CN117336570B

CN117336570B - Video tamper-proof system and method based on digital watermark, electronic equipment and medium

Info

Publication number: CN117336570B
Application number: CN202311599031.9A
Authority: CN
Inventors: 金成�; 李东生; 冯建平; 尹国燕
Original assignee: Beijing Fortis Asia News Network Technology Co ltd
Current assignee: Beijing Fortis Asia News Network Technology Co ltd
Priority date: 2023-11-28
Filing date: 2023-11-28
Publication date: 2024-02-13
Anticipated expiration: 2043-11-28
Also published as: CN117336570A

Abstract

The present disclosure relates to the field of video processing technologies, and in particular, to a video tamper-proof system, method, electronic device, and medium based on digital watermarking. The video transmitting end of the video tamper-proof system based on the digital watermark is used for transmitting video images generated by the current conference; the output intermediate device is used for determining a target watermark form at the current moment based on the conference time of the current conference, the device information of the video transmitting end and the video image, determining a dividing mode of the video image according to the target watermark form and the image attribute of the video image, performing imprinting encoding on each sub-video image according to the target watermark form, and transmitting the obtained target video image to the access intermediate device; the access intermediate equipment is used for carrying out watermark analysis on the target video image to obtain an analysis result, and transmitting the analysis result and the target video image to the video receiving end; the video receiving end is used for outputting and displaying the target video image and determining whether the target video image is tampered or not according to the analysis result.

Description

Video tamper-proof system and method based on digital watermark, electronic equipment and medium

Technical Field

The present disclosure relates to the field of video processing technologies, and in particular, to a video tamper-proof system, method, electronic device, and medium based on digital watermarking.

Background

Along with the development of science and technology, social organizations such as enterprises and high efficiency gradually transfer the conference developing mode from off-line conference to on-line video conference, and convenience of the conference is improved. Since the internal conference may relate to the confidentiality contents such as development decisions of enterprises, advanced institutions and universities, technical development and the like, the security of the video generated by the online conference is very important, and if dangerous situations such as leakage, tampering and the like of the video cannot be found in time, the loss or malignant influence on social organizations such as enterprises, universities and the like is likely to be caused.

At present, video data can be continuously generated in the conference process, but in the data transmission process, security holes can exist in a transmission channel, the video data can be tampered by people, and the situation that the content viewed by a video viewer is inconsistent with the actual content can occur. In the related art, the probability of the occurrence of the security hole is generally reduced by detecting a data transmission path between the video sharing party and the video watching party, but the situation that the security hole occurs in the transmission path still occurs, so that the effect of the current method on preventing the video from being tampered is still poor.

Disclosure of Invention

In order to improve the video tamper-proof effect, the application provides a video tamper-proof system, a method, electronic equipment and a medium based on digital watermarking.

In a first aspect, the present application provides a video tamper resistant system based on digital watermarking, comprising: the system comprises a video sending end, an output intermediate device, an access intermediate device and a video receiving end;

the video sending end, the output intermediate device, the access intermediate device and the video receiving end are sequentially connected;

the video sending end is used for sending video images generated by the current conference;

the output intermediate device is used for determining a target watermark form at the current moment based on the conference time of the current conference, the device information of the video transmitting end and the video image, determining a division mode of the video image according to the target watermark form and the image attribute of the video image, performing imprinting encoding on each sub video image according to the target watermark form, and transmitting the obtained target video image to the access intermediate device, wherein the sub video image is an image obtained by dividing the target video image according to the division mode, and the target video image is an encoded video image;

The access intermediate device is used for carrying out watermark analysis on the target video image to obtain an analysis result, and transmitting the analysis result and the target video image to the video receiving end;

the video receiving end is used for outputting and displaying the target video image, determining whether the target video image is tampered or not according to the analysis result, and if so, marking the target video image and sending a prompt to a processor.

By adopting the technical scheme, by adding the watermark information, unauthorized users can be prevented from copying, tampering and other operations on the video, thereby protecting the copyright and the integrity of the video. By watermark analysis of the target video image, whether the target video image is tampered can be detected. If the target video image is tampered, the target video image can be marked and a prompt can be sent to a processor, so that tampering can be timely found and processed. Meanwhile, the method can be suitable for various video transmission scenes, such as conference live broadcast, video monitoring, streaming media transmission and the like, and has wide application prospects. By dividing the target video image into a plurality of sub video images and performing imprinting encoding on each sub video image, the reliability and stability of the target video image can be improved, thereby ensuring the quality and stability of video transmission. When each sub-video image is subjected to imprinting coding, different imprinting coding modes and algorithms can be adopted, so that higher robustness and safety are realized, and the video tamper-proof effect is improved as a whole.

Optionally, when determining the target watermark form at the current moment based on the conference time of the current conference, the device information of the video sending end and the video image, the output intermediate device is specifically configured to:

extracting the starting time and the preset conference duration of the current conference from the conference time of the current conference;

extracting an identity code of the video transmitting end from the equipment information of the video transmitting end;

determining a digital sequence for generating a watermark based on the duration corresponding to the starting time to the current time, the preset conference duration and the identity code;

determining a video content theme of the current moment according to a plurality of video images of the current meeting in a preset proceeding period, wherein the preset proceeding period takes the current moment as a termination moment;

determining a watermark adding mode at the current moment according to the video content theme, wherein the watermark adding mode comprises alternate association adding and consistent adding;

generating a primary watermark form at the current moment according to the digital sequence and the watermark adding mode;

and adjusting the initially selected watermark form based on the image content of the video image, and determining the target watermark form at the current moment.

