CN104537607A - Automatic efficient photo collage method based on binary tree and layer sequencing - Google Patents
Automatic efficient photo collage method based on binary tree and layer sequencing Download PDFInfo
- Publication number
- CN104537607A CN104537607A CN201410813937.0A CN201410813937A CN104537607A CN 104537607 A CN104537607 A CN 104537607A CN 201410813937 A CN201410813937 A CN 201410813937A CN 104537607 A CN104537607 A CN 104537607A
- Authority
- CN
- China
- Prior art keywords
- node
- parent
- width
- height
- father
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
Abstract
The invention discloses an automatic efficient photo collage method based on a binary tree and layer sequencing. The method includes the following steps of firstly, rapidly cutting canvas on the basis of a binary tree cutting algorithm; secondly, inputting a photo, completing the mapping between the photo and tree nodes, and traversing all inner nodes of the binary tree in a layer mode from leaf nodes to root nodes from bottom to top till the width to height ratio of each inner node is determined; thirdly, sequencing the nodes of each layer according to the calculation results of the width to height ratios of the nodes; fourthly, calculating the sizes and placement positions, represented by the nodes, of the canvas from top to bottom. The second step and the third step are alternately conducted till all the nodes are calculated, wherein the ratios of the inner nodes are calculated layer by layer in the second step, and the calculation results of each layer are sequenced in the third step. The method is suitable for a computer and an intelligent mobile platform and can be used for photo collage; meanwhile, different collage effects can be produced for the same photo set, and the different requirements are met to the maximum extent.
Description
Technical field
Picture Processing Technique of the present invention, particularly relates to a kind of automatical and efficient photo collage effect method.
Background technology
In recent years, along with constantly popularizing of the digital product such as smart mobile phone, high definition camera, photo has become one of people's main carriers recording life.This record intuitively, had both been applicable to recalling, and had also been applicable to sharing.Meanwhile, various photo sharing website also emerges in an endless stream, and makes people can share photos at any time.But, a large amount of photos not only make management become difficulty, also make to share become inconvenience.Photo collage effect, as a kind of important photo disposal means, is intended to be pieced together by multiple pictures in a painting canvas, can well solves the inconvenience that a large amount of photo brings.But, manually piece together not only consuming time, and usually need certain professional skill, piece result together also not fully up to expectations.Just because of this, automatic photograph pieces the concern that technology is more and more subject to people together.Automatically technology of piecing together is faster in processing speed, and does not need professional skill.Someone proposes the algorithm solving problems, but has certain weak point.
Such as, the photo collage effect algorithm at present under someone the two and three dimensions space that proposes.Document [1] is that a kind of 2-dimentional photo that Microsoft proposes pieces method AutoCollage together: first screen input photo according to photo size, ignore less photo, then the area-of-interest (ROI) of photo is often opened in Detection and Extraction, piece together and smoothing processing the region of extracting, whole process is more consuming time.Document [2] adopts to be split painting canvas based on the method for Voronoi figure, then calculate and determine the importance of often opening photo, again according to the difference adjustment photo size of importance, also want comparison film to carry out cutting to adapt to the shape of subregion, processing procedure is equally very consuming time simultaneously.Document [3], by extracting the object in photo, is pieced into together the photo that a width has hazy and illusionary color.Document [4] and [5] all adopt the algorithm based on binary tree to split painting canvas, difference is that the relation between photo is taken into account when piecing together by the former, need repeatedly to adjust, consume when can bring thus, the latter does not consider the mutual relationship between photo, in speed quickly, but piece result together and there is the situation easily occurring that crack etc. is undesirable.In field of three dimension, the Connection Constrained 3DCollage of document [6] and document [7] [photo collage effect is three-dimensional model by Structured Mechanical Collage, can be applied to the fields such as development of games.
Forefathers propose some and piece method together, but are all difficult in processing speed and piece together between quality and obtain good balance.Wherein based on the method for region of interesting extraction, because needs carry out area-of-interest identification, processing procedure is very consuming time, and can cause information dropout; The content-based method processing speed retained completely is very fast, but it is not ideal enough to piece result together.
List of references:
[1]Rother C,Bordeaux L,Hamadi Y,et al.Autocollage.ACM Transactions on Graphics(TOG),2006,25(3)：847-852.
[2]Yu Z,Lu L,Guo Y,Fan RF,Liu MM,Wang WP.Content-aware photo collage using circlepacking.IEEE Transactions on Visualization and Computer Graphics,2014,20(2):182-195.
[3]Goferman S,Tal A,Zelnik-Manor L.Puzzle-like collage.Computer Graphics Forum,2010,29(2):459-468.
[4]Atkins C B.Blocked recursive image composition.In Proceedings ofthe 16th ACMinternational conference on Multimedia,2008,pp.821-824.
[5]Wu Z,Aizawa K.PicWall:Photo collage on-the-fly.In Proceedings of Signal andInformation ProcessingAssociationAnnual Summit and Conference(APSIPA),2013,pp.1-10.
[6]Huang Z,Wang J,Lau Rynson WH,Fu HB.Connection constrained 3D collage.InProceedings ofComputer Graphics International,2014.
[7]Huang Z,Wang J,Fu HB,Lau Rynson WH.Structured mechanical collage.IEEETransactions on Visualization and Computer Graphics,2014,20(7):1076-1082.
Summary of the invention
In order to overcome above-mentioned prior art, the present invention proposes a kind of automatical and efficient photo collage effect method based on binary tree and layer sorting, a kind of automatic photograph taking into account speed and effect can be realized and piece algorithm together, algorithm process efficiency is high and not high to hardware requirement, can realize on different platforms, comprise smart mobile phone and PC.
The present invention proposes a kind of automatical and efficient photo collage effect method based on binary tree and layer sorting, the method comprises the following steps:
Step one, based on binary tree partitioning algorithm, Fast Segmentation is carried out to painting canvas, segmentation result canvas area is produced a complete binary tree, the leaf node quantity wherein set is equal with number of pictures, the internal node of tree preserves the attribute of painting canvas segmentation type, segmentation type attribute comprises laterally or longitudinally two kinds, and produces at random;
Step 2, input photo, complete the mapping between photo and tree node, by leaf node to root node, each internal node of level binary tree traversal from bottom to top, until determine the wide high proportion of each internal node;
Step 3, to node successively, the result of calculation according to its wide high proportion sorts;
The size of step 4, from top to bottom painting canvas representated by computing node and putting position;
Above-mentioned flow process, step 2 and step 3 hocket, and step 2 successively calculates the ratio of internal node, and the result of calculation of the every one deck of step 3 sorts, until complete the calculating of all nodes.
The calculating of the wide high proportion of each internal node in described step 2, specifically comprises following process:
When calculating the wide high proportion of father node by child node, if father node segmentation type is " V ", then child nodes height in left and right is consistent; If father node segmentation type is " H ", then child nodes width in left and right is consistent, and computing formula is as follows:
Father node segmentation type is ' V ': Ar
parent=Ar
left+ Ar
right
Father node segmentation type is ' H ': 1/Ar
parent=1/Ar
left+ 1/Ar
right
Wherein, the wide high proportion in region representated by Ar representation node, Ar
parentrepresent the wide high proportion in region representated by father node, Ar
leftand Ar
rightrepresent the wide high proportion in region representated by the child nodes of father node left and right respectively;
Its wide high proportion leaf node is to the wide high proportion of photo corresponding to it, the wide high proportion of internal node calculates according to its left and right child node and obtains.
The result of calculation of the wide high proportion of described each internal node need meet pre-conditioned, if result of calculation exceeds preset ratio scope, then adjusts the segmentation type of father node, re-starts calculating.
The size of the calculating painting canvas of described step 4, its computing formula is as follows:
Father node segmentation type is ' V ':
node.Height＝node.Parent.Height
node.Width＝node.Height×node.Ar
Father node segmentation type is ' H ':
node.Width＝node.Parent.Width
node.Height＝node.Width/node.Ar
In formula, node.Height and node.Width represents width and the height in the region representated by present node respectively, node.Parent.Height and node.Parent.Width represents height and the width of present node father node respectively, and node.Ar represents the wide high proportion in region representated by present node.
The putting position of the calculating painting canvas of described step 4, its computing formula is as follows:
Node is left child nodes
node.Pox＝node.Parent.Pox
node.Poy＝node.Parent.Poy
Node is right child nodes
Father node segmentation type is ' V '
node.Pox＝node.Parent.Left.Pox+node.Parent.Left.Width
node.Poy＝node.Parent.Poy
Father node segmentation type is ' H '
node.Pox＝node.Parent.Pox
node.Poy＝node.Parent.Poy+node.Parent.Left.Height
In formula, node.Pox and node.Poy represents the coordinate in the upper left corner in the region representated by present node, node.Parent.Pox and node.Parent.Poy represents horizontal ordinate and the ordinate in the upper left corner, region representated by present node father node, the horizontal ordinate in the upper left corner in region representated by the left child nodes that node.Parent.Left.Pox represents the father node of present node, the width in region representated by the left child nodes that node.Parent.Left.Width and node.Parent.Left.Height represents present node father node and height.
In described step 3, after sequence completes, the corresponding relation of adjustment sequence layer and its child node layer, makes it again meet mapping relations.
Compared with prior art, the present invention may be used for the fields such as photograph album is pieced together, picture retrieval result shows, video frequency abstract is pieced together, by arranging different parameters, can produce different result.Simultaneously for same photograph collection, can produce and differently piece result together, meet the different needs to greatest extent.
Accompanying drawing explanation
What Fig. 1 was number of pictures when being 20 pieces result schematic diagram together;
What Fig. 2 was number of pictures when being 100 pieces result schematic diagram together;
Fig. 3 is preferred forms process flow diagram of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail, but practical range of the present invention is not limited thereto.
Best implementing procedure mainly contains following step: produce painting canvas segmentation binary tree fast, successively calculate the ratio of internal node from bottom to top, successively sort according to checkout result, the size and location of computing node from top to bottom.Process flow diagram is as shown in Figure 3:
Step 1, fast generation painting canvas segmentation binary tree.
In order to carry out Fast Segmentation to painting canvas, this step needs generation complete binary tree, the leaf node number of tree is equal with number of pictures to be pieced together, the internal node of tree stores segmentation type (H or V), H represents horizontal partition painting canvas, V represents longitudinally splits painting canvas, and segmentation type is determined at random by program.After binary tree produces, the photo of input is sorted according to photo wide high proportion.After having sorted, photo is mapped on the leaf node of binary tree, a unique corresponding leaf node of photo.
Step 2, successively calculate the wide high proportion of internal node from bottom to top.
After completing photo mapping, need the node of level binary tree traversal from bottom to top, determine the wide high proportion of each internal node.When calculating the wide high proportion of father node by child node, if father node segmentation type is " V ", then child nodes height in left and right is consistent; If father node segmentation type is " H ", then child nodes width in left and right is consistent.Computing formula can be derived thus:
Father node segmentation type is ' V ': Ar
parent=Ar
left+ Ar
right(1)
Father node segmentation type is ' H ': 1/Ar
parent=1/Ar
left+ 1/Ar
right(2)
Wherein, the wide high proportion in region representated by Ar representation node, Ar
parentrepresent the wide high proportion in region representated by father node, Ar
leftand Ar
rightrepresent the wide high proportion in region representated by the child nodes of father node left and right respectively.Its wide high proportion leaf node is to the wide high proportion of photo corresponding to it, the wide high proportion of internal node calculates according to its left and right child node and obtains.
Meanwhile, in computation process, also to guarantee that result of calculation meets pre-conditioned, if result of calculation exceeds preset ratio scope, then adjust the segmentation type of father node, re-start calculating.After completing the calculating of each node layer, enter step 3.
