CN113784114A - Screen projection device for detecting content in real time - Google Patents
Screen projection device for detecting content in real time Download PDFInfo
- Publication number
- CN113784114A CN113784114A CN202110995709.XA CN202110995709A CN113784114A CN 113784114 A CN113784114 A CN 113784114A CN 202110995709 A CN202110995709 A CN 202110995709A CN 113784114 A CN113784114 A CN 113784114A
- Authority
- CN
- China
- Prior art keywords
- screen
- content
- deep learning
- projection device
- screen projection
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 238000011897 real-time detection Methods 0.000 claims abstract 2
- 238000013135 deep learning Methods 0.000 claims description 33
- 230000002159 abnormal effect Effects 0.000 abstract description 12
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 238000010801 machine learning Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000005549 size reduction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009323 psychological health Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/4302—Content synchronisation processes, e.g. decoder synchronisation
- H04N21/4307—Synchronising the rendering of multiple content streams or additional data on devices, e.g. synchronisation of audio on a mobile phone with the video output on the TV screen
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
The utility model provides a throw screen device of real-time detection content, throw the screen device and be used for receiving and wait to throw the screen picture, throw the screen device and can be connected with display device data transmission, throw the screen device and be used for will waiting to throw the screen picture and send display device to show, throw the screen device still including the degree of depth study detection module, degree of depth study detection module is used for treating and throws the screen picture and detect to shield or not send corresponding content to display device with corresponding content when detecting predetermined content. Through the technical scheme, the video stream passing through the screen projector can be subjected to content detection by utilizing the technical scheme of integrating the machine learning algorithm in the screen projector, so that abnormal pictures in the video stream can be filtered, and a data flow path displayed by the display device for the abnormal pictures is shielded.
Description
Technical Field
The invention relates to the field of video processing, in particular to a device for improving screen projection content security.
Background
The existing screen projection products, no matter professional usb screen projectors or screen projection functions of mobile phones, can only project contents out intact and do not have the functions of content detection and content filtering. If the contents of horror, bloody smell and pornography appear in the contents of screen projection, serious social influence can be caused. And meanwhile, the physical and psychological health of the viewer is not facilitated.
Disclosure of Invention
Therefore, it is desirable to provide a device and method capable of processing images, which can achieve the technical effect of avoiding abnormal images in the images projected by the screen projection device.
In order to achieve the above object, the inventor provides a screen projection device for detecting content in real time, the screen projection device is used for receiving a screen to be projected, the screen projection device can be in data transmission connection with a display device, the screen projection device is used for sending the screen to be projected to the display device for displaying,
the screen projection device further comprises a deep learning detection module, wherein the deep learning detection module is used for detecting a screen to be projected and shielding or not sending corresponding content to the display device when detecting preset content.
Specifically, the screen to be projected is a video stream, and the deep learning detection module is configured to perform frame-by-frame detection on the video stream.
Specifically, when the preset content is detected, the corresponding content is replaced by the preset picture.
Specifically, the deep learning detection module is used for loading a trained deep learning detection algorithm model and detecting a screen to be projected by using the deep learning detection algorithm model.
Optionally, the deep learning detection algorithm model is an inclusion-V4 algorithm model.
Optionally, the system further comprises a network module, wherein the network module is configured to receive the deep learning detection algorithm model from the server and update the deep learning detection algorithm model to the deep learning detection module.
Optionally, the network module is further configured to receive the picture to be detected, and the network module is further configured to send the picture to be projected to the display device for displaying.
Through the technical scheme, the video stream passing through the screen projector can be subjected to content detection by utilizing the technical scheme of integrating the machine learning algorithm in the screen projector, so that abnormal pictures in the video stream can be filtered, and a data flow path displayed by the display device for the abnormal pictures is shielded.
Drawings
Fig. 1 is a block diagram of a screen projection apparatus for real-time content detection according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an inclusion v4 architecture according to an embodiment of the present invention;
FIG. 3 is a schematic view of Stem according to an embodiment of the present invention;
fig. 4 is a schematic view of an inclusion block according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a Reduction block according to an embodiment of the present invention.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
As shown in fig. 1, the screen projection device 1 is configured to detect content in real time, the screen projection device 1 is configured to receive a screen to be projected, the screen projection device 1 may be connected to a display device 2 in a data transmission manner, the screen projection device 1 is configured to send the screen to be projected to the display device 2 for displaying, the screen projection device 1 further includes a deep learning detection module 100, and the deep learning detection module 100 is configured to detect the screen to be projected, and shield or not send corresponding content to the display device 2 when detecting preset content.
The screen projection device 1 can be a television box, can be a mobile intelligent terminal such as a mobile phone, the screen projection device 1 can be connected with the display device 2, and can also be connected with an upper computer generating picture content, and the screen projection device can better finish gating shielding of abnormal pictures by detecting pictures to be projected generated by the upper computer and then delivering the pictures to the display device 2.
