the identity of the joint point, JiRepresenting the two-dimensional coordinates of the joint point i in the k-th frame image, wiRepresenting the weight corresponding to the joint point i. Wherein, Σ wi1. That is, the two-dimensional coordinates of the center point of the person in the frame image can be calculated by performing weighted average of the two-dimensional coordinates of the joint points (0,1,2, … …, 17) in the frame image.
In some embodiments, some of the joint points (0,1,2,5,8,11) of the joint points (0,1,2, … …, 17) may be selected to calculate the two-dimensional coordinates of the person in the image. Specifically, the two-dimensional coordinates of the joint point (0,1,2,5,8,11) in the frame image are sequentially denoted as J0,J 1,J 2,J 5,J 8,J 11. The weights corresponding to the joint points (0,1,2,5,8,11) are sequentially denoted as w0,w 1,w 2,w 5,w 8,w 11. For example, w1＝0.25，w 2＝0.2，w 0＝0.15，w 5＝0.2，w 8＝0.1，w 11＝0.1。center kCan be calculated by the following formula (2):
center k＝0.25J 1+0.2J 2+0.15J 0+0.2J 5+0.1J 8+0.1J 11 (2)
it can be understood that the position of the photographic subject, for example, the person shown in fig. 3, in the k-th frame image can be calculated according to the above formula (1) or (2), and the position of the photographic subject in each frame image in the plurality of frame images can be calculated in the same way, and the specific calculation process is not described herein again.
In addition, it is understood that the selection of some joint points (0,1,2,5,8,11) of the joint points (0,1,2, … …, 17) to calculate the two-dimensional coordinates of the person in each image is only an illustrative example and is not limited in particular, for example, other joint points may be selected to calculate.
Optionally, the size of the photographic subject in each frame of image is determined according to the distance between the joint points of the photographic subject in each frame of image.
As shown in FIG. 3, the size of the subject, e.g., a person, in the k-th frame image is denoted as scalek，scale kCan be calculated by the following formula (3):
Figure PCTCN2020079754-APPB-000001
wherein D is1,0Represents the distance between the joint point 1 and the joint point 0 in the k-th frame image. D1,2、D 1,5、D 1,8、D 1,11Meaning of (A) and D1,0Are similar in meaning and will not be described in detail herein. When the photographic subject is far from the photographing device, the size of the photographic subject in the image becomes smaller, whereas when the photographic subject is near the photographing device, the size of the photographic subject in the image becomes larger.
It can be understood that the size of the photographic subject, for example, the person shown in fig. 3, in the k-th frame image can be calculated according to the above formula (3), and similarly, the size of the photographic subject in each frame image in the multiple frame images can be calculated, and the specific calculation process is not described herein again.
It is understood that, the selection of some joint points (0,1,2,5,8,11) of the joint points (0,1,2, … …, 17) to calculate the size of the person in each image is only an illustrative example and is not limited in particular, for example, other joint points may be selected to calculate.
The embodiment determines the position of the shooting object in each frame of image through the position of the joint point of the shooting object in each frame of image, and/or determines the size of the shooting object in each frame of image through the distance between the joint points of the shooting object in each frame of image, thereby improving the calculation accuracy of the position and/or size of the shooting object in each frame of image.
On the basis of the above-described embodiments, the reference dimensions and/or the reference positions can be determined in a number of ways, and several possible implementations are described below.
In a possible implementation manner, after the determining the photographic subject in each frame of the plurality of frames of images, the method further includes: determining a first target image in the multi-frame image; the reference size is a size of the photographic subject in the first target image; and/or the reference position is the position of the photographic subject in the first target image.
As shown in fig. 4, 40 represents the multi-frame image as described above, after the ground control terminal 12 determines the photographic subject in each frame of the multi-frame image 40, it may further determine a first target image in the multi-frame image 40, take the size of the photographic subject in the first target image as a reference size, and take the position of the photographic subject in the first target image as a reference position, that is, the first target image is a reference image in the multi-frame image 40, adjust the size of the photographic subject in each frame of the multi-frame image 40 with reference to the size of the photographic subject in the reference image, and/or adjust the position of the photographic subject in each frame of the multi-frame image 40 with reference to the position of the photographic subject in the reference image.
Optionally, the first target image is a starting image in the multi-frame images. Or, the first target image is an image selected by a user from the plurality of frame images.
In another possible implementation manner, after the determining the photographic subject in each frame of the plurality of frames of images, the method further includes: determining the reference size according to the size of the shooting object in each frame of image; and/or determining the reference position according to the position of the shooting object in each frame of image.
For example, after the ground control terminal 12 determines the photographic subject in each frame of image in the multiple frames of images 40, the reference size is determined according to the size of the photographic subject in each frame of image; and/or determining the reference position according to the position of the shooting object in each frame of image.
Specifically, the determining the reference size according to the size of the photographic subject in each frame of image includes the following steps as shown in fig. 5:
s501, determining the average size of the shot object according to the size of the shot object in each frame of image.
For example, the multi-frame image 40 includes the image 41, the image 42, … …, and the image 4n, and the size of the subject in each of the image 41, the image 42, … …, and the image 4n can be calculated according to the formula (3) described above, and further, the average size of the subject can be calculated according to the size of the subject in each of the image 41, the image 42, … …, and the image 4 n.
Optionally, the determining an average size of the photographic subject according to the size of the photographic subject in each frame of image includes: removing a second target image in the multiple frames of images according to the size of the shot object in each frame of image, wherein the size of the shot object in the second target image exceeds a preset size range; and determining the average size of the shot object according to the size of the shot object in the rest images except the second target image in the multi-frame images.
Since the size of the photographic subject in each frame of image may be constantly changing, that is, the size of the photographic subject in the partial image may be too large or too small, that is, beyond the preset size range, a second target image, which may be one or more second target images, in the multi-frame image 40 may be determined according to the size of the photographic subject in each frame of image. For example, if the size of the subject in the images 41 and 43 exceeds the preset size range, the images 41 and 43 can be used as the second target image. Further, the images 41 and 43 are removed from the multi-frame image 40 to obtain a residual image, and the average size of the photographic subject is determined according to the size of the photographic subject in each frame of image in the residual image. The preset size range may be determined according to a normal distribution of sizes of the photographic subject in each frame of image.
And S502, determining the reference size according to the average size of the shot object.
In one possible approach, the reference size is an average size of the photographic subject. That is, the average size of the photographic subject as described above is taken as the reference size.
In another possible mode, the determining the reference size according to the average size of the photographic subject includes: determining a fourth target image in the multi-frame images according to the average size of the shot object, wherein the difference between the size of the shot object in the fourth target image and the average size is within a first preset difference range; the reference size is a size of the photographic subject in the fourth target image.
For example, the fourth target image is determined in the multi-frame image 40 according to the average size of the photographic subject, so that the difference between the size of the photographic subject in the fourth target image and the average size is within a first preset difference range, that is, the size of the photographic subject in the fourth target image is similar to or the same as the average size. Further, the size of the photographic subject in the fourth target image is taken as a reference size.
Specifically, the determining the reference position according to the position of the photographic subject in each frame of image includes the following steps as shown in fig. 6:
s601, determining the average position of the shooting object according to the position of the shooting object in each frame of image.
For example, the multi-frame image 40 includes the image 41, the image 42, the image 43, … …, and the image 4n, and the position of the subject in each of the image 41, the image 42, the image 43, … …, and the image 4n can be calculated according to the above formula (1) or (2), and further, the average position of the subject can be calculated according to the position of the subject in each of the image 41, the image 42, the image 43, … …, and the image 4 n.
Optionally, the determining an average position of the photographic subject according to the position of the photographic subject in each frame of image includes: removing a third target image in the multiple frames of images according to the position of the shooting object in each frame of image, wherein the position of the shooting object in the third target image exceeds a preset position range; and determining the average position of the shooting object according to the position of the shooting object in the rest images except the third target image in the multi-frame images.
Since the position of the photographic subject in each frame of image may be constantly changing, that is, the position of the photographic subject in some of the images may be more concentrated and the position of the photographic subject in other ones of the images may be more dispersed, a third target image, which may be one or more third target images, in the multi-frame image 40 may be determined according to the position of the photographic subject in each frame of image. For example, if the position of the photographic subject in the images 41 and 42 is beyond the preset position range, the images 41 and 42 may be used as the third target image. Further, the images 41 and 42 are removed from the multi-frame image 40 to obtain a residual image, and the average position of the photographic subject is determined according to the position of the photographic subject in each frame of image in the residual image. The preset position range can be determined according to the normal distribution of the position of the shooting object in each frame of image.