By adopting the technical scheme, the proceeding stage of the conference can be determined according to the starting time of the current conference and the preset conference time length, so that the watermark adding mode is better selected. The source and the authorized condition of the video can be identified by extracting the identity code of the video transmitting end, so that the safety and the credibility of the video are ensured. Based on the time length from the starting time of the current conference to the current time, the preset conference time length, the identity code and other factors, a digital sequence with stronger robustness and reliability can be generated, and the tamper resistance and the recognition rate of the watermark are improved. By analyzing a plurality of video images of the current conference in a preset proceeding period, the video content theme at the current moment can be determined, so that the watermark adding mode can be more accurately selected. The watermark adding mode is determined according to the video content theme, so that the watermark can be added more flexibly and accurately. By adjusting the primary watermark form based on the image content of the video image, a more accurate and reliable target watermark form can be generated, and the recognition rate and tamper resistance of the watermark are improved. The reliability and the robustness of the watermark can be improved, and the copyright and the integrity of the video can be protected.

Optionally, when determining the digital sequence for generating the watermark based on the duration corresponding to the starting time to the current time, the preset conference duration and the identity code, the output intermediate device is specifically configured to:

determining a number to be selected for generating a watermark based on the duration corresponding to the starting time to the current time, the preset conference duration and the identity code;

and converting the number to be selected into binary numbers, converting the converted number to be selected into a form of American information exchange standard codes to obtain target characters, and determining the target characters as a number sequence for generating watermarks.

By adopting the technical scheme, the proceeding stage of the conference can be calculated according to the duration from the starting time to the current time and the preset conference duration, so that the watermark generation mode can be more accurately selected. By converting the number to be selected into a binary number, the complexity and robustness of the digital sequence can be increased, and the tamper resistance of the watermark can be improved. And converting the converted number to be selected into a form of an American information exchange standard code, and obtaining a target character, so that the number sequence is converted into a form which is easier to identify and analyze. The target character is determined to be a digital sequence for generating the watermark, so that the watermark information can be more accurately represented, and the recognition rate and tamper resistance of the watermark are improved. The method can improve the reliability and the robustness of the watermark, protect the copyright and the integrity of the video, is suitable for various video transmission scenes, and has wide application prospect.

Optionally, the output intermediate device is further configured to:

acquiring and analyzing historical video watermark data, and determining target colors and preliminary sizes of embeddable pixel points of the target characters;

the output intermediate device is specifically configured to, when adjusting the initially selected watermark form based on the image content of the video image and determining the target watermark form at the current time,:

determining the colors and positions of a plurality of image pixel points correspondingly contained based on the image content of the video image;

comparing the colors of the plurality of image pixel points with the target colors to determine the image pixel points corresponding to the embeddable pixel points;

based on the position of the image pixel point, adjusting the preliminary size of the corresponding target character to obtain the target size, wherein the adjustment process comprises size adjustment and direction adjustment of the target character;

and adjusting the initially selected watermark form based on the target size, and determining the target watermark form at the current moment.

By adopting the technical scheme, the target color and the primary size of the embeddable pixel point of the target character can be obtained more accurately and reliably by analyzing the historical video watermark data, and the recognition rate and the tamper resistance of the watermark are improved. The method has the advantages that the initial watermark form is adjusted based on the image content of the video image, so that the watermark can be added more flexibly and accurately, and the reliability and the robustness of the watermark are improved. By comparing the colors of a plurality of image pixels with the target colors, the image pixels corresponding to the embeddable pixels can be determined, and the concealment and the safety of the watermark are improved. The preliminary size of the target character is adjusted based on the position of the image pixel point, so that the target size can be obtained, the target character can be more suitable for the content and the characteristics of the video image, and the recognition rate and the tamper resistance of the watermark are improved. By adjusting the size and the direction of the target character, the target character can be more suitable for the size and the proportion of the video image, and the concealment and the safety of the watermark are improved. The reliability and the robustness of the watermark can be improved, the copyright and the integrity of the video can be protected, and the watermark method is suitable for various video transmission scenes.

Optionally, when determining the division manner of the video image according to the target watermark form and the image attribute of the video image, the output intermediate device is specifically configured to:

analyzing the image attribute to determine the image size and the image theme of the video image;

extracting a minimum coding mark from the target watermark form, and obtaining the minimum compression size of the minimum coding mark;

comparing the minimum compression size with a dividing size threshold, and if the minimum compression size is larger than or equal to the dividing size threshold, determining the minimum compression size as a target dividing size;

and determining the dividing mode of the video image according to the image size, the image theme and the target dividing size, so that the minimum area width of the divided video image is the target dividing size.

By adopting the technical scheme, more details and characteristic information of the video image can be obtained by analyzing the image attribute, so that the watermark adding mode can be better selected and adjusted, and the reliability and the robustness of the watermark are improved. The minimum coding mark is extracted, so that more accurate and reliable watermark information can be obtained, and the recognition rate and tamper resistance of the watermark are improved. The target division size is determined according to the comparison result of the minimum compression size and the division size threshold, so that the divided video image is more suitable for the requirement of watermark adding and analysis, and the recognition rate and tamper resistance of the watermark are improved. The dividing mode of the video image is determined according to the image size, the image subject and the target dividing size, so that the divided video image is more uniform and smooth, and the concealment and the safety of the watermark are improved. The reliability and the robustness of the watermark can be improved, and the anti-tampering effect of the video is improved.

Optionally, the video receiving end is further configured to:

analyzing the analysis result to determine tampered content of the target video image;

determining a processing mode corresponding to the current tampering condition based on the tampered content and a preset processing mode, wherein the processing mode comprises watermark shielding of the tampered content;

the video receiving terminal is specifically configured to, when outputting and displaying the target video image:

and processing the target video image according to a processing mode, and outputting and displaying the processed target video image.

