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

A saliency object detection method and device based on a bidirectional fusion network

A technology that integrates network and object detection. It is applied in the fields of computer vision, deep learning, and pattern recognition. It can solve the problems of ineffective use of low-level detail information, and achieve the effect of improving the effect, increasing the number of channels, and fine edges.

Active Publication Date: 2019-05-28
中科人工智能创新技术研究院(青岛)有限公司
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The low-level detailed information can only work in the last few stages, and cannot effectively use the low-level detailed information.

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 saliency object detection method and device based on a bidirectional fusion network
  • A saliency object detection method and device based on a bidirectional fusion network
  • A saliency object detection method and device based on a bidirectional fusion network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present disclosure will be further described below in conjunction with the accompanying drawings and embodiments.

[0051]It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used in this disclosure have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0052] It should be noted that the terminology used here is only used to describe specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and / or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and / or comb...

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 saliency object detection method and device based on a bidirectional fusion network. The method and the device can achieve the better fusion of the characteristics of different levels through employing the bidirectional fusion network. The method comprises the following steps of extracting a multi-scale and multi-level feature map of an input picture; gradually fusing themulti-scale and multi-level feature map from the bottom layer to the top layer by adopting a forward feature fusion sub-neural network to obtain a seed feature map; adopting a reverse feature fusionsub-neural network to fuse the seed feature map with the multi-scale multi-level feature map layer by layer from the top layer to the bottom layer to obtain a feature map with the same resolution as the input picture; and carrying out multi-convolution fusion on the obtained feature map with the same resolution as the input picture by adopting a plurality of convolution layers of the reverse fusion sub-neural network to obtain a significant object segmentation map.

Description

technical field [0001] The present disclosure relates to the fields of pattern recognition, computer vision, and deep learning, in particular to a salient object detection method and device based on a two-way fusion network. Background technique [0002] The salient object detection task aims to identify and segment the most attention-grabbing objects in an image. It is a fundamental problem in the field of computer vision and is often used as a preprocessing process for visual tasks such as object detection, image editing, and image segmentation. With the development of deep convolutional neural networks, especially the publication of fully convolutional neural networks, dense predictions such as salient object detection have achieved important developments in recent years. [0003] In general, deep convolutional networks can extract different levels of features from input images. Specifically, the top layers of deep convolutional networks encode high-level semantic infor...

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): G06N3/04G06K9/62
Inventor 谭铁牛张彰王亮胡学财王海滨
Owner 中科人工智能创新技术研究院(青岛)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