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

Two-dimensional video saliency detection method based on long-term and short-term memory

A long-short-term memory and two-dimensional video technology, which is applied in the digital image and digital video processing and multimedia fields, to achieve the effects of strong scalability, improved performance, and reasonable and efficient algorithms

Pending Publication Date: 2019-10-15
方玉明
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Although there are many visual attention models introduced above, the visual attention model still has limitations in the study of two-dimensional videos.

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
  • Two-dimensional video saliency detection method based on long-term and short-term memory
  • Two-dimensional video saliency detection method based on long-term and short-term memory
  • Two-dimensional video saliency detection method based on long-term and short-term memory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0052] Wherein, the technical features, abbreviations / abbreviations, symbols, etc. involved in this article are explained, defined / illustrated based on the well-known knowledge / common understanding of those skilled in the art.

[0053] The process of the present invention is as figure 1 As shown, the specific process is as follows:

[0054] The present invention designs a 3D convolutional network (3D-ConvNet) to extract video short-term temporal features. ...

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 relates to a two-dimensional video saliency detection method based on long-term and short-term memory. The method is characterized by comprising the following steps: firstly, extractingshort-term time sequence features by utilizing a 3D convolutional network (3D-ConvNet); secondly, extracting long-term time sequence features by adopting a bidirectional long-term and short-term memory network (B-ConvLSTM); fusing the extracted short-term time sequence features and long-term time sequence features; and finally, obtaining a saliency map through fusion result deconvolution. The model is combined with long-term and short-term time sequence characteristics, the operation information of the salient target in the video can be effectively reserved, and the saliency prediction experiment result of the two-dimensional video proves that the proposed model can obtain a good detection effect.

Description

technical field [0001] The invention relates to a visual attention detection method for detecting the salience of two-dimensional video, which belongs to the technical field of multimedia, specifically belongs to the technical field of digital image and digital video processing, and is specifically a two-dimensional video saliency detection method based on long short-term memory . Background technique [0002] Visual attention is an important mechanism in visual perception. It can quickly detect salient information in natural images. When observing natural images, selective attention will allow you to focus on some specific salient information, and because Limit processing resources and ignore other unimportant information. Basically, visual attention methods can be divided into two types: bottom-up and top-down; bottom-up processing is data-driven and task-independent automatic salient region detection, while top-down methods involve some specific tasks cognitive process....

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): G06K9/46G06K9/00G06N3/04
CPCG06N3/049G06V20/46G06V10/462G06N3/045
Inventor 方玉明黄汉秦乐晨阳
Owner 方玉明
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