CN105611209A - Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file - Google Patents
Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file Download PDFInfo
- Publication number
- CN105611209A CN105611209A CN201510972517.1A CN201510972517A CN105611209A CN 105611209 A CN105611209 A CN 105611209A CN 201510972517 A CN201510972517 A CN 201510972517A CN 105611209 A CN105611209 A CN 105611209A
- Authority
- CN
- China
- Prior art keywords
- face
- nvr
- video
- human face
- retrieval
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/765—Interface circuits between an apparatus for recording and another apparatus
- H04N5/77—Interface circuits between an apparatus for recording and another apparatus between a recording apparatus and a television camera
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Television Signal Processing For Recording (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a human face retrieving and snapshooting method based on an NVR (Network Video Recorder) video file, which comprises the following steps that: a front end IPC (Information Processing Center) carries out video acquisition and intelligent human face analysis, inserts a human face detection result into real-time code stream data, and storing the human face detection result in a video of an NVR device; a user sends a retrieval request by an interface module of the NVR device, and a main program module carries out video inquiry and file retrieval according to the request and sends a processing result to the interface module to display for the user; and the interface module sends a snapshooting request, the main program module processes and cuts a snapshot picture as required according to human face information and stores the snapshot picture, and the user plays the video of a time point by clicking the picture. According to the human face retrieving and snapshooting method based on the NVR video file, which is disclosed by the invention, retrieval and snapshooting on the human face information in an nvr video can be achieved without depending on real-time code stream information, primary screening and positioning of the human face information are completed, a workload of inquiring face features of personnel in the video is greatly reduced, and practicality of a human face detection technology is greatly promoted.
Description
Technical field
The present invention relates to protection and monitor field, relate in particular to a kind of face retrieval and grasp shoot method based on NVR video file.
Background technology
Embedded NVR(NetworkVideoRecorder is network hard disk video recorder) Core Feature of kind equipment is storage, NVR equipment is web camera by the ipc(IPcamera of self link) code stream that spreads out of of front end is converted into the video record file of storing on NVR local disk, as video file data, inquire about and have access to for user.
Recognition of face is one of main algorithm of supporting in embedded NVR kind equipment intellectual analysis, can be in the identified region of setting, and the face picture that initiative recognition occurs.
In embedded nvr kind equipment, traditional intellectual analysis face algorithmic technique is all generally based on real-time code stream, real-time analysis, Realtime Alerts, the similar line of mixing, circumference, invasion, leaves the post etc., report to the police and trigger the various subsequent actions of rear interlock, as: interlock sound, capture video recording, port output etc., do like this problem existing and be:
1. face testing result is not directly perceived: because algorithm is only analyzed real-time code stream, testing result flashes across, and from user perspective, analysis result is intuitively not easy-to-use.
2. do not support face key area to capture: if user need to preserve the face information detecting, the result of traditional intelligence analysis is not supported to preserve, directly use the result detecting to cause very large obstacle to user.
3. can not retrieve: the result of intellectual analysis is not supported to preserve, if user wants to check personnel's facial characteristics of appearance in a large amount of video record files, workload is large, and efficiency is very low.
4. can not accurately locate: can not be positioned video file based on face testing result.
Summary of the invention
For addressing the above problem, the scheme providing of the present invention is:
A kind of face retrieval and grasp shoot method based on NVR video file of the present invention, comprises the steps:
A front end IPC carries out video acquisition and Intelligent human-face analysis, face testing result is inserted in real-time bit stream data, and face testing result is kept in the video recording of NVR equipment;
The interface module of party B-subscriber by NVR equipment sends retrieval request, and main program module record a video and inquired about and document retrieval according to request, and result is sent to interface module presents to user;
C interface module sends the request of candid photograph, and main program module is captured picture and cuts out according to face information processing according to request, and preserves and capture picture, and user is by clicking the video recording of this time point of picture playing.
Advantage and good effect that the present invention has are:
The present invention can not rely on real-time code stream information and realize face information retrieval and candid photograph in nvr video record, Preliminary screening and the location of face information are completed, reduce greatly the workload of personnel query facial characteristics in video recording, the practicality of human face detection tech is promoted greatly.
Brief description of the drawings
Fig. 1 is flow chart of the present invention;
Fig. 2 is interface module of the present invention and main program module workflow diagram.
Detailed description of the invention
Referring to drawings and Examples, face retrieval and the grasp shoot method based on NVR video file of the present invention is described in detail.
Face retrieval based on NVR video file and grasp shoot method, is characterized in that as shown in Figure 1, comprises the steps:
A front end IPC carries out video acquisition and Intelligent human-face analysis, face testing result is inserted in real-time bit stream data, and face testing result is kept in the video recording of NVR equipment;
The interface module of party B-subscriber by NVR equipment sends retrieval request, and main program module record a video and inquired about and document retrieval according to request, and result is sent to interface module presents to user;
C interface module sends the request of candid photograph, and main program module is captured picture and cuts out according to face information processing according to request, and preserves and capture picture, and user is by clicking the video recording of this time point of picture playing.
The retrieval request that described step B median surface module sends comprises time period and channel information.
In described step B, result comprises time point and the positional information of face in picture that face detected.
In described step C, the request of capturing comprises time point and the positional information of face in picture that face detected.
In described step C, tailoring process is according to the area size that face detected.
In embedded NVR kind equipment, in conjunction with the Intelligent human-face analysis of front end IPC, face testing result is inserted in real-time bit stream data. Make in the video recording of NVR equipment to be able to face testing result to be preserved.
This specific embodiment adopts front end IPC equipment to carry out video acquisition, in front end IPC equipment, also there is Intelligent human-face analytic function simultaneously, in video acquisition, video is carried out to Intelligent human-face analysis, the result that face is detected is inserted among real-time bit stream data, bit stream data is transmitted through the network to NVR equipment in real time, NVR equipment is kept at video data and Intelligent human-face analysis data in video file simultaneously, and described video data can be also that multichannel is recorded a video simultaneously for single channel.
In embedded nvr kind equipment, there is interface module and main program module, interface module can be used for man-machine interaction, user sets after face search time and passage in interface module, face in video record file in main program module search local disk detects information, and the time point that occurs face in video monitoring process is presented to user, user can inquire about video file by the time point that occurs face.
Embedded nvr kind equipment to occurring that the precise region that the face picture of time point of face arrives according to recognition of face implements to capture, saves as the form of picture by automatically, clicks picture and can be positioned to video time point and play. Because the video record file navigating to is full-scale picture, now to carry out cutting to picture according to the region in face information, then capture and be stored as picture file.
Claims (5)
1. the face retrieval based on NVR video file and a grasp shoot method, is characterized in that, comprises the steps:
A front end IPC carries out video acquisition and Intelligent human-face analysis, face testing result is inserted in real-time bit stream data, and face testing result is kept in the video recording of NVR equipment;
The interface module of party B-subscriber by NVR equipment sends retrieval request, and main program module record a video and inquired about and document retrieval according to request, and result is sent to interface module presents to user;
C interface module sends the request of candid photograph, and main program module is captured picture and cuts out according to face information processing according to request, and preserves and capture picture, and user is by clicking the video recording of this time point of picture playing.
2. face retrieval and the grasp shoot method based on NVR video file according to claim 1, is characterized in that: the retrieval request that described step B median surface module sends comprises time period and channel information.
3. face retrieval and the grasp shoot method based on NVR video file according to claim 1, is characterized in that: in described step B, result comprises time point and the positional information of face in picture that face detected.
4. face retrieval and the grasp shoot method based on NVR video file according to claim 1, is characterized in that: in described step C, the request of capturing comprises time point and the positional information of face in picture that face detected.
