CN112884796A - Background group removing system based on multi-image intelligent identification - Google Patents
Background group removing system based on multi-image intelligent identification Download PDFInfo
- Publication number
- CN112884796A CN112884796A CN202110043867.5A CN202110043867A CN112884796A CN 112884796 A CN112884796 A CN 112884796A CN 202110043867 A CN202110043867 A CN 202110043867A CN 112884796 A CN112884796 A CN 112884796A
- Authority
- CN
- China
- Prior art keywords
- module
- background
- image
- main body
- image storage
- 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
- 230000005540 biological transmission Effects 0.000 claims abstract description 30
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 13
- 230000001502 supplementing effect Effects 0.000 claims description 7
- 239000013589 supplement Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G06T5/77—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The invention discloses a background group removing system based on multi-image intelligent identification. The background group removing system based on multi-image intelligent identification is characterized in that when the background group removing system is used, firstly, a high-frequency photographing module of an image acquisition terminal performs high-frequency photographing on a target main body to form a large number of continuous photos, the photos are temporarily stored in an image storage module of the image acquisition terminal, and the acquired data stored in the image storage module is transmitted to an artificial intelligent identification terminal by the image acquisition terminal through a data transmission module of the image acquisition terminal after the high-frequency photographing module detects the high-frequency photos. The artificial intelligence intelligent recognition terminal receives the data through the data transmission module contained in the artificial intelligence intelligent recognition terminal, stores the data in the image storage module of the artificial intelligence recognition terminal, and then intelligently recognizes and judges background crowds which are not shot targets in the multi-image data, and screens out scene backgrounds in multiple data.
Description
Technical Field
The invention relates to the field of photographing, in particular to a background group removing system based on multi-image intelligent identification.
Background
A photo is a picture of a person or object made by exposing a photographic paper to light and then developing and fixing the exposed paper. Photographing is also called photographing, photography, and generally refers to a process of exposing a photosensitive medium to light reflected by an object, and a mechanical camera or a digital camera is generally used. With the popularization of smart phones, the use of mobile phones to take pictures and record life is becoming more popular.
However, in the conventional photographing technology, under the condition that the background has a large amount of people and sundries, a large amount of other passersby are usually included in a photographed photo, and the photo needs to be repaired in the later period so as to reduce the influence of a background crowd on a photographing main body, so that a background crowd removing system is provided to solve the problem of the influence of the background crowd.
Disclosure of Invention
The invention aims to provide a background group removing system based on multi-image intelligent identification, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a background group removing system based on multi-image intelligent identification comprises an image acquisition terminal, an artificial intelligent identification terminal and a computing terminal, wherein the image acquisition terminal comprises a high-frequency photographing module, an image storage module and a data transmission module, the high-frequency photographing module is electrically connected with the image storage module through a lead, the image storage module is electrically connected with the data transmission module through a lead, the artificial intelligent identification terminal comprises a data transmission module, an image storage module, a background identification module and a main body identification module, the data transmission module is electrically connected with the image storage module through a lead, the image storage module is simultaneously electrically connected with the background identification module and the main body identification module through leads, the computing terminal comprises a background supplementing module, a background blurring processing module, a main body background combination module, an image storage module and a data transmission module, the background supplement module, the background fuzzification processing module and the main body background combination module are electrically connected with the image storage module through leads, the image storage module is electrically connected with the data transmission module through leads, and the image acquisition terminal and the artificial intelligence recognition terminal are wirelessly connected with the computing terminal through the data transmission module.
As a further scheme of the invention: the data transmission modules are all 4G modules and used for wirelessly transmitting data, and the image storage modules are all used for storing image data.
As a still further scheme of the invention: the high-frequency photographing module is used for instantly acquiring images for multiple times.
As a still further scheme of the invention: the background identification module is used for identifying the effective background of each picture through multi-picture comparison, and the main body identification module is used for identifying the photographing main body through multi-picture comparison.
As a still further scheme of the invention: the background blurring processing module is used for blurring the outer part of the photo main body, the background supplementing module is used for combining and overlapping all backgrounds identified by the background identification module, and the main body background combining module is used for combining and overlapping the backgrounds and the main body.
Compared with the prior art, the invention has the beneficial effects that:
the invention uses the cooperation of the image acquisition terminal, the artificial intelligence recognition terminal and the calculation terminal, thereby judging and distinguishing the background crowd of the non-photographed target through the artificial intelligence recognition system through a plurality of continuously shot image data, supplementing scene data to the removed background crowd through the artificial intelligence operation, realizing the automatic background crowd removing effect, wherein, the main shot target is recognized through the size, the motion speed and the facial feature of the person, and the background crowd is removed through the mode of combining the interframe difference, the non-main body blurring and the image style repairing, thereby obtaining the blurred main body picture and the background picture of the single main body, thereby leading the background crowd removing system based on the multi-image intelligence recognition to integrate and rapidly process the shot image through the arrangement of a high-frequency shooting camera and an artificial intelligence recognition processing system, the effect of removing background non-target people is achieved.
