CN111597385A - Video archive processing method and system based on portrait recognition - Google Patents
Video archive processing method and system based on portrait recognition Download PDFInfo
- Publication number
- CN111597385A CN111597385A CN202010376523.1A CN202010376523A CN111597385A CN 111597385 A CN111597385 A CN 111597385A CN 202010376523 A CN202010376523 A CN 202010376523A CN 111597385 A CN111597385 A CN 111597385A
- Authority
- CN
- China
- Prior art keywords
- video
- information
- person
- personnel
- identification
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims description 15
- 230000001815 facial effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 1
Images
Classifications
-
- 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
- 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
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- 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
- G06F16/787—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a video archive processing method based on portrait recognition, which comprises the following steps: s100: establishing a personnel information base, and inputting related information of personnel into the personnel information base; s200: acquiring video information of a public area through a video acquisition system; s300: monitoring video information acquired by a video acquisition system through an image identification device, and identifying the face of a person by the image identification device if the image identification device detects that the face of the person appears in the video information, and matching corresponding person information; s400: the image recognition device automatically identifies the video appearing in the person, and generates a video file by the identification information and the original video; or the image recognition device automatically identifies and clips the video in which the person appears to generate a video file in human units. The video recording system can record working conditions, learning conditions and the like of personnel in a video mode, and stores video information as files, so that the video recording system has remarkable commemorative significance.
Description
Technical Field
The invention relates to a video archive processing method based on portrait recognition, and belongs to the technical field of archive management.
Background
The archive is a directly formed history. The 'direct forming' indicates that the file inherits the originality of the file, and the 'history record' indicates that the file inherits the originality of the file and also inherits the recordability of the file, and is an original document for reproducing the real face of the history. Just because the archive inherits the original recordability of the file and has the historical reproducibility, the archive has the important attribute of the voucher value and is distinguished from book information and cultural relics.
At present, files of school students and party administrative enterprises and public institutions staff are mainly written, paper files and electronic files are provided, and the content of the files capable of being recorded is very limited, and only some basic information and major events can be recorded. With the change of information technology, the rapid development of smart cities, education and medical treatment, a large amount of audio and video information is generated in the future, and the information is filed to form a video archive set, so that the method has great significance.
Disclosure of Invention
The invention aims to provide a video archive processing method based on portrait recognition, which can record the working condition, the learning condition, the living condition and the like of personnel in a video mode, store video information as an archive and have remarkable commemorative significance.
In order to solve the technical problems, the invention adopts the following technical scheme:
a video archive processing method based on portrait recognition comprises the following steps: s100: establishing a personnel information base, and inputting related information of personnel into the personnel information base; s200: collecting videos of a public area through a video collecting system; s300: detecting video information acquired by a video acquisition system through an image identification device, if the image identification device detects that the face of a person appears in the video, extracting the face image of the person by the image identification device, comparing the extracted face image information of the person with the related information of the person in a person information base one by the image identification device, matching the related information of the person corresponding to the extracted face image information, and associating the person in the video with the person in the person information base;
s400: the image recognition device automatically identifies the video appearing in the person, performs virtual slicing on the video, and generates a video file by the identification information and the original video; or the image recognition device automatically identifies and clips the video presented by the person to generate a video file taking the person as a unit;
s500: and archiving the video archive in the step S400 to generate a video archive library.
In the video archive processing method based on portrait recognition, the identification information includes shooting date, name, gender, start time, end time, duration, location, scene, event, and video title, and is automatically stored in descending order by default with the shooting date and time as a keyword, and the priority of the keyword in the identification information can be manually set.
In the video archive processing method based on portrait recognition, the identification method specifically includes: respectively marking according to the times of the people appearing in the video, taking the first frame of picture of a certain person as the starting time of the mark, taking the last frame of picture of the certain person as the ending time of the mark, and calculating the continuous appearing time of the certain person. The start and end times of the identification may be set manually.
In the video archive processing method based on portrait recognition, the video is further operated, the start part and the stop part of the identification are virtually sliced, a piece of complete identification information is generated by combining the video address identification and the personnel information base, the identification information and the video are associated, and the identification information and the video are stored in the corresponding identification base.
In the video archive processing method based on portrait recognition, the video is further operated, the start part and the stop part of the identification are clipped, a complete identification information is formed by combining the video address and the related information of the corresponding personnel, and the identification information and the clipped video are associated and stored in the corresponding identification library and the corresponding personnel video archive.
The video archive processing method based on portrait recognition further comprises the following steps: combining all virtual slices corresponding to the same date and the same event of the same person into one virtual slice according to the time sequence, realizing continuous playing of a plurality of segments, and associating corresponding identification information; and combining all the clipped videos corresponding to the same date and the same event of the same person into one video according to the time sequence, generating an independent file, realizing continuous playing and storage, and associating corresponding identification information.
In the video archive processing method based on portrait recognition, the identification library can be used for searching, video information and identification information are searched in a mode of inputting keywords, or searching is carried out through pictures containing facial images of people; the retrieval results are supported to be combined according to the time sequence, and the continuous playing of a plurality of segments is realized; combination rules may also be set.
In the video archive processing method based on portrait identification, the step S300 further includes the following steps: after the image recognition device matches the related information of the person appearing in the video, the image recognition device records the appearance feature of the person, and the video with the appearance feature of the person is automatically identified and/or edited.
In the video archive processing method based on portrait identification, the step S200 further includes the following steps: after the video is collected by the video collection system, the video is automatically identified according to the address displayed by the collected video.
In the video archive processing method based on portrait identification, the step S200 further includes the following steps: s210: intercepting part of pictures in a video acquired by a video acquisition system; s220: analyzing the scene of the captured picture; s230: and automatically identifying the video according to the analysis result of the step S220.
A video archive processing system based on portrait recognition has a video playing function, can live broadcast, replay and order videos, and comprises: the video acquisition system is arranged in the public area and used for acquiring video information of the public area and sending the video information to the video processing system; the video processing system is used for receiving the video information sent by the video acquisition system, the video processing system has a face recognition function, if the face of a person appears in the video, the video processing system matches the face of the person with the person information base to match the person information corresponding to the face of the person with the person information base; the video processing system clips or marks the video with the appearance characteristics of the person, and stores the clipped video into a person video archive corresponding to the clipped video or stores the marks and video information into a video archive; identifying content includes: shooting date, name, gender, start time, end time, duration, location, scene, event, video title; the storage equipment is used for storing a personnel information base and a personnel video archive base, and the personnel information stored in the personnel information base comprises the face information of personnel; the system has a video retrieval function, video information and identification information are retrieved in a mode of inputting keywords, or a picture containing a person face image is retrieved, the person face image and the person face information stored in a person information base are compared and retrieved, and the retrieved video information or identification information is combined into a piece of continuously played video information according to the sequence of shooting time. The public area refers to a campus, an enterprise unit, a public institution unit, a government agency unit, and the like.
Compared with the prior art, the video recording system can record working conditions, learning conditions and the like of personnel in a video mode, and stores video information as files, so that the commemorative significance is remarkable. The technical scheme of the invention is also suitable for enterprise units, public institutions, government institutions and the like.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a schematic diagram of the operation of a virtual slice;
FIG. 3 is a schematic diagram of how a clip operates;
fig. 4 is a schematic diagram of a processing manner of video information.
The invention is further described with reference to the following figures and detailed description.
Detailed Description
Example 1: a video archive processing method based on portrait recognition is applied to a campus environment and comprises the following steps:
s100: establishing a personnel information base, and inputting related information of personnel into the personnel information base; the related information includes: basic information such as personnel name, gender, birth year and month, age, class, photo and the like, and the class and the photo are updated in years.
S200: acquiring video information of a public area through a video acquisition system; the video acquisition system can be arranged in the areas such as classrooms, libraries, academic report halls, meeting rooms and gymnasiums, and the video acquisition device can be a camera with an angle adjusting function so as to acquire videos in a wider range. After the video is collected by the video collecting system, the video information is automatically identified according to the address displayed by the collected video. That is, each camera has a tag that is marked with a location corresponding to the captured video, and then the video is automatically identified according to the tag, such as: the camera collects the image information of the library, and the output video information of the camera is identified as the library.
S300: the video information collected by the video collection system is detected through the image recognition device, if the image recognition device detects that the face of a person appears in the video, the image recognition device extracts the face image of the person, the image recognition device compares the extracted face image information of the person with the related information of the person in the person information base one by one, the related information of the person corresponding to the extracted face image information is matched, and the person in the video is associated with the person in the person information base.
S400: the image recognition device automatically identifies the video appearing in the person, and generates a video file by the identification information and the original video. The specific method comprises the following steps: the video collected by the video collecting system is automatically identified by identifying according to the times of people in the video, the time 1s before the first frame of picture of a certain person is taken as the starting time of the identification, the time for ending the last frame of picture of the person is taken as the ending time of the identification, the continuous appearing time of the person is calculated, and the starting time and the ending time of the identification can also be manually set. The identification information comprises shooting date, name, gender, starting time, ending time, duration, place, scene, event and video title, the shooting date and the shooting time are automatically defaulted and stored as keywords in descending order, and the priority of the keywords in the identification information can be manually set. And virtually slicing the mark start-stop part, generating a piece of complete mark information by combining the video information address mark and the personnel information base, associating the mark information with the video information, and storing the mark information and the video information into a corresponding mark base. After the image recognition device matches the related information of the person appearing in the video, the image recognition device records the appearance characteristics of the person, wherein the appearance characteristics can be facial image information, dressing image information, hair style image information, posture image information and the like of the person, marks the starting time and the ending time of the video where the person appears, and stores all identification information of the person into a corresponding identification library. In this case, the original video is not edited, and the video archive cannot be opened away from the original video.
S500: and archiving the video archive in the step S400 to generate a video archive library. The identification library can be subjected to related operations, for example, all virtual slices corresponding to the same date and the same event of the same person are combined into one virtual slice according to the time sequence, so that a plurality of segments of the same date and the same event are continuously played, and corresponding identification information is associated; or the video information and the identification information are retrieved in a mode of inputting keywords through a retrieval identification library, or the retrieval result is supported to be combined according to the time sequence through retrieving pictures containing the face images of the people, so that the continuous playing of a plurality of segments is realized; combination rules may also be set. Different combination modes are realized through different operations of the identification library, 1 person corresponding to 1 piece of video information, 1 person corresponding to a plurality of pieces of video information, 1 piece of video information corresponding to a plurality of persons and a plurality of pieces of video information corresponding to a plurality of persons can be realized in the same video according to the number of persons appearing in the video, but no independent video file is generated.
S600: and storing the student personnel video archive in the corresponding equipment. When the video archive is watched, a play button under a certain identification information operation field in the identification library is clicked, and videos in the start-stop time period of the identification in the videos collected by the video collection system associated with the identification information are directly played.
Example 2: a video archive processing method based on portrait recognition is applied to a campus environment, and is different from the embodiment 1 in that:
s400: and editing the video of the start-stop part of the mark, combining the video address and the related information of the corresponding personnel to form a piece of complete mark information, associating the mark information with the edited video and storing the associated mark information and the edited video in a corresponding mark library and a corresponding personnel video archive. In this case, the original video is edited, and the video archive can be opened apart from the original video.
S500: and archiving the video archive in the step S400 to generate a video archive library. The identification library can be subjected to related operations, for example, all clipped videos corresponding to the same date and the same event of the same person are combined into one piece of video information according to the time sequence, an independent file is generated, continuous playing is realized, and corresponding identification information is related. Different combination modes are realized through different operations of the identification library, 1 person corresponding to 1 video, 1 person corresponding to a plurality of videos, a plurality of persons corresponding to 1 video and a plurality of persons corresponding to a plurality of videos can be realized by the same video according to the number of people appearing in the video, and an independent video file is generated.
S600: and storing the student personnel video archive in the corresponding equipment. When watching the video file, clicking a play button under a certain identification information operation field in the identification library to directly play the whole video associated with the identification information.
Example 3: a video archive processing method based on portrait recognition is applied to enterprise environment and comprises the following steps:
s100: establishing a personnel information base, and inputting related information of personnel into the personnel information base; the related information includes: basic information such as personnel name, gender, birth year and month, age, department, position, title, specialty, school calendar, school, time of job entry, working age, photo and the like.
S200: acquiring video information of a public area through a video acquisition system; the video acquisition system can be arranged in areas such as offices, meeting rooms and dining halls, and the video acquisition device can be a camera with an angle adjusting function so as to acquire videos in a wider range. The specific steps of step S200 are as follows: s210: intercepting part of pictures in a video acquired by a video acquisition system; s220: analyzing the scene of the captured picture; s230: and automatically identifying the video according to the analysis result of the step S220. For example: the video acquired by the video acquisition system is a scene of a meeting, pictures need to be captured from the video, then the pictures are analyzed, the actions of persons related to the pictures are analyzed, and then a piece of video information related to the meeting is judged according to the information.
S300: detecting video information acquired by a video acquisition system through an image identification device, if the image identification device detects that the face of a person appears in the video, extracting the face image of the person by the image identification device, comparing the extracted face image information of the person with the related information of the person in a person information base one by the image identification device, matching the related information of the person corresponding to the extracted face image information, and associating the person in the video with the person in the person information base;
s400: the image recognition device automatically identifies and clips the video in which the person appears, and generates a video file in units of people. The specific method comprises the following steps: the video information collected by the video collecting system is automatically identified by identifying according to the times of people in the video, the starting time of the identification is 1s before the first frame of picture of a certain person, the ending time of the identification is the last frame of picture of the person, the continuous appearing time of the person is calculated, and the starting time and the ending time of the identification can be manually set. The identification information comprises shooting date, name, gender, starting time, ending time, duration, place, scene, event and video title, the shooting date and the shooting time are automatically defaulted and stored as keywords in descending order, and the priority of the keywords in the identification information can be manually set. And editing the video of the start-stop part of the mark, combining the video address and the related information of the corresponding personnel to form a piece of complete mark information, associating the mark information with the edited video information and storing the associated mark information and the associated personnel video archive. After the image recognition device matches the related information of the person appearing in the video, the image recognition device records the appearance characteristics of the person, wherein the appearance characteristics can be facial image information, dressing image information, hair style image information, posture image information and the like of the person, marks the starting time and the ending time of the video where the person appears, and stores all identification information of the person into a corresponding identification library. In this case, the original video is edited, and the video archive can be opened apart from the original video.
S500: and archiving the video archive in the step S400 to generate a video archive library. The identification library can be subjected to related operations, for example, all clipped videos corresponding to the same date and the same event of the same person are combined into one piece of video information according to the time sequence, an independent file is generated, continuous playing is realized, and corresponding identification information is related. Different combination modes are realized through different operations of the identification library, 1 person corresponding to 1 video, 1 person corresponding to a plurality of videos, a plurality of persons corresponding to 1 video and a plurality of persons corresponding to a plurality of videos can be realized by the same video according to the number of people appearing in the video, and an independent video file is generated.
S600: and storing the student personnel video archive in the corresponding equipment. When watching the video file, clicking a play button under a certain identification information operation field in the identification library to directly play the whole video associated with the identification information.
A video archive processing system based on portrait recognition has a video playing function, can live broadcast, replay and order videos, and comprises: the video acquisition system is arranged in the public area and used for acquiring videos in the public area and sending video information to the video processing system; the video processing system is used for receiving the video information sent by the video acquisition system, the video processing system has a face recognition function, if the face of a person appears in the video, the video processing system matches the face of the person with the person information base to match the person information corresponding to the face of the person with the person information base; the video processing system clips or marks the video with the appearance characteristics of the person, and stores the clipped video into a person video archive corresponding to the clipped video or stores the marks and video information into a video archive; identifying content includes: shooting date, name, gender, start time, end time, duration, location, scene, event, video title; the storage equipment is used for storing a personnel information base and a personnel video archive base, and the personnel information stored in the personnel information base comprises the face information of personnel; the system has a video retrieval function, video information and identification information are retrieved in a mode of inputting keywords, or a picture containing a person face image is retrieved, the person face image and the person face information stored in a person information base are compared and retrieved, and the retrieved video information or identification information is combined into a piece of continuously played video information according to the sequence of shooting time. The public area refers to a campus, an enterprise unit, a public institution unit, a government agency unit, and the like.
Claims (10)
1. A video archive processing method based on portrait recognition is characterized by comprising the following steps:
s100: establishing a personnel information base, and inputting related information of personnel into the personnel information base;
s200: collecting videos of a public area through a video collecting system;
s300: detecting video information acquired by a video acquisition system through an image identification device, if the image identification device detects that the face of a person appears in the video information, extracting facial images of the person by the image identification device, comparing the extracted facial image information of the person with related information of the person in a person information base one by the image identification device, matching the related information of the person corresponding to the extracted facial image information, and associating the person in the video with the person in the person information base;
s400: the image recognition device automatically identifies the video appearing in the person, performs virtual slicing on the video, and generates a video file by the identification information and the original video; or the image recognition device automatically identifies and clips the video presented by the person to generate a video file taking the person as a unit;
s500: and archiving the video archive in the step S400 to generate a video archive library.
2. The method as claimed in claim 1, wherein the identification information comprises a shooting date, a name, a gender, a starting time, an ending time, a duration, a location, a scene, an event, a video title, and the shooting date and time are automatically stored in descending order by default, and the priority of the keywords in the identification information can be manually set.
3. The method for processing a video archive based on face recognition according to claim 1, wherein the identification is performed by: respectively marking according to the times of the people appearing in the video, taking the first frame of picture of a certain person as the starting time of the mark, taking the last frame of picture of the certain person as the ending time of the mark, and calculating the continuous appearing time of the certain person.
4. The method for video archive processing based on face recognition according to claim 1, wherein the following method is adopted for virtually slicing the video: and virtually slicing the mark start-stop part, generating a piece of complete mark information by combining the video address mark and the personnel information base, associating the mark information with the video, and storing the mark information into the corresponding mark base.
5. The method for processing a video archive based on face recognition as claimed in claim 1, wherein the following method is adopted for clipping the video: and editing the start-stop part of the identification, combining the video information address and the related information of the corresponding personnel to form a piece of complete identification information, associating the identification information with the edited video and storing the associated video in a corresponding identification library and a corresponding personnel video archive.
6. The method for video archive processing based on portrait recognition according to claim 4 or claim 5, further comprising the following steps: combining all virtual slices corresponding to the same date and the same event of the same person into one virtual slice according to the time sequence, realizing continuous playing of a plurality of segments, and associating corresponding identification information; and combining all the clipped videos corresponding to the same date and the same event of the same person into one video according to the time sequence, generating an independent file, realizing continuous playing, and associating corresponding identification information.
7. The method of claim 4, wherein the video archive processing based on face recognition comprises: the identification library can be used for searching, video information and identification information are searched in a mode of inputting keywords, or searching is carried out through pictures containing face images of people; the retrieval results are supported to be combined according to the time sequence, and the continuous playing of a plurality of segments is realized; the combination rule can be set automatically; and searching the marked video segments through the keywords, and then playing the video segments according to the time sequence or generating a new video segment and storing the new video segment.
8. The method for processing a video archive based on human image recognition according to claim 4 or 5, wherein the step S300 further comprises the following steps: after the image recognition device matches the related information of the person appearing in the video, the image recognition device records the appearance characteristics of the person and automatically identifies and/or clips the video with the appearance characteristics of the person; the step S200 further includes the following method: after the video is collected by the video collecting system, the video information is automatically identified according to the address displayed by the collected video.
9. The method for processing a video archive based on human image recognition as claimed in claim 1, wherein said step S200 further comprises the steps of:
s210: intercepting part of pictures in a video acquired by a video acquisition system;
s220: analyzing the scene of the captured picture;
s230: and automatically identifying the video according to the analysis result of the step S220.
10. The utility model provides a video archives processing system based on portrait discernment, has the video instant broadcast function, can live, playback, video on demand, its characterized in that includes:
the video acquisition system is arranged in the public area and used for acquiring videos in the public area and sending video information to the video processing system;
the video processing system is used for receiving the video information sent by the video acquisition system, the video processing system has a face recognition function, if the face of a person appears in the video, the video processing system matches the face of the person with the person information base to match the person information corresponding to the face of the person with the person information base;
the video processing system clips or marks the video with the appearance characteristics of the person, and stores the clipped video into a person video archive corresponding to the clipped video or stores the marks and video information into a video archive;
identifying content includes: shooting date, name, gender, start time, end time, duration, location, scene, event, video title;
the storage equipment is used for storing a personnel information base and a personnel video archive base, and the personnel information stored in the personnel information base comprises the face information of personnel;
the system has a video retrieval function, retrieves video information and identification information in a mode of inputting keywords, also can retrieve through pictures containing personnel face images, performs comparison retrieval through the personnel face images and the personnel face information stored in a personnel information base, and combines the retrieved video information or identification information into a continuously played video according to the sequence of shooting time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010376523.1A CN111597385B (en) | 2020-05-07 | 2020-05-07 | Video archive processing method and system based on portrait identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010376523.1A CN111597385B (en) | 2020-05-07 | 2020-05-07 | Video archive processing method and system based on portrait identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111597385A true CN111597385A (en) | 2020-08-28 |
| CN111597385B CN111597385B (en) | 2024-03-29 |
Family
ID=72186901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010376523.1A Active CN111597385B (en) | 2020-05-07 | 2020-05-07 | Video archive processing method and system based on portrait identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111597385B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1975761A (en) * | 2006-12-15 | 2007-06-06 | 昆明利普机器视觉工程有限公司 | Visual frequency data excavating system and method for automatic identifying human figure |
| WO2018126742A1 (en) * | 2017-01-05 | 2018-07-12 | 福建亿榕信息技术有限公司 | Electronic batch processing method and system for stored archives, and storage medium |
| CN109344271A (en) * | 2018-09-30 | 2019-02-15 | 南京物盟信息技术有限公司 | Video portrait records handling method and its system |
| CN111046235A (en) * | 2019-11-28 | 2020-04-21 | 福建亿榕信息技术有限公司 | Method, system, equipment and medium for searching acoustic image archive based on face recognition |
-
2020
- 2020-05-07 CN CN202010376523.1A patent/CN111597385B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1975761A (en) * | 2006-12-15 | 2007-06-06 | 昆明利普机器视觉工程有限公司 | Visual frequency data excavating system and method for automatic identifying human figure |
| WO2018126742A1 (en) * | 2017-01-05 | 2018-07-12 | 福建亿榕信息技术有限公司 | Electronic batch processing method and system for stored archives, and storage medium |
| CN109344271A (en) * | 2018-09-30 | 2019-02-15 | 南京物盟信息技术有限公司 | Video portrait records handling method and its system |
| CN111046235A (en) * | 2019-11-28 | 2020-04-21 | 福建亿榕信息技术有限公司 | Method, system, equipment and medium for searching acoustic image archive based on face recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111597385B (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11195557B2 (en) | Methods, systems, and computer program products for annotating video content with audio information | |
| US8385588B2 (en) | Recording audio metadata for stored images | |
| Jaimes et al. | Memory cues for meeting video retrieval | |
| CN103119595B (en) | Shared by the automatic media hitting by shutter | |
| US9037569B2 (en) | Identifying particular images from a collection | |
| JP3895892B2 (en) | Multimedia information collection management device and storage medium storing program | |
| US20180025215A1 (en) | Anonymous live image search | |
| US20040093349A1 (en) | System for and method of capture, analysis, management, and access of disparate types and sources of media, biometric, and database information | |
| US7813560B2 (en) | Classifying complete and incomplete date-time information | |
| US8836811B2 (en) | Content storage management in cameras | |
| WO2019129075A1 (en) | Video searching method and device and computer readable storage medium | |
| CN105468675A (en) | Picture display system and method combining figure identification and holiday and festival information | |
| CN111860523B (en) | Intelligent recording system and method for sound image files | |
| CN114333005A (en) | Object recognition method, system and storage medium | |
| CN111597385B (en) | Video archive processing method and system based on portrait identification | |
| US20190171653A1 (en) | Method of automating and creating challenges, calls to action, interviews, and questions | |
| Chua et al. | Stratification approach to modeling video | |
| JPH09163276A (en) | Information recording and reproducing device with marking function | |
| US7215833B1 (en) | Method of matching a digital camera image to a database using a timestamp device | |
| JP2006350550A (en) | Album content automatic preparation method and system | |
| JP2002288178A (en) | Multimedia information collection and management device and program | |
| US20080082537A1 (en) | Method and system for collecting sales prospect information | |
| JP6179027B2 (en) | Slide show creation server, user terminal, and slide show creation method | |
| Blighe et al. | MyPlaces: detecting important settings in a visual diary | |
| Amadi | Implementation of Deep Learning in the Application of Lecture Attendance System with Face Recognition Technology Based on OpenCV |
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 |