Unlock instant, AI-driven research and patent intelligence for your innovation.

Image salient target detection method using filtering fusion

A significant and filtered technology, applied in the field of image processing, can solve the problems of low segmentation accuracy and inability to effectively integrate different levels, so as to achieve the effect of improving the effect

Pending Publication Date: 2021-10-22
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing image salient target segmentation methods cannot effectively integrate features of different levels, resulting in low segmentation accuracy

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 salient target detection method using filtering fusion
  • Image salient target detection method using filtering fusion
  • Image salient target detection method using filtering fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0029] An image salient target detection method using filter fusion proposed by the present invention uses a computer to automatically segment a salient target in the image for an image.

[0030] Such as figure 1 Shown, method of the present invention comprises the following steps:

[0031] The specific method of step (1) is as follows:

[0032] Image features are encoded using a Resnet34 network pretrained on ImageNet. The network parameters of Resnet34 are shown in Table 1. The output features of conv2_x, conv3_x, conv4_x, conv5_x are taken out as the output of the 4 levels of the encoder. The known input feature is (H, W, 3) (the first two numbers in brackets indicate the resolution, and the last number indicates the number of channels). Then the output feature of conv2_x is (H / 4, W / 4, 64), the output feature of conv3_x is (H / 8, W / 8, 128), the output ...

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 segmentation method using filtering fusion, and the method comprises the steps of carrying out the encoding of an image through employing an encoder network, and obtaining the features of m levels after the encoding; fusing the features then in a decoder using a filtering fusion module; performing sigmoid after conv of the high level feature, then performing up-sampling to serve as a weight multiplied by the current level feature to serve as a filtered feature of the current level, then performing up-sampling on the high level feature, performing conv processing on the high level feature, then connecting the high level feature with the feature in a channel dimension, and performing conv processing to obtain a fused feature of the current level; and finally, optimizing the network model by using a loss function. According to the method, the image salient target detection effect can be improved. And through the use of the filtering fusion module, features of different levels can be effectively fused.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting a salient object in an image. Background technique [0002] Image salient object detection refers to the automatic segmentation of salient objects in images by computer. The technology has a wide range of application scenarios, such as image compression, or as a preprocessing task for object recognition, semantic segmentation, object tracking, etc. [0003] In order to obtain accurate image salient object segmentation results, the traditional solution is to manually design a feature extraction method, and then perform pixel-by-pixel classification based on this feature. [0004] Existing image salient target segmentation methods cannot effectively integrate features of different levels, resulting in low segmentation accuracy. Therefore, this paper proposes a method that can effectively fuse different levels of features. Contents of the inventio...

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): G06T7/10G06K9/46G06K9/62
CPCG06T7/10G06T2207/10016G06F18/253Y02T10/40
Inventor 张继勇吕成涛颜成钢孙垚棋李宗鹏
Owner HANGZHOU DIANZI UNIV