Method for estimating geometrical information of scene from single image through GAN (Generative Adversarial Network)

A single image and geometric information technology, applied in biological neural network models, image enhancement, image analysis, etc., can solve the problems of low output image resolution, long training time, large training samples, etc., to improve performance and accuracy , increase the number of layers, reduce the effect of measurement cost

Active Publication Date: 2018-11-16
QICHEN GUANGZHOU ELECTRONICS TECH CO LTD
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention adopts the structure of the fully convolutional network, removes the fully connected layer, and effectively reduces the parameter amount of the network. Although it can improve the problem of low resolution of the output image during the convolution process, the training samples required by this method are particularly large. long training time

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
  • Method for estimating geometrical information of scene from single image through GAN (Generative Adversarial Network)
  • Method for estimating geometrical information of scene from single image through GAN (Generative Adversarial Network)
  • Method for estimating geometrical information of scene from single image through GAN (Generative Adversarial Network)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In order to better understand the technical solution proposed by the present invention, the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0057] Usually, in order to obtain the geometric information of a certain scene, especially the depth information, people use the Kinect camera to take the depth image of the scene, but the measurement distance of the Kinect is short, and the acquired depth information is sparse. In order to obtain all the depth information of the scene, multiple measurements are required. Therefore, we hope to estimate the full depth information of the scene by using the RGB image captured by the normal camera and the sparse depth image captured by the Kinect camera. An ordinary camera takes an RGB image and a Kinect takes a depth image at the same position and angle.

[0058] In the present invention, the image of the scene and the depth of several pixels in the image are...

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 method for estimating the geometrical information of a scene from a single image through a GAN (Generative Adversarial Network), and the method comprises the steps: inputtingan image of the scene and the depths of a plurality of pixels in the image into a trained GAN to obtain a depth image of the scene, wherein the depths of the pixels are the distances from the points,corresponding to the pixels in the image, in the scene to an observer, and the depth image is the sum of the depths of all pixels of one image. According to the invention, the method takes the image of the scene and the depths of a few of corresponding pixels in the image as the input, and employs a dual-consistency constraint GAN for predicting or estimating the depth image of the scene, so the method is simple and effective, and is low in cost.

Description

technical field [0001] The invention belongs to the field of computer image processing, and relates to a method for estimating scene geometric information from a single image, in particular to a method for estimating scene geometric information from a single image by using a generative confrontation network. Background technique [0002] Depth information prediction and estimation are very important in engineering applications, such as robotics, autonomous driving, augmented reality (AR) and 3D modeling. At present, there are mainly two methods for obtaining depth images, which are direct ranging and indirect ranging. Direct ranging refers to the use of various hardware devices to directly obtain depth information. For example, the TOF camera obtains the distance between the object in the target scene and the transmitter by emitting continuous near-infrared pulses; the laser radar scans the object in the measured scene by emitting laser light, and then obtains the distance ...

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): G06T7/50G06N3/04
CPCG06N3/04G06T2207/20081G06T7/50
Inventor 李俊黄韬张露娟马震远
Owner QICHEN GUANGZHOU ELECTRONICS TECH CO LTD
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