And S602, determining the reference position according to the average position of the shooting object.
In one possible approach, the reference position is an average position of the photographic subject. That is, the average position of the photographic subject as described above is taken as the reference position.
In another possible mode, the determining the reference position according to the average position of the photographic subject includes: determining a fifth target image in the multi-frame images according to the average position of the shot object, wherein the difference between the position of the shot object in the fifth target image and the average position is within a second preset difference range; the reference position is a position of the photographic subject in the fifth target image.
For example, a fifth target image is determined in the multi-frame image 40 according to the average position of the photographic subject, so that the difference between the position of the photographic subject in the fifth target image and the average position is within a second preset difference range, that is, the position of the photographic subject in the fifth target image is close to or the same as the average position. Further, the position of the photographic subject in the fifth target image is taken as a reference position.
It will be appreciated that the methods of determining the reference dimension and/or the reference position are not limited to the methods described above, and that other methods may be used to determine the reference dimension and/or the reference position, and are not limited herein.
In the above embodiments, the reference dimension and/or the reference position may be fixed. For example, the reference size is scaleDatumThe reference position is noted as centerDatum. One way to adjust the size of the photographic subject in each frame of the image based on the reference size of the photographic subject and/or to adjust the position of the photographic subject in each frame of the image based on the reference position of the photographic subject is to process each pixel in each frame of the plurality of frames of the image, e.g., pOld position of pixelTwo-dimensional coordinates, p, representing the ith pixel in the kth frame of image 40PixelNew positionRepresents the two-dimensional coordinates of the i-th pixel in the k-th frame of the multi-frame image 40 in the adjusted image, centerkScale representing the position of the subject in the k-th frame imagekScale representing the size of the subject in the k-th frame imageDatum、center Datum、p New position of pixel、p Old position of pixel、center kAnd scalekThe relationship therebetween can be expressed as the following formula (4):
Figure PCTCN2020079754-APPB-000002
each pixel in the kth frame image is processed by adopting the formula (4), so that an adjusted image corresponding to the kth frame image can be obtained, and similarly, each frame of image in the multi-frame images 40 is processed, so that adjusted images corresponding to each frame of image can be obtained. For example, as shown in fig. 7, 71 indicates an image obtained by adjusting the image 41 using the formula (4), 72 indicates an image obtained by adjusting the image 42 using the formula (4), and so on, and 7n indicates an image obtained by adjusting the image 4n using the formula (4). Further, the adjusted images 71, 72, … …, and 7n constitute the target video 70 as described above, so that the size and/or position of the photographic subject in the target video can be kept stable, and the picture quality of the target video is improved.
In some embodiments, the reference size and/or the reference position may also be varied, and optionally, the reference size varies smoothly with the sequence corresponding to the multi-frame images, and/or the reference position varies smoothly with the sequence corresponding to the multi-frame images.
As shown in FIG. 7, when the image 41 is adjusted by the formula (4), the scale in the formula (4)Datum、 center DatumCan be respectively recorded as scaleReference 1、center Reference 1(ii) a When the image 42 is adjusted by the formula (4), the scale in the formula (4)Datum、center DatumCan be respectively recorded as scaleReference 2、center Reference 2(ii) a Analogizing in turn, when the image 4n is adjusted by the formula (4), the scale in the formula (4)Datum、center DatumCan be respectively recorded as scaleReference n、center Reference n. Wherein, scaleReference 1、scale Reference 2、……、scale Reference nSmoothly varying, e.g. scaleReference 1、scale Reference 2、……、scale Reference nThe material can be gradually enlarged in sequence, or gradually reduced in sequence, or gradually enlarged in sequence and then reduced in sequence, or gradually reduced in sequence and then enlarged in sequence. In the same way, centerReference 1、center Reference 2、……、center Reference nOr may vary smoothly, e.g. centerReference 1、center Reference 2、……、center Reference nThe trajectory of the points on the two-dimensional coordinates respectively identified in the same image may be a preset trajectory, and the preset trajectory may be a straight line from left to right, a straight line from right to left, or an arc, so that the movement trajectory of the photographic subject in the picture is the preset trajectory.
