A sample extraction method and device for a video classification problem

A technology for video classification and extraction methods, applied in video data retrieval, video data query, instruments, etc., can solve problems such as unfavorable model training, uneven sample quality, insufficient coverage of clips, etc., to enhance sample quality and improve training quality. Effect

Pending Publication Date: 2019-05-07
BOE TECH GRP CO LTD
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the above sample is equivalent to a video clip, it is likely that the clip cannot fully cover the content information of the entire 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A sample extraction method and device for a video classification problem
  • A sample extraction method and device for a video classification problem
  • A sample extraction method and device for a video classification problem

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0072] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present invention will be more thoroughly understood, and will fully convey the scope of the present invention to those skilled in the art.

[0073] The embodiment of the present invention provides a sample extraction method for a video classification problem, such as figure 1 As shown in the figure, the method extracts a feature image that can summarize the content information of the video data from a plurality of consecutive single-frame images corresponding to the video data, so as to form a sample, thereby ensuring the quality of the sample. The embodiment of the p...

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 invention discloses a sample extraction method and device for a video classification problem, and relates to the technical field of video classification. the method for extracting the samples fromthe video data is optimized so as to ensure that the samples can cover the whole content information of the video data, meanwhile, redundant image data in the samples are avoided, the sample qualityis enhanced, and the training quality of a video classification model can be improved. The technical scheme includes; acquiring video data; Analyzing the video data to obtain a plurality of continuoussingle-frame images corresponding to the video data; extracting Feature images from the plurality of continuous single-frame images to form a sample, wherein the feature images are used for summarizing content information of the video data, and the sample does not contain redundant image data. The method is applied to extracting the samples for training the video classification model from the video data.

Description

technical field [0001] The present invention relates to the technical field of video classification, in particular to a sample extraction method and device for video classification problems. Background technique [0002] With the rise of deep learning based on graphics processors, video classification has become easier to implement. Today's video classification usually refers to video classification based on deep learning. Video classification depends on huge data sets. If you want to achieve video classification in general fields, tens of thousands or even hundreds of thousands of databases may not be enough for training video classification models. Therefore, the existing video classification model based on deep learning is mainly trained in the subdivision field. Since this can focus video classification only on a specific scene, it is relatively easy to collect sufficient video data for training, such as : Collect video data matching specific scenes from video libraries...

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
IPC IPC(8): G06K9/62G06F16/73
CPCG06V20/44G06V20/47G06V20/49G06F18/214G06V20/41G06F18/22
Inventor 贾红红赵骥伯
Owner BOE TECH GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products