Unlock instant, AI-driven research and patent intelligence for your innovation.

Classification method, terminal and computer storage medium

A classification method and classification algorithm technology, applied in computer parts, computing, neural learning methods, etc., can solve problems such as low accuracy of classification results

Pending Publication Date: 2021-01-01
OPPO CHONGQING INTELLIGENT TECH CO LTD
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the focus of the existing models is on the processing algorithm of the video frame, and the video frame to be classified is simply extracted by processing all the video frames or down-sampling the original video at a fixed frequency; it can be seen that the existing There is a technical problem of low accuracy in the classification results obtained by the video classification method

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Classification method, terminal and computer storage medium
  • Classification method, terminal and computer storage medium
  • Classification method, terminal and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] An embodiment of the present application provides a classification method, which is applied to a terminal, figure 1 For a schematic flow chart of an optional classification method provided in the embodiment of this application, refer to figure 1 As shown, the above classification methods may include:

[0027] S101: Obtain the original video frame of the video to be classified;

[0028] At present, when the existing video classification algorithm performs video preprocessing before classification, it generally down-samples the original video at a fixed frequency. However, when the sampling frequency is too high, more redundant information will be introduced into the video frames obtained by sampling, which will reduce the efficiency of the algorithm. However, when the sampling frequency is too low, more original video information will be lost and the performance of the algorithm will be reduced. Moreover, fixed frequency is easy to sample to get fuzzy frames, which is ...

Embodiment 2

[0115] Figure 4 Schematic diagram of the structure of a terminal provided in the embodiment of this application Figure 1 ,Such as Figure 4 As shown, the embodiment of this application provides a terminal, including:

[0116] Obtaining module 41, for obtaining the original video frame of video to be classified;

[0117] Clustering module 42, is used for clustering the feature vector of original video frame based on clustering algorithm, obtains clustering result;

[0118] Extraction module 43, is used for extracting video frame from the cluster cluster of clustering result, obtains the key frame of video to be classified;

[0119] The classification module 44 is configured to classify key frames of the video to be classified according to an image classification algorithm to obtain a classification result of the video to be classified.

[0120] Optionally, the terminal also includes:

[0121] Determination module, for after obtaining the original video frame of the video...

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

No PUM Login to View More

Abstract

The embodiment of the invention discloses a classification method, which is applied to a terminal, and comprises the steps of obtaining an original video frame of a to-be-classified video, clusteringfeature vectors of the original video frame based on a clustering algorithm to obtain a clustering result, extracting a video frame from a clustering cluster of the clustering result to obtain a key frame of the to-be-classified video; and classifying the key frames of the to-be-classified video according to an image classification algorithm to obtain a classification result of the to-be-classified video. The embodiment of the invention further provides a terminal and a computer storage medium.

Description

technical field [0001] The present application relates to video classification technology, in particular to a classification method, terminal and computer storage medium. Background technique [0002] Nowadays, with the great success of the convolutional neural network (CNN, Convolutional Neural Networks) model based on deep learning theory in the fields of image classification and target detection, and video gradually becoming an important information carrier in daily life, CNN-based video classification It has become a research hotspot in the industry. [0003] The existing video classification models generally have two ideas, one is to process each frame in the video as an independent image, and finally fuse the classification results of each frame; the other is to mine the differences between frames. correlation for better classification. However, the focus of the existing models is on the processing algorithm of the video frame, and the video frame to be classified is...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/75G06K9/62G06N3/04G06N3/08
CPCG06F16/75G06N3/08G06N3/045G06F18/23
Inventor 尹康
Owner OPPO CHONGQING INTELLIGENT TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com