Step 3, successively to sort according to checkout result
Mainly (being defaulted as sort descending) is sorted to the result of calculation of every one deck in this step.If not this process, then piecing together in result, occur between adjacent photo that the probability of greatly different in size this situation is very large, the aesthetic property of result is pieced in impact together.Successively sort and can avoid the appearance of this situation, ensure to piece in result size between adjacent photo together close, make to piece result together more attractive in appearance.
After sequence completes, need to adjust the corresponding relation between father and son's node, because the process of sequence can break original node corresponding relation, certainly just need the corresponding relation of adjustment sequence layer and its child node layer, other layers do not need adjustment.
It is to be noted that step 2 and step 3 hocket, step 2 successively calculates the ratio of internal node, and the result of calculation of the every one deck of step 3 sorts, until complete the calculating of all nodes.
The size and location of step 4, from top to bottom computing node
This step will be carried out after first three has walked.First according to presetting painting canvas height H or width W, the wide high proportion calculating in conjunction with root vertex obtains the size of painting canvas.
The formula calculating canvas size is as follows:
Father node segmentation type is ' V ': (3)
node.Height＝node.Parent.Height
node.Width＝node.Height×node.Ar
Father node segmentation type is ' H ': (4)
node.Width＝node.Parent.Width
node.Height＝node.Width/node.Ar
In formula, node.Height and node.Width represents width and the height in the region representated by present node respectively, node.Parent.Height and node.Parent.Width represents height and the width of present node father node respectively, and node.Ar represents the wide high proportion in region representated by present node.
The formula calculating position is as follows:
Node is left child nodes (5)
node.Pox＝node.Parent.Pox
node.Poy＝node.Parent.Poy
Node is right child nodes
Father node segmentation type is ' V ' (6)
node.Pox＝node.Parent.Left.Pox+node.Parent.Left.Width
node.Poy＝node.Parent.Poy
Father node segmentation type is ' H ' (7)
node.Pox＝node.Parent.Pox
node.Poy＝node.Parent.Poy+node.Parent.Left.Height
In formula, node.Pox and node.Poy represents the coordinate in the upper left corner in the region representated by present node, node.Parent.Pox and node.Parent.Poy represents horizontal ordinate and the ordinate in the upper left corner, region representated by present node father node, the horizontal ordinate in the upper left corner in region representated by the left child nodes that node.Parent.Left.Pox represents the father node of present node, the width in region representated by the left child nodes that node.Parent.Left.Width and node.Parent.Left.Height represents present node father node and height.
For each node, first calculate the size of its painting canvas according to computing formula, then calculate its position.Calculate from left to right for every one deck.
Less demanding to running environment of the present invention, may operate on common smart mobile phone and PC.
Smart mobile phone: more than 1G internal memory configure
Computer: more than 2G internal memory configure
Although invention has been described for composition graphs above; but the present invention is not limited to above-mentioned embodiment; above-mentioned embodiment is only schematic; instead of it is restrictive; those of ordinary skill in the art is under enlightenment of the present invention; when not departing from present inventive concept, can also make a lot of distortion, these all belong within protection of the present invention.
Claims (5)
1., based on an automatical and efficient photo collage effect method for binary tree and layer sorting, it is characterized in that, the method comprises the following steps:
Step one, based on binary tree partitioning algorithm, Fast Segmentation is carried out to painting canvas, segmentation result canvas area is produced a complete binary tree, the leaf node quantity wherein set is equal with number of pictures, the internal node of tree preserves the attribute of painting canvas segmentation type, segmentation type attribute comprises laterally or longitudinally two kinds, and produces at random;
Step 2, input photo, complete the mapping between photo and tree node, by leaf node to root node, each internal node of level binary tree traversal from bottom to top, until determine the wide high proportion of each internal node;
Step 3, to node successively, the result of calculation according to its wide high proportion sorts;
The size of step 4, from top to bottom painting canvas representated by computing node and putting position;
Above-mentioned flow process, step 2 and step 3 hocket, and step 2 successively calculates the ratio of internal node, and the result of calculation of the every one deck of step 3 sorts, until complete the calculating of all nodes.
