Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Adaptive pooling video behavior identification method

A recognition method and adaptive technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem of inability to distinguish the importance of any video frame, and achieve the effect of verifying the validity

Active Publication Date: 2017-12-05
广西荷福智能科技有限公司
View PDF20 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the image content of adjacent video frames is relatively similar, a large amount of redundant information will be generated. Generally, methods based on neural network deep learning cannot distinguish the importance of any video frame for the current video classification.
At the same time, when such methods classify videos, they are essentially completing multiple image classification operations, and do not treat the video as a whole

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
  • Adaptive pooling video behavior identification method
  • Adaptive pooling video behavior identification method
  • Adaptive pooling video behavior identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0036] see figure 1 Provided is an adaptive pooling video behavior recognition method, which is implemented through the following steps:

[0037] Step 1: Perform pre-training of the video feature extraction network, including feature description based on video appearance and video feature description based on superimposed motion information, and complete feature description for video frame images;

[0038] Step 2: Construct a video frame importance prediction...

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 provides an adaptive pooling video behavior identification method. By adopting an adaptive pooling encoding way, important information in a video is effectively used, and the video as an integrated body is processed correspondingly, and the importance degree of every frame of the tested video is predicted, and in addition, based on the level of the importance degree, the pooling encoding operation of the video frames is carried out. Based on the distribution of the important frames of the current video, the characteristic codes of the video are determined, and therefore adaptive performance is provided, and the most suitable description scheme is found for any video samples.

Description

technical field [0001] The invention proposes an adaptive pooling video behavior recognition method, which is a novel application technology for classifying and recognizing video samples. Background technique [0002] With the popularity of smartphones and the Internet, the amount of video sharing has increased exponentially. A large number of online videos are shot on the target of some kind of human behavior. The main purpose of video behavior recognition is to effectively classify massive video files so that people can quickly extract the video files they are interested in. Video behavior recognition has become a popular field with a wide range of application scenarios, such as: abnormal target behavior classification, video content understanding, home surveillance video detection, video recommendation, etc. [0003] In the field of computer vision, there are many methods that can be used for video action recognition. These methods can be mainly divided into two catego...

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): G06K9/00
CPCG06V20/46
Inventor 王嘉欣刘袆楠王兵
Owner 广西荷福智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com