Key video frame extraction method and device and storage medium
A video key frame, video technology, applied in the field of computer vision, can solve the problem of difficulty in extracting video key frames, and achieve the effect of reducing redundant information, improving speed, and saving costs
Inactive Publication Date: 2020-01-10
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
View PDF5 Cites 13 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, if the motion deformation in the video is small, the phenomenon of similar I frames will also occur. This extraction technology based on inter-frame deformation is sometimes difficult to extract video key frames that reflect the difference in video content.
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 approach
[0064] In order to improve the accuracy of conversion from the RGB color space of the video frame to the binary coding space, in the embodiment of the present invention, a deep hash network structure is provided, such as figure 1 As shown, the deep hash network provided by the embodiment of the present invention includes a feature learning network and a hash function learning network. The feature learning network is a twin convolutional neural network based on weight sharing (Weight Sharing), including 3 convolutional layers (Conv ) and 1 fully connected layer (FC1), where each convolutional layer is connected to the maximum pooling layer (Pool) and the Relu activation function, and the second maximum pooling layer is connected to the local response normalization layer ( LRN); It should be noted that the fully connected layer FC1 is subsequently connected to the Relu activation function. It should be understood that the above network structure is only one embodiment of the pre...
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 key video frame extraction method, a video key frame extraction device and a storage medium, which are used for reducing redundant information in a video processing process and improving the video processing speed. The video key frame extraction method comprises the steps of extracting an I frame from a to-be-analyzed video; for each extracted I frame, determining a corresponding deep hash code by using a deep hash network, the deep hash network being obtained by training by using a pre-generated image sample pair; according to the depth hash code corresponding to eachI frame, determining a Hamming distance between every two I frame depth hash codes; clustering the extracted I frames according to the Hamming distance between every two I frame depth hash codes; foreach cluster, respectively determining the information entropy of each I frame contained in the cluster; and extracting an I frame with the maximum information entropy from each cluster to form a keyframe of the to-be-analyzed video.
Description
technical field [0001] The present invention relates to the technical field of computer vision, in particular to a key video frame extraction method, device and storage medium. Background technique [0002] In content-based video indexing and retrieval systems, a large number of videos usually need to be processed. However, video is composed of continuous video frames, and a piece of adjacent video frames often have the same semantic information. These frames are redundant for analyzing video content. If processed frame by frame, it will bring huge amount of calculation and noise. . By analyzing and determining the most representative frames in the video, from the low-level perceptual description to the high-level semantic description, the main points of the video at each meaning level can be obtained. Therefore, extracting video keyframes is one of the key steps in video analysis. [0003] The traditional video key frame extraction technology usually uses the I frame to ...
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 Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06V20/46G06N3/045
Inventor 段运强井雅琪原春锋时磊李扬曦胡燕林郭承禹张翠佟玲玲段东圣任博雅谢程利刘雨帆张子琦胡卫明
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT