A Deep Learning Saliency Detection Method Based on Global Prior and Local Context

A deep learning and context technology, applied in the field of image processing and computer vision, can solve the problems of inability to effectively detect salient objects in complex background images, misdetection of high-level features, etc., and achieve reduced learning ambiguity, good robustness, and high detection results accurate effect

Active Publication Date: 2020-10-13
BEIJING UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The problem to be solved by the present invention is: in the salient object detection technology of images, the salient objects in complex background images cannot be effectively detected simply by relying on manually set features and some prior knowledge; The saliency detection method based on deep learning only takes the original image or the local area of ​​the original image as the input of the deep learning model, which may cause false detection due to the noise of the extracted high-level features

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 Deep Learning Saliency Detection Method Based on Global Prior and Local Context
  • A Deep Learning Saliency Detection Method Based on Global Prior and Local Context
  • A Deep Learning Saliency Detection Method Based on Global Prior and Local Context

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The invention provides a deep learning saliency detection method based on global prior and local context. The method first performs superpixel segmentation on color images and depth images, and based on middle-level features such as compactness, uniqueness and background of superpixels , through the global prior deep learning model, the global prior saliency map is calculated; combined with the global prior saliency map and the local context information in the color image and the depth image, the initial saliency map is obtained through the deep learning model; finally, according to the spatial consistency The initial saliency map is optimized based on the similarity of sex and appearance, and the final saliency map is obtained. The invention is suitable for image salience detection, has good robustness, and the detection result is accurate.

[0034] Such as figure 1 Shown, the present invention comprises the following steps:

[0035] 1) Use the SLIC superpixel segmen...

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 deep learning saliency detection method based on global prior and local context. First, superpixel segmentation is performed on color images and depth images. Based on the middle-level features such as compactness, uniqueness and background of each superpixel, Obtain the global prior feature map of each superpixel, and further pass the deep learning model to obtain the global prior saliency map; then, combine the global prior saliency map and the local context information in the color image and the depth image, and pass the deep learning model , to obtain the initial saliency map; finally, optimize the initial saliency map according to the spatial consistency and appearance similarity, and obtain the final saliency map. The application of the present invention solves the problem that the traditional saliency detection method cannot effectively detect salient objects in complex background images, and also solves the problem that the existing saliency detection method based on deep learning causes false detection due to noise in the extracted high-level features. question.

Description

technical field [0001] The invention belongs to the field of image processing and computer vision, in particular to a deep learning saliency detection method based on global prior and local context. Background technique [0002] When human eyes perceive the external environment, they can always extract interesting content from scenes containing a lot of information. This ability is called visual attention. Visual attention is a research hotspot in computer vision. There are two main aspects of research: one is to study eye gaze based on visual attention mechanism, and the other is to study the extraction of salient target regions, that is, saliency detection. The purpose of saliency detection is to separate the more eye-catching target area from the background in the image, and then extract the target and the information it carries, which is widely used in image segmentation, image recognition, video anomaly detection and other fields. [0003] At present, the research on s...

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 Patents(China)
IPC IPC(8): G06T7/11G06T7/162G06K9/46
CPCG06T7/11G06T7/162G06T2207/20081G06T2207/10028G06T2207/10024G06V10/462
Inventor 付利华丁浩刚李灿灿崔鑫鑫
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products