CN104159116A - Method of adding face recognition information into H264 video stream - Google Patents
Method of adding face recognition information into H264 video stream Download PDFInfo
- Publication number
- CN104159116A CN104159116A CN201410424087.5A CN201410424087A CN104159116A CN 104159116 A CN104159116 A CN 104159116A CN 201410424087 A CN201410424087 A CN 201410424087A CN 104159116 A CN104159116 A CN 104159116A
- Authority
- CN
- China
- Prior art keywords
- recognition
- face information
- data
- encapsulation
- added
- 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
Landscapes
- Image Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a method of adding face recognition information into H264 video stream, after data packaging and anti-competition processing are carried out on the face recognition information, the H264 video stream is added and is transmitted to a client to extract the face recognition information in the H264 code stream data, the face recognition information is added without influencing the H264 standard code stream so as to facilitate development of a network intelligence camera based on the existing network camera products, on the one hand, the product performance is improved; on the other hand, the pace to put a product on the market is accelerated, and the method has good application prospect.
Description
Technical field
The present invention relates to a kind of recognition of face information be added to the method in H264 video flowing, belong to technical field of video monitoring.
Background technology
Current, web camera, for reaching more high coding efficiency, reduces the data volume of video flowing simultaneously, and its Video coding mode substantially all adopts H264 coding, according to the market demand, with the application of the network intelligence video camera of face identification functions, will be more and more extensive.
Aspect Video processing, web camera is mainly divided into two modules: IMAQ coding module and data processing transport module, IMAQ coding module is mainly responsible for gathering video, and original video data is encoded, and is converted to the data of H264 coded format; Data processing transport module is mainly responsible for H264 bit stream data to pack in modes such as RTP, then by Ethernet, sends to client, by client to the bit stream data demonstration of decoding.As can be seen here, relative web camera, a face identification functions module that networking intelligent camera is many, this module obtains the data of piece image from IMAQ coding module, and analyze, thereby obtain the coordinate position of people's face of occurring in this width image, then give data processing transport module, by data processing transport module, coordinate position data is added in the H264 bit stream data of this width image again, be transferred to together client, by client, bit stream data is decoded, if needed, can extract people's face according to people's face coordinate position, the formation of web camera and network intelligence video camera and the relation between modules, as shown in Figure 1.
But the information of recognition of face does not also meet H264 coding standard, how fast and effectively the information of recognition of face to be added in the video flowing of H264 coding, be the current bottleneck problem running into the network intelligence video camera of face identification functions, in the urgent need to address.
Summary of the invention
The object of the invention is to overcome and existing web camera is upgraded to network intelligence video camera, the information of recognition of face does not also meet H264 coding standard, is inconvenient to upgrade, and network intelligence video camera is used in simple replacing, expensive, be not easy to the problem of promoting the use of of network intelligence video camera.Of the present invention recognition of face information is added to the method in H264 video flowing, on the basis that does not affect H264 standard code stream, add recognition of face information, be conducive to developing network intelligent camera on existing network video camera product basis, enhance product performance on the one hand, accelerate on the other hand the product paces that put goods on the market, have a good application prospect.
In order to achieve the above object, the technical solution adopted in the present invention is:
Recognition of face information is added to the method in H264 video flowing, it is characterized in that: comprise with following steps,
Step (1), carries out data encapsulation by recognition of face information, the coding standard of the recognition of face information conforms H264 video flowing after encapsulation;
Step (2), carries out anti-competition process by the recognition of face information after encapsulation;
Step (3), the recognition of face information after anti-competition process is processed joins H264 bit stream data, after adding implantation site and be H264 code stream I frame or P frame data;
Step (4), will add the H264 bit stream data of recognition of face information to pass to client;
Step (5), client is extracted the recognition of face information in H264 bit stream data, reduction recognition of face information.
Aforesaidly a kind of recognition of face information is added to the method in H264 video flowing, it is characterized in that: the process that step (1) is carried out data encapsulation by recognition of face information is,
(1) the data head of recognition of face information is increased to the first flag bit of fixing hexadecimal data;
(2) calculate the data length of recognition of face information, and data length position is increased to the rear portion of flag bit;
(3) recognition of face information is added to rear portion, data length position;
(4) after recognition of face information, increase the tail flag bit of fixing hexadecimal data.
Aforesaidly a kind of recognition of face information is added to the method in H264 video flowing, it is characterized in that: the process that step (2) is carried out anti-competition process by the recognition of face information after encapsulation is, while occurring two continuous 00 in recognition of face information, thereafter, increase Data Labels 03, and revise corresponding data length position.
Aforesaidly a kind of recognition of face information is added to the method in H264 video flowing, it is characterized in that: step (5), the method that client is extracted the recognition of face information in H264 bit stream data is,
(1) inquiry of recognition of face information
In decoder extracts H264 bit stream data, when I frame or P frame, will inquire about these frame data, whether inquiry there is the recognition of face information after encapsulation, if do not exist, carries out video decode Graphics Processing; If exist, according to revising corresponding data length position, tail flag bit, determine whether correctly, if incorrect, carry out video decode Graphics Processing, if correct, extract recognition of face information;
(2) recognition of face information go anti-competition process
While occurring two continuous 00 in the recognition of face information of extracting, delete the Data Labels 03 increasing, reduction recognition of face information;
(3) application of recognition of face information data
According to the recognition of face information of reduction, coordinates computed, width, highly, apply.
The invention has the beneficial effects as follows: of the present invention recognition of face information is added to the method in H264 video flowing, recognition of face information is carried out adding H264 bit stream data after data encapsulation, anti-competition process, sending client to extracts the recognition of face information in H264 bit stream data, on the basis that does not affect H264 standard code stream, add recognition of face information, be conducive to developing network intelligent camera on existing network video camera product basis, enhance product performance on the one hand, accelerate on the other hand the product paces that put goods on the market, have a good application prospect.
Accompanying drawing explanation
Fig. 1 is the flow chart that recognition of face information is added to the method in H264 video flowing of the present invention.
Fig. 2 is the flow chart that client of the present invention is extracted the recognition of face information in H264 bit stream data.
Embodiment
Below in conjunction with Figure of description, the invention will be further described.Following examples are only for technical scheme of the present invention is more clearly described, and can not limit the scope of the invention with this.
As shown in Figure 1, a kind of recognition of face information is added to the method in H264 video flowing, it is characterized in that: comprise with following steps,
Step (1), carries out data encapsulation by recognition of face information, the coding standard of the recognition of face information conforms H264 video flowing after encapsulation,
(1) the data head of recognition of face information is increased to the first flag bit of fixing hexadecimal data;
(2) calculate the data length of recognition of face information, and data length position is increased to the rear portion of flag bit;
(3) recognition of face information is added to rear portion, data length position;
(4) after recognition of face information, increase the tail flag bit of fixing hexadecimal data.
Encapsulating structure is as shown in table 1,
The encapsulating structure of table 1 recognition of face information
Header | Data?length | Data | Tail |
4byte | 2byte | N*14byte | 4byte |
Fixing (0x55aa55aa) | The length of indication Data data | Recognition of face information | Fixing (0x44dd44dd) |
Wherein, Header: headed by flag bit, be fixed as hexadecimal data 0x55aa55aa; Data length: be data length position, the data length of indicating recognition of face packets of information thereafter to contain; Data: for people's face identifying information data, include N people's face; Tail: be tail flag bit, be fixed as hexadecimal data 0x44dd44dd;
The 0x55aa55aa here, 0x44dd44dd can be according to user's needs, and oneself is chosen, and the byte number of each data bit can be set as required;
Below according to above-mentioned encapsulation mode, the recognition of face information after an encapsulation: 55 aa 55 aa 00 1c 12 34 56 78 00 00 01 24 00 D4 00 64 00 64 00 00 00 01 00 00 01 36 00 45 00 64 00 64 44 dd 44 dd;
Step (2), recognition of face information after encapsulation is carried out to anti-competition process, while occurring two continuous 00 in recognition of face information, thereafter, increase Data Labels 03, and revise corresponding data length position, after the anti-competition process of recognition of face information after an above-mentioned encapsulation, be 55 aa 55 aa 00 1f 12 34 56 78 00 00 03 01 24 00 D4 00 64 00 64 00 00 03 00 01 00 00 03 01 36 00 45 00 64 00 64 44 dd 44 dd;
Step (3), the recognition of face information after anti-competition process is processed joins H264 bit stream data, after adding implantation site and be H264 code stream I frame or P frame data, facilitates follow-up inquiry to extract;
Step (4), will add the H264 bit stream data of recognition of face information to pass to client;
Step (5), client is extracted the recognition of face information in H264 bit stream data, reduction recognition of face information, the method for extraction is,
(1) inquiry of recognition of face information
In decoder extracts H264 bit stream data, when I frame or P frame, will inquire about these frame data, whether inquiry there is the recognition of face information after encapsulation, if do not exist, carries out video decode Graphics Processing; If exist, according to revising corresponding data length position, tail flag bit, determine whether correctly, if incorrect, carry out video decode Graphics Processing, if correct, extract recognition of face information;
(2) recognition of face information go anti-competition process
While occurring two continuous 00 in the recognition of face information of extracting, delete the Data Labels 03 increasing, reduction recognition of face information;
(3) application of recognition of face information data
According to the recognition of face information of reduction, coordinates computed, width, highly, apply.
In sum, of the present invention recognition of face information is added to the method in H264 video flowing, on the basis that does not affect H264 standard code stream, add recognition of face information, be conducive to developing network intelligent camera on existing network video camera product basis, enhance product performance on the one hand, accelerate on the other hand the product paces that put goods on the market, have a good application prospect.
More than show and described basic principle of the present invention, principal character and advantage.The technical staff of the industry should understand; the present invention is not restricted to the described embodiments; that in above-described embodiment and specification, describes just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications, and these changes and improvements all fall in the claimed scope of the invention.The claimed scope of the present invention is defined by appending claims and equivalent thereof.
Claims (4)
1. recognition of face information is added to the method in H264 video flowing, it is characterized in that: comprise with following steps,
Step (1), carries out data encapsulation by recognition of face information, the coding standard of the recognition of face information conforms H264 video flowing after encapsulation;
Step (2), carries out anti-competition process by the recognition of face information after encapsulation;
Step (3), the recognition of face information after anti-competition process is processed joins H264 bit stream data, after adding implantation site and be H264 code stream I frame or P frame data;
Step (4), will add the H264 bit stream data of recognition of face information to pass to client;
Step (5), client is extracted the recognition of face information in H264 bit stream data, reduction recognition of face information.
2. according to claim 1ly a kind of recognition of face information is added to the method in H264 video flowing, it is characterized in that: the process that step (1) is carried out data encapsulation by recognition of face information is,
(1) the data head of recognition of face information is increased to the first flag bit of fixing hexadecimal data;
(2) calculate the data length of recognition of face information, and data length position is increased to the rear portion of flag bit;
(3) recognition of face information is added to rear portion, data length position;
(4) after recognition of face information, increase the tail flag bit of fixing hexadecimal data.
3. according to claim 1 and 2ly a kind of recognition of face information is added to the method in H264 video flowing, it is characterized in that: the process that step (2) is carried out anti-competition process by the recognition of face information after encapsulation is, while occurring two continuous 00 in recognition of face information, thereafter, increase Data Labels 03, and revise corresponding data length position.
4. according to claim 1 and 2ly a kind of recognition of face information is added to the method in H264 video flowing, it is characterized in that: step (5), the method that client is extracted the recognition of face information in H264 bit stream data is,
(1) inquiry of recognition of face information
In decoder extracts H264 bit stream data, when I frame or P frame, will inquire about these frame data, whether inquiry there is the recognition of face information after encapsulation, if do not exist, carries out video decode Graphics Processing; If exist, according to revising corresponding data length position, tail flag bit, determine whether correctly, if incorrect, carry out video decode Graphics Processing, if correct, extract recognition of face information;
(2) recognition of face information go anti-competition process
While occurring two continuous 00 in the recognition of face information of extracting, delete the Data Labels 03 increasing, reduction recognition of face information;
(3) application of recognition of face information data
According to the recognition of face information of reduction, coordinates computed, width, highly, apply.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410424087.5A CN104159116B (en) | 2014-08-26 | 2014-08-26 | A kind of method for adding recognition of face information in H264 video flowings |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410424087.5A CN104159116B (en) | 2014-08-26 | 2014-08-26 | A kind of method for adding recognition of face information in H264 video flowings |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104159116A true CN104159116A (en) | 2014-11-19 |
CN104159116B CN104159116B (en) | 2018-02-02 |
Family
ID=51884506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410424087.5A Expired - Fee Related CN104159116B (en) | 2014-08-26 | 2014-08-26 | A kind of method for adding recognition of face information in H264 video flowings |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104159116B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105611209A (en) * | 2015-12-23 | 2016-05-25 | 天津天地伟业数码科技有限公司 | Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file |
CN106534151A (en) * | 2016-11-29 | 2017-03-22 | 北京旷视科技有限公司 | Method and device for playing video streams |
CN108200395A (en) * | 2018-01-05 | 2018-06-22 | 贵州远诚自控科技有限公司 | Unattended Sewage Disposal based on the processing of equipment operation image video |
CN109040587A (en) * | 2018-08-01 | 2018-12-18 | 北京旷视科技有限公司 | It captures processing method, device, capture mechanism, equipment and storage medium |
CN109688383A (en) * | 2018-12-29 | 2019-04-26 | 江苏润扬通用航空有限公司 | Aircraft aviation data center safety and protection monitoring system and method based on web camera |
CN111372023A (en) * | 2018-12-25 | 2020-07-03 | 杭州海康威视数字技术股份有限公司 | Code stream encryption and decryption method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070113242A1 (en) * | 2005-11-16 | 2007-05-17 | Fetkovich John E | Selective post-processing of compressed digital video |
CN101360228A (en) * | 2008-09-08 | 2009-02-04 | 北京中星微电子有限公司 | Image compression method and video monitoring system for video monitoring system |
CN101867750A (en) * | 2010-06-07 | 2010-10-20 | 杭州华三通信技术有限公司 | OSD information processing method and device for video monitoring system |
CN102469344A (en) * | 2010-11-16 | 2012-05-23 | 腾讯科技(深圳)有限公司 | Video stream encryption and decryption method, video stream encryption and decryption device, communication terminal and storage terminal |
CN103324919A (en) * | 2013-06-25 | 2013-09-25 | 郑州吉瑞特电子科技有限公司 | Video monitoring system based on face recognition and data processing method thereof |
-
2014
- 2014-08-26 CN CN201410424087.5A patent/CN104159116B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070113242A1 (en) * | 2005-11-16 | 2007-05-17 | Fetkovich John E | Selective post-processing of compressed digital video |
CN101360228A (en) * | 2008-09-08 | 2009-02-04 | 北京中星微电子有限公司 | Image compression method and video monitoring system for video monitoring system |
CN101867750A (en) * | 2010-06-07 | 2010-10-20 | 杭州华三通信技术有限公司 | OSD information processing method and device for video monitoring system |
CN102469344A (en) * | 2010-11-16 | 2012-05-23 | 腾讯科技(深圳)有限公司 | Video stream encryption and decryption method, video stream encryption and decryption device, communication terminal and storage terminal |
CN103324919A (en) * | 2013-06-25 | 2013-09-25 | 郑州吉瑞特电子科技有限公司 | Video monitoring system based on face recognition and data processing method thereof |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105611209A (en) * | 2015-12-23 | 2016-05-25 | 天津天地伟业数码科技有限公司 | Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file |
CN106534151A (en) * | 2016-11-29 | 2017-03-22 | 北京旷视科技有限公司 | Method and device for playing video streams |
CN106534151B (en) * | 2016-11-29 | 2019-12-03 | 北京旷视科技有限公司 | For playing the method and device of video flowing |
CN108200395A (en) * | 2018-01-05 | 2018-06-22 | 贵州远诚自控科技有限公司 | Unattended Sewage Disposal based on the processing of equipment operation image video |
CN109040587A (en) * | 2018-08-01 | 2018-12-18 | 北京旷视科技有限公司 | It captures processing method, device, capture mechanism, equipment and storage medium |
CN111372023A (en) * | 2018-12-25 | 2020-07-03 | 杭州海康威视数字技术股份有限公司 | Code stream encryption and decryption method and device |
CN111372023B (en) * | 2018-12-25 | 2023-04-07 | 杭州海康威视数字技术股份有限公司 | Code stream encryption and decryption method and device |
CN109688383A (en) * | 2018-12-29 | 2019-04-26 | 江苏润扬通用航空有限公司 | Aircraft aviation data center safety and protection monitoring system and method based on web camera |
Also Published As
Publication number | Publication date |
---|---|
CN104159116B (en) | 2018-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104159116A (en) | Method of adding face recognition information into H264 video stream | |
HUE034267T2 (en) | Data processing device, data processing method, and program | |
CN102647252A (en) | Serial communication method | |
CN202907302U (en) | A cascade structure of a LED lamp string | |
CN109525370B (en) | Data packet sending method based on zigbee | |
CN106452684A (en) | Self-checking method for IEC61850 report data transmission message | |
CN104935944A (en) | Method and device for coding and decoding video data | |
CN104394415B (en) | A kind of method of video big data distribution decoding | |
CN104601284A (en) | Method, device and system for transmitting data information | |
CN107005497A (en) | The method and apparatus of the signaling and operation of the low latency consumption of media data in MMT | |
CN104079580B (en) | Educational administration's instructional map is as speech recognition system and method | |
CN105376594A (en) | Multi-platform multi-terminal advertisement data synchronously distributing device and system | |
CN105024923B (en) | The method and device that message category based on XMPP extension message is realized | |
CN102968286B (en) | A kind of data transfer tracking, device and system | |
CN109327552A (en) | A kind of wisdom street lamp data transfer management method based on NB-IoT | |
CN104717032A (en) | Coding and decoding method suitable for AFDX network data transparent transmission | |
CN104486625A (en) | Video coding method used for SVAC standard | |
CN105912513A (en) | Fast analytic method of smart substation SCL files | |
CN202276420U (en) | Wireless video monitor system based on H264 | |
EP2985996A1 (en) | Depth information encoding and decoding method, system, and device | |
CN103440548A (en) | Method for converting radio frequency label into two-dimensional codes | |
CN106656853B (en) | The method and device of traffic flow information is extracted under Ethernet chip low-delay mode | |
CN105407351A (en) | Method and apparatus for reconstructing encoding mode from real-time transport protocol packet | |
CN104426978A (en) | Sending method and sending system for shared data of breathing machine | |
CN104009923B (en) | A kind of IPV6 message hardware analytic methods based on pointer iteration |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180202 Termination date: 20180826 |
|
CF01 | Termination of patent right due to non-payment of annual fee |