Video semantic information obtaining method and apparatus
A semantic information and video acquisition technology, applied in the video field, can solve the problems of inability to completely restore the specific semantic information of the video, cannot reflect the specific details of the video content, and limited video information, so as to facilitate directional analysis and acquisition and complete video semantic information Accurate, accuracy-enhancing effects
Active Publication Date: 2018-08-10
BEIJING ALLOOK TECH CO LTD
View PDF3 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The former is mainly based on the video introduction, and the video content covered by the video introduction is limited and cannot reflect the specific details of the video content; the latter is mainly for character recognition and emotion recognition on the video screen, so the restored video information is limited and cannot Completely restore the specific semantic information corresponding to the video
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0085] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations as sequential processing, many of the operations may be performed in parallel, concurrently, or simultaneously. In addition, the order of operations can be rearranged. The process may be terminated when its operations are complete, but may also have additional steps not included in the figure. The processing may correspond to a method, function, procedure, subroutine, subroutine, or the like.
[0086] The "processing equipment" referred to in this context is "computer equipment", also known as "computer", which refers to intelligent electronic devices that can perform predetermined processing procedures such as numerical calculations and / or logic calculations by running predetermined programs or instructions. The device may include a processor and a m...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention aims to provide a video semantic information obtaining method and device. The method comprises the steps of performing target extraction on video frames in a video to determine vision objects comprised in the video frames; then according to object features corresponding to the vision objects, determining scene information corresponding to one or more video frames; and finally according to the scene information, determining video semantic information corresponding to the video frames of the video. Compared with the prior art, detailed complete video semantic information can be automatically obtained based on the video, so that a large amount of manpower resources used for obtaining the video semantic information are saved; and meanwhile, the obtained video semantic informationis convenient for subsequent video analysis, search or the like.
Description
technical field [0001] The invention relates to the field of video technology, in particular to a technology for acquiring video semantic information. Background technique [0002] At present, methods for obtaining video content mainly include: obtaining according to a video introduction, or obtaining after analyzing the video content. The former is mainly based on the video introduction, and the video content covered by the video introduction is limited and cannot reflect the specific details of the video content; the latter is mainly for character recognition and emotion recognition on the video screen, so the restored video information is limited and cannot Completely restore the specific semantic information corresponding to the video. [0003] Therefore, how to obtain detailed video semantic information and further support video applications has become one of the problems to be solved urgently by those skilled in the art. Contents of the invention [0004] The objec...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityApplications(China)
IPC IPC(8): G06K9/00G06F17/30
CPCG06F16/7844G06V20/40G06F16/7837
Inventor罗江春陈锡岩
OwnerBEIJING ALLOOK TECH CO LTD