Method and system for implanting content information in video in batch

文档序号:1601731 发布日期:2020-01-07 浏览:7次 中文

阅读说明:本技术 一种视频中批量植入内容信息的方法和系统 (Method and system for implanting content information in video in batch ) 是由 陈访访 于 2018-06-29 设计创作,主要内容包括:本发明的实施例提供了一种视频中批量植入内容信息的方法和系统,该方法读入已有视频的图像序列,通过物体识别和分类等技术获取视频中所有物体的图像数据,通过智能分析选取插入信息的目标物体,将待插入的内容植入到目标物体上,按照规则调整并优化图像,输出植入信息后的视频,并将系统获取的数据进行统计分析,方便数据的复用及插入内容的改变。为广告植入、特效植入等特定问题提供批量且智能的方法,提高精度和效果,同时节省人力和时间成本。(The embodiment of the invention provides a method and a system for implanting content information in a video in batches, the method comprises the steps of reading in an image sequence of an existing video, obtaining image data of all objects in the video through technologies such as object identification and classification, selecting a target object with inserted information through intelligent analysis, implanting content to be inserted into the target object, adjusting and optimizing the image according to rules, outputting the video with the inserted information, and performing statistical analysis on data obtained by the system, so that multiplexing of the data and changing of the inserted content are facilitated. The method provides a batch and intelligent method for specific problems such as advertisement implantation, special-effect implantation and the like, improves the precision and effect, and saves labor and time cost.)

1. A method for implanting content information in a video in batch is characterized by comprising the following steps:

acquiring an original video, and carrying out object detection and classification on the content of the original video;

screening objects which accord with preset implantation rules from the object detection and classification results;

acquiring implantation content information, replacing the object which accords with the preset implantation rule, and carrying out image adaptation;

analyzing the image sequence of the video implanted with the content information, and adjusting and optimizing the position, the angle and the size according to the data implanted with the content information and the data of the object according with the preset implantation rule;

and after completing content information implantation frame by frame, outputting the video with implanted content.

2. The method for batch embedding of content information in video according to claim 1, further comprising the steps of:

presetting a bottom database; the bottom database comprises all content information to be implanted, corresponding artificial tags and characteristic data of the content;

and acquiring implanted content information from the bottom-layer database.

3. The method of claim 2, wherein the underlying database further comprises:

rule data of object detection and classification and result data of detection and classification;

and carrying out object detection and classification on the original video content according to the rule data of object detection and classification in the bottom database.

4. The method of claim 2, wherein the underlying database further comprises:

preset implantation rules and corresponding objects and classifications;

and screening the objects according with the implantation rules according to the preset implantation rules in the bottom database and the corresponding objects and classifications.

5. The method according to claim 1, wherein the replacing the object according to the preset embedding rule and performing image adaptation comprises:

and replacing or covering the corresponding object in the original video by the implanted content information, and carrying out image adaptation on the implanted content information according to the information of the original image so that the implanted content information is consistent with the image of the original video.

6. A system for implanting content information in a video in batches is characterized by comprising a detection unit, an analysis unit, an implantation unit, an adaptation unit and an output unit, wherein,

the detection unit is used for acquiring an original video and carrying out object detection and classification on the content of the original video;

the analysis unit is used for screening the objects which accord with preset implantation rules from the results of the object detection and classification;

the implantation unit is used for acquiring implantation content information, replacing the object which accords with the preset implantation rule and carrying out image adaptation;

the adaptive unit is used for analyzing the image sequence of the video implanted with the content information and adjusting and optimizing the position, the angle and the size according to the data implanted with the content information and the data of the object according with the preset implantation rule;

and the output unit is used for outputting the video with the implanted content after completing the implantation of the content information frame by frame.

7. The system for mass embedding of content information in video according to claim 6, further comprising an underlying database unit, wherein,

the bottom database unit is used for presetting a bottom database; the bottom database comprises all content information to be implanted, corresponding artificial tags and characteristic data of the content;

and the implantation unit is used for acquiring implantation content information from the bottom database.

8. The system for mass embedding of content information in video according to claim 6, further comprising an underlying database unit, wherein,

the bottom database unit is used for presetting a bottom database; the bottom database comprises rule data of object detection and classification and result data of detection and classification;

and the detection unit is used for carrying out object detection and classification on the original video content according to the rule data of object detection and classification in the bottom database.

9. The system for mass embedding of content information in video according to claim 6, further comprising an underlying database unit, wherein,

the bottom database unit is used for presetting a bottom database; the bottom database comprises preset implantation rules, corresponding objects and classifications;

and the analysis unit is used for screening the objects which accord with the implantation rules according to the preset implantation rules in the bottom database and the corresponding objects and classification.

10. The system for batch embedding of content information in video according to claim 6, further comprising a statistical unit, wherein,

the statistical unit is used for acquiring the characteristic data of each content and the operation data of the whole system, generating a video implantation production report and establishing a video implantation model.

Technical Field

The invention relates to the technical field of video processing, in particular to a method and a system for implanting content information in a video in batch.

Background

Disclosure of Invention

In view of the foregoing technical problems, embodiments of the present invention provide a method and a system for implanting content information in a video in batch, which can implant specified content or information in a video in batch, thereby providing a more intelligent and efficient scheme for video rewriting and post-production.

The embodiment of the invention provides a method for implanting content information in a video in batch on one hand, which comprises the following steps:

acquiring an original video, and carrying out object detection and classification on the content of the original video;

screening objects which accord with preset implantation rules from the object detection and classification results;

acquiring implantation content information, replacing the object which accords with the preset implantation rule, and carrying out image adaptation;

analyzing the image sequence of the video implanted with the content information, and adjusting and optimizing the position, the angle and the size according to the data implanted with the content information and the data of the object according with the preset implantation rule;

and after completing content information implantation frame by frame, outputting the video with implanted content.

Further comprising the steps of:

presetting a bottom database; the bottom database comprises all content information to be implanted, corresponding artificial tags and characteristic data of the content;

and acquiring implanted content information from the bottom-layer database.

The bottom-layer database further comprises:

rule data of object detection and classification and result data of detection and classification;

and carrying out object detection and classification on the original video content according to the rule data of object detection and classification in the bottom database.

The bottom-layer database further comprises:

preset implantation rules and corresponding objects and classifications;

and screening the objects according with the implantation rules according to the preset implantation rules in the bottom database and the corresponding objects and classifications.

The replacing the object according with the preset implantation rule and performing image adaptation comprise:

and replacing or covering the corresponding object in the original video by the implanted content information, and carrying out image adaptation on the implanted content information according to the information of the original image so that the implanted content information is consistent with the image of the original video.

In another aspect, an embodiment of the present invention further provides a system for implanting content information in a video in batches, which includes a detection unit, an analysis unit, an implantation unit, an adaptation unit, and an output unit, wherein,

the detection unit is used for acquiring an original video and carrying out object detection and classification on the content of the original video;

the analysis unit is used for screening the objects which accord with preset implantation rules from the results of the object detection and classification;

the implantation unit is used for acquiring implantation content information, replacing the object which accords with the preset implantation rule and carrying out image adaptation;

the adaptive unit is used for analyzing the image sequence of the video implanted with the content information and adjusting and optimizing the position, the angle and the size according to the data implanted with the content information and the data of the object according with the preset implantation rule;

and the output unit is used for outputting the video with the implanted content after completing the implantation of the content information frame by frame.

And also includes an underlying database unit, wherein,

the bottom database unit is used for presetting a bottom database; the bottom database comprises all content information to be implanted, corresponding artificial tags and characteristic data of the content;

and the implantation unit is used for acquiring implantation content information from the bottom database.

And also includes an underlying database unit, wherein,

the bottom database unit is used for presetting a bottom database; the bottom database comprises rule data of object detection and classification and result data of detection and classification;

and the detection unit is used for carrying out object detection and classification on the original video content according to the rule data of object detection and classification in the bottom database.

And also includes an underlying database unit, wherein,

the bottom database unit is used for presetting a bottom database; the bottom database comprises preset implantation rules, corresponding objects and classifications;

and the analysis unit is used for screening the objects which accord with the implantation rules according to the preset implantation rules in the bottom database and the corresponding objects and classification.

And a statistical unit, wherein,

the statistical unit is used for acquiring the characteristic data of each content and the operation data of the whole system, generating a video implantation production report and establishing a video implantation model.

The technical scheme has the following advantages or beneficial effects:

in each embodiment of the invention, an image sequence of an existing video is read in, image data of all objects in the video is obtained through technologies such as object identification and classification, a target object with information inserted is selected through intelligent analysis, content to be inserted is implanted into the target object, the image is adjusted and optimized according to rules, the video with the information implanted is output, and data obtained by a system is subjected to statistical analysis, so that data multiplexing and inserted content changing are facilitated. The method provides a batch and intelligent method for the problem of specific content implantation such as advertisement implantation, special effect implantation and the like, improves the precision and the effect, and saves the labor and the time cost.

Drawings

Fig. 1 is a flowchart illustrating a process of embedding content information in a video in a batch manner according to an embodiment of the present invention.

Fig. 2 is a schematic structural diagram of a system for embedding content information in a video in batch according to a second embodiment of the present invention.

Fig. 3 is a schematic structural diagram of a system for embedding content information in a video in bulk according to a third embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

In each embodiment of the invention, the method is mainly applied to a specific object or position in the video file, and content information such as characters, icons, advertisements and the like is implanted. Such as but not limited to the following: the method comprises the steps of inputting various image information such as watermarks, advertisement LOGO, pictures and slogans into one or more specific objects or specific positions of a car body, a wall surface, a bus stop, a building, a person and the like in a video, such as movies, television shows, short films, comprehensive videos, video files shot by a person or an organization and the like. The specific application example can be that the advertisement icons are implanted into all bus bodies and bus stop boards in the video.

In each embodiment of the invention, the artificial intelligence technologies such as image recognition, object detection, object tracking and the like are utilized to provide a method for automatically implanting contents in batches on a target object in a video, so that the target object covering each frame of image in the video can be implanted naturally. Provides a more intelligent method for advertisement implantation, special effect production and the like. The method changes the mode of content implantation in the video by the traditional operation software, and saves a large amount of labor and time cost. The method has the advantages that a database is established for objects in the video, label management and statistics are carried out, reusable information is provided for different contents inserted into the video, and post-production of the video is more intelligent and efficient.

Fig. 1 is a flowchart illustrating a process of embedding content information in a video in a batch manner according to an embodiment of the present invention. As shown in fig. 1, the process of embedding content information in a video in batches includes the following steps:

step 101, obtaining an original video, and performing object detection and classification on the content of the original video.

The original video is the video to be embedded with the content, and the content embedding needs to be performed on part of the content. Content placement includes, but is not limited to, image placement, text placement, or other types of content placement. The content implantation mode can be a direct replacement mode or a mode of overlaying the original video image.

The original video comprises an object or content which needs to be replaced by content implantation, and after the original video is obtained, content analysis needs to be carried out on the original video to find out the object which needs to be replaced or covered, namely, object detection and classification are carried out. The detection aims at finding objects needing to be replaced or covered, and the classification aims at performing unified analysis on the same type of objects.

And 102, screening the objects which accord with preset implantation rules from the object detection and classification results.

The implantation rules are preset, namely objects needing to be implanted for replacement and replacement modes are preset. And further analyzing the object and the related classification data detected from the original video, thereby screening out the object which really needs to be replaced.

The implantation rule is the type, position, replacement or coverage mode, implantation content and the like of the replacement object, and the specific replacement object is determined according to the implantation content.

And 103, acquiring implantation content information, replacing the object which accords with the preset implantation rule, and performing image adaptation.

After the object to be replaced is obtained, the embedded content information, that is, the image or other content information for replacing the object, is acquired. And replacing the object which accords with the preset implantation rule with the implantation content information, so that the implantation content information replaces the related object in the original video.

The replaced image may not completely conform to the original image due to various reasons such as image content, effect, pixel, size and the like, so that further image adaptation is needed, and the implanted content information and the original video image are subjected to consent adaptation processing so as to be fused together.

And 104, analyzing the image sequence of the video implanted with the content information, and adjusting and optimizing the position, the angle and the size according to the data implanted with the content information and the data of the object according with the preset implantation rule.

Various problems still occur in the adapted image, and therefore, the image sequence of the video with the content information embedded therein needs to be further analyzed, the image content not covered by the embedded content information needs to be erased, and the background image in the original video image needs to be restored. Meanwhile, according to the specific data of the embedded content information and the data of the corresponding object, optimization adjustment of the position, the angle, the size and the like of the embedded content is needed, so that the image after the embedded content is more vivid.

And 105, after completing content information implantation frame by frame, outputting the video with implanted content.

After the content of the original video is implanted frame by frame, a new video is obtained, wherein the content is replaced, namely the video with the content information implanted in batches in the video is obtained.

Further, a bottom database needs to be preset; the bottom database comprises all content information to be implanted, corresponding artificial tags and characteristic data of the content; and acquiring implanted content information from the bottom-layer database.

The bottom database further comprises: rule data of object detection and classification and result data of detection and classification; and carrying out object detection and classification on the original video content according to the rule data of object detection and classification in the bottom database.

The bottom database further comprises: preset implantation rules and corresponding objects and classifications; and screening the objects according with the implantation rules according to the preset implantation rules in the bottom database and the corresponding objects and classifications.

Implanting content to replace the object meeting the preset implantation rule and performing image adaptation, comprising: and replacing the corresponding object in the original video by the implanted content information, and carrying out image adaptation on the implanted content information according to the information of the original image so that the implanted content information is consistent with the image of the original video.

Furthermore, it is also necessary to obtain feature data of each embedded content and operation data of the whole system, generate a video content embedding production report, and establish a video content embedding model.

In order to implement the above flow, another embodiment of the technical solution of the present invention provides a system for implanting content information in a video in batch, and fig. 2 is a schematic structural diagram of the system for implanting content information in a video in batch according to a second embodiment of the present invention.

As shown in fig. 2, the child story playing system includes a detection unit 21, an analysis unit 22, an implantation unit 23, an adaptation unit 24, and an output unit 25, wherein,

the detection unit 21 is configured to acquire an original video, and perform object detection and classification on the original video content;

the analysis unit 22 is used for screening the objects which accord with preset implantation rules from the results of the object detection and classification;

the implantation unit 23 is configured to acquire implantation content information, replace the object that meets the preset implantation rule, and perform image adaptation;

the adaptation unit 24 is configured to analyze an image sequence of the video into which the content information is embedded, and adjust and optimize a position, an angle, and a size according to the data of the embedded content information and the data of the object that meets the preset embedding rule;

the output unit 25 is configured to output the video with the content embedded after completing the content information embedding frame by frame.

Further, the system comprises an underlying database unit 26, wherein,

the bottom database unit 26 is used for presetting a bottom database; the bottom database comprises all implantation content information to be implanted, corresponding artificial tags and characteristic data of the content;

the implanting unit 23 is configured to obtain implanted content information from the underlying database.

The bottom database unit 26 is further configured to preset a bottom database; the bottom database comprises rule data of object detection and classification and result data of detection and classification;

the detecting unit 21 is configured to perform object detection and classification on the original video content according to the rule data of object detection and classification in the underlying database.

The bottom database unit 26 is used for presetting a bottom database; the bottom database comprises preset implantation rules, corresponding objects and classifications;

the analysis unit 22 is configured to screen the objects that meet the implantation rules according to the preset implantation rules in the bottom database and the corresponding objects and classifications.

Further, the system comprises a statistics unit 27, wherein,

the statistical unit 27 is configured to obtain feature data of each content and operation data of the entire system, generate a video implantation production report, and establish a video implantation model.

As shown in fig. 3, a third embodiment of the present invention provides another system for embedding content information in a video in a batch manner, wherein,

the system comprises three main parts: video reading, information embedding and video output.

The video reading mainly comprises a reading module which can read in the target video.

The information implantation is the most important part of the system, can process the read-in video, identify the target object in the video, select the target image to be implanted, implant the target image into the video according to a certain rule, and comprises five functional modules: the system comprises a target image library, an intelligent detection module, an intelligent analysis module, an intelligent implantation module and an intelligent statistic module. According to the information to be inserted, the images to be inserted are made in advance, all the images are subjected to label and data management to form a target image library, and the target image library is stored in a database; the intelligent detection module performs image recognition on the read target video to complete object detection and classification, and transmits all acquired image data to the intelligent analysis module; the intelligent analysis module analyzes the data such as categories and coordinates obtained by the intelligent detection module, screens out a target object according to the analysis result, and transmits the data of the target object to the intelligent implantation module; the intelligent implantation module inserts the image to be inserted into the target object according to the analysis result obtained by the intelligent analysis module, and automatically adjusts and optimizes the position, the angle and the size according to the data of the inserted image and the data of the target object; the intelligent statistical module can be used for counting data of all the intelligent detection modules, the intelligent analysis modules and the intelligent implantation modules and giving data statistical conditions before and after video processing; the data obtained by all modules will be stored in a database.

The video output mainly comprises an output module which can acquire all processed image sequences and export the processed video.

Specifically, the video reading mainly comprises a reading module which can read in a target video; the information implantation is the most important part of the system, can process the read-in video, identify the target object in the video, select the target image to be implanted, implant the target image into the video according to a certain rule, and comprises five functional modules: the system comprises a database, an intelligent detection module, an intelligent analysis module, an intelligent implantation module and an intelligent statistic module; the video output mainly comprises an output module which can export the processed video.

The five main modules about the information implantation part are as follows:

all image information and data are stored in the database. And according to the information required to be inserted, after the label management is carried out on the image to be inserted which is made in advance, forming a target image stock and storing the target image stock in a database. Image characteristic information generated in the system is also stored in the database.

The intelligent detection module is used for carrying out image recognition on the read target video, completing object detection and classification and transmitting all acquired image data to the intelligent analysis module;

the intelligent analysis module is used for analyzing the data such as categories, coordinates and the like obtained by the intelligent detection module, screening out a target object according to an analysis result, and transmitting the data of the target object to the intelligent implantation module;

the intelligent implantation module is used for inserting the image to be inserted into the target object according to the analysis result obtained by the intelligent analysis module, and automatically adjusting and optimizing the position, the angle and the size according to the data of the inserted image and the data of the target object;

and the intelligent statistical module can count the data of all the intelligent detection modules, the intelligent analysis modules and the intelligent implantation modules and give the data statistical conditions before and after video processing.

In each embodiment of the invention, an image sequence of an existing video is read in, image data of all objects in the video is obtained through technologies such as object identification and classification, a target object with information inserted is selected through intelligent analysis, content to be inserted is implanted into the target object, the image is adjusted and optimized according to rules, the video with the information implanted is output, and data obtained by a system is subjected to statistical analysis, so that data multiplexing and inserted content changing are facilitated. The method provides a batch and intelligent method for the problem of specific content implantation such as advertisement implantation, special effect implantation and the like, improves the precision and the effect, and saves the labor and the time cost.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the transceiving method according to various embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

While the preferred embodiments of the present invention have been described, it should be understood that modifications and adaptations to those embodiments may occur to one skilled in the art without departing from the principles of the present invention and are within the scope of the present invention.

11页详细技术资料下载
上一篇:一种医用注射器针头装配设备
下一篇:基于对比度识别动漫图像的观影限制方法

网友询问留言

已有0条留言

还没有人留言评论。精彩留言会获得点赞!

精彩留言,会给你点赞!

技术分类