5. face retrieval and the grasp shoot method based on NVR video file according to claim 1, is characterized in that: in described step C, tailoring process is according to the area size that face detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510972517.1A CN105611209A (en) | 2015-12-23 | 2015-12-23 | Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510972517.1A CN105611209A (en) | 2015-12-23 | 2015-12-23 | Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105611209A true CN105611209A (en) | 2016-05-25 |
Family
ID=55990717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510972517.1A Pending CN105611209A (en) | 2015-12-23 | 2015-12-23 | Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105611209A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263613A (en) * | 2019-04-25 | 2019-09-20 | 深圳市商汤科技有限公司 | Monitor video processing method and processing device |
| CN111079633A (en) * | 2019-12-12 | 2020-04-28 | 天地伟业技术有限公司 | Method for managing face recognition machine by embedded common NVR (network video recorder) equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101196990A (en) * | 2007-10-11 | 2008-06-11 | 北京海鑫科金高科技股份有限公司 | Network built-in type multiplex face detecting system and method thereof |
| CN102665036A (en) * | 2012-05-10 | 2012-09-12 | 江苏友上科技实业有限公司 | High-definition three-in-one network video recorder system |
| CN103049460A (en) * | 2011-10-17 | 2013-04-17 | 天津市亚安科技股份有限公司 | Video surveillance scene information classifying and storing method and search method |
| US20130177219A1 (en) * | 2010-10-28 | 2013-07-11 | Telefonaktiebolaget L M Ericsson (Publ) | Face Data Acquirer, End User Video Conference Device, Server, Method, Computer Program And Computer Program Product For Extracting Face Data |
| CN103824064A (en) * | 2014-03-11 | 2014-05-28 | 深圳市中安视科技有限公司 | Huge-amount human face discovering and recognizing method |
| CN104159116A (en) * | 2014-08-26 | 2014-11-19 | 江苏瑞奥风软件科技有限公司 | Method of adding face recognition information into H264 video stream |
-
2015
- 2015-12-23 CN CN201510972517.1A patent/CN105611209A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101196990A (en) * | 2007-10-11 | 2008-06-11 | 北京海鑫科金高科技股份有限公司 | Network built-in type multiplex face detecting system and method thereof |
| US20130177219A1 (en) * | 2010-10-28 | 2013-07-11 | Telefonaktiebolaget L M Ericsson (Publ) | Face Data Acquirer, End User Video Conference Device, Server, Method, Computer Program And Computer Program Product For Extracting Face Data |
| CN103049460A (en) * | 2011-10-17 | 2013-04-17 | 天津市亚安科技股份有限公司 | Video surveillance scene information classifying and storing method and search method |
| CN102665036A (en) * | 2012-05-10 | 2012-09-12 | 江苏友上科技实业有限公司 | High-definition three-in-one network video recorder system |
| CN103824064A (en) * | 2014-03-11 | 2014-05-28 | 深圳市中安视科技有限公司 | Huge-amount human face discovering and recognizing method |
| CN104159116A (en) * | 2014-08-26 | 2014-11-19 | 江苏瑞奥风软件科技有限公司 | Method of adding face recognition information into H264 video stream |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263613A (en) * | 2019-04-25 | 2019-09-20 | 深圳市商汤科技有限公司 | Monitor video processing method and processing device |
| CN111079633A (en) * | 2019-12-12 | 2020-04-28 | 天地伟业技术有限公司 | Method for managing face recognition machine by embedded common NVR (network video recorder) equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210042533A1 (en) | Inmate tracking system in a controlled environment | |
| CN101631237B (en) | Video monitoring data storing and managing system | |
| CN101299812B (en) | Method, system for analyzing, storing video as well as method, system for searching video | |
| CN102244774B (en) | There is the surveillance of immediate data storehouse service memory | |
| US20160019426A1 (en) | Method of video analysis | |
| CN101692706B (en) | Intelligent storage equipment for security monitoring | |
| CN103260010B (en) | Intelligent skynet rapid video retrieval system | |
| WO2014106384A1 (en) | Method, apparatus and video monitoring system for providing monitoring video information | |
| WO2007111966A3 (en) | System for pruning video data, and application thereof | |
| EP1482736A3 (en) | Method and system for media playback architecture | |
| CN101764998A (en) | Alarm interlocking method in network video monitoring system and network video monitoring system | |
| CN101860731A (en) | Video information processing method, system and server | |
| CN110290346B (en) | Bidding video acquisition method based on intelligent video analysis | |
| CN102572215A (en) | City-class visual video analysis method and server | |
| CN104883548A (en) | Monitoring-video face-capturing processing method and system | |
| CN104284162A (en) | Video retrieval method and system | |
| CN112232211A (en) | Intelligent video monitoring system based on deep learning | |
| EP1150503A3 (en) | Signal processing device and signal processing method | |
| CN102067589A (en) | Digital video recorder system and operating method thereof | |
| WO2018024165A1 (en) | Method and device for storing warning image | |
| CN102143351A (en) | Surveillance video positioning method, image capturing method, device and system | |
| CN105611209A (en) | Human face retrieving and snapshooting method based on NVR (Network Video Recorder) video file | |
| CN105245845A (en) | Method for controlling camera to follow and shoot automatically based on gathering trend in match field | |
| CN102547221A (en) | Video recording and network transmitting method based on motion detection | |
| CN114926757A (en) | Method and system for retrieving lost article, electronic equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160525 |
|
| RJ01 | Rejection of invention patent application after publication |