In a specific embodiment, the screen to be projected is a video stream, and the deep learning detection module 100 is configured to perform frame-by-frame detection on the video stream. The video stream generated by the upper computer is detected frame by frame, so that the detection shielding action of the video stream can be completed.
In order to better achieve the shielding effect, the technical scheme further comprises the step of replacing the corresponding content with a preset picture when the preset content is detected. The corresponding content may be all of the abnormal frame pictures identified by the deep learning algorithm, or may be a pixel block with abnormal content of the identified abnormal frame pictures. Only the pixel block part with abnormal content of the abnormal frame picture can be replaced by the preset picture, or the whole frame picture can be replaced by the frame picture, and then the replaced video stream is sent to the screen projection device 1 for screen projection display.
In a specific embodiment, the deep learning detection module 100 is configured to load a trained deep learning detection algorithm model, and detect a to-be-projected screen image by using the deep learning detection algorithm model. The deep learning detection algorithm model herein is a detection algorithm model for detecting preset picture contents. The training method of the algorithm model can be implemented by inputting a training set containing preset picture contents according to the prior art. The trained deep learning detection algorithm model can be obtained by downloading through a server.
In some optional embodiments, the deep learning detection algorithm model is an inclusion-V4 algorithm model, the overall architecture of which can be shown in fig. 2, and before the softmax layer, a drop out with a keep prob of 0.8 is used to prevent overfitting. Specifically, in the embodiment shown in fig. 3, the Stem module: in the Stem, a parallel structure and an asymmetric convolution kernel structure are used, so that the calculation amount can be reduced under the condition of ensuring that the information loss is small enough. The 1 x1 convolution kernel in the structure is also used to reduce the dimension and also adds non-linearity. The V-labeled mark in the figure indicates that valid padding is used for the convolution kernel, and the same padding is used for the rest, and the number represents the number of channels. The feature map output is 35 × 384. The inclusion-A, Inception-B and inclusion-C are shown in the embodiment shown in fig. 4: all the inceptionblock is controlled by parameters during realization, so that the internal structure can be conveniently adjusted during later use. The number of the three types of inclusion blocks of the inclusion V4 is 4 (inclusion-A), 7 (inclusion-B) and 3 (inclusion-C), so that the inclusion layer is deeper, the structure is more complex, and the channels of the feature map are more. The kernel _ size of Avg Pooling is 3, padding is 1, and stride is 1. In the example shown in FIG. 5, Reduction-A and Reduction-B are shown: inclusion v4 introduced a dedicated "reduction block" that was used to change the width and height of the grid. The structures of Reduction-A and Reduction-B are placed after the incorporation-A and incorporation-B, respectively, to reduce the computational complexity. The step size (stride) of the convolution is 2, and validpacking is used to reduce the size of the bitmap. In the structure, the calculation amount is reduced by convolution of parallel asymmetric convolution and 1 x 1. Reduction-a (size Reduction from 35x35 to 17x 17) and Reduction-B (size Reduction from 17x17 to 8x 8).
In an alternative embodiment, our screen projection device 1 further comprises a network module 102, and the network module 102 is configured to receive the deep learning detection algorithm model from the server and update the deep learning detection algorithm model to the deep learning detection module 100. The contact with the cloud server is established through the network module 102, so that abnormal content can be better updated in real time, and the screen projection device 1 is always kept in the latest algorithm model updating state.
In other optional embodiments, the network module 102 is further configured to establish a network transmission protocol with an upper computer, receive the picture to be detected, and set the network module 102 to establish the network transmission protocol with the real device, and the network module 102 is further configured to send the picture to be projected to the display device 2 for displaying. The network module 102 transmits the video stream of the picture to be detected, so that the space occupied by wiring can be saved, and hardware interfaces outside the screen projection device 1 are saved, thereby saving the design volume of the screen projection device 1.
It should be noted that, although the above embodiments have been described herein, the invention is not limited thereto. Therefore, based on the innovative concepts of the present invention, the technical solutions of the present invention can be directly or indirectly applied to other related technical fields by making changes and modifications to the embodiments described herein, or by using equivalent structures or equivalent processes performed in the content of the present specification and the attached drawings, which are included in the scope of the present invention.
Claims (7)
1. A screen projection device for detecting content in real time is characterized in that the screen projection device is used for receiving a screen to be projected, the screen projection device is used for sending the screen to be projected to a display device for displaying,
the screen projection device further comprises a deep learning detection module, wherein the deep learning detection module is used for detecting a screen to be projected and shielding or not sending corresponding content to the display device when detecting preset content.
2. The device for projecting screen of real-time detection content according to claim 1, wherein the picture to be projected is a video stream, and the deep learning detection module is configured to perform frame-by-frame detection on the video stream.
3. The screen-projecting apparatus for detecting content in real time according to claim 1, wherein when the preset content is detected, the corresponding content is replaced with a preset picture.
4. The screen projection device for detecting content in real time according to claim 1, wherein the deep learning detection module is configured to load a trained deep learning detection algorithm model, and detect a screen to be projected by using the deep learning detection algorithm model.
5. The screen-projecting device for detecting content in real time according to claim 4, wherein the deep learning detection algorithm model is an inclusion-V4 algorithm model.
6. The screen projection device for detecting content in real time as claimed in claim 4, further comprising a network module, wherein the network module is configured to receive the deep learning detection algorithm model from the server and update the deep learning detection algorithm model to the deep learning detection module.
7. The screen-projecting device for detecting content in real time according to claim 6, wherein the network module is further configured to receive a picture to be detected, and the network module is further configured to send the picture to be projected to a display device for displaying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110995709.XA CN113784114A (en) | 2021-08-27 | 2021-08-27 | Screen projection device for detecting content in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110995709.XA CN113784114A (en) | 2021-08-27 | 2021-08-27 | Screen projection device for detecting content in real time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113784114A true CN113784114A (en) | 2021-12-10 |
Family
ID=78839571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110995709.XA Pending CN113784114A (en) | 2021-08-27 | 2021-08-27 | Screen projection device for detecting content in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113784114A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105100907A (en) * | 2014-04-28 | 2015-11-25 | 宇龙计算机通信科技(深圳)有限公司 | Selective screen projection method and device thereof |
| CN108920937A (en) * | 2018-07-03 | 2018-11-30 | 广州视源电子科技股份有限公司 | Screen projection system, screen projection method and screen projection device |
| US20210195286A1 (en) * | 2019-12-19 | 2021-06-24 | Sling Media Pvt Ltd | Method and system for analyzing live broadcast video content with a machine learning model implementing deep neural networks to quantify screen time of displayed brands to the viewer |
| CN113033379A (en) * | 2021-03-18 | 2021-06-25 | 贵州大学 | Intra-frame evidence-obtaining deep learning method based on double-current CNN |
| CN113268216A (en) * | 2021-06-15 | 2021-08-17 | 北京字跳网络技术有限公司 | Screen projection control method and device and readable storage medium |
-
2021
- 2021-08-27 CN CN202110995709.XA patent/CN113784114A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105100907A (en) * | 2014-04-28 | 2015-11-25 | 宇龙计算机通信科技(深圳)有限公司 | Selective screen projection method and device thereof |
| CN108920937A (en) * | 2018-07-03 | 2018-11-30 | 广州视源电子科技股份有限公司 | Screen projection system, screen projection method and screen projection device |
| US20210195286A1 (en) * | 2019-12-19 | 2021-06-24 | Sling Media Pvt Ltd | Method and system for analyzing live broadcast video content with a machine learning model implementing deep neural networks to quantify screen time of displayed brands to the viewer |
| CN113033379A (en) * | 2021-03-18 | 2021-06-25 | 贵州大学 | Intra-frame evidence-obtaining deep learning method based on double-current CNN |
| CN113268216A (en) * | 2021-06-15 | 2021-08-17 | 北京字跳网络技术有限公司 | Screen projection control method and device and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108074241B (en) | Quality scoring method and device for target image, terminal and storage medium | |
| CN109164997B (en) | Distributed picture rendering and picture playing control method, device and equipment | |
| CN110930335B (en) | Image processing method and electronic equipment | |
| WO2023124054A1 (en) | Method and apparatus for monitoring physical world on basis of digital twins, and storage medium | |
| US20220164952A1 (en) | Capture and Storage of Magnified Images | |
| CN106846495A (en) | Realize the method and apparatus of augmented reality | |
| CN111127358B (en) | Image processing method, device and storage medium | |
| CN104700405B (en) | A kind of foreground detection method and system | |
| RU2598802C2 (en) | Animation playing method, device and apparatus | |
| CN110062157B (en) | Method and device for rendering image, electronic equipment and computer readable storage medium | |
| CN107295082A (en) | Running software processing method, apparatus and system | |
| CN112633313A (en) | Bad information identification method of network terminal and local area network terminal equipment | |
| CN110968375A (en) | Interface control method and device, intelligent terminal and computer readable storage medium | |
| CN108595011A (en) | Information displaying method, device, storage medium and electronic equipment | |
| CN113784114A (en) | Screen projection device for detecting content in real time | |
| CN112511890A (en) | Video image processing method and device and electronic equipment | |
| CN116962612A (en) | Video processing method, device, equipment and storage medium applied to simulation system | |
| CN114881889A (en) | Video image noise evaluation method and device | |
| CN108845784A (en) | A kind of display screen Mura compensation method and device | |
| AU2021313596A1 (en) | Failure identification and handling method, and system | |
| CN113516674A (en) | Image data detection method and device, computer equipment and storage medium | |
| CN111290721A (en) | Online interaction control method, system, electronic device and storage medium | |
| CN110865911A (en) | Image testing method and device, storage medium, image acquisition card and upper computer | |
| CN109060831A (en) | A kind of automatic dirty detection method based on bottom plate fitting | |
| CN115100081B (en) | LCD display screen gray scale image enhancement method, device, equipment and storage medium |
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 |