Supercharge Your Innovation With Domain-Expert AI Agents!

Image saliency object detection method and system based on extreme downsampling

An object detection, extreme technology, applied in the field of computer vision, can solve problems such as easy to lose salient objects

Active Publication Date: 2021-03-19
NANKAI UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As mentioned above, high-level semantic feature learning has not been well explored in salient object detection tasks, which also makes various methods that can obtain better salient object edges, but it is easy to lose the entire salient object.

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
  • Image saliency object detection method and system based on extreme downsampling
  • Image saliency object detection method and system based on extreme downsampling
  • Image saliency object detection method and system based on extreme downsampling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment provides an image salient object detection method based on extreme downsampling;

[0033] Image salient object detection methods based on extreme downsampling, including:

[0034] S101: Acquire a target image to be detected;

[0035] S102: Input the target image to be detected into the trained neural network model based on extreme downsampling, and output salient objects in the target image.

[0036] As one or more examples, such as figure 1 As shown, the neural network based on extreme downsampling, the network structure includes: an encoder and a decoder connected to each other;

[0037] The encoder includes: a bottom-up network connected to each other and an extreme downsampling module;

[0038] The decoder includes: a top-down network;

[0039] Among them, the extreme downsampling module takes the last feature of the bottom-up network as an input value, and performs deep downsampling on the last feature to obtain global features;

[0040] And th...

Embodiment 2

[0088] This embodiment provides an image salient object detection system based on extreme downsampling;

[0089] An image salient object detection system based on extreme downsampling, including:

[0090] An acquisition module configured to: acquire a target image to be detected;

[0091] The output module is configured to: input the target image to be detected into the trained neural network model based on extreme downsampling, and output salient objects in the target image.

[0092] It should be noted here that the above acquisition module and output module correspond to steps S101 to S102 in the first embodiment, and the examples and application scenarios realized by the above modules and the corresponding steps are the same, but are not limited to those disclosed in the first embodiment above content. It should be noted that, as a part of the system, the above-mentioned modules can be executed in a computer system such as a set of computer-executable instructions.

[0093...

Embodiment 3

[0096] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.

[0097] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, o...

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 an image saliency object detection method and system based on extreme downsampling. The method comprises the steps: acquiring a to-be-detected target image; and inputting a to-be-detected target image into the trained neural network model based on extreme downsampling, and outputting the salient object in the target image. An extreme down-sampling module is designed based on the new extreme down-sampling technology of the invention, and through gradually deeper underground sampling, extracted features after down-sampling become smaller and globalized, and the space sizeof the features gradually becomes smaller until the features become feature vectors, so that global modeling of the saliency object of the whole natural image is obtained, and the deep convolutionalneural network can better locate the position of the salient object, so that the salient object is not easy to leak, and the detection precision of the salient object is greatly improved on the basis.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a method and system for detecting salient objects in an image based on extreme downsampling. Background technique [0002] The statements in this section merely mention the background art related to this application, and do not necessarily constitute the prior art. [0003] The goal of salient object detection is to detect and segment the most salient objects in a given natural image, which is a very important basic task in the field of computer vision. It plays a pivotal role in computer vision and is applied to a variety of sub-tasks in the field of computer vision, such as image editing, weakly supervised semantic and instance segmentation, visual target tracking, etc. These tasks often regard salient object detection as an important task. pre-steps to enhance their performance, or to extract features more easily. In addition, salient object detection is al...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/20G06V10/40G06V2201/07G06N3/045G06F18/253
Inventor 程明明吴宇寰刘云
Owner NANKAI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com