CN111131744A - Privacy protection method based on video communication - Google Patents
Privacy protection method based on video communication Download PDFInfo
- Publication number
- CN111131744A CN111131744A CN201911365632.7A CN201911365632A CN111131744A CN 111131744 A CN111131744 A CN 111131744A CN 201911365632 A CN201911365632 A CN 201911365632A CN 111131744 A CN111131744 A CN 111131744A
- Authority
- CN
- China
- Prior art keywords
- video frame
- video
- portrait
- transmitted
- background
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Studio Circuits (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a privacy protection method based on video communication. The method specifically comprises the following steps: (1) the two clients establish video communication, and one end for privacy protection collects video frame data and sends the video frame data; (2) carrying out portrait identification processing on a received video frame, storing the identified portrait, remembering the position of the area where the portrait corresponds to the video frame, and storing the video frame in a path form; (3) processing the transmitted original image of the video frame to replace the whole background; (4) and (3) after receiving the portrait area path transmitted in the step (2) and the processed video frame background transmitted in the step (3), synthesizing the portrait area path and the video frame background to a specified position according to the path. The invention has the beneficial effects that: the background of video communication is processed, so that privacy can be protected while video communication is carried out smoothly.
Description
Technical Field
The invention relates to the technical field related to video communication, in particular to a method based on video communication privacy protection.
Background
In the era of the great development of the internet, with the continuous speed increase and popularization of the network, video communication has entered into various aspects of work and life. However, sometimes, when the video communication is performed with a stranger or an unfamiliar person, the background of the video may reveal the privacy of the person or give a bad impression. For example, when a video interview is performed, the background of a home is too much, and a bad impression is given to the video interview. In addition, when video chat is performed with a net friend, the intention of the other party cannot be determined, the background of the home is exposed, and unnecessary troubles may be brought.
Disclosure of Invention
The invention provides a method for processing video communication background based on video communication privacy protection, aiming at overcoming the defects in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method based on video communication privacy protection specifically comprises the following steps:
(1) starting video communication: under a set scene, the two clients establish video communication, and one end for privacy protection sends the collected video frame data to the step (2);
(2) and (3) portrait recognition: carrying out portrait identification processing on a received video frame, storing the identified portrait, memorizing the area position of the portrait corresponding to the video frame, storing in a path form, and transmitting the video frame original image to the step (3) and the portrait area path to the step (4);
(3) replacing the original image of the video frame transmitted in the step (2) into a designated map or processing the video frame, so that the background is replaced entirely after the processing, a privacy sensitive picture existing in the background of the video frame is replaced or processed, wherein the replacing or processing process mainly comprises two processes of map replacement and Gaussian blur processing, and then the processed background data of the video frame is transmitted to the step (4);
(4) and (3) after receiving the portrait area path transmitted in the step (2) and the processed video frame background transmitted in the step (3), synthesizing the portrait area path and the video frame background to a specified position according to the path.
The method is mainly a problem caused by exposing the background during video communication. At this time, the background of the video communication needs to be processed, so that privacy can be protected while video communication is carried out smoothly.
Preferably, in step (1), the transmitted video frames are transmitted frame by frame, and each video frame has a time stamp, so that the video frames are encoded and transmitted in a set time sequence after being processed.
Preferably, in step (2), when the video frame of the previous step is received, the number of the open threads is determined according to the number of cores of the CPU, so as to open the multiple threads to process the video frame synchronously, and the path format refers to a point-by-point coordinate format of the face contour.
Preferably, the specific operation method of the portrait area path is as follows: the portrait only takes the outline of the outermost layer and places the outline in a coordinate system, the coordinates of each point in the outline are taken in sequence in a certain direction by taking a certain point as a starting point, the density of the points is a preset value, and then the coordinates of the points are stored into a data structure to form a portrait area path.
Preferably, in step (3), the map replacement means: and replacing the video frame by the pre-prepared map, wherein the map can be replaced by one or more of landscape map, simple picture, pure color, RGB color value and dynamic map.
Preferably, in step (3), the gaussian blur processing means: the original image of the video frame is obtained and processed by using a Gaussian blur algorithm, only an approximate outline can be seen from the background image of the video frame after processing, detailed information in the video frame is hidden, and the blur degree selected in the Gaussian blur algorithm can be selected according to actual conditions.
The invention has the beneficial effects that: the background of video communication is processed, so that privacy can be protected while video communication is carried out smoothly.
Detailed Description
The invention is further described with reference to specific embodiments.
A method based on video communication privacy protection specifically comprises the following steps:
(1) starting video communication: under a set scene, the two clients establish video communication, and one end for privacy protection sends the collected video frame data to the step (2); the transmitted video frames are transmitted frame by frame, and each video frame is provided with a time stamp so that the video frames are encoded and transmitted according to a set time sequence after being processed.
(2) And (3) portrait recognition: carrying out portrait identification processing on a received video frame, storing the identified portrait, memorizing the area position of the portrait corresponding to the video frame, storing in a path form, and transmitting the video frame original image to the step (3) and the portrait area path to the step (4); when the video frame of the previous step is received, the number of the threads to be started can be determined according to the number of the cores of the CPU, so that the multiple threads can be started to synchronously process the video frame (for example, 4 threads can be started at the same time), and the form of the path refers to the form of the point-by-point coordinates of the face contour.
The specific operation method of the portrait area path is as follows: the portrait only takes the outline of the outermost layer, and places it in a coordinate system, and takes the coordinates of each point in the outline in a certain direction (for example, clockwise direction) with a certain point as a starting point (for example, the topmost point), and the density of the points is a preset value (the denser the points are, the higher the accuracy is, here, about 150 points are taken by a portrait outline), and then the coordinates of the points are stored into a data structure to form a portrait area path.
(3) Replacing the original image of the video frame transmitted in the step (2) into a designated map or processing the video frame, so that the background is replaced entirely after the processing, a privacy sensitive picture existing in the background of the video frame is replaced or processed, wherein the replacing or processing process mainly comprises two processes of map replacement and Gaussian blur processing, and then the processed background data of the video frame is transmitted to the step (4);
the map replacement means: and replacing the video frame by the pre-prepared map, wherein the map can be replaced by one or more of landscape map, simple picture, pure color, RGB color value and dynamic map. If the color is replaced by pure color, the picture does not need to be prepared; directly replacing the color values with RGB; if the demand is higher, the dynamic mapping can be replaced, such as a dynamic mapping of sea waves or twinkling stars and the like.
The gaussian blur processing means: the original image of the video frame is obtained and processed by using a Gaussian blur algorithm, only an approximate outline can be seen from the background image of the video frame after processing, detailed information in the video frame is hidden, and the blur degree selected in the Gaussian blur algorithm can be selected according to actual conditions.
(4) And (3) after receiving the portrait area path transmitted in the step (2) and the processed video frame background transmitted in the step (3), synthesizing the portrait area path and the video frame background to a specified position according to the path.
The method is mainly a problem caused by exposing the background during video communication. At this time, the background of the video communication needs to be processed, so that privacy can be protected while video communication is carried out smoothly.
Claims (6)
1. A method based on video communication privacy protection is characterized by comprising the following steps:
(1) starting video communication: under a set scene, the two clients establish video communication, and one end for privacy protection sends the collected video frame data to the step (2);
(2) and (3) portrait recognition: carrying out portrait identification processing on a received video frame, storing the identified portrait, memorizing the area position of the portrait corresponding to the video frame, storing in a path form, and transmitting the video frame original image to the step (3) and the portrait area path to the step (4);
(3) replacing the original image of the video frame transmitted in the step (2) into a designated map or processing the video frame, so that the background is replaced entirely after the processing, a privacy sensitive picture existing in the background of the video frame is replaced or processed, wherein the replacing or processing process mainly comprises two processes of map replacement and Gaussian blur processing, and then the processed background data of the video frame is transmitted to the step (4);
(4) and (3) after receiving the portrait area path transmitted in the step (2) and the processed video frame background transmitted in the step (3), synthesizing the portrait area path and the video frame background to a specified position according to the path.
2. The method according to claim 1, wherein in step (1), the transmitted video frames are transmitted frame by frame, and each video frame has a time stamp, so that the video frames are encoded and transmitted according to a set time sequence after being processed.
3. The method according to claim 1, wherein in step (2), when the video frame of the previous step is received, the number of the open threads is determined according to the number of cores of the CPU to open the multiple threads for processing the video frame synchronously, and the path format refers to a point-by-point coordinate format of the face contour.
