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

Video saliency detection method based on deep fusion

A detection method, a significant technology, applied in the field of computer vision, can solve the problems of not making full use of video spatial information and temporal information, performance degradation, etc.

Inactive Publication Date: 2020-03-24
HANGZHOU DIANZI UNIV
View PDF1 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Unfortunately, these models still cannot make full use of the rich spatial information and temporal information in the video, resulting in the performance of these models will also be reduced to a certain extent when dealing with complex 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
  • Video saliency detection method based on deep fusion
  • Video saliency detection method based on deep fusion
  • Video saliency detection method based on deep fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with accompanying drawing.

[0042] Such as figure 1 Shown, the inventive method is specifically as follows:

[0043] Step (1). The extraction of depth features, the specific method is as follows:

[0044] First construct a deep feature extraction network, the deep feature extraction network is composed of a symmetrical spatial feature extraction branch and a temporal feature extraction branch; the spatial feature extraction branch and the temporal feature extraction branch are constructed based on the VGG-16 model, Each branch includes 13 convolutional layers, that is, 5 convolutional blocks, the convolution kernel size is set to 3×3, the stride size is 1, and 4 maximum pooling layers, the pooling size is set to 2×2, The stride size is 2; the convolutional layers of different branches have different weight parameters. The reason is that the inputs of the two branches are different, and each branch ...

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 video saliency detection method based on deep fusion. The method comprises a deep feature extraction network, a deep feature fusion network and a saliency prediction network.Firstly, a depth feature extraction network extracts multistage depth features to generate depth space features and depth time features; then, an attention module is adopted to respectively reinforceand learn the depth features generated by each stage in the two branches, and the depth features are fused with the multi-stage depth features in a depth feature fusion network grading mode; and thedepth features obtained by fusion is combined with boundary information and prediction is carried out by a salient prediction network to generate a final significance map of the current frame. According to the network model provided by the invention, spatial information and time information can be fully and effectively utilized to predict the salient target in the video.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a video saliency detection method based on deep fusion. Background technique [0002] Saliency detection is a research hotspot in the field of computer vision, and has a wide range of applications in related research directions, such as pedestrian re-identification, content-based video compression, image quality assessment, and object detection and segmentation. s concern. Depending on the type of input, saliency detection models can be divided into two categories, namely image saliency detection models and video saliency detection models. So far, there have been many works dedicated to image saliency detection, but due to the lack of large-scale pixel-by-pixel annotated video datasets, and the difficulty of mining the relationship between frames in videos, the focus on video saliency Research on detection models has received relatively little attention. [0003] The...

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): G06K9/00G06N3/04
CPCG06V20/40G06N3/045
Inventor 周晓飞温洪发张继勇颜成钢
Owner HANGZHOU DIANZI 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