Drawings
Fig. 1 is a schematic diagram of an operation structure of a background group removing system based on multi-image intelligent recognition.
Fig. 2 is a block diagram of an image acquisition terminal in a background group removal system based on multi-image intelligent recognition.
Fig. 3 is a block diagram of an artificial intelligence recognition terminal in a background group removal system based on multi-image intelligent recognition.
Fig. 4 is a block diagram of a computing terminal in a background group removing system based on multi-image intelligent recognition.
Fig. 5 is a system block diagram in a background group removing system based on multi-image intelligent recognition.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 5, in an embodiment of the present invention, a background group removing system based on multi-image intelligent recognition includes an image collecting terminal, an artificial intelligent recognition terminal and a computing terminal, wherein the image collecting terminal includes a high-frequency photographing module, an image storage module and a data transmission module, the high-frequency photographing module is electrically connected to the image storage module through a wire, the image storage module is electrically connected to the data transmission module through a wire, the artificial intelligent recognition terminal includes a data transmission module, an image storage module, a background recognition module and a main body recognition module, the data transmission module is electrically connected to the image storage module through a wire, the image storage module is simultaneously electrically connected to the background recognition module and the main body recognition module through a wire, the computing terminal includes a background supplementing module, a background blurring processing module, a main body background combining module, a background combining module, the image acquisition terminal and the artificial intelligence recognition terminal are wirelessly connected with the computing terminal through the data transmission module.
The data transmission modules are all 4G modules and used for wireless transmission of data, the image storage modules are all used for storing image data, and the data of the terminal is stored so as to facilitate the output and the receiving of the data transmission modules.
The high-frequency photographing module is used for instantly acquiring images for multiple times to form the effect of multiple pictures in the same scene, so that the scene can be conveniently integrated and filled in the later period.
The background recognition module is used for recognizing the effective background of each picture through multi-picture comparison, so that later-stage integration and filling are facilitated, and the main body recognition module is used for recognizing the photographing main body through multi-picture comparison, so that the background recognition module can recognize the background conveniently.
The background blurring processing module is used for blurring the outer part of the main body of the photo to form a main body photo of a blurring background, the background supplementing module is used for combining and overlapping all backgrounds recognized by the background recognition module to form a complete single background, a large number of pedestrians are prevented from being contained in the photo, the main body cannot be completely embodied, and the main body background combining module is used for combining the backgrounds and the main body in a superposition mode, so that a complete main body background photo is formed.
The working principle of the invention is as follows:
during the use, at first the high-frequency of image acquisition terminal shoots the module and carries out the high-frequency to the target subject, forms a large amount of continuity photos to store the photo temporarily in image storage module at image acquisition terminal, visit back image acquisition terminal and carry the collection data that image storage module stored to artificial intelligence identification terminal through its data transmission module of self. The artificial intelligent recognition terminal receives data through a data transmission module contained in the artificial intelligent recognition terminal and stores the data in an image storage module of the artificial intelligent recognition terminal, then the background recognition module intelligently recognizes and judges background crowds which are not shot targets in the multi-image data and screens out scene backgrounds in multiple data, and meanwhile, the main body recognition module recognizes a main body through face recognition and size comparison; carrying out multi-figure alignment according to the main body; the difference value of subtracting the multiple pictures is used for judging which numerical values are relatively unchanged and which numerical values are changed, so that the unchanged scenes and the scenes which change rapidly in the corresponding images are distinguished and correspond to the main body and the background crowd, the background crowd which needs to be removed is judged, and the corresponding pixels are subtracted, at the moment, the artificial intelligent identification terminal identifies a plurality of background pictures with defects and complete main body pictures, and then the artificial intelligent identification terminal conveys the background pictures, the main body pictures and the received original pictures which are identified to the computing terminal through the data transmission module of the artificial intelligent identification terminal. The computing terminal receives data through a data transmission module of the computing terminal, the received data are stored in an image storage module of the computing terminal, at the moment, a background blurring module performs background blurring processing on collected original data of the image collecting terminal to form a background blurring picture, meanwhile, a background supplementing module performs comprehensive supplementation on a background picture with defects to form a complete background, and meanwhile, a main body background combining module combines the formed background and a main body to form a main body background picture.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention can be made without departing from the spirit and scope of the invention.
Claims (5)
1. The utility model provides a background crowd gets rid of system based on many image intelligent recognition, includes image acquisition terminal, artificial intelligence identification terminal and computational terminal, its characterized in that: the image acquisition terminal comprises a high-frequency photographing module, an image storage module and a data transmission module, wherein the high-frequency photographing module is electrically connected with the image storage module through a lead, the image storage module is electrically connected with the data transmission module through a lead, the artificial intelligent identification terminal comprises a data transmission module, an image storage module, a background identification module and a main body identification module, the data transmission module is electrically connected with the image storage module through a lead, the image storage module is simultaneously electrically connected with the background identification module and the main body identification module through leads, the computing terminal comprises a background supplement module, a background blurring processing module, a main body background combination module, an image storage module and a data transmission module, the background supplement module, the background blurring processing module and the main body background combination module are electrically connected with the image storage module through leads, the image storage module is electrically connected with the data transmission module through a wire, and the image acquisition terminal and the artificial intelligence recognition terminal are both in wireless connection with the computing terminal through the data transmission module.
