RGB-D saliency target detection method

A RGB-D and target detection technology, applied in the field of image processing and stereo vision, can solve the problems of not being able to effectively highlight salient targets, suppress background areas, and not make full use of them, so as to achieve good salient target detection performance and improve accuracy Effect

Active Publication Date: 2020-08-25
TIANJIN UNIV
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Secondly, in the post-fusion strategy, most of the existing technologies fuse the saliency predictions of the RGB stream and the depth stream through pixel-level addition or multiplication.

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
  • RGB-D saliency target detection method
  • RGB-D saliency target detection method
  • RGB-D saliency target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Embodiments of the present invention propose a RGB-D salient object detection method based on cross-modal joint feature extraction and low value fusion loss. By designing the cross-modal joint feature extraction part, the complementarity between RGB features and depth features is effectively captured; by designing the salient object detection part, the single-modal multi-scale features and cross-modal joint are effectively integrated feature, which improves the accuracy of saliency detection per stream; by designing a low-value fusion loss, the lower bound of the saliency value is effectively improved, and the fusion between different detection results is promoted.

[0036] The whole process is divided into six parts: 1) single-modal feature extraction; 2) cross-modal joint feature extraction; 3) salient target detection; 4) low-value fusion loss design; 5) overall network loss design; 6) network training Strategy design, the specific steps are as follows:

[0037] 1. ...

Embodiment 2

[0081] figure 1 The technical flow chart of the present invention is given, mainly including six parts: single-modal feature extraction, cross-modal joint feature extraction, salient target detection, low-value fusion loss design, overall network loss design and network training strategy design.

[0082] figure 2 A specific implementation block diagram of the present invention is given.

[0083] image 3 The structural diagrams of the cross-modal feature extraction module (CFM) and the RGB saliency detection part of the fusion block (FB) are given.

[0084] Figure 4 An example of RGB-D salient object detection is given. Among them, the first column is the RGB image, the second example is the depth map, the third column is the truth map of the salient object detection, and the fourth column is the result obtained by the method of the present invention.

[0085] It can be seen from the results that the method of the present invention effectively fuses the information of t...

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 RGB-D saliency target detection method, and the method comprises the following steps: respectively obtaining the single-mode saliency features of each stage of an RGB imageand a depth image through single-mode feature extraction; selecting RGB and depth single-mode saliency features of each level through cross-mode joint feature extraction, capturing complementary features of an RGB image and a depth image level by level, and generating cross-mode joint features; inputting the cross-modal joint features and the single-modal saliency features into a saliency target detection part. By designing low-value fusion loss and network overall loss, fusion of RGB flow and deep flow detection results and supervised learning of the network are realized, and a final saliencydetection result is output. According to the method, valuable cross-modal joint features are extracted and captured through the cross-modal joint features, the network pays attention to a low-value significance region of the significance graph through designed low-value fusion loss, and the lower bound of the significance value is improved.

Description

technical field [0001] The invention relates to the technical fields of image processing and stereo vision, in particular to an RGB-D salient target detection method. Background technique [0002] In the face of complex natural scenes, the human visual system has the ability to quickly search and locate regions of interest and targets. By introducing the visual attention mechanism into computer vision, computing resources can be optimized so that the processing of visual information is more in line with the visual characteristics of the human eye. Salient object detection aims to automatically identify salient regions in different scenes, and has been widely used in tasks such as segmentation, redirection, retrieval, encoding, and classification. Significant progress has been made in image salient object detection in recent years. In fact, the human visual system also has the ability to perceive the depth information in the scene, and the depth information can be used as t...

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): G06K9/62G06K9/46G06N3/04
CPCG06V10/40G06N3/045G06F18/253
Inventor 雷建军祝新鑫范晓婷石雅南李奕
Owner TIANJIN UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap