RGBD saliency detection method and related device

A detection method, RGB image technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problem of insignificant effect of saliency detection

Pending Publication Date: 2020-10-27
NANKAI UNIV +1
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the existing saliency detection schemes, such as low contrast, small objects, multiple objects and other complex scenes, th

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
  • RGBD saliency detection method and related device
  • RGBD saliency detection method and related device
  • RGBD saliency detection method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Embodiments of the present application are described below with reference to the drawings in the embodiments of the present application. The terms used in the embodiments of the present application are only used to explain specific embodiments of the present application, and are not intended to limit the present application.

[0061] We first describe some of the concepts involved in this article.

[0062] (1) RGB-D image data. In 3D computer graphics, RGB-D image data includes two images: one is an ordinary RGB three-channel color image (RGB image for short), and the other is a depth image (Depth Map).

[0063] The pixel value in the RGB image is a red, green and blue (BlueGreenRed, RGB) color value, and the pixel value can be a long integer representing the color. For example, the pixel value is 256*R+100*G+76B, where R represents the red component, G represents the green component, and B represents the blue component. In each color component, the smaller the value...

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 provides an RGBD saliency detection method and device. The method comprises the steps: importing an RGB image and a depth image into a neural network model comprising a plurality of feature extraction modules and a plurality of feature enhancement modules for processing, and obtaining a plurality of cross-modal feature maps; wherein any feature extraction module is used for performing feature extraction on input data to obtain a processing result of the feature extraction module; wherein any feature enhancement module is used for carrying out feature extraction on the depth imageto obtain a depth contrast enhancement map, and optimizing a processing result of the feature extraction module by utilizing the depth contrast enhancement map to obtain a cross-modal feature map ofthe feature enhancement module. And finally, fusing the plurality of cross-modal feature maps by using a pyramid model to obtain a detection result map of saliency detection. By implementing the method and the device, a relatively good saliency detection effect can be achieved in complex scenes such as low contrast.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to an RGBD saliency detection method and related devices. Background technique [0002] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is the branch of computer science that attempts to understand the nature of intelligence and produce a new class of intelligent machines that respond in ways similar to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making. Research in the field of artificial intelligence includes ro...

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): G06K9/62G06K9/46
CPCG06V10/462G06F18/253G06F18/214
Inventor 程明明曹洋吴日辉白蔚
Owner NANKAI 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