2., as claimed in claim 1 based on the automatical and efficient photo collage effect method of binary tree and layer sorting, it is characterized in that, the calculating of the wide high proportion of each internal node in described step 2, specifically comprises following process:
When calculating the wide high proportion of father node by child node, if father node segmentation type is " V ", then child nodes height in left and right is consistent; If father node segmentation type is " H ", then child nodes width in left and right is consistent, and computing formula is as follows:
Father node segmentation type is ' V ': Ar
parent=Ar
left+ Ar
right
Father node segmentation type is ' H ': 1/Ar
parent=1/Ar
left+ 1/Ar
right
Wherein, the wide high proportion in region representated by Ar representation node, Ar
parentrepresent the wide high proportion in region representated by father node, Ar
leftand Ar
rightrepresent the wide high proportion in region representated by the child nodes of father node left and right respectively;
Its wide high proportion leaf node is to the wide high proportion of photo corresponding to it, the wide high proportion of internal node calculates according to its left and right child node and obtains.
3. as claimed in claim 1 or 2 based on the automatical and efficient photo collage effect method of binary tree and layer sorting, it is characterized in that, the result of calculation of the wide high proportion of described each internal node need meet pre-conditioned, if result of calculation exceeds preset ratio scope, then adjust the segmentation type of father node, re-start calculating.
4., as claimed in claim 1 based on the automatical and efficient photo collage effect method of binary tree and layer sorting, it is characterized in that, the size of the calculating painting canvas of described step 4, its computing formula is as follows:
Father node segmentation type is ' V ':
node.Height＝node.Parent.Height
node.Width＝node.Height×node.Ar
Father node segmentation type is ' H ':
node.Width＝node.Parent.Width
node.Height＝node.Width/node.Ar
In formula, node.Height and node.Width represents width and the height in the region representated by present node respectively, node.Parent.Height and node.Parent.Width represents height and the width of present node father node respectively, and node.Ar represents the wide high proportion in region representated by present node.
The putting position of the calculating painting canvas of described step 4, its computing formula is as follows:
Node is left child nodes
node.Pox＝node.Parent.Pox
node.Poy＝node.Parent.Poy
Node is right child nodes
Father node segmentation type is ' V '
node.Pox＝node.Parent.Left.Pox+node.Parent.Left.Width
node.Poy＝node.Parent.Poy
Father node segmentation type is ' H '
node.Pox＝node.Parent.Pox
node.Poy＝node.Parent.Poy+node.Parent.Left.Height
In formula, node.Pox and node.Poy represents the coordinate in the upper left corner in the region representated by present node, node.Parent.Pox and node.Parent.Poy represents horizontal ordinate and the ordinate in the upper left corner, region representated by present node father node, the horizontal ordinate in the upper left corner in region representated by the left child nodes that node.Parent.Left.Pox represents the father node of present node, the width in region representated by the left child nodes that node.Parent.Left.Width and node.Parent.Left.Height represents present node father node and height.
5., as claimed in claim 1 based on the automatical and efficient photo collage effect method of binary tree and layer sorting, it is characterized in that, in described step 3, after sequence completes, the corresponding relation of adjustment sequence layer and its child node layer, makes it again meet mapping relations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410813937.0A CN104537607B (en) | 2014-12-23 | 2014-12-23 | Automatical and efficient photo collage effect method based on binary tree and layer sorting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410813937.0A CN104537607B (en) | 2014-12-23 | 2014-12-23 | Automatical and efficient photo collage effect method based on binary tree and layer sorting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104537607A true CN104537607A (en) | 2015-04-22 |
| CN104537607B CN104537607B (en) | 2017-08-01 |
Family
ID=52853126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410813937.0A Active CN104537607B (en) | 2014-12-23 | 2014-12-23 | Automatical and efficient photo collage effect method based on binary tree and layer sorting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104537607B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106445931A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Database node association relationship display method and apparatus |
| GB2552969A (en) * | 2016-08-16 | 2018-02-21 | Fujitsu Ltd | Image processing system |
| CN110868319A (en) * | 2019-11-08 | 2020-03-06 | 北京浪潮数据技术有限公司 | Network topology drawing method, device, equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060150092A1 (en) * | 2003-09-30 | 2006-07-06 | Atkins C B | Arranging graphic objects on pages |
| US7555730B2 (en) * | 2005-05-12 | 2009-06-30 | Hewlett-Packard Development Company, L.P. | Method for arranging graphic assemblies |
| CN102831593A (en) * | 2012-07-23 | 2012-12-19 | 陈华 | Digital picture splicing system and method for carrying out mosaic picture splicing by using system |
| CN104112007A (en) * | 2014-07-16 | 2014-10-22 | 深圳大学 | Data storage, organization and retrieval methods of image gradation segmentation result |
-
2014
- 2014-12-23 CN CN201410813937.0A patent/CN104537607B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060150092A1 (en) * | 2003-09-30 | 2006-07-06 | Atkins C B | Arranging graphic objects on pages |
| US7555730B2 (en) * | 2005-05-12 | 2009-06-30 | Hewlett-Packard Development Company, L.P. | Method for arranging graphic assemblies |
| CN102831593A (en) * | 2012-07-23 | 2012-12-19 | 陈华 | Digital picture splicing system and method for carrying out mosaic picture splicing by using system |
| CN104112007A (en) * | 2014-07-16 | 2014-10-22 | 深圳大学 | Data storage, organization and retrieval methods of image gradation segmentation result |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106445931A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Database node association relationship display method and apparatus |
| CN106445931B (en) * | 2015-08-04 | 2019-06-28 | 阿里巴巴集团控股有限公司 | Database node incidence relation methods of exhibiting and device |
| GB2552969A (en) * | 2016-08-16 | 2018-02-21 | Fujitsu Ltd | Image processing system |
| GB2552969B (en) * | 2016-08-16 | 2022-04-13 | Fujitsu Ltd | Image processing system |
| CN110868319A (en) * | 2019-11-08 | 2020-03-06 | 北京浪潮数据技术有限公司 | Network topology drawing method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104537607B (en) | 2017-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6553692B2 (en) | Moving image background removal method and moving image background removal system | |
| TW577227B (en) | Method and apparatus for removing background of visual content | |
| WO2021012837A1 (en) | Method and apparatus for determining recommendation information implantation position, device and storage medium | |
| Amato et al. | Accurate moving cast shadow suppression based on local color constancy detection | |
| Ye et al. | Co-saliency detection via co-salient object discovery and recovery | |
| CN102194241B (en) | Internet-based design method of artistic picture splicing system | |
| CN109472832B (en) | Color scheme generation method and device and intelligent robot | |
| Zhang et al. | A naturalness preserved fast dehazing algorithm using HSV color space | |
| US20130222696A1 (en) | Selecting between clustering techniques for displaying images | |
| CN105321177B (en) | A kind of level atlas based on image importance pieces method together automatically | |
| US20150332117A1 (en) | Composition modeling for photo retrieval through geometric image segmentation | |
| CN104537607A (en) | Automatic efficient photo collage method based on binary tree and layer sequencing | |
| EP2013850A1 (en) | Salience estimation for object-based visual attention model | |
| Yu et al. | Identifying photorealistic computer graphics using convolutional neural networks | |
| Zhang et al. | Segmentation of hand gesture based on dark channel prior in projector-camera system | |
| Yang et al. | Automatic objects removal for scene completion | |
| Zhang et al. | Multiscale adaptation fusion networks for depth completion | |
| Hung et al. | Generalized playfield segmentation of sport videos using color features | |
| CN111080748B (en) | Automatic picture synthesizing system based on Internet | |
| Khan et al. | Systematic skin segmentation: merging spatial and non-spatial data | |
| CN104994368B (en) | Non-key frame sort method in 2D 3D Video Quality Metrics | |
| Cavallaro et al. | Object-based video: extraction tools, evaluation metrics and applications | |
| CN103679170B (en) | Method for detecting salient regions based on local features | |
| CN106203447B (en) | Foreground target extraction method based on pixel inheritance | |
| CN106446764B (en) | Video object detection method based on improved fuzzy color aggregated vector |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |