EP2791778A1 - Verfahren zur echtzeit-verarbeitung einer videosequenz auf mobilen endgeräten - Google Patents
Verfahren zur echtzeit-verarbeitung einer videosequenz auf mobilen endgerätenInfo
- Publication number
- EP2791778A1 EP2791778A1 EP12808803.6A EP12808803A EP2791778A1 EP 2791778 A1 EP2791778 A1 EP 2791778A1 EP 12808803 A EP12808803 A EP 12808803A EP 2791778 A1 EP2791778 A1 EP 2791778A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- image
- frame
- video sequence
- embedded
- opacity
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000009466 transformation Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 claims description 4
- 238000000844 transformation Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 2
- 238000012986 modification Methods 0.000 claims description 2
- 239000003086 colorant Substances 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 claims 1
- 230000008859 change Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 2
- 101100269850 Caenorhabditis elegans mask-1 gene Proteins 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- VJYFKVYYMZPMAB-UHFFFAOYSA-N ethoprophos Chemical compound CCCSP(=O)(OCC)SCCC VJYFKVYYMZPMAB-UHFFFAOYSA-N 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001795 light effect Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000006740 morphological transformation Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
- G06F3/147—Digital output to display device ; Cooperation and interconnection of the display device with other functional units using display panels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/04—Synchronising
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G2340/00—Aspects of display data processing
- G09G2340/10—Mixing of images, i.e. displayed pixel being the result of an operation, e.g. adding, on the corresponding input pixels
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G2340/00—Aspects of display data processing
- G09G2340/12—Overlay of images, i.e. displayed pixel being the result of switching between the corresponding input pixels
- G09G2340/125—Overlay of images, i.e. displayed pixel being the result of switching between the corresponding input pixels wherein one of the images is motion video
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G2340/00—Aspects of display data processing
- G09G2340/14—Solving problems related to the presentation of information to be displayed
- G09G2340/145—Solving problems related to the presentation of information to be displayed related to small screens
Definitions
- the present invention relates to the general field of image processing, in particular video sequences on mobile terminals. It relates more particularly to a method of embedding real-time images within a video sequence representing for example characters in motion.
- the invention relates to a method for processing video sequences on mobile terminals, more specifically, a real-time image inlay in the video stream.
- the video stream is read with the embedded images.
- the image is merged with the video stream, frame by frame. For each frame, the image is positioned at the right place. This method involves the fact that the image undergoes in real time a trapezoidal matrix transformation so that it can adapt to the video stream.
- the invention aims firstly at a method of incrustation of an image to be embedded in a video sequence, for a mobile terminal of the tablet type or smartphone,
- step 100 may also occur after the beginning of step 300 of playing the video.
- the method comprises a step 600 of applying a deformation to the image to be embedded, so as to match this image to be embedded in the shape of the keying area.
- the method comprises a step 750 of tracking the movement of an incrustation zone, by identification of the pixel movements, or in real time using the known motion detection algorithms, shapes, or object recognition by learning, either in pre-production.
- step 500 the identification of the keying area is done by touch input by a user on the display interface of the mobile terminal
- step 500 in the case where the key points are not pre-calculated, keying points defining the keying area are calculated in real time by the mobile terminal, by using keying methods. recognition of images by motion detection or object recognition by learning.
- step 500 in the case of a prior determination of the key points, a file containing the coordinates of the key points in the video sequence is associated with said video sequence, so as to be read (at the latest at the same time) by the mobile terminal.
- the method comprises means for reading a table of coordinates, associated with the video sequence, these coordinates representing, for each frame, the positions of the four extreme points of the incrustation zone, that is to say of the image to be embedded in the video.
- step 700 to insert the image to be embedded, when the video is displayed in real time on the mobile terminal, the method implements a function responsible for seeking the transformation of the image to be embedded with respect to the current frame, said function being called at each frame display.
- step 700 to insert the image to be embedded, the image of the video is merged with the image to be embedded by re-calculating a resulting image by merging the images. raw data of the two images, and this one is displayed.
- the method comprises the following steps:
- the method includes a step of synchronizing the mask with the video sequence.
- the sequence video and the mask are synchronized by a process of double video: the original video sequence being played in a first part, intended to be displayed, and a second part, not displayed, of this video sequence containing only the information allowing the color changes and modifying the opacity of the video sequence, the method comprising, during the display of the video sequence on the mobile terminal, a step of applying the opacity and / or color transformations given by the second part on the first part.
- the opacity or mask information is encoded in a color management format, a color channel managing the opacity, and other channels managing the objects.
- FIG. 1 a flowchart of the steps involved in the present process
- Figure 2 an illustration of a frame of a video sequence in the case of application of an opacity on a part of the image.
- the invention implements a display terminal, here but not limited to smartphone type.