Optionally, the video receiving end is further configured to:

analyzing the target video image and determining corresponding image content;

and if the image content is confidentiality data, sending the image content to the processing personnel to generate dangerous suggestions so that the processing personnel generate a confidential leakage corresponding mode.

In a second aspect, the present application provides a video tamper-proof method based on digital watermarking, which is applied to an output intermediate device in the video tamper-proof system based on digital watermarking according to the first aspect, and includes:

determining a target watermark form at the current moment based on the conference time of the current conference, the equipment information of a video transmitting end and the video image transmitted by the video transmitting end;

Determining a division mode of the video image according to the target watermark form and the image attribute of the video image;

and according to the target watermark form, performing imprinting coding on each sub-video image, transmitting the obtained target video image to an access intermediate device, so that the access intermediate device performs watermark analysis on the target video image to obtain an analysis result, transmitting the analysis result and the target video image to a video receiving end, enabling the video receiving end to output and display the target video image, determining whether the target video image is tampered or not according to the analysis result, and if so, marking the target video image and sending a prompt to a processor, wherein the sub-video image is an image obtained by dividing the target video image according to a dividing mode, and the target video image is the coded video image.

In a third aspect, the present application provides an output intermediate device, applied to the video tamper resistant system based on digital watermarking as described in the first aspect, comprising:

the target watermark form determining module is used for determining a target watermark form at the current moment based on the conference time of the current conference, the equipment information of the video transmitting end and the video image transmitted by the video transmitting end;

The division mode determining module is used for determining the division mode of the video image according to the target watermark form and the image attribute of the video image;

the marking coding module is used for marking and coding each sub video image according to the target watermark form, transmitting the obtained target video image to the access intermediate device, enabling the access intermediate device to carry out watermark analysis on the target video image to obtain an analysis result, transmitting the analysis result and the target video image to the video receiving end, enabling the video receiving end to output and display the target video image, determining whether the target video image is tampered or not according to the analysis result, marking the target video image and sending a prompt to a processor if the target video image is tampered, wherein the sub video image is an image obtained by dividing the target video image according to a dividing mode, and the target video image is the coded video image.

In a fourth aspect, the present application provides an electronic device, comprising: a memory and a processor, the memory having stored thereon a computer program capable of being loaded by the processor and performing the method of the second aspect.

In a fifth aspect, the present application provides a computer readable storage medium storing a computer program capable of being loaded by a processor and performing the method of the second aspect.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief description will be given below of the drawings that are needed in the embodiments or the prior art descriptions, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.

Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application;

fig. 2 is a schematic structural diagram of a video tamper-proof system based on digital watermarking according to an embodiment of the present application

Fig. 3 is a flowchart of a video tamper-proof method based on digital watermarking according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an output intermediate device according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It will be apparent that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.

Embodiments of the present application are described in further detail below with reference to the drawings attached hereto.

Along with the development of science and technology, the mode that social organizations such as enterprises, universities and the like will develop the meeting is gradually transferred from off-line meeting to on-line video meeting, convenience of the meeting is improved, and the work such as anchor of some on-line platforms and carrying goods also needs to be developed on line. For online conferences, video image data is required to be transmitted in both online conferences and live broadcast processes, and sometimes, the transmitted video image refers to relatively confidential contents such as screen shared files, ppt and experimental data, and if intercepted or tampered in transmission, the video image data is likely to cause loss to social organizations such as enterprises, universities and the like. For live broadcasting of an online platform, selling of commodities of different brands may be involved in the live broadcasting process, if live broadcasting images of the commodities displayed by a live broadcasting player are tampered during transmission, the correct brands are likely to be covered, and losses are likely to be caused to the brands. Therefore, the security of the video data in the transmission process is very important, and the current video tamper resistance is mainly realized by detecting the transmission channel, but the security hole of the transmission channel is difficult to completely avoid, once the situation of tamper occurs, the current method cannot detect in time, so that the video image displayed by the video watching party is deviated.

Based on the above, the application provides a video tamper-proof system, a method, electronic equipment and a medium based on digital watermarking. The video tamper-proof system based on the digital watermark comprises a video sending end, an output intermediate device, an access intermediate device and a video receiving end. The video transmitting end, the output intermediate device, the access intermediate device and the video receiving end are sequentially connected, the video transmitting end can transmit video images generated by a current conference, the output intermediate device can determine a target watermark form at the current moment based on the conference time of the current conference, device information of the video transmitting end and the video images, a dividing mode of the video images is determined according to the target watermark form and image attributes of the video images, each sub video image is subjected to imprinting encoding according to the target watermark form, the obtained target video images are transmitted to the access intermediate device, the sub video images are images obtained by dividing the target video images according to the dividing mode, and the target video images are encoded video images. The access intermediate equipment analyzes the watermark of the target video image to obtain an analysis result, the analysis result and the target video image are transmitted to the video receiving end, the target video image is output and displayed after the video receiving end receives the analysis result, whether the target video image is tampered or not is determined according to the analysis result, and if the target video image is tampered, the target video image is marked and a prompt is sent to a processor.

Fig. 1 is a schematic view of an application scenario provided in the present application. The social organization of enterprises and universities can utilize a video tamper-proof system based on digital watermarking to conduct online conferences, one party performing screen sharing to generate video images can be used as a video sender, and one party viewing the video images shared by the video sender can be used as a video receiver. The video sender can carry out online conference on the system, share the screen, and the system can transmit the generated video image in real time, carry out watermark adding and detecting in the transmission process and then display the watermark to the video receiver.

Reference may be made to the following examples for specific implementation.

Fig. 2 is a schematic structural diagram of a video tamper-proof system based on digital watermarking according to an embodiment of the present application, and as shown in fig. 2, a video tamper-proof system 200 based on digital watermarking according to the embodiment includes: a video transmitting end 201, an output intermediate device 202, an access intermediate device 203 and a video receiving end 204;

the video sending end 201, the output intermediate device 202, the access intermediate device 203 and the video receiving end 204 are sequentially connected;

the video transmitting terminal 201 is configured to transmit a video image generated by a current conference;

The output intermediate device 202 is configured to determine a target watermark form at a current moment based on a conference time of a current conference, device information of the video transmitting terminal 201, and video images, determine a division manner of the video images according to the target watermark form and image attributes of the video images, perform imprinting encoding on each sub-video image according to the target watermark form, and transmit the obtained target video image to the access intermediate device 203, where the sub-video image is an image obtained by dividing the target video image according to the division manner, and the target video image is an encoded video image;

the access intermediate device 203 is configured to perform watermark analysis on the target video image to obtain an analysis result, and transmit the analysis result and the target video image to the video receiving end 204;

the video receiving end 204 is configured to output and display the target video image, determine whether the target video image is tampered according to the analysis result, and if so, mark the target video image and send a prompt to a processor.

Optionally, when determining the target watermark form at the current moment based on the conference time of the current conference, the device information of the video transmitting end and the video image, the output intermediate device 202 is specifically configured to:

Extracting the starting time of the current conference and the preset conference time from the conference time of the current conference;

extracting an identity code of a video transmitting end from equipment information of the video transmitting end;

determining a digital sequence for generating the watermark based on a duration corresponding to the starting time to the current time, a preset conference duration and an identity code;

determining a video content theme at the current moment according to a plurality of video images of the current meeting in a preset proceeding period, wherein the preset proceeding period takes the current moment as a termination moment;

according to the video content theme, determining a watermark adding mode at the current moment, wherein the watermark adding mode comprises alternate association adding and consistent adding;

and adjusting the primary watermark form based on the image content of the video image, and determining the target watermark form at the current moment.

Optionally, when determining the digital sequence for generating the watermark based on the duration corresponding from the start time to the current time, the predetermined conference duration and the identity code, the output intermediate device 202 is specifically configured to:

determining a number to be selected for generating a watermark based on a duration corresponding to the starting time to the current time, a preset conference duration and an identity code;

And converting the number to be selected into binary numbers, converting the converted number to be selected into a form of American information exchange standard codes to obtain target characters, and determining the target characters as a digital sequence for generating watermarks.

Optionally, the output intermediate device 202 is further configured to:

acquiring and analyzing historical video watermark data, and determining target colors and preliminary sizes of embeddable pixel points of target characters;

the output intermediate device 202 is specifically configured to, when adjusting the initially selected watermark form based on the image content of the video image and determining the target watermark form at the current time:

comparing the colors of a plurality of image pixel points with the target colors to determine the image pixel points corresponding to the embeddable pixel points;

based on the positions of the image pixel points, the preliminary size of the corresponding target character is adjusted to obtain the target size, and the adjustment process comprises size adjustment and direction adjustment of the target character;

Optionally, the output intermediate device 202 is specifically configured to, when determining the division manner of the video image according to the target watermark form and the image attribute of the video image:

Analyzing the image attribute, and determining the image size and the image theme of the video image;

extracting a minimum coding mark from a target watermark form, and obtaining the minimum compression size of the minimum coding mark;

and determining a dividing mode of the video image according to the image size, the image subject and the target dividing size, so that the minimum area width of the divided video image is the target dividing size.

Optionally, the video receiving end 204 is further configured to:

the video receiving end 204 is specifically configured to, when outputting and displaying the target video image:

and processing the target video image according to the processing mode, and outputting and displaying the processed target video image.

The analysis result may include a tampered image area in the target video, and the image content corresponding to the image area corresponds to tampered content. The preset processing mode can be used for representing different solutions corresponding to tampered image content, and comprises specific operation modes such as selection of different processing personnel, watermark shielding and the like, emergency of tampered image content and loss of content leakage to a current enterprise. If the locations of text, data and the like are tampered with, the situation is dangerous, and tampering with the content indicates that the content is also revealed, and the current enterprise is likely to be affected.

Specifically, tampered content of the target video image can be extracted from the analysis result, the tampered content is matched with a preset processing mode, a processing mode corresponding to the current tampering condition is obtained, and then the target video image is processed and then output and displayed to a video receiver.

Optionally, the video receiving end 204 is further configured to:

analyzing the target video image and determining corresponding image content;

if the image content is confidential data, the image content is sent to a processor to generate dangerous advice so that the processor generates a confidential disclosure corresponding mode.

The image content may include various features in the video image including characters, background, data, text, etc., and the confidentiality data may include data for programs, plans, etc. The content possibly tampered is not confidentiality data, but once the target video image is tampered, the target video image can be intercepted, all the content on the image can be leaked, at the moment, the whole analysis is carried out on the target video image, the image content possibly leaked is sent to a processor at the first time of determining that the image content is confidential data, and dangerous advice is generated, the processor is informed that the data is very important, and large loss can be caused, so that the processor can quickly carry out whole planning, scheme and other adjustment on the confidentiality data in the image content, and the method can be used as a confidential leakage corresponding mode

Fig. 3 is a flowchart of a video tamper-proof method based on digital watermarking according to an embodiment of the present application, where the method of the present embodiment may be applied to the output intermediate device in the above embodiment. As shown in fig. 3, the method includes:

s301, determining a target watermark form at the current moment based on the conference time of the current conference, the equipment information of the video transmitting end and the video image transmitted by the video transmitting end.

In online conferences, important data, text or pictures are generally emphasized, and screen sharing or direct sharing of data, text or the like by video conferences is involved. At this time, a user who performs screen sharing may act as a video sender, and the apparatus used as a video sender. The meeting time of the current meeting may include a time at which the meeting begins and a predetermined end time. The device information of the video sender may include an identity id, an ip address, etc. of the video sender. The target watermark form may be used to indicate how the video image at the current time is to be watermarked, e.g. a fixed watermark is used in its entirety on the video image, but the watermark of the different areas is part of the fixed watermark, or each area of the video image is added with a complete fixed watermark, etc.

Different meeting time, setting information and target watermark forms corresponding to video images can be preset, and then the target watermark form at the current moment is correspondingly determined.

S302, determining a division mode of the video image according to the target watermark form and the image attribute of the video image.

The image attribute may include sharpness, image size, etc. of the video image, and in order to ensure that the watermark on the image cannot be identified due to the fact that the watermark is not distorted after the video image is compressed, the size of the area after the video image is divided needs to be determined, that is, the dividing mode is determined.

In some implementations, a division mode determination model may be pre-established using a neural network model, the target watermark form and the image attribute are input into the division mode determination model, and the division mode of the video image is directly output and determined.

S303, performing imprinting coding on each sub-video image according to a target watermark form, transmitting the obtained target video image to the access intermediate device, enabling the access intermediate device to perform watermark analysis on the target video image to obtain an analysis result, transmitting the analysis result and the target video image to the video receiving end, enabling the video receiving end to output and display the target video image, determining whether the target video image is tampered according to the analysis result, and marking the target video image and sending a prompt to a processor if the target video image is tampered.

The sub video images are images obtained by dividing target video images in a dividing mode, and the target video images are encoded video images.

In the video tamper-proof system based on the digital watermark, one party viewing video content shared by a video sender is taken as a video receiver, and used equipment is taken as a video receiving end. Dividing the target video according to a dividing mode to obtain a plurality of sub video images, and performing imprinting coding on each sub video image according to a target watermark mode. Specifically, the imprinting coding can be realized by adding dummy rows and dummy columns which do not affect normal display into the target video image, and adding information such as letters, numbers, symbols and the like corresponding to the target watermark form into the dummy rows and the dummy columns in each sub video image.

If the target video image is tampered by an external person in the process of sending the target video image to the access intermediate device by the output intermediate device, the watermark of the target video image can be changed, and the access intermediate device can analyze the watermark of the target video image at the moment to obtain an analysis result. If the watermark is not deformed, distorted, lost and the like, the analysis result is not tampered, and if the watermark is changed, the analysis result is tampered and tampered image areas. The access intermediate device can send the target video image and the analysis result to the video receiving end, and if the video receiving end analyzes the analysis result to determine that the target video image is tampered, the target video image can be marked and a prompt can be sent to a processor.

By adding watermark information, the embodiment can prevent unauthorized users from copying, tampering and other operations on the video, thereby protecting the copyright and the integrity of the video. By watermark analysis of the target video image, whether the target video image is tampered can be detected. If the target video image is tampered, the target video image can be marked and a prompt can be sent to a processor, so that tampering can be timely found and processed. Meanwhile, the method can be suitable for various video transmission scenes, such as conference live broadcast, video monitoring, streaming media transmission and the like, and has wide application prospects. By dividing the target video image into a plurality of sub video images and performing imprinting encoding on each sub video image, the reliability and stability of the target video image can be improved, thereby ensuring the quality and stability of video transmission. When each sub-video image is subjected to imprinting coding, different imprinting coding modes and algorithms can be adopted, so that higher robustness and safety are realized, and the video tamper-proof effect is improved as a whole.

In some embodiments, the digital sequence and the watermarking scheme may be generated separately to generate the primary watermark form, and the target watermark form is determined after adjustment. Specifically, extracting a starting time and a preset conference duration of a current conference from the conference time of the current conference; extracting an identity code of a video transmitting end from equipment information of the video transmitting end; determining a digital sequence for generating the watermark based on a duration corresponding to the starting time to the current time, a preset conference duration and an identity code; determining a video content theme at the current moment according to a plurality of video images of the current meeting in a preset proceeding period, wherein the preset proceeding period takes the current moment as a termination moment; according to the video content theme, determining a watermark adding mode at the current moment, wherein the watermark adding mode comprises alternate association adding and consistent adding; generating a primary watermark form at the current moment according to the digital sequence and the watermark adding mode; and adjusting the primary watermark form based on the image content of the video image, and determining the target watermark form at the current moment.

The start time may be used to indicate the time at which the current meeting starts, and when it starts and when it ends may be scheduled before the online meeting starts, and then the scheduled meeting time period may be the period between the start time and the end time. Each video sender may have a unique id, which may be called an identity code, as a credential to distinguish it from other video senders. The duration corresponding to the starting time to the current time, the preset conference duration and the identity code all comprise a plurality of numbers, and the numbers are arranged randomly, so that a number sequence for generating the watermark can be obtained.

The emphasis of the content in different video images is different, the content may include data and codes, and may also include a shared device main interface, etc., specifically, the features in the video images may be extracted, and when the data and the codes occupy eighty percent of the content of the whole video image, the theme of the video content may be regarded as full-image data, full-image codes, etc. The preset proceeding period may be a period corresponding to a period from the start of screen sharing to the current time in the conference. Watermark adding modes corresponding to different video content topics can be preset, and the watermark adding modes can comprise a distribution mode of watermarks on video images, a position selection mode of adding watermarks on the video images and the like. Wherein full view watermarking may be selected in the case of video content subject matter such as full view data, full view code, and the like. The specific adding mode can include alternate association adding, namely, a complete watermark is added on one video image, and a part of watermark is added to each area on the video image, so that the complete watermark is obtained by connecting the two areas. The method can also comprise consistent addition, namely, each area is added with the same watermark in a plurality of areas divided on one video image, so that the video image is intercepted by an external person, and the watermark can still be identified after clipping.

Then, the whole digital sequence and the watermark adding mode can be used as a primary watermark form, and because the directions and the sizes of the pixels of the numbers, letters and other characteristics in the image content of the video image are different, the primary watermark form needs to be adjusted based on the directions and the sizes of the pixels, so that each number in the digital sequence can be attached to the image content, and the display mode of the image content is prevented from being changed.

According to the embodiment, the proceeding stage of the conference can be determined according to the starting time of the current conference and the preset conference time length, so that the watermark adding mode is better selected. The source and the authorized condition of the video can be identified by extracting the identity code of the video transmitting end, so that the safety and the credibility of the video are ensured. Based on the time length from the starting time of the current conference to the current time, the preset conference time length, the identity code and other factors, a digital sequence with stronger robustness and reliability can be generated, and the tamper resistance and the recognition rate of the watermark are improved. By analyzing a plurality of video images of the current conference in a preset proceeding period, the video content theme at the current moment can be determined, so that the watermark adding mode can be more accurately selected. The watermark adding mode is determined according to the video content theme, so that the watermark can be added more flexibly and accurately. By adjusting the primary watermark form based on the image content of the video image, a more accurate and reliable target watermark form can be generated, and the recognition rate and tamper resistance of the watermark are improved. The reliability and the robustness of the watermark can be improved, and the copyright and the integrity of the video can be protected.

In some embodiments, the number to be selected may be determined first, followed by conversion of the binary number and ASCII code, thereby generating a sequence of numbers. Specifically, determining a number to be selected for generating a watermark based on a duration corresponding to a starting time to a current time, a preset conference duration and an identity code; and converting the number to be selected into binary numbers, converting the converted number to be selected into a form of American information exchange standard codes to obtain target characters, and determining the target characters as a digital sequence for generating watermarks.

The duration corresponding to the starting time to the current time, the preset conference duration and the identity code all comprise a plurality of numbers, and the numbers can be used as the numbers to be selected. A video image can be regarded as an aggregate consisting of a number of 0 and 1 data, so that the number to be selected can be converted into a binary number first and then into the form of american standard code for information interchange (ASCII code), which can be ensured to be embedded in the image without changing the display condition of the video image itself. The converted ASCII codes, the directions of the ASCII codes and the ASCII codes are used as target characters, and the target characters are used as a digital sequence for generating the watermark.

According to the embodiment, the proceeding stage of the conference can be calculated according to the duration from the starting time to the current time and the preset conference duration, so that the watermark generation mode can be more accurately selected. By converting the number to be selected into a binary number, the complexity and robustness of the digital sequence can be increased, and the tamper resistance of the watermark can be improved. And converting the converted number to be selected into a form of an American information exchange standard code, and obtaining a target character, so that the number sequence is converted into a form which is easier to identify and analyze. The target character is determined to be a digital sequence for generating the watermark, so that the watermark information can be more accurately represented, and the recognition rate and tamper resistance of the watermark are improved. The method can improve the reliability and the robustness of the watermark, protect the copyright and the integrity of the video, is suitable for various video transmission scenes, and has wide application prospect.

In some embodiments, the target colors and preliminary sizes of embeddable pixels of different target characters may be determined first, based on which the size and orientation of the target characters are adjusted in conjunction with the colors and locations of image pixels in the image content of the video image. Specifically, historical video watermark data is acquired and analyzed, and the target color and the preliminary size of embeddable pixel points of the target character are determined.

Correspondingly, determining the colors and positions of a plurality of image pixel points correspondingly contained based on the image content of the video image; comparing the colors of a plurality of image pixel points with the target colors to determine the image pixel points corresponding to the embeddable pixel points; based on the positions of the image pixel points, the preliminary size of the corresponding target character is adjusted to obtain the target size, and the adjustment process comprises size adjustment and direction adjustment of the target character; and adjusting the initially selected watermark form based on the target size, and determining the target watermark form at the current moment.

The historical video watermark data may be used to represent data of relevant video images of an online meeting that was carried out prior to the current time. The target character needs to be embedded in the video image, and in order to ensure that normal display is not disturbed, the target character needs to be added to positions with relatively consistent colors and directions, and the positions can be used as embeddable pixel points. It should be noted that the embeddable pixel does not necessarily refer to a single pixel on the video image, and some target characters have a larger size, so the embeddable pixel may be a set of several adjacent pixels on the video image. The target color and preliminary size of the embeddable pixel point may correspond to the target character.

Specifically, the image content of the video image may be analyzed first to obtain which pixels are included in the image, the colors of the pixels, and the positions of the pixels. And comparing the colors of a plurality of pixel points on the video image with the target colors, determining which image pixel points on the video image meet the requirement of embeddable pixel points, and adjusting the preliminary size of the target character based on the positions of the image pixel points after determining, so as to avoid the influence of the target character on the display of the video image and obtain the target size. Based on this, the initially selected watermark form is changed to obtain the target watermark form.

According to the embodiment, through analyzing the historical video watermark data, the target color and the primary size of the embeddable pixel point of the target character can be obtained more accurately and reliably, and the recognition rate and the tamper resistance of the watermark are improved. The method has the advantages that the initial watermark form is adjusted based on the image content of the video image, so that the watermark can be added more flexibly and accurately, and the reliability and the robustness of the watermark are improved. By comparing the colors of a plurality of image pixels with the target colors, the image pixels corresponding to the embeddable pixels can be determined, and the concealment and the safety of the watermark are improved. The preliminary size of the target character is adjusted based on the position of the image pixel point, so that the target size can be obtained, the target character can be more suitable for the content and the characteristics of the video image, and the recognition rate and the tamper resistance of the watermark are improved. By adjusting the size and the direction of the target character, the target character can be more suitable for the size and the proportion of the video image, and the concealment and the safety of the watermark are improved. The reliability and the robustness of the watermark can be improved, the copyright and the integrity of the video can be protected, and the watermark method is suitable for various video transmission scenes.

In some embodiments, the minimum coding mark in the form of the target watermark may be determined first, then the target division size may be determined, and then the division manner may be obtained by combining the image size, the image subject and the target division size, specifically, the image attribute may be analyzed, and the image size and the image subject of the video image may be determined; extracting a minimum coding mark from a target watermark form, and obtaining the minimum compression size of the minimum coding mark; comparing the minimum compression size with a dividing size threshold, and if the minimum compression size is larger than or equal to the dividing size threshold, determining the minimum compression size as a target dividing size; and determining a dividing mode of the video image according to the image size, the image subject and the target dividing size, so that the minimum area width of the divided video image is the target dividing size.

Image attributes may include an image size of the video image, which may be used to represent the size of the image, and an image theme, which may be used to represent the primary content in the image. The watermark corresponding to the target watermark form can comprise numbers, letters, symbols and the like, the recognizabilities of the watermarks with different sizes are different, when the watermark is compressed to the minimum compression size, the watermark can be just recognized, and if the watermark is compressed again, the watermark deformation can be caused. The smallest encoded stamp may be used to represent the smallest sized watermark. In addition, in order to ensure the definition of the picture, the video image needs to set a dividing size threshold value, so that the unclear content of the divided picture caused by excessive dividing is avoided. The target division size may characterize the length, width, etc. of each portion of the image division.

Specifically, the image size and the image theme of the video image can be extracted from the image attribute, then the minimum coding mark is extracted from the target watermark form, the pre-stored corresponding minimum compression size is obtained, the minimum compression size is compared with the dividing size threshold, if the minimum compression size is larger than or equal to the dividing size threshold, the minimum compression size is determined as the target dividing size, and each part can be added with clear watermarks after the video image is divided. Since the image sizes are different, when dividing according to the target division size, there may be a part of the remaining part that is not the target division size, and this part may be merged with the adjacent region or directly discarded. The choice of merging or discarding may be made in particular in connection with the image theme, which part may be merged for watermarking if it is important for the image theme, and which part may be discarded for watermarking if it is not important, but which part will still be transmitted when transmitted to the access intermediary device.

In some implementations, if the minimum compression size is less than the division size threshold, the division size threshold is taken as a target division size, if an outsider intercepts the video image, the image is compressed and then released onto the platform, and the digital watermark-based video tamper-proof system can detect the watermark. If the exor compression is smaller than the division size threshold, the video image content will not be readable.

The embodiment analyzes the image attribute to obtain more details and characteristic information of the video image, so that the watermark adding mode is better selected and adjusted, and the reliability and the robustness of the watermark are improved. The minimum coding mark is extracted, so that more accurate and reliable watermark information can be obtained, and the recognition rate and tamper resistance of the watermark are improved. The target division size is determined according to the comparison result of the minimum compression size and the division size threshold, so that the divided video image is more suitable for the requirement of watermark adding and analysis, and the recognition rate and tamper resistance of the watermark are improved. The dividing mode of the video image is determined according to the image size, the image subject and the target dividing size, so that the divided video image is more uniform and smooth, and the concealment and the safety of the watermark are improved. The reliability and the robustness of the watermark can be improved, and the anti-tampering effect of the video is improved.

In other embodiments, the present application provides a method for tamper resistance of video based on digital watermarking technology (a method for tamper resistance of video based on digital watermarking), which can prevent tampering during video transmission.

The technical scheme is as follows:

running system (digital watermark based video tamper resistant system): the system comprises a video sending end and a video receiving end, wherein the two video conference terminals are actually applied by clients, and data of a video conference are transmitted in real time through network connection. The method is implemented by adding an intermediate device (output intermediate device and access intermediate device) to the video communication interface of each terminal, the device can add watermark to the outgoing video when the video is output, and the device can detect the watermark in the video when the video is accessed, so as to judge whether the video is tampered.

Firstly, each video conference terminal agrees with a rule of watermark addition, video watermarks are added when video is output, and a receiver (access intermediate equipment) analyzes whether the video images contain the video watermarks or whether the video images are missing, deformed and the like when receiving the video images, namely judges whether the video images are tampered or not according to the video watermarks.

In particular, the content of the video watermark may be associated with the ID and time of the video conferencing terminal, the video watermark is spread throughout the video content, for example by dividing the video content into an array of small rectangles and adding one bit of video watermark code within each small rectangle, or adding the entire video watermark code within one small rectangle. Thus, whether the video is tampered can be determined through the arrangement integrity, the shape, the coded content and the like of the watermark.

Video watermarks are essentially image data, but in order not to affect viewing, video watermarks are invisible image data that are only reflected in the parameter variations of the pixels and are difficult for the naked eye to identify. The specific means may be that the addition of video watermarks is achieved by changing parameters of pixels in the video image (on the premise of not affecting viewing), such as brightness, chromaticity or combination with frequency, and the output video image contains conference video content and also contains video watermarks, and the video watermarks can be resolved by the parameters of the pixels, but the video watermarks cannot be distinguished by naked eyes of a video receiver, and the video receiver sees or conferences video content.

The video watermark is added without influencing the watching, and the video can be prevented from being tampered by the video 0 watermark technology.

Fig. 4 is a schematic structural diagram of an output intermediate device according to an embodiment of the present application, as shown in fig. 4, an output intermediate device 400 of the present embodiment includes: a target watermark form determination module 401, a division mode determination module 402 and an imprint encoding module 403.

A target watermark form determining module 401, configured to determine a target watermark form at a current moment based on a conference time of a current conference, device information of a video transmitting end, and a video image transmitted by the video transmitting end;

a division mode determining module 402, configured to determine a division mode of the video image according to the target watermark form and the image attribute of the video image;

the imprinting encoding module 403 is configured to perform imprinting encoding on each sub-video image according to the target watermark form, and transmit the obtained target video image to the access intermediate device, so that the access intermediate device performs watermark analysis on the target video image to obtain an analysis result, and after transmitting the analysis result and the target video image to the video receiving end, the video receiving end outputs and displays the target video image, and determines whether the target video image is tampered according to the analysis result, if so, marks the target video image and sends a prompt to a processor, where the sub-video image is an image obtained by dividing the target video image according to the dividing mode, and the target video image is an encoded video image.

Optionally, the target watermark form determination module 401 is specifically configured to:

Optionally, the target watermark form determining module 401 is specifically configured to, when determining the digital sequence for generating the watermark based on the duration corresponding from the start time to the current time, the predetermined conference duration and the identity code:

Optionally, the output mediation device 400 further comprises a color sizing module 404 for:

the target watermark form determining module 401 is specifically configured to, when adjusting the initially selected watermark form based on the image content of the video image to determine the target watermark form at the current time:

Optionally, the partition mode determining module 402 is specifically configured to:

The apparatus of this embodiment may be used to perform the method of any of the foregoing embodiments, and its implementation principle and technical effects are similar, and will not be described herein again.

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application, as shown in fig. 5, an electronic device 500 according to the embodiment may include: a memory 501 and a processor 502.

The memory 501 has stored thereon a computer program that can be loaded by the processor 502 and that performs the methods of the embodiments described above.

Wherein the processor 502 is coupled to the memory 501, such as via a bus.

Optionally, the electronic device 500 may also include a transceiver. It should be noted that, in practical applications, the transceiver is not limited to one, and the structure of the electronic device 500 is not limited to the embodiment of the present application.

The processor 502 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 502 may also be a combination of computing functions, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

A bus may include a path that communicates information between the components. The bus may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The Memory 501 may be, but is not limited to, ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, EEPROM (Electrically Erasable Programmable Read Only Memory ), CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

The memory 501 is used to store application code for executing the present application and is controlled by the processor 502 for execution. The processor 502 is configured to execute the application code stored in the memory 501 to implement what is shown in the foregoing method embodiments.

Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. But may also be a server or the like. The electronic device shown in fig. 5 is only an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present application.

The electronic device of the present embodiment may be used to execute the method of any of the foregoing embodiments, and its implementation principle and technical effects are similar, and will not be described herein.

The present application also provides a computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the method in the above embodiments.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.

Claims

1. A digital watermark-based video tamper resistant system, comprising: the system comprises a video sending end, an output intermediate device, an access intermediate device and a video receiving end;

the video receiving end is used for outputting and displaying the target video image, determining whether the target video image is tampered or not according to the analysis result, and if so, marking the target video image and sending a prompt to a processor;

the output intermediate device is specifically configured to, when determining a target watermark form at a current moment based on a conference time of the current conference, device information of the video transmitting end, and the video image:

2. The video tamper-resistant system based on digital watermarking according to claim 1, wherein the output intermediate device is configured to, when determining the digital sequence for generating the watermark based on the duration corresponding from the start time to the current time, the predetermined conference duration and the identity code:

3. The digital watermark based video tamper resistant system of claim 2, wherein the output intermediary device is further configured to:

4. The digital watermark based video tamper resistant system according to claim 1, wherein said output intermediate device, when determining a division manner of said video image according to said target watermark form and an image attribute of said video image, is specifically configured to:

5. The digital watermark-based video tamper resistant system according to any one of claims 1 to 4, wherein said video receiving end is further configured to:

6. The digital watermark-based video tamper resistant system of claim 1, wherein the video receiving end is further configured to:

analyzing the target video image and determining corresponding image content;

7. A digital watermark based video tamper resistant method, applied to an output intermediate device in a digital watermark based video tamper resistant system as claimed in any one of claims 1 to 5, comprising:

according to the target watermark form, performing imprinting coding on each sub-video image, transmitting the obtained target video image to an access intermediate device, so that the access intermediate device performs watermark analysis on the target video image to obtain an analysis result, transmitting the analysis result and the target video image to a video receiving end, enabling the video receiving end to output and display the target video image, determining whether the target video image is tampered according to the analysis result, if so, marking the target video image and sending a prompt to a processor, wherein the sub-video image is an image obtained by dividing the target video image according to a dividing mode, and the target video image is a coded video image;

the determining the target watermark form at the current moment based on the conference time of the current conference, the equipment information of the video transmitting end and the video image comprises the following steps:

8. An electronic device, comprising: a memory and a processor;

the memory is used for storing program instructions;

the processor is configured to invoke and execute the program instructions in the memory to perform the digital watermark-based video tamper resistant method as recited in claim 7.

9. A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored therein; the computer program, when executed by a processor, implements a digital watermark-based video tamper-proof method as claimed in claim 7.