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

A monocular image depth estimation method and apparatus fusing sparse known tags

An image depth and depth estimation technology, applied in the field of image processing, can solve the problem of inaccurate image depth estimation and achieve the effect of reducing uncertainty and reliable scene depth

Inactive Publication Date: 2019-03-12
INST OF AUTOMATION CHINESE ACAD OF SCI +1
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims to provide a method and device for estimating monocular image depth by fusing sparse known labels to solve the current problem of inaccurate image depth estimation

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 monocular image depth estimation method and apparatus fusing sparse known tags
  • A monocular image depth estimation method and apparatus fusing sparse known tags
  • A monocular image depth estimation method and apparatus fusing sparse known tags

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0050] Such as figure 1 As shown, the present invention provides a monocular image depth estimation method that fuses sparse known labels, and the process is as follows:

[0051] S101. Obtain an RGB image to be estimated;

[0052] S102. Obtain sparse known labels by using single-line laser radar;

[0053] S103. Input the RGB image to be es...

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 a monocular image depth estimation method and a device for fusing sparse known tags, comprising the following steps: acquiring an RGB image to be estimated; Acquisition of Sparse Known Labels by Single-line Lidar; Inputting the RGB image to be estimated into a pre-established depth estimation model to obtain a first depth map of the RGB image to be estimated; The first depthmap is fused with a sparse known tag by a full connection layer to obtain a final depth map of the RGB image to be estimated. The technical proposal provided by the invention reduces the uncertaintyof mapping from a monocular image to a depth map by fusing sparse known tags, thereby effectively estimating a more reliable scene depth.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a monocular image depth estimation method and device for fusing sparse known labels. Background technique [0002] Estimating scene depth from monocular images is an important method for understanding the geometric structure in the scene, and incorporating depth information can improve the performance of algorithms when studying many other computer vision problems, such as semantic segmentation, pose estimation, and object detection. At present, there are depth sensors (such as Microsoft Kinect) that can acquire RGB-D depth images, but such sensors have a limited range of perception depth (less than 4m), and will generate a lot of noise under strong light, so they are used in various application scenarios. its limitations. [0003] There are many problems in the existing monocular image depth estimation. For example, a two-dimensional image corresponds to an infinite vari...

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): G06T7/521
CPCG06T7/521G06T2207/10028G06T2207/20081G06T2207/20084
Inventor 张一帆李耀宇
Owner INST OF AUTOMATION CHINESE ACAD OF SCI