2. The background group removing system based on multi-image intelligent recognition according to claim 1, wherein: the data transmission modules are all 4G modules and used for wirelessly transmitting data, and the image storage modules are all used for storing image data.
3. The background group removing system based on multi-image intelligent recognition according to claim 1, wherein: the high-frequency photographing module is used for instantly acquiring images for multiple times.
4. The background group removing system based on multi-image intelligent recognition according to claim 1, wherein: the background identification module is used for identifying the effective background of each picture through multi-picture comparison, and the main body identification module is used for identifying the photographing main body through multi-picture comparison.
5. The background group removing system based on multi-image intelligent recognition according to claim 1, wherein: the background blurring processing module is used for blurring the outer part of the photo main body, the background supplementing module is used for combining and overlapping all backgrounds identified by the background identification module, and the main body background combining module is used for combining and overlapping the backgrounds and the main body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110043867.5A CN112884796A (en) | 2021-01-13 | 2021-01-13 | Background group removing system based on multi-image intelligent identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110043867.5A CN112884796A (en) | 2021-01-13 | 2021-01-13 | Background group removing system based on multi-image intelligent identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112884796A true CN112884796A (en) | 2021-06-01 |
Family
ID=76045625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110043867.5A Pending CN112884796A (en) | 2021-01-13 | 2021-01-13 | Background group removing system based on multi-image intelligent identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112884796A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023087215A1 (en) * | 2021-11-18 | 2023-05-25 | Citrix Systems, Inc. | Online meeting non-participant detection and remediation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10147216B1 (en) * | 2017-11-01 | 2018-12-04 | Essential Products, Inc. | Intelligent camera |
| CN109769094A (en) * | 2019-02-14 | 2019-05-17 | 任奕洁 | Scenery photo beautification method based on artificial intelligence |
| US20200380697A1 (en) * | 2017-03-31 | 2020-12-03 | Sony Semiconductor Solutions Corporation | Image processing device, imaging device, image processing method, and program |
-
2021
- 2021-01-13 CN CN202110043867.5A patent/CN112884796A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200380697A1 (en) * | 2017-03-31 | 2020-12-03 | Sony Semiconductor Solutions Corporation | Image processing device, imaging device, image processing method, and program |
| US10147216B1 (en) * | 2017-11-01 | 2018-12-04 | Essential Products, Inc. | Intelligent camera |
| CN109769094A (en) * | 2019-02-14 | 2019-05-17 | 任奕洁 | Scenery photo beautification method based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 秦爱梅;丁雨;: "基于人工智能视觉的特定场景识别系统设计", 现代电子技术, no. 10 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023087215A1 (en) * | 2021-11-18 | 2023-05-25 | Citrix Systems, Inc. | Online meeting non-participant detection and remediation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116582741B (en) | Shooting method and equipment | |
| CN110198417A (en) | Image processing method, device, storage medium and electronic equipment | |
| WO2019237992A1 (en) | Photographing method and device, terminal and computer readable storage medium | |
| CN110445988A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN107948514B (en) | Image blurs processing method, device, mobile device and computer storage medium | |
| CN111447374B (en) | Light supplement adjusting method and device, electronic equipment and storage medium | |
| CN107948500A (en) | Image processing method and device | |
| WO2022141376A1 (en) | Posture estimation method related apparatus | |
| CN108093158B (en) | Image blurring processing method and device, mobile device and computer readable medium | |
| CN111339831B (en) | Lighting lamp control method and system | |
| WO2022141445A1 (en) | Image processing method and device | |
| CN107392192A (en) | A kind of personal identification method, device and multi-cam module | |
| CN110445989A (en) | Image processing method, device, storage medium and electronic equipment | |
| WO2022141477A1 (en) | Image processing method and device | |
| CN109618102B (en) | Focusing processing method and device, electronic equipment and storage medium | |
| CN115086567B (en) | Time delay photographing method and device | |
| WO2023217046A1 (en) | Image processing method and apparatus, nonvolatile readable storage medium and electronic device | |
| CN113810590A (en) | Image processing method, electronic device, medium, and system | |
| CN112802033A (en) | Image processing method and device, computer readable storage medium and electronic device | |
| CN112884796A (en) | Background group removing system based on multi-image intelligent identification | |
| CN108282616B (en) | Processing method, device, storage medium and the electronic equipment of image | |
| CN113298735A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN116055895B (en) | Image processing method and device, chip system and storage medium | |
| CN116095476B (en) | Camera switching method and device, electronic equipment and storage medium | |
| CN110837771A (en) | Bird identification method and device based on convolutional neural network |
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 |