4. The method according to claim 3, wherein the specific operation method of the portrait area path is as follows: the portrait only takes the outline of the outermost layer and places the outline in a coordinate system, the coordinates of each point in the outline are taken in sequence in a certain direction by taking a certain point as a starting point, the density of the points is a preset value, and then the coordinates of the points are stored into a data structure to form a portrait area path.
5. The method for protecting privacy based on video communication according to claim 1, wherein in the step (3), the map replacement means: and replacing the video frame by the pre-prepared map, wherein the map can be replaced by one or more of landscape map, simple picture, pure color, RGB color value and dynamic map.
6. The method for privacy protection based on video communication according to claim 1, wherein in the step (3), the gaussian blurring process refers to: the original image of the video frame is obtained and processed by using a Gaussian blur algorithm, only an approximate outline can be seen from the background image of the video frame after processing, detailed information in the video frame is hidden, and the blur degree selected in the Gaussian blur algorithm can be selected according to actual conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911365632.7A CN111131744B (en) | 2019-12-26 | 2019-12-26 | Privacy protection method based on video communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911365632.7A CN111131744B (en) | 2019-12-26 | 2019-12-26 | Privacy protection method based on video communication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111131744A true CN111131744A (en) | 2020-05-08 |
| CN111131744B CN111131744B (en) | 2021-04-20 |
Family
ID=70502896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911365632.7A Active CN111131744B (en) | 2019-12-26 | 2019-12-26 | Privacy protection method based on video communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111131744B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022253025A1 (en) * | 2021-05-31 | 2022-12-08 | 华为技术有限公司 | Video call processing method and apparatus |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140362163A1 (en) * | 2013-06-10 | 2014-12-11 | Citrix Systems, Inc. | Providing user video having a virtual curtain to an online conference |
| CN104378553A (en) * | 2014-12-08 | 2015-02-25 | 联想(北京)有限公司 | Image processing method and electronic equipment |
| CN104580678A (en) * | 2013-10-26 | 2015-04-29 | 西安群丰电子信息科技有限公司 | Method for realizing call with background of mobile phone |
| CN104574306A (en) * | 2014-12-24 | 2015-04-29 | 掌赢信息科技（上海）有限公司 | Face beautifying method for real-time video and electronic equipment |
| CN107465885A (en) * | 2016-06-06 | 2017-12-12 | 中兴通讯股份有限公司 | A kind of method and apparatus for realizing video communication |
| US20180103292A1 (en) * | 2013-10-22 | 2018-04-12 | Google Llc | Systems and Methods for Associating Media Content with Viewer Expressions |
| CN108040230A (en) * | 2017-12-19 | 2018-05-15 | 司马大大（北京）智能系统有限公司 | A kind of monitoring method and device for protecting privacy |
| US20180255249A1 (en) * | 2017-03-03 | 2018-09-06 | Canon Kabushiki Kaisha | Image processing apparatus and control method for controlling the same |
| CN109064525A (en) * | 2018-08-20 | 2018-12-21 | 广州视源电子科技股份有限公司 | Picture format conversion method, device, equipment and storage medium |
| CN109145827A (en) * | 2018-08-24 | 2019-01-04 | 阿里巴巴集团控股有限公司 | Video communication method and device |
| CN109146991A (en) * | 2018-08-20 | 2019-01-04 | 广州视源电子科技股份有限公司 | Picture format conversion method, device, equipment and storage medium |
| CN109274919A (en) * | 2017-07-18 | 2019-01-25 | 福州瑞芯微电子股份有限公司 | Method for secret protection, system, video call terminal and system in video calling |
| CN110166725A (en) * | 2019-04-19 | 2019-08-23 | 平安科技（深圳）有限公司 | Video method, device, computer equipment and storage medium |
| CN110175950A (en) * | 2018-10-24 | 2019-08-27 | 广东小天才科技有限公司 | Privacy protection method based on wearable device and wearable device |
| CN110213485A (en) * | 2019-06-04 | 2019-09-06 | 维沃移动通信有限公司 | A kind of image processing method and terminal |
-
2019
- 2019-12-26 CN CN201911365632.7A patent/CN111131744B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140362163A1 (en) * | 2013-06-10 | 2014-12-11 | Citrix Systems, Inc. | Providing user video having a virtual curtain to an online conference |
