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

Salient Object Detection Method Combining Color and Depth Information

A technology of depth information and target detection, applied in the field of image processing, to increase robustness and reliability, and improve the effect of detection

Active Publication Date: 2019-02-05
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: how to robustly highlight the most prominent objects in the image evenly in complex scenes with known depth priors

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
  • Salient Object Detection Method Combining Color and Depth Information
  • Salient Object Detection Method Combining Color and Depth Information
  • Salient Object Detection Method Combining Color and Depth Information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0024] figure 1 It is a flow chart of the salient object detection method combining color and depth information of the present invention. The process includes two major steps of locating the salient target and inferring the boundary of the salient target, and further details of each major step are as follows:

[0025] A. Input binocular image. The entire flowchart is based on the left figure, and the binocular image is used to calculate the depth map for step C. The calculation of the depth map uses the method "Stereo matching with nonparametric smoothness priors in feature space" of Smith et al.

[0026] B. Compute saliency using region color contrast on the left co...

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 salient object detection method combining color and depth information, comprising: S1: inputting a binocular image, and calculating the depth map of the left image; S2: calculating the initial saliency map of the left image by using a region color contrast method , and then calculate the second saliency map based on the depth map; S3: Combine the two saliency maps in S2 to generate a saliency map that filters out background noise, extract salient regions from it, and sample seed points from it, as Estimation of the salient object position; S4: Using the seed point in S3, infer the boundary of the salient object, and diffuse the entire salient object. The invention can significantly improve the detection effect of salient objects.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a salient target detection method combining color and depth information. Background technique [0002] Saliency detection is a way for computers to emulate the human visual system to understand scenes in images. When the human eye observes a picture, it always focuses on a part of the most interesting area. Saliency detection is to simulate this process, filter out irrelevant information, and highlight the most attractive foreground area. Driven by different application types, saliency detection can be divided into two categories: gaze point prediction and salient object detection. The former is mainly to predict the position of human eyes in the image, which is mainly used in robot positioning, recognition and advertising. The latter allows the computer to automatically identify the most prominent object in the image, and is mainly used in segmentation of objects of ...

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): G06K9/46G06T7/11G06T7/55
CPCG06T2207/10024G06T2207/10004G06V10/462
Inventor 童若锋唐延龙唐敏张赟
Owner ZHEJIANG UNIV