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

Video action detection method based on time sequence convolution modeling

A timing and action technology, applied in video processing and image fields, can solve problems such as difficult training and poor performance of dual-stream networks, and achieve the effects of accurate detection and overcoming incompleteness

Active Publication Date: 2020-01-14
HUNAN UNIV
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it has more parameters than 2D ConvNets due to the extra temporal dimension, which makes it difficult to train
In practice, its performance is often found to be inferior to dual-stream networks

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
  • Video action detection method based on time sequence convolution modeling
  • Video action detection method based on time sequence convolution modeling
  • Video action detection method based on time sequence convolution modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. figure 1 A flow chart of a video timing action detection method based on timing convolution modeling provided by the present invention, the method includes the following steps:

[0032] S100: Traverse the video stream through the motion proposal generation technology to generate proposal fragments that contain as much motion as possible.

[0033] The above actions are not limited in type and complexity, and can also be a certain kind of activity, such as running, horse riding, etc.

[0034] In one implementation, a multi-scale action proposal can be generated by sliding windows of different scales on the video sequence. The binary classification model can be further used to remove some background fragments and retain the action fragments, thereby optimizing the quality of the proposal.

[0035] In another impl...

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 a video action detection method based on time sequence convolution modeling. The method comprises the steps of firstly, adopting an action proposal generation technology to generate proposal fragments containing complete actions as much as possible; secondly, screening out a complete proposal with high overlapping degree by using non-maximum suppression in cooperation with weighted IoU, and then performing sparse sampling on the proposal to obtain a specified number of video frames; extracting space-time features of the video frames by adopting a deep network model; dividing the obtained frame-level spatial-temporal features into three stages according to an evolution mode, and performing sequential modeling on the features of each stage by using sequential convolution; and finally, predicting an action category and detecting an action occurrence time interval by using a classifier and a regression device. By applying the method, the incompleteness of the proposal can be overcome, and the time sequence information of the video stream is reserved to the maximum extent, so that the action in the video can be detected more accurately.

Description

Technical field [0001] The invention relates to the technical field of image and video processing, in particular to a video action detection method based on time series convolution modeling. Background technique [0002] Motion detection is one of the research directions that have attracted much attention in the field of video analysis in recent years. It not only requires the recognition of the action category, but also the location of the time interval in which the action occurs in the uncut, arbitrarily long video. [0003] Since the THUMOS’14 challenge switched spatio-temporal positioning tasks to temporal positioning tasks, rapid progress has been made in the field of motion detection in recent years. However, high-precision and high-efficiency motion detection is still a major difficulty in the field of video analysis. The difficulty of the task is that it not only has the background, noise, occlusion, blur and other common interferences in static image processing, but also c...

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): G06K9/00G06K9/62
CPCG06V40/20G06V20/41G06V20/46G06F18/241G06F18/253
Inventor 张汗灵龙亚艺
Owner HUNAN UNIV
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