| US20180103292A1 (en) * | 2013-10-22 | 2018-04-12 | Google Llc | Systems and Methods for Associating Media Content with Viewer Expressions |
| CN104580678A (en) * | 2013-10-26 | 2015-04-29 | 西安群丰电子信息科技有限公司 | Method for realizing call with background of mobile phone |
| CN104378553A (en) * | 2014-12-08 | 2015-02-25 | 联想(北京)有限公司 | Image processing method and electronic equipment |
| CN104574306A (en) * | 2014-12-24 | 2015-04-29 | 掌赢信息科技（上海）有限公司 | Face beautifying method for real-time video and electronic equipment |
| CN107465885A (en) * | 2016-06-06 | 2017-12-12 | 中兴通讯股份有限公司 | A kind of method and apparatus for realizing video communication |
| US20180255249A1 (en) * | 2017-03-03 | 2018-09-06 | Canon Kabushiki Kaisha | Image processing apparatus and control method for controlling the same |
| CN109274919A (en) * | 2017-07-18 | 2019-01-25 | 福州瑞芯微电子股份有限公司 | Method for secret protection, system, video call terminal and system in video calling |
| CN108040230A (en) * | 2017-12-19 | 2018-05-15 | 司马大大（北京）智能系统有限公司 | A kind of monitoring method and device for protecting privacy |
| CN109146991A (en) * | 2018-08-20 | 2019-01-04 | 广州视源电子科技股份有限公司 | Picture format conversion method, device, equipment and storage medium |
| CN109064525A (en) * | 2018-08-20 | 2018-12-21 | 广州视源电子科技股份有限公司 | Picture format conversion method, device, equipment and storage medium |
| CN109145827A (en) * | 2018-08-24 | 2019-01-04 | 阿里巴巴集团控股有限公司 | Video communication method and device |
| CN110175950A (en) * | 2018-10-24 | 2019-08-27 | 广东小天才科技有限公司 | Privacy protection method based on wearable device and wearable device |
| CN110166725A (en) * | 2019-04-19 | 2019-08-23 | 平安科技（深圳）有限公司 | Video method, device, computer equipment and storage medium |
| CN110213485A (en) * | 2019-06-04 | 2019-09-06 | 维沃移动通信有限公司 | A kind of image processing method and terminal |
Non-Patent Citations (1)
| Title |
|---|
| 牛德姣: "基于视频的目标跟踪及隐私保护技术的研究与实现", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022253025A1 (en) * | 2021-05-31 | 2022-12-08 | 华为技术有限公司 | Video call processing method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111131744B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8509499B2 (en) | Automatic face detection and identity masking in images, and applications thereof | |
| JP2020530920A (en) | Image lighting methods, devices, electronics and storage media | |
| CN105303161A (en) | Method and device for shooting multiple people | |
| CN110599387A (en) | Method and device for automatically removing image watermark | |
| CN107506406B (en) | Picture archiving method and system for power transmission line tower | |
| JP2014501405A (en) | Augmented reality processing based on eye capture in handheld devices | |
| CN111259968A (en) | Illegal image recognition method, device, equipment and computer readable storage medium | |
| CN112132836A (en) | Video image clipping method and device, electronic equipment and storage medium | |
| CN112508812B (en) | Image color cast correction method, model training method, device and equipment | |
| CN113329252A (en) | Live broadcast-based face processing method, device, equipment and storage medium | |
| CN111131744B (en) | Privacy protection method based on video communication | |
| CN110619652B (en) | Image registration ghost elimination method based on optical flow mapping repeated area detection | |
| CN108519734A (en) | A kind of system of determining surface pointer position | |
| CN115034982A (en) | Underwater image enhancement method based on multi-scale attention mechanism fusion | |
| CN107169973A (en) | The background removal and synthetic method and device of a kind of image | |
| CN111524083A (en) | Active and passive combined underwater aerial imaging image recovery method based on structured light | |
| CN114862707A (en) | Multi-scale feature recovery image enhancement method and device and storage medium | |
| CN111275729B (en) | Method and system for finely dividing sky area and method and system for changing sky of image | |
| CN108549845A (en) | A kind of method of determining surface pointer position | |
| CN112788254A (en) | Camera image matting method, device, equipment and storage medium | |
| CN111104987B (en) | Face recognition method and device and electronic equipment | |
| CN117409463A (en) | Live broadcast strategy management system | |
| US11113780B2 (en) | Watermarking digital content | |
| CN111241934A (en) | Method and device for acquiring photophobic region in face image | |
| CN115988330A (en) | Color image high-dynamic imaging method based on single-frame exposure |
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 |