For example, the multi-frame image 40 shown in fig. 4 or fig. 7 includes 7 frames of images, that is, n is 7, scaleReference 1、scale Reference 2、……、scale Reference 7Gradually becoming larger and then becoming smaller, wherein, scaleReference 4And max. centerReference 1、center Reference 2、……、center Reference 7The locus of the points in the two-dimensional coordinates identified in each case in the same image is an arc 80 as shown in fig. 8, and the change in the images 71, 72, … …, 77 of the photographic subject is shown in fig. 9. Further, when the images 71, 72, … …, 77 are configured as the target video as described above, the size and/or position of the photographic subject in the target video can be stably changed, thereby improving the picture quality of the target video.
Alternatively, as shown in FIG. 4 orAs shown in fig. 7, the multi-frame image 40 represents an original image captured by the camera, and the position of the photographic subject in each frame image can be determined according to the above formula (1) or (2), and the size of the photographic subject in each frame image can be determined according to the above formula (3). E.g. center1(u 1,v 1)、center 2(u 2,v 2)、……、center n(u n,v n) Sequentially indicates the positions of the photographic subjects in the image 41, the image 42, … … and the image 4n, wherein the center1(u 1,v 1) Pixel coordinates, center, of the object in the image 412(u 2,v 2)、……、center n(u n,v n) Similarly, no further description is given. Scale1、scale 2、……、scale nThe sizes of the photographic subjects in the image 41, the image 42, … …, and the image 4n are indicated in this order. Further, it is also possible to pair the center in the u direction and the v direction of the pixel coordinate system1(u 1,v 1)、center 2(u 2,v 2)、……、center n(u n,v n) Gaussian smoothing is performed to obtain center after smoothing'1(u' 1,v' 1)、center' 2(u' 2,v' 2)、……、center' n(u' n,v' n). Similarly, scales can be also matched1、scale 2、……、scale nGaussian smoothing is carried out to obtain smoothed scale'1、scale' 2、……、scale' n. Further, center in the formula (4)kCan also be replaced by smoothed center'kScale in equation (4)kCan also be replaced by smoothed scale'kThat is, at the counter center1(u 1,v 1)、center 2(u 2,v 2)、……、center n(u n,v n)、scale 1、scale 2、……、scale nAfter Gaussian smoothing, according to scaleDatum、center DatumThe image 41, the image 42, the image … …, and the image 4n are adjusted in order. Thus, the picture quality of the target video can be further improved.
The embodiment of the application provides an image processing device. Fig. 10 is a block diagram of an image processing apparatus according to an embodiment of the present application, and as shown in fig. 10, an image processing apparatus 100 includes: a memory 101 and a processor 102; wherein the memory 101 is used for storing program codes; the processor 102 invokes the program code, which when executed, is configured to: acquiring a multi-frame image; determining a shooting object in each frame of image in the multiple frames of images; adjusting the size of the shot object in each frame of image according to the reference size of the shot object; and/or adjusting the position of the shooting object in each frame of image according to the reference position of the shooting object so as to generate a target video based on the adjusted multi-frame image.
In some embodiments, the image processing apparatus 100 may further include a communication interface 103, for example, the communication interface 103 may receive a plurality of frames of images captured by the capturing apparatus.
Optionally, after determining the photographic subject in each frame of image in the multiple frames of images, the processor is further configured to: determining a first target image in the multi-frame image; the reference size is a size of the photographic subject in the first target image; and/or the reference position is the position of the photographic subject in the first target image.
Optionally, the first target image is a starting image in the multi-frame images.
Optionally, the first target image is an image selected by a user from the plurality of frame images.
Optionally, after determining the photographic subject in each frame of image in the multiple frames of images, the processor is further configured to: determining the reference size according to the size of the shooting object in each frame of image; and/or determining the reference position according to the position of the shooting object in each frame of image.
Optionally, when the processor determines the reference size according to the size of the photographic subject in each frame of image, the processor is specifically configured to: determining the average size of the shot object according to the size of the shot object in each frame of image; and determining the reference size according to the average size of the shooting object.
Optionally, when the processor determines the average size of the photographic subject according to the size of the photographic subject in each frame of image, the processor is specifically configured to: removing a second target image in the multiple frames of images according to the size of the shot object in each frame of image, wherein the size of the shot object in the second target image exceeds a preset size range; and determining the average size of the shot object according to the size of the shot object in the rest images except the second target image in the multi-frame images.
Optionally, when the processor determines the reference position according to the position of the shooting object in each frame of image, the processor is specifically configured to: determining the average position of the shooting object according to the position of the shooting object in each frame of image; and determining the reference position according to the average position of the shooting object.
Optionally, when the processor determines the average position of the photographic subject according to the position of the photographic subject in each frame of image, the processor is specifically configured to: removing a third target image in the multiple frames of images according to the position of the shooting object in each frame of image, wherein the position of the shooting object in the third target image exceeds a preset position range; and determining the average position of the shooting object according to the position of the shooting object in the rest images except the third target image in the multi-frame images.
Optionally, the reference size is an average size of the photographic subject.
Optionally, the reference position is an average position of the photographic subject.
Optionally, when determining the reference size according to the average size of the photographic subject, the processor is specifically configured to: determining a fourth target image in the multi-frame images according to the average size of the shot object, wherein the difference between the size of the shot object in the fourth target image and the average size is within a first preset difference range; the reference size is a size of the photographic subject in the fourth target image.
Optionally, when the processor determines the reference position according to the average position of the photographic subject, the processor is specifically configured to: determining a fifth target image in the multi-frame images according to the average position of the shot object, wherein the difference between the position of the shot object in the fifth target image and the average position is within a second preset difference range; the reference position is a position of the photographic subject in the fifth target image.
Optionally, the reference size changes smoothly with the sequence corresponding to the multi-frame images.
Optionally, the reference position changes smoothly with the sequence corresponding to the multi-frame images.
Optionally, the motion trajectory of the shot object in the picture is a preset trajectory.
Optionally, when the processor determines the photographic object in each frame of image of the multiple frames of images, the processor is specifically configured to: and determining the joint point of the shooting object in each frame of image in the plurality of frames of images.
Optionally, the position of the photographic subject in each frame of image is determined according to the position of the joint point of the photographic subject in each frame of image.
Optionally, the size of the photographic subject in each frame of image is determined according to the distance between the joint points of the photographic subject in each frame of image.
Optionally, when the processor acquires a plurality of frames of images, the processor is specifically configured to: acquiring a video shot by a shooting device; and extracting the multi-frame image from the video.
Optionally, when the processor adjusts the size of the photographic object in each frame of image, the processor is specifically configured to: and adjusting the size of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
Optionally, when the processor adjusts the position of the photographic object in each frame of image, the processor is specifically configured to: and adjusting the position of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
The specific principle and implementation of the image processing apparatus provided in the embodiment of the present application are similar to those of the above embodiments, and are not described herein again.
Optionally, the ground control terminal 12, the drone 10, the handheld camera, or the remote server as described above may include the image processing device.
In addition, the present embodiment also provides a computer-readable storage medium on which a computer program is stored, the computer program being executed by a processor to implement the image processing method described in the above embodiment.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may also be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working process of the device described above, reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims (45)

  1. An image processing method, comprising:
    acquiring a multi-frame image;
    determining a shooting object in each frame of image in the multiple frames of images;
    adjusting the size of the shot object in each frame of image according to the reference size of the shot object; and/or adjusting the position of the shooting object in each frame of image according to the reference position of the shooting object so as to generate a target video based on the adjusted multi-frame image.
  2. The method according to claim 1, wherein after determining the photographic subject in each of the plurality of frames of images, the method further comprises:
    determining a first target image in the multi-frame image;
    the reference size is a size of the photographic subject in the first target image; and/or the reference position is the position of the photographic subject in the first target image.
  3. The method of claim 2, wherein the first target image is a starting image of the plurality of frame images.
  4. The method according to claim 2, wherein the first target image is an image selected by a user from the plurality of frame images.
  5. The method according to claim 1, wherein after determining the photographic subject in each of the plurality of frames of images, the method further comprises:
    determining the reference size according to the size of the shooting object in each frame of image; and/or
    And determining the reference position according to the position of the shooting object in each frame of image.
  6. The method according to claim 5, wherein the determining the reference size according to the size of the photographic subject in each frame image comprises:
    determining the average size of the shot object according to the size of the shot object in each frame of image;
    and determining the reference size according to the average size of the shooting object.
  7. The method according to claim 6, wherein the determining an average size of the photographic subject according to the size of the photographic subject in each frame of the image comprises:
    removing a second target image in the multiple frames of images according to the size of the shot object in each frame of image, wherein the size of the shot object in the second target image exceeds a preset size range;
    and determining the average size of the shot object according to the size of the shot object in the rest images except the second target image in the multi-frame images.
  8. The method according to any one of claims 5 to 7, wherein the determining the reference position according to the position of the photographic subject in each frame image comprises:
    determining the average position of the shooting object according to the position of the shooting object in each frame of image;
    and determining the reference position according to the average position of the shooting object.
  9. The method according to claim 8, wherein determining the average position of the photographic subject according to the position of the photographic subject in each frame of image comprises:
    removing a third target image in the multiple frames of images according to the position of the shooting object in each frame of image, wherein the position of the shooting object in the third target image exceeds a preset position range;
    and determining the average position of the shooting object according to the position of the shooting object in the rest images except the third target image in the multi-frame images.
  10. The method according to any one of claims 5 to 9, wherein the reference size is an average size of the photographic subject.
  11. The method according to any one of claims 5 to 9, wherein the reference position is an average position of the photographic subject.
  12. The method according to claim 6 or 7, wherein the determining the reference size according to the average size of the photographic subject comprises:
    determining a fourth target image in the multi-frame images according to the average size of the shot object, wherein the difference between the size of the shot object in the fourth target image and the average size is within a first preset difference range;
    the reference size is a size of the photographic subject in the fourth target image.
  13. The method according to claim 8 or 9, wherein the determining the reference position according to the average position of the photographic subject comprises:
    determining a fifth target image in the multi-frame images according to the average position of the shot object, wherein the difference between the position of the shot object in the fifth target image and the average position is within a second preset difference range;
    the reference position is a position of the photographic subject in the fifth target image.
  14. The method according to claim 1, wherein the reference size varies smoothly with the sequence corresponding to the plurality of frame images.
  15. The method according to claim 1 or 14, wherein the reference position changes smoothly with the sequence corresponding to the plurality of frame images.
  16. The method according to claim 15, wherein the motion track of the photographic subject in the picture is a preset track.
  17. The method according to any one of claims 1-16, wherein said determining the photographic subject in each of the plurality of frames of images comprises:
    and determining the joint point of the shooting object in each frame of image in the plurality of frames of images.
  18. The method according to claim 17, wherein the position of the photographic subject in each frame image is determined based on the position of the joint of the photographic subject in each frame image.
  19. The method of claim 17, wherein the size of the photographic subject in each frame of the image is determined according to a distance between joint points of the photographic subject in each frame of the image.
  20. The method of any one of claims 1-19, wherein said acquiring a plurality of frames of images comprises:
    acquiring a video shot by a shooting device;
    and extracting the multi-frame image from the video.
  21. The method of any one of claims 1-20, wherein the resizing the photographic subject in each frame of image comprises:
    and adjusting the size of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
  22. The method according to any one of claims 1-21, wherein said adjusting the position of said photographic subject in each frame of image comprises:
    and adjusting the position of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
  23. An image processing apparatus characterized by comprising:
    a memory and a processor;
    the memory is used for storing program codes;
    the processor, invoking the program code, when executed, is configured to:
    acquiring a multi-frame image;
    determining a shooting object in each frame of image in the multiple frames of images;
    adjusting the size of the shot object in each frame of image according to the reference size of the shot object; and/or adjusting the position of the shooting object in each frame of image according to the reference position of the shooting object so as to generate a target video based on the adjusted multi-frame image.
  24. The image processing apparatus of claim 23, wherein after the processor determines the photographic subject in each frame of the plurality of frames of images, the processor is further configured to:
    determining a first target image in the multi-frame image;
    the reference size is a size of the photographic subject in the first target image; and/or the reference position is the position of the photographic subject in the first target image.
  25. The apparatus according to claim 24, wherein the first target image is a starting image of the plurality of frame images.
  26. The apparatus according to claim 24, wherein the first target image is an image selected by a user from the plurality of frame images.
  27. The image processing apparatus of claim 23, wherein after the processor determines the photographic subject in each frame of the plurality of frames of images, the processor is further configured to:
    determining the reference size according to the size of the shooting object in each frame of image; and/or
    And determining the reference position according to the position of the shooting object in each frame of image.
  28. The image processing apparatus according to claim 27, wherein the processor is configured to, when determining the reference size according to a size of the photographic subject in each frame of the image, specifically:
    determining the average size of the shot object according to the size of the shot object in each frame of image;
    and determining the reference size according to the average size of the shooting object.
  29. The image processing apparatus of claim 28, wherein the processor, when determining the average size of the photographic subject according to the size of the photographic subject in each frame of the image, is specifically configured to:
    removing a second target image in the multiple frames of images according to the size of the shot object in each frame of image, wherein the size of the shot object in the second target image exceeds a preset size range;
    and determining the average size of the shot object according to the size of the shot object in the rest images except the second target image in the multi-frame images.
  30. The image processing apparatus according to any one of claims 27 to 29, wherein the processor is configured to, when determining the reference position according to the position of the photographic subject in each frame of image, specifically:
    determining the average position of the shooting object according to the position of the shooting object in each frame of image;
    and determining the reference position according to the average position of the shooting object.
  31. The image processing apparatus according to claim 30, wherein the processor, when determining the average position of the photographic subject according to the position of the photographic subject in each frame of the image, is specifically configured to:
    removing a third target image in the multiple frames of images according to the position of the shooting object in each frame of image, wherein the position of the shooting object in the third target image exceeds a preset position range;
    and determining the average position of the shooting object according to the position of the shooting object in the rest images except the third target image in the multi-frame images.
  32. The image processing apparatus according to any one of claims 27 to 31, wherein the reference size is an average size of the photographic subject.
  33. The image processing apparatus according to any one of claims 27 to 31, wherein the reference position is an average position of the photographic subject.
  34. The image processing apparatus according to claim 28 or 29, wherein the processor is configured to, when determining the reference size from the average size of the subject, in particular:
    determining a fourth target image in the multi-frame images according to the average size of the shot object, wherein the difference between the size of the shot object in the fourth target image and the average size is within a first preset difference range;
    the reference size is a size of the photographic subject in the fourth target image.
  35. The image processing apparatus according to claim 30 or 31, wherein the processor is configured to, when determining the reference position based on the average position of the subject, specifically:
    determining a fifth target image in the multi-frame images according to the average position of the shot object, wherein the difference between the position of the shot object in the fifth target image and the average position is within a second preset difference range;
    the reference position is a position of the photographic subject in the fifth target image.
  36. The apparatus according to claim 23, wherein the reference size varies smoothly with the order in which the plurality of frame images correspond.
  37. The apparatus according to claim 23 or 36, wherein the reference position changes smoothly with the order of the plurality of frame images.
  38. The image processing apparatus according to claim 37, wherein a motion trajectory of the photographic subject in the screen is a preset trajectory.
  39. The image processing apparatus according to any one of claims 23 to 38, wherein the processor is configured to, when determining the photographic subject in each of the plurality of frames of images, in particular:
    and determining the joint point of the shooting object in each frame of image in the plurality of frames of images.
  40. The apparatus according to claim 39, wherein a position of the photographic subject in the each frame image is determined based on a position of a joint of the photographic subject in the each frame image.
  41. The apparatus according to claim 39, wherein a size of the photographic subject in each of the frames of images is determined according to a distance between joint points of the photographic subject in each of the frames of images.
  42. The image processing apparatus according to any of claims 23 to 41, wherein the processor is specifically configured to, when acquiring a plurality of frames of images:
    acquiring a video shot by a shooting device;
    and extracting the multi-frame image from the video.
  43. The image processing apparatus according to any of claims 23 to 42, wherein the processor is configured to, when adjusting the size of the photographic subject in each frame of image, in particular:
    and adjusting the size of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
  44. The image processing apparatus according to any of claims 23 to 43, wherein the processor is configured to, when adjusting the position of the photographic subject in each frame of image:
    and adjusting the position of the shooting object in each frame of image by at least one of cutting, rotating and scaling each frame of image.
  45. A computer-readable storage medium, having stored thereon a computer program for execution by a processor to perform the method of any one of claims 1-22.
CN202080025830.3A 2020-03-17 2020-03-17 Image processing method, device and storage medium Pending CN114128247A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/079754 WO2021184207A1 (en) 2020-03-17 2020-03-17 Image processing method and device, and storage medium

Publications (1)

Publication Number Publication Date
CN114128247A true CN114128247A (en) 2022-03-01

Family

ID=77767942

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080025830.3A Pending CN114128247A (en) 2020-03-17 2020-03-17 Image processing method, device and storage medium

Country Status (2)

Country Link
CN (1) CN114128247A (en)
WO (1) WO2021184207A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170180807A1 (en) * 2015-12-18 2017-06-22 Le Holdings (Beijing) Co., Ltd. Method and electronic device for amplifying video image
CN108476289A (en) * 2017-07-31 2018-08-31 深圳市大疆创新科技有限公司 A kind of method for processing video frequency, equipment, aircraft and system
CN109190520A (en) * 2018-08-16 2019-01-11 广州视源电子科技股份有限公司 Super-resolution face image reconstruction method and device
CN110262737A (en) * 2019-06-25 2019-09-20 维沃移动通信有限公司 A kind of processing method and terminal of video data

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007079598A (en) * 2006-11-02 2007-03-29 Mitsubishi Electric Corp Portable terminal equipment with camera
CN107197162B (en) * 2017-07-07 2020-11-13 盯盯拍（深圳）技术股份有限公司 Shooting method, shooting device, video storage equipment and shooting terminal
CN110149476A (en) * 2018-06-21 2019-08-20 深圳市浩瀚卓越科技有限公司 A kind of time-lapse photography method, apparatus, system and terminal device
EP3817370A1 (en) * 2018-06-29 2021-05-05 SZ DJI Technology Co., Ltd. Time-lapse photography control method and control device, imaging system, and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170180807A1 (en) * 2015-12-18 2017-06-22 Le Holdings (Beijing) Co., Ltd. Method and electronic device for amplifying video image
CN108476289A (en) * 2017-07-31 2018-08-31 深圳市大疆创新科技有限公司 A kind of method for processing video frequency, equipment, aircraft and system
CN109190520A (en) * 2018-08-16 2019-01-11 广州视源电子科技股份有限公司 Super-resolution face image reconstruction method and device
CN110262737A (en) * 2019-06-25 2019-09-20 维沃移动通信有限公司 A kind of processing method and terminal of video data

Also Published As

Publication number Publication date
WO2021184207A1 (en) 2021-09-23

Similar Documents

Publication Publication Date Title
US20200228730A1 (en) Automatic composition of composite images or videos from frames captured with moving camera
CN104205804B (en) Image processing apparatus, filming apparatus and image processing method
CN109788190B (en) Image processing method and device, mobile terminal and storage medium
CN109474780B (en) Method and device for image processing
CN107770452B (en) Photographing method, terminal and related medium product
JP6907274B2 (en) Imaging device and imaging method
US20210051273A1 (en) Photographing control method, device, apparatus and storage medium
WO2021168804A1 (en) Image processing method, image processing apparatus and image processing system
CN108200337A (en) It takes pictures method, apparatus, terminal and the storage medium of processing
CN116310105B (en) Object three-dimensional reconstruction method, device, equipment and storage medium based on multiple views
CN113411498A (en) Image shooting method, mobile terminal and storage medium
CN113283319A (en) Method and device for evaluating face ambiguity, medium and electronic equipment
CN111712857A (en) Image processing method, device, holder and storage medium
CN103945116A (en) Apparatus and method for processing image in mobile terminal having camera
CN108683847B (en) Photographing method, device, terminal and storage medium
WO2016029380A1 (en) Image processing method, computer storage medium, device, and terminal
CN114128247A (en) Image processing method, device and storage medium
US20220114740A1 (en) Camera motion information based three-dimensional (3d) reconstruction
JP2017021430A (en) Panoramic video data processing device, processing method, and program
KR102452581B1 (en) Method and Device for video stitching
WO2021024860A1 (en) Information processing device, information processing method, and program
CN111656763B (en) Image acquisition control method, image acquisition control device and movable platform
CN112154652A (en) Control method and control device of handheld cloud deck, handheld cloud deck and storage medium
CN112561787A (en) Image processing method, image processing device, electronic equipment and storage medium
CN113807124B (en) Image processing method, device, storage medium and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination