A video retrieval method
A video and video library technology, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve problems such as large amount of calculation, limited accurate retrieval, and impact on retrieval speed, to ensure retrieval accuracy, improve accuracy and Flexibility, the effect of improving video retrieval speed
Active Publication Date: 2017-03-22
BEIJING AEROSPACE MEASUREMENT & CONTROL TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Most of the previous video retrieval methods were to extract and compare the features of the video itself or only use the characteristics of the brightness value, texture value or chromaticity of a single frame image, and then form the video feature curve and compare the curves, not only in terms of accurate retrieval Limited, and the amount of calculation is relatively large, which affects the retrieval speed
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
no. 1 example
[0032] In the first embodiment of the present invention, a video retrieval method, such as figure 1 As shown, when searching in the video library based on the sample video, the method includes the following specific steps:
[0033] Step S101, process all the videos in the video library, determine the key frames of each video and the key points on each key frame;
[0034] Step S102, processing the sample video to determine key frames of the sample video and key points on each key frame;
[0035] Specifically, the processing of all videos in the video library in step S101 and the processing of sample videos in step S102 include the following processes:
[0036] A1: Based on the inter-frame difference of the feature of the video to be processed, key frames are extracted from each frame of the video to be processed;
[0037] Further, the types of the features include at least one of the following: color features, shape features, texture features, edge features and motion feature...
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 provides a video retrieval method. The video retrieval method comprises: processing all videos in a video database to identify key frames of all the videos and key points of the key frames; processing a sample video to identify key frames of the sample video and key points of the key frames of the sample video; searching the video database on the basis of the key frames and key points of the sample video. If the sum of the key points of the key frames of a video in the video database is correspondingly matched with the sample video and is capable of reaching a setting condition, the video is identified to be the sample video; otherwise no sample video is identified. According to this arrangement, the precise retrieval of an image in video retrieval can be achieved to improve video retrieval speed and ensure retrieval accuracy. When the display performance of videos changing, the retrieval accuracy is hardly influenced. The video retrieval method is capable of retrieving within a particular area so as to improve the accuracy and flexibility of the video retrieval.
Description
technical field [0001] The invention relates to the technical field of video image processing, in particular to a video retrieval method. Background technique [0002] With the accumulation of TV programs and film and television works, the increase of digital video on the Internet, the development of wireless multimedia, and the application of a large number of multimedia such as video surveillance, digital library, video on demand, distance learning, and video advertisement, how to quickly retrieve massive videos The required information is becoming more and more important. In military operations, reconnaissance activities are essential, and the amount of information contained in videos is the largest among all media. Therefore, it is a common method to use automatic reconnaissance aircraft to shoot reconnaissance videos to achieve the purpose of reconnaissance of the enemy. When the automatic reconnaissance plane brings back a large number of videos, it will be quite time...
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 & Authority Patents(China)
IPC IPC(8): G06F17/30G06K9/46
CPCG06F16/7847
Inventor 张丽君韩暋贾凡王宗超党静雅张化良董碹陈韬张腾贾伟
Owner BEIJING AEROSPACE MEASUREMENT & CONTROL TECH