- This display terminal is, in the present non-limiting embodiment, supposed to have means for storing image sequences, calculation means, for example of the microprocessor type, adapted to execute a software application previously loaded in memory, image display means, and advantageously data input means by a user of said terminal.
- the invention relates to a method for processing a video sequence on a mobile terminal, in particular of the smartphone type.
- the video sequence of which he As an example, here are characters or objects moving within the display area during the video sequence.
- the purpose of the method is then to embed an image, called the image to be embedded, on a part of an object (for example the face of a character), called the incrustation zone, this image to be embedded according to the movement of the this object's overlay area during the video sequence, so as to create a sense of realism.
- the keying area may typically be the face of a moving character, said character approaching or moving away from the camera, and the face facing or turning during the sequence.
- the overlay area is a shape that includes the portion of the object to be replaced by the image to be embedded.
- the image to be embedded is trapezoidal, rectangular, polygonal or elliptical.
- the shape of the incrustation zone is, in the present nonlimiting example of implementation of the method, of the same type as the image to be embedded: for example, if the image to be embedded has the shape of a polygon, the area of inlay will be a polygon having the same number of edges, while being possibly deformed (different angles and lengths of the different edges). Similarly, if the image to be embedded has the shape of an ellipse, the key area will also be elliptical.
- the method makes it possible to determine a deformation function of the incrustation zone, then to deform the image to be embedded in a similar way.
- this method includes a step of pre-calculating particular points of the video sequence, called points. incrustation (ie coordinates in time and on a predetermined area of the display area) defining the area of incrustation, so as not to require third intervention during the inlay, and be quite sparing in computing resources for use on mobile devices.
- points. incrustation ie coordinates in time and on a predetermined area of the display area
- key points are calculated in real time by the mobile terminal. This is achieved for example by using image recognition methods by motion detection or object recognition by learning.
- the image to be embedded is merged with the video stream, frame by frame.
- the image to be embedded is positioned at the right place, ie at the location of the overlay area, reproducing the shape.
- Positioning at the location of the keying area requires prior identification of a moving area integrated in the video stream, by identifying pixel movements in real time using known motion detection algorithms, shapes, or recognition object by learning, either in pre-production.
- a file containing the coordinates of the key points in the video sequence is associated with said video sequence, so as to be read (at the latest at the same time) by the terminal mobile.
- each video sequence corresponds to an array of coordinates which represent for each frame, the positions of the four extreme points of the incrustation area, that is to say of the image to be placed in the video.
- the process can use two techniques:
- the image to be embedded is displayed at these coordinates, after having been deformed to be fixed on the corresponding coordinates (four points in the case of a trapezoid) . That is to say that, in a particular mode of implementation, not limiting, the shape of the image to be embedded and its position in the image must correspond exactly to the shape and position of the inlay area to this moment of the video sequence.
- the image of the video is merged with the image to be incrusted by recalculating a resulting image by merging the raw data of the two images, and then this one is displayed.
- This second technique saves the resources of the mobile terminal.
- the pants is highlighted (which corresponds to the area to be embedded). Information about these pants can then be displayed in a new window.
- the method comprises a first step 100 of choosing the image to be embedded.
- a second step 200 the image to be embedded is resized by an adjustment of the user.
- step 300 the video sequence is read. Then, in step 300, the video sequence is read. Then a frame of this video sequence is displayed in step 400.
- step 500 determines whether the frame has a keying area (to check if this image is likely to receive an image to be embedded).
- step 400 If this is not the case, the process returns to step 400, otherwise the step
- a trapezoidal deformation is applied to the image to be embedded in such a way that the shape of the image to be imaged corresponds to the shape of the incrustation zone.
- step 700 this image is displayed in step 700, replacing the overlay area. After this last step, the process returns to step 400.
- a step of the method consists in making the video sequence more or less opaque by locations.
- the image to be embedded can be a color mask, it is necessary to be able to synchronize the mask with the video sequence concerned: the display of the mask on the video sequence must be perfectly synchronized.
- the video sequence and the mask are synchronized by a double video process: the original video sequence (without mask) is played in the visible part, but a non-displayed part of this video sequence is composed by the mask.
- the opacity or mask information is encoded in the RGB (or other color management system) format, a color channel that handles the opacity, and the others. channels managing the objects.
- the object to be embedded is a car 210, and we want to change the color of the head of a pedestrian 220 present on the original video sequence.
- the opacity is coded on the B channel (Blue) and the color change on the R channel (Red).
- the video sequence is here decomposed into two parts: a first part 230, here but not limited to the upper part of the image of the transmitted video file, representing the inlaid object (the car) and the original video sequence, a second part 240 , here but not limited to the lower part of the image of the transmitted video file, displaying only the information allowing the color changes and the modification of the opacity of the video sequence.
- the information is thus encoded in a single video file, and the display is responsible for applying the opacity and / or color transformations given by the lower part on the upper part.
- the process then comprises the following additional steps:
- the opacity is managed on the red channel, in the lower field weft less than one pixel having a color in RGB corresponding to a value FF0000 in hexadecimal. So we recover the R value here FF, to apply it on the opacity of the pixel to be displayed on the main frame.
- the Alpha channel (opacity) of the main frame will therefore have value for the corresponding pixel FF.
- the transformation can be a color change. To can change the color of different objects in real time, you must be able to create matching masks.
- Each mask is encoded in RGB on the second part of the frame. This encoding consists of 2 parts: one channel is used to manage the opacity of the mask, another channel to identify the masks.
- the embedded image gives the impression of blending into the context of the video.
- the calculation and display is done on a mobile terminal.
- the method makes it possible to modify the object of the video by a tactile interaction.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1161847A FR2984668B3 (fr) | 2011-12-16 | 2011-12-16 | Procede de traitement de sequence video sur les terminaux mobiles en temps reel |
PCT/EP2012/075828 WO2013087935A1 (fr) | 2011-12-16 | 2012-12-17 | Procédé de traitement de séquence vidéo sur les terminaux mobiles en temps réel |
Publications (1)
Publication Number | Publication Date |
---|---|
EP2791778A1 true EP2791778A1 (de) | 2014-10-22 |
Family
ID=47469980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP12808803.6A Withdrawn EP2791778A1 (de) | 2011-12-16 | 2012-12-17 | Verfahren zur echtzeit-verarbeitung einer videosequenz auf mobilen endgeräten |
Country Status (4)
Country | Link |
---|---|
US (1) | US8866970B1 (de) |
EP (1) | EP2791778A1 (de) |
FR (1) | FR2984668B3 (de) |
WO (1) | WO2013087935A1 (de) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10154196B2 (en) | 2015-05-26 | 2018-12-11 | Microsoft Technology Licensing, Llc | Adjusting length of living images |
FR3066671B1 (fr) | 2017-05-18 | 2020-07-24 | Darmon Yves | Procede d'incrustation d'images ou de video au sein d'une autre sequence video |
WO2019239396A1 (en) * | 2018-06-12 | 2019-12-19 | Kliots Shapira Ela | Method and system for automatic real-time frame segmentation of high resolution video streams into constituent features and modifications of features in each frame to simultaneously create multiple different linear views from same video source |
CN113766147B (zh) * | 2020-09-22 | 2022-11-08 | 北京沃东天骏信息技术有限公司 | 视频中嵌入图像的方法、平面预测模型获取方法和装置 |
CN112738325B (zh) * | 2020-12-25 | 2021-11-23 | 浙江工业大学 | 一种基于Android手机的智能LED识别方法 |
Family Cites Families (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5398074A (en) * | 1992-11-24 | 1995-03-14 | Thomson Consumer Electronics, Inc. | Programmable picture-outside-picture display |
US6008860A (en) * | 1995-12-29 | 1999-12-28 | Thomson Consumer Electronics, Inc. | Television system with provisions for displaying an auxiliary image of variable size |
US6201879B1 (en) * | 1996-02-09 | 2001-03-13 | Massachusetts Institute Of Technology | Method and apparatus for logo hiding in images |
KR100616258B1 (ko) * | 1996-05-06 | 2007-04-25 | 코닌클리케 필립스 일렉트로닉스 엔.브이. | 그래픽이미지와비디오이미지동시표시방법및장치 |
US6473102B1 (en) * | 1998-05-11 | 2002-10-29 | Apple Computer, Inc. | Method and system for automatically resizing and repositioning windows in response to changes in display |
US6542621B1 (en) * | 1998-08-31 | 2003-04-01 | Texas Instruments Incorporated | Method of dealing with occlusion when tracking multiple objects and people in video sequences |
KR100282397B1 (ko) * | 1998-12-31 | 2001-02-15 | 구자홍 | 디지탈 영상 데이터의 디인터레이싱 장치 |
US6493038B1 (en) * | 2000-06-21 | 2002-12-10 | Koninklijke Philips Electronics N.V. | Multi-window pip television with the ability to watch two sources of video while scanning an electronic program guide |
GB2364841B (en) * | 2000-07-11 | 2002-09-11 | Motorola Inc | Method and apparatus for video encoding |
GB2364842A (en) * | 2000-07-11 | 2002-02-06 | Motorola Inc | Method and system for improving video quality |
US20020070957A1 (en) * | 2000-12-12 | 2002-06-13 | Philips Electronics North America Corporation | Picture-in-picture with alterable display characteristics |
US7206029B2 (en) * | 2000-12-15 | 2007-04-17 | Koninklijke Philips Electronics N.V. | Picture-in-picture repositioning and/or resizing based on video content analysis |
US6697124B2 (en) * | 2001-03-30 | 2004-02-24 | Koninklijke Philips Electronics N.V. | Smart picture-in-picture |
US6778224B2 (en) * | 2001-06-25 | 2004-08-17 | Koninklijke Philips Electronics N.V. | Adaptive overlay element placement in video |
US20070195196A1 (en) * | 2003-12-16 | 2007-08-23 | Koninklijke Philips Electronic, N.V. | Radar |
JP2006310896A (ja) * | 2005-04-26 | 2006-11-09 | Matsushita Electric Ind Co Ltd | 画像処理装置 |
AU2005203074A1 (en) * | 2005-07-14 | 2007-02-01 | Canon Information Systems Research Australia Pty Ltd | Image browser |
US20100188579A1 (en) * | 2009-01-29 | 2010-07-29 | At&T Intellectual Property I, L.P. | System and Method to Control and Present a Picture-In-Picture (PIP) Window Based on Movement Data |
JP5465620B2 (ja) * | 2010-06-25 | 2014-04-09 | Kddi株式会社 | 映像コンテンツに重畳する付加情報の領域を決定する映像出力装置、プログラム及び方法 |
-
2011
- 2011-12-16 FR FR1161847A patent/FR2984668B3/fr not_active Expired - Fee Related
-
2012
- 2012-12-17 US US14/364,941 patent/US8866970B1/en not_active Expired - Fee Related
- 2012-12-17 EP EP12808803.6A patent/EP2791778A1/de not_active Withdrawn
- 2012-12-17 WO PCT/EP2012/075828 patent/WO2013087935A1/fr active Application Filing
Non-Patent Citations (1)
Title |
---|
See references of WO2013087935A1 * |
Also Published As
Publication number | Publication date |
---|---|
US20140300814A1 (en) | 2014-10-09 |
FR2984668B3 (fr) | 2014-09-05 |
WO2013087935A1 (fr) | 2013-06-20 |
FR2984668A3 (fr) | 2013-06-21 |
US8866970B1 (en) | 2014-10-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113179368B (zh) | 一种车辆定损的数据处理方法、装置、处理设备及客户端 | |
CN106254933B (zh) | 字幕提取方法及装置 | |
US20200364802A1 (en) | Processing method, processing apparatus, user terminal and server for recognition of vehicle damage | |
US20180096502A1 (en) | Techniques for incorporating a text-containing image into a digital image | |
EP1519343A2 (de) | Verfahren und Apparat zur Zusammenfassung und Indexierung von Inhalten einer audio-visuellen Präsentation | |
US8719687B2 (en) | Method for summarizing video and displaying the summary in three-dimensional scenes | |
CN104618803A (zh) | 信息推送方法、装置、终端及服务器 | |
EP2791778A1 (de) | Verfahren zur echtzeit-verarbeitung einer videosequenz auf mobilen endgeräten | |
EP3238213B1 (de) | Verfahren und vorrichtung zur erzeugung eines extrapolierten bildes auf basis von objektdetektion | |
US20150042837A1 (en) | Image acquiring method and electronic device | |
GB2513218A (en) | Object detection metadata | |
WO2014187265A1 (zh) | 一种照片拍摄处理方法、设备和计算机存储介质 | |
Bagiwa et al. | Chroma key background detection for digital video using statistical correlation of blurring artifact | |
US20190311744A1 (en) | Comparing frame data to generate a textless version of a multimedia production | |
FR2982448A1 (fr) | Procede de traitement d'image stereoscopique comprenant un objet incruste et dispositif correspondant | |
WO2023123981A1 (zh) | 一种视频处理方法、装置、计算机设备和存储介质 | |
US9171357B2 (en) | Method, apparatus and computer-readable recording medium for refocusing photographed image | |
CN113722541A (zh) | 视频指纹的生成方法及装置、电子设备和存储介质 | |
CN105306961B (zh) | 一种抽帧的方法及装置 | |
CN108334811B (zh) | 一种人脸图像处理方法及装置 | |
CN110457998A (zh) | 影像数据关联方法和设备、数据处理设备及介质 | |
US10282633B2 (en) | Cross-asset media analysis and processing | |
CN114170470A (zh) | 样本生成方法、装置、设备和存储介质 | |
Xiong et al. | Dual diversified dynamical Gaussian process latent variable model for video repairing | |
CN108419092A (zh) | 一种确定相同视频的方法及装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20140617 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAX | Request for extension of the european patent (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
18D | Application deemed to be withdrawn |
Effective date: 20150203 |