CN116309081B - Video panorama stitching method and system based on spherical camera linkage - Google Patents
Video panorama stitching method and system based on spherical camera linkage Download PDFInfo
- Publication number
- CN116309081B CN116309081B CN202310540831.7A CN202310540831A CN116309081B CN 116309081 B CN116309081 B CN 116309081B CN 202310540831 A CN202310540831 A CN 202310540831A CN 116309081 B CN116309081 B CN 116309081B
- Authority
- CN
- China
- Prior art keywords
- video
- individual
- individuals
- group
- image
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000256626 Pterygota <winged insects> Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- 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
- G06T2207/10016—Video; Image sequence
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention provides a video panorama stitching method and a system based on spherical camera linkage, wherein the method comprises the following steps: acquiring a target video, wherein the target video is a video section shot by a plurality of different spherical cameras; extracting images of first time nodes in each section of video section, performing two-dimensional expansion, and forming a first image group by the expanded images of the video section images of the plurality of first time nodes; marking all targets in the first image group, wherein the targets are the same points of images in the plane image, and the same targets are classified into the same group; dividing the first image group into a plurality of individuals, determining whether each individual has a target point, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual; splicing individual groups formed by individuals with different targets, and splicing a plurality of individual groups to form a second image group; and determining a spliced result video in the target video based on the superposition position of the second image group and the first image group.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a video panorama stitching method and system based on spherical camera linkage.
Background
With the rapid development of fields such as virtual reality, live-action roaming, game development and the like, the demand for high-quality panoramic images is also increasing. Traditional panoramic image stitching methods often require shooting different angles of the same scene multiple times, and then performing image processing and stitching operations by using a computer. However, the method has the problems of inaccurate image registration, unsatisfactory splicing effect and the like.
In order to solve these problems, a panoramic photographing technique based on a spherical camera has appeared in recent years. The spherical camera can shoot panoramic images in a field of view, so that the problems of multiple shooting and image registration are avoided. Meanwhile, the spherical camera can adjust the position and the angle through the linkage controller, so that the splicing effect of the panoramic image is more accurate and natural.
However, the current panoramic stitching technology of the spherical cameras has some problems, such as inaccurate linkage control between the spherical cameras, insufficient stitching effect, and large load on a computer. Therefore, there is a need for a more accurate and efficient method and system for stitching video panoramas based on spherical camera linkage to address these issues.
Disclosure of Invention
The embodiment of the invention provides a video panorama stitching method and a system based on spherical camera linkage, which aim to solve or partially solve the problems in the background technology.
In order to solve the technical problems, the invention is realized as follows:
in a first aspect, the present invention provides a video panorama stitching method based on spherical camera linkage, the method comprising the steps of: acquiring a target video, wherein the target video is a plurality of sections of video sections shot by different spherical cameras, and the start and stop time of each section of video section is the same; extracting images of first time nodes in each section of video section, performing two-dimensional expansion, and forming a first image group by the expanded images of the video section images of the plurality of first time nodes; marking all targets in the first image group, wherein the targets are the same points of images in the plane image, and the same targets are classified into the same group; dividing the first image group into a plurality of individuals, determining whether each individual has a target point, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual; splicing individual groups formed by individuals with different targets, and splicing a plurality of individual groups to form a second image group; and determining a spliced result video in the target video based on the superposition position of the second image group and the first image group.
With reference to the first aspect, in some embodiments, labeling all targets in the first image set includes: segmenting the first image group and generating a plurality of image units; and acquiring pixel arrangement in each image unit, determining the image units with the same arrangement sequence as targets through an approximation principle, and marking.
With reference to the first aspect, in some embodiments, the first image group is segmented into a plurality of individuals, and it is determined whether each individual has a target, and the individuals having the same set of targets are overlapped, and each overlapped individual forms an individual group, and further including: if the individual does not have the target point, splicing the individuals to form an individual unit; judging whether the individual units have targets, and if the individual units have targets, overlapping the individual units with the individuals with the same targets.
With reference to the first aspect, in some embodiments, stitching individual groups of individuals having different targets, the stitching of the plurality of individual groups and forming a second image group includes:
acquiring pixel arrangements of individuals in each individual group, wherein each pixel has a corresponding score, and determining a score of the pixel arrangement of the individuals in each individual according to each score;
determining a score for the individual group according to the scores of the pixel arrangements of all the individuals in the individual group, wherein the score of the individual group is an average score of all the individuals composing the individual group;
determining a top-level pixel arrangement for the individual group based on the average score;
and splicing the individual groups according to the top-layer pixel arrangement and forming a second image group.
With reference to the first aspect, in some embodiments, stitching the individual groups according to the top-level pixel arrangement and forming the second image group includes: acquiring the arrangement of edge pixels in the top-layer pixel arrangement; overlapping the same edge pixels; and outputting a second image group according to the overlapping result.
With reference to the first aspect, in some embodiments, determining a stitched resultant video in the target video based on the coincident positions of the second image group and the first image group includes: determining the positions of all the points in the second image group in a plurality of video sections; cutting and splicing a plurality of video sections with point positions in the second image group; and determining a result video according to the splicing position of the video sections.
In a second aspect, the present application further provides a video panorama stitching system based on spherical camera linkage, the system comprising: the first acquisition module is used for acquiring target videos, wherein the target videos are video sections shot by multiple sections of different spherical cameras, and the start and stop time of each section of video section is the same; the first extraction module is used for extracting images of first time nodes in each section of video section and performing two-dimensional expansion, and the images after the expansion of the video section images of the plurality of first time nodes form a first image group; the first marking module is used for marking all target points in the first image group, wherein the target points are the same points of images in the plane image, and the same target points are classified into the same group; the first segmentation module is used for segmenting the first image group into a plurality of individuals, determining whether each individual has a target point or not, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual; the first splicing module is used for splicing individual groups formed by individuals with different targets, and a plurality of individual groups are spliced to form a second image group; the second splicing module is used for determining spliced result videos in the target video based on the superposition positions of the second image group and the first image group.
With reference to the second aspect, in some embodiments, the first marking module includes: the second segmentation module is used for segmenting the first image group and generating a plurality of image units; the second acquisition module is used for acquiring pixel arrangement in each image unit, determining the image units with the same arrangement sequence as targets through an approximation principle, and marking.
With reference to the second aspect, in some embodiments, the first dividing module further includes: the third splicing module is used for splicing the individuals to form individual units if the individuals do not have the target points; the judging module is used for judging whether the individual units have targets or not, and if the individual units have the targets, the individual units are overlapped with the individuals with the same targets.
In a third aspect, the present application further proposes another video panorama stitching system based on spherical camera linkage, the system comprising: the processor is configured to implement the method according to the first aspect of the present invention when executing the program stored on the memory; and the communication interface, the memory and the communication bus, wherein the memory is used for completing the communication among the communication interfaces through the communication bus and storing the computer program.
A fourth aspect of the embodiments of the present invention proposes a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as proposed in the first aspect of the embodiments of the present invention.
The embodiment of the invention has the following advantages: firstly, acquiring a target video, extracting images of first time nodes in each video section, performing two-dimensional expansion, and forming a first image group by the expanded images of the video section images of a plurality of first time nodes. Then, marking all target points in the first image group, wherein the target points are the same points of the images in the plane image, and the same target points are classified into the same group; then, dividing the first image group into a plurality of individuals, determining whether each individual has a target point, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual; splicing individual groups formed by individuals with different targets, and splicing a plurality of individual groups to form a second image group; and finally, determining the spliced result video in the target video based on the superposition position of the second image group and the first image group. According to the invention, the standard for splicing is carried out according to the stop-motion images shot by different cameras at the same time, and the video is restored according to the spliced images, so that the video is spliced more accurately, and meanwhile, the load of a computer is reduced, and the splicing process is more efficient.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for stitching a video panorama based on a spherical camera linkage in an embodiment of the present invention;
fig. 2 is a schematic block diagram of a video panorama stitching system based on spherical camera linkage according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that some, but not all embodiments of the invention are described. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the related art, for example, linkage control between spherical cameras is not accurate enough, splicing effect is not natural enough, and load on a computer is large. Therefore, there is a need for a more accurate and efficient method and system for stitching video panoramas based on spherical camera linkage to address these issues. Based on the above, the application provides a brand-new video panorama stitching method based on spherical camera linkage.
In the following, a brand-new video panorama stitching method based on spherical camera linkage is described, as shown in fig. 1, and fig. 1 shows a flow diagram of a video panorama stitching method based on spherical camera linkage.
The application provides a video panorama stitching method based on spherical camera linkage, which comprises steps S101-S106.
S101: and acquiring a target video, wherein the target video is a plurality of video sections shot by different spherical cameras, and the start and stop time of each video section is the same.
It can be understood that in the present embodiment, the images captured by the plurality of spherical cameras differ in the screen of the plurality of images due to the different setting positions of the spherical cameras. The main purpose of the present application is to stitch the pictures taken by a plurality of spherical cameras into one complete and continuous picture.
S102: and extracting images of the first time nodes in each video section, performing two-dimensional expansion, and forming a first image group by the images of the expanded video section images of the plurality of first time nodes.
Based on the characteristics of the spherical camera, the image shot by the spherical camera is in a spherical shape in a three-dimensional space, and operations such as cutting or splicing are directly performed on the spherical image, so that the loads on an operating system and computer hardware are large, and therefore, in the application, a mode of two-dimensionally expanding the spherical video segments is adopted.
Specifically, in order to ensure the synchronization of still pictures of a plurality of video sections, pictures extracted from the plurality of video sections at the same time are also simultaneously in the initial video, thereby avoiding the problems such as tearing of the pictures. Meanwhile, the pictures intercepted in the video sections are formed into a first image group, the first image group is a fragmented image picture, and a plurality of repeated target point images exist in the first image group.
S103: and marking all targets in the first image group, wherein the targets are the same points of the images in the plane image, and the same targets are classified into the same group.
In this application, the target point is used for the function of locating picture information at the time of stitching. It can be understood that the target point may be a point location with obvious characteristics in the picture, and may be a bright spot in the picture, such as a light source. When the light sources are arranged in the pictures shot by the spherical cameras, the targets can be classified into the same type, and the positions of the targets can be overlapped in the video splicing process.
In some embodiments, step S103 comprises the steps of:
s103-1: the first image group is segmented and a plurality of image units are generated.
It can be appreciated that in the process of acquiring the target point, a segmentation method may be adopted to divide the first image group equally into a plurality of images with equal sizes. By the method, which segmented images are identical, namely identical targets, can be judged more quickly.
S103-2: and acquiring pixel arrangement in each image unit, determining the image units with the same arrangement sequence as targets through an approximation principle, and marking.
In this embodiment, the segmented image has a pixel arrangement mode to a certain extent, so in this application, whether the pixel arrangement order is the same is adopted to determine whether the image is the same target point. In other embodiments, the target point may be selected by another method, such as AI intelligent recognition, etc., which is not limited herein.
S104: dividing the first image group into a plurality of individuals, determining whether each individual has a target point, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual.
It can be appreciated that, to facilitate video stitching, the first image set is segmented into a plurality of individuals to achieve integration of the frames. It should be noted that, in the process of dividing the first image group into individuals in this step, the dividing size is far greater than the dividing and identifying the size of the target point in step S103-1, so that the load on the computer or the apparatus is small in the process after the dividing.
For the same reason, in order to simplify the stitching process, in the present application, individuals with the same target points on multiple individuals are classified into the same class, that is, multiple individuals are different pictures of the same scene captured by different cameras. In the process of splicing, the two units are required to be overlapped, so that a plurality of units are overlapped into a unit group, and the unit groups are the same target point, namely the same scene.
In the process of segmentation, targets can be segmented at the same time, so that some images are lost, and the accuracy of splicing is reduced. Thus, in some embodiments, step S104 further comprises the steps of:
s104-1: if the individual does not have the target point, a plurality of individuals are spliced to form an individual unit.
It will be appreciated that by assembling individual units from multiple individuals without targets, the cut targets form a complete target after assembly.
S104-2: judging whether the individual units have targets, and if the individual units have targets, overlapping the individual units with the individuals with the same targets.
In this way, the loss of the image frame due to the cut target point can be avoided.
S105: and splicing individual groups consisting of individuals with different targets, and splicing a plurality of individual groups to form a second image group.
It can be understood that, in the individual groups obtained after the foregoing steps, one individual group is an individual group formed by scene images at the same position, and the second image group is formed after the scene groups at different positions are spliced, so that repeated images in the second image group have been proposed, and no repeated image images exist in the spliced second image group.
Specifically, as an embodiment, the process of splicing individual groups may be processed by the following steps.
First, obtaining pixel arrangements of individuals in each individual group, wherein each pixel has a corresponding score, and determining a score of the pixel arrangement of the individuals in each individual according to each score; determining a score for the individual group according to the scores of the pixel arrangements of all the individuals in the individual group, wherein the score of the individual group is an average score of all the individuals composing the individual group; determining a top-level pixel arrangement for the individual group based on the average score;
and splicing the individual groups according to the top-layer pixel arrangement and forming a second image group. It will be appreciated that, as an embodiment, the arrangement of edge pixels in the top-level pixel arrangement may be obtained by obtaining the arrangement of edge pixels in the top-level pixel arrangement; overlapping the same edge pixels; and outputting a second image group according to the overlapping result. In other embodiments, the second image group may be stitched in other ways.
By splicing the individual groups in the mode, the splicing result can be accurate, and meanwhile, the problem that pixels suddenly change due to unreasonable picture fluctuation, such as winged insects and the like, which suddenly appear in a picture, is effectively avoided due to the fact that the average score is adopted for selection.
S106: and determining a spliced result video in the target video based on the superposition position of the second image group and the first image group.
In this embodiment, by fitting the overlapping positions of the first image group and the second image group, a single picture after the target video is spliced can be determined. And processing each frame of images in the target video in the mode to obtain the spliced result video. Specifically, as an implementation manner, the positions of the points in the second image group in the plurality of video sections can be determined; cutting and splicing a plurality of video sections with point positions in the second image group; and determining a result video according to the splicing position of the video sections.
The embodiment of the invention provides a video panorama stitching method based on spherical camera linkage, which comprises the steps of firstly, obtaining a target video, extracting images of first time nodes in each section of video section, performing two-dimensional expansion, and forming a first image group by the images of the expanded video section images of a plurality of first time nodes. Then, marking all target points in the first image group, wherein the target points are the same points of the images in the plane image, and the same target points are classified into the same group; then, dividing the first image group into a plurality of individuals, determining whether each individual has a target point, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual; splicing individual groups formed by individuals with different targets, and splicing a plurality of individual groups to form a second image group; and finally, determining the spliced result video in the target video based on the superposition position of the second image group and the first image group. According to the invention, the standard for splicing is carried out according to the stop-motion images shot by different cameras at the same time, and the video is restored according to the spliced images, so that the video is spliced more accurately, and meanwhile, the load of a computer is reduced, and the splicing process is more efficient.
Referring to fig. 2, the present application further provides a video panorama stitching system 200 based on spherical camera linkage, the system comprising:
the first obtaining module 201 is configured to obtain a target video, where the target video is a video section captured by multiple different spherical cameras, and start and stop times of each video section are the same.
The first extraction module 202, where the first extraction module 202 is configured to extract images of first time nodes in each video segment and perform two-dimensional expansion, and the images of the video segment images of the plurality of first time nodes after expansion form a first image group.
The first marking module 203, where the first marking module 203 is configured to mark all targets in the first image group, where the targets are identical points of images in the planar image, and the identical targets are grouped into the same group.
The first segmentation module 204 is configured to segment the first image group into a plurality of individuals, determine whether each individual has a target, and overlap the individuals having the same set of targets, where each overlapped individual forms an individual group.
The first stitching module 205, the first stitching module 205 is configured to stitch individual groups formed by individuals with different targets, and stitch a plurality of individual groups to form a second image group.
The second stitching module 206, the second stitching module 206 is configured to determine a stitched result video in the target video based on the overlapping positions of the second image group and the first image group.
In some embodiments, the first marking module comprises:
the second segmentation module is used for segmenting the first image group and generating a plurality of image units; the second acquisition module is used for acquiring pixel arrangement in each image unit, determining the image units with the same arrangement sequence as targets through an approximation principle, and marking.
In some embodiments, the first splitting module further comprises:
the third splicing module is used for splicing the individuals to form individual units if the individuals do not have the target points; the judging module is used for judging whether the individual units have targets or not, and if the individual units have the targets, the individual units are overlapped with the individuals with the same targets.
Based on the same inventive concept, the embodiment of the application also provides another video panorama stitching system based on spherical camera linkage, the system comprises:
at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a spherical camera linkage-based video panorama stitching method according to an embodiment of the present application.
In addition, in order to achieve the above objective, an embodiment of the present application further provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements a video panorama stitching method based on linkage of a spherical camera according to the embodiment of the present application.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. "and/or" means either or both of which may be selected. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or terminal device comprising the element.
The above describes in detail a video panorama stitching method and system based on spherical camera linkage, and specific examples are applied to illustrate the principles and embodiments of the present invention, and the above description of the examples is only used to help understand the method and core idea of the present invention; meanwhile, as those skilled in the art will vary in the specific embodiments and application scope according to the idea of the present invention, the present disclosure should not be construed as limiting the present invention in summary.
Claims (10)
1. A video panorama stitching method based on spherical camera linkage, the method comprising the steps of:
acquiring a target video, wherein the target video is a plurality of sections of video sections shot by different spherical cameras, and the start and stop time of each section of video section is the same;
extracting images of first time nodes in each section of video nodes, and performing two-dimensional expansion, wherein the images of the video nodes after the expansion of the images of the first time nodes form a first image group;
marking all targets in the first image group, wherein the targets are the same points of images in a plane image, and the same targets are classified into the same group;
dividing the first image group into a plurality of individuals, determining whether each individual has a target point, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual;
splicing individual groups formed by individuals with different targets, and splicing a plurality of the individual groups to form a second image group;
and determining a spliced result video in the target video based on the superposition position of the second image group and the first image group.
2. The spherical camera linkage based video panorama stitching method according to claim 1, wherein the marking all targets in the first image set comprises:
dividing the first image group and generating a plurality of image units;
and acquiring pixel arrangement in each image unit, determining the image units with the same arrangement sequence as targets by using the pixel arrangement through an approximation principle, and marking.
3. The method of stitching together a spherical camera linkage-based video panorama of claim 2, wherein the stitching together the first image set into a plurality of individuals and determining whether each of the individuals has a target point and overlapping the individuals having the same set of target points, each of the overlapping individuals forming an individual set, further comprising:
if the individual does not have the target point, splicing a plurality of the individuals to form an individual unit;
judging whether the individual unit has the target point or not, and if the individual unit has the target point, overlapping the individual unit with the individual unit having the same target point.
4. A method of stitching together a spherical camera linkage based video panorama as claimed in claim 3, wherein said stitching together individual groups of individuals having different targets, a plurality of said individual groups being stitched together and forming a second image group, comprises:
obtaining pixel arrangements of the individuals in each individual group, wherein each pixel has a corresponding score, and determining a score of the pixel arrangement of each individual in the individuals according to each score;
determining a score for the group of individuals based on the scores of the pixel arrangements of all individuals in the group of individuals, the score for the group of individuals being an average score for all of the individuals comprising the group of individuals;
determining a top-level pixel arrangement for the individual group based on the average score;
and splicing the individual groups according to the top-layer pixel arrangement and forming a second image group.
5. The method of stitching a spherical camera linkage based video panorama according to claim 4, wherein the stitching the individual groups according to the top-level pixel arrangement and forming a second image group comprises:
acquiring the arrangement of edge pixels in the top-layer pixel arrangement;
overlapping the same edge pixels;
and outputting the second image group according to the overlapping result.
6. The spherical camera linkage based video panorama stitching method according to claim 5, wherein the determining the stitched resultant video in the target video based on the coincident positions of the second image set and the first image set comprises:
determining the positions of all the points in the second image group in a plurality of video sections;
clipping and splicing a plurality of video sections with the point positions in the second image group;
and determining the result video according to the splicing position of the video section.
7. A spherical camera linkage-based video panorama stitching system, the system comprising:
the first acquisition module is used for acquiring target videos, wherein the target videos are video sections shot by multiple sections of different spherical cameras, and the start and stop time of each section of video section is the same;
the first extraction module is used for extracting images of first time nodes in each section of video section and performing two-dimensional expansion, and the images after the expansion of the video section images of the plurality of first time nodes form a first image group;
the first marking module is used for marking all targets in the first image group, the targets are the same points of images in the plane image, and the same targets are classified into the same group;
the first segmentation module is used for segmenting the first image group into a plurality of individuals, determining whether each individual has a target point, overlapping the individuals with the same group of target points, and forming an individual group by each overlapped individual;
the first splicing module is used for splicing individual groups formed by individuals with different targets, and a plurality of the individual groups are spliced to form a second image group;
and the second splicing module is used for determining a spliced result video in the target video based on the superposition position of the second image group and the first image group.
8. The spherical camera linkage based video panorama stitching system according to claim 7, wherein the first marking module comprises:
the second segmentation module is used for segmenting the first image group and generating a plurality of image units;
the second acquisition module is used for acquiring pixel arrangement in each image unit, determining the image units with the same arrangement sequence as targets and marking the targets through an approximation principle.
9. The spherical camera linkage based video panorama stitching system according to claim 8, wherein the first segmentation module further comprises:
the third splicing module is used for splicing a plurality of individuals and forming an individual unit if the individuals do not have the target points;
and the judging module is used for judging whether the individual unit has the target point, and if the individual unit has the target point, the individual unit is overlapped with the individual unit with the same target point.
10. A spherical camera linkage-based video panorama stitching system, the system comprising:
a processor for implementing the method according to any one of claims 1 to 6 when executing a program stored on a memory; and
the device comprises a communication interface, a memory and a communication bus, wherein the communication interface, the memory and the memory are communicated with each other through the communication bus, and the memory is used for storing computer programs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310540831.7A CN116309081B (en) | 2023-05-15 | 2023-05-15 | Video panorama stitching method and system based on spherical camera linkage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310540831.7A CN116309081B (en) | 2023-05-15 | 2023-05-15 | Video panorama stitching method and system based on spherical camera linkage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116309081A CN116309081A (en) | 2023-06-23 |
| CN116309081B true CN116309081B (en) | 2023-08-04 |
Family
ID=86794383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310540831.7A Active CN116309081B (en) | 2023-05-15 | 2023-05-15 | Video panorama stitching method and system based on spherical camera linkage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116309081B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104639911A (en) * | 2015-02-09 | 2015-05-20 | 浙江宇视科技有限公司 | Panoramic video stitching method and device |
| CN105205853A (en) * | 2014-06-20 | 2015-12-30 | 西安英诺视通信息技术有限公司 | 3D image splicing synthesis method for panoramic view management |
| WO2018121401A1 (en) * | 2016-12-28 | 2018-07-05 | 深圳市掌网科技股份有限公司 | Splicing method for panoramic video images, and panoramic camera |
| CN112017222A (en) * | 2020-09-08 | 2020-12-01 | 北京正安维视科技股份有限公司 | Video panorama stitching and three-dimensional fusion method and device |
| CN112218099A (en) * | 2020-08-28 | 2021-01-12 | 新奥特（北京）视频技术有限公司 | Panoramic video generation method, panoramic video playing method, panoramic video generation device, and panoramic video generation system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2402867B1 (en) * | 2010-07-02 | 2018-08-22 | Accenture Global Services Limited | A computer-implemented method, a computer program product and a computer system for image processing |
| CN105760919B (en) * | 2016-02-06 | 2018-08-07 | 深圳市天朗时代科技有限公司 | A kind of coding of dot matrix Quick Response Code and recognition methods |
| WO2019061295A1 (en) * | 2017-09-29 | 2019-04-04 | 深圳市大疆创新科技有限公司 | Video processing method and device, unmanned aerial vehicle and system |
-
2023
- 2023-05-15 CN CN202310540831.7A patent/CN116309081B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205853A (en) * | 2014-06-20 | 2015-12-30 | 西安英诺视通信息技术有限公司 | 3D image splicing synthesis method for panoramic view management |
| CN104639911A (en) * | 2015-02-09 | 2015-05-20 | 浙江宇视科技有限公司 | Panoramic video stitching method and device |
| WO2018121401A1 (en) * | 2016-12-28 | 2018-07-05 | 深圳市掌网科技股份有限公司 | Splicing method for panoramic video images, and panoramic camera |
| CN112218099A (en) * | 2020-08-28 | 2021-01-12 | 新奥特（北京）视频技术有限公司 | Panoramic video generation method, panoramic video playing method, panoramic video generation device, and panoramic video generation system |
| CN112017222A (en) * | 2020-09-08 | 2020-12-01 | 北京正安维视科技股份有限公司 | Video panorama stitching and three-dimensional fusion method and device |
Non-Patent Citations (1)
| Title |
|---|
| 全网络数字视频监控系统在机房工程中的应用;胡桂霞;;智能建筑(第10期);62-66 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116309081A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10540806B2 (en) | Systems and methods for depth-assisted perspective distortion correction | |
| KR101956151B1 (en) | A foreground image generation method and apparatus used in a user terminal | |
| JP5313127B2 (en) | Video composition method, video composition system | |
| WO2011145322A1 (en) | Panoramic expansion image display device and method of displaying panoramic expansion image | |
| US10785469B2 (en) | Generation apparatus and method for generating a virtual viewpoint image | |
| CN110430359A (en) | Shoot householder method, device, computer equipment and storage medium | |
| US9426514B1 (en) | Graphic reference matrix for virtual insertions | |
| US10380719B2 (en) | Device and method for generating panorama image | |
| US20120229678A1 (en) | Image reproducing control apparatus | |
| KR102082277B1 (en) | Method for generating panoramic image and apparatus thereof | |
| KR20030002919A (en) | realtime image implanting system for a live broadcast | |
| CN116309081B (en) | Video panorama stitching method and system based on spherical camera linkage | |
| KR102138333B1 (en) | Apparatus and method for generating panorama image | |
| CN116233615B (en) | Scene-based linkage type camera control method and device | |
| CN116109484A (en) | Image splicing method, device and equipment for retaining foreground information and storage medium | |
| CN114419121B (en) | BIM texture generation method based on image | |
| CN113947671A (en) | Panoramic 360-degree image segmentation and synthesis method, system and medium | |
| KR20160101762A (en) | The method of auto stitching and panoramic image genertation using color histogram | |
| CN113490009A (en) | Content information embedding method, device, server and storage medium | |
| JP2021149972A (en) | Method for identifying landmark in panoramic image, device, and storage medium | |
| CN106202130A (en) | A kind of method and device of shot segmentation | |
| CN112634460B (en) | Outdoor panorama generation method and device based on Haar-like features | |
| CN109040619A (en) | A kind of video fusion method and apparatus | |
| JP2010272093A (en) | Image connecting method, device and program | |
| CN117809224A (en) | Panoramic monitoring image processing method and processing system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |