Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Binocular visual sense depth information obtaining method based on deep learning

A technology of depth information and binocular vision, applied in the field of stereo vision, can solve the problems of inapplicability, large distance, poor effect, etc., and achieve the effect of convenient expansion and low cost

Inactive Publication Date: 2017-04-26
HANGZHOU LANXIN TECH CO LTD
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the mainstream products currently on the market still have their own scope of use and limitations
For example, Microsoft's Kinect (TOF) can only be used indoors and outdoor scenes with limited light, and the distance is limited; monocular structured light technology needs to emit active energy, and it is also not suitable for outdoor scenes with strong light; Binocular stereo matching technology belongs to the field of computer stereo vision. Although this technology is suitable for indoors and outdoors, it is not effective when dealing with missing textures, and there are problems such as precise focusing and calculation time; equipment such as lidar is relatively expensive, and Most of them can only obtain the depth information of the two-dimensional plane

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
  • Binocular visual sense depth information obtaining method based on deep learning
  • Binocular visual sense depth information obtaining method based on deep learning
  • Binocular visual sense depth information obtaining method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0021] This embodiment provides a method for acquiring binocular stereo information based on deep learning. The specific implementation method is as follows: Step 1: Acquire binocular pictures and depth pictures. Get N pairs of pictures taken by the binocular vision system {P i |i=1,2,...,N}, each image pair includes the left image captured by the left camera and the right picture taken by the right camera The superscript i represents the image order. Get each image pair P at the same time i The corresponding depth map D i . {P i ,D i |i=1,2,...,N} constitute the original data set.

[0022] The depth camera for collecting data in the present invention adopts Microsoft Kinect (using TOF-time-of-flight technology). When collecting, it should be as close as possible to the binocular camera, and ensure that the center position is aligned. The pos...

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 binocular visual sense depth information obtaining method based on deep learning, which belongs to the stereoscopic visual sense technology field and comprises the following steps: 1) obtaining training data; 2) marking the original data set to generate the training data; 3) conducting deep learning network training to the obtained image and depth information; and 4) obtaining the depth map output. According to the invention, the luminance information of the left image and the right image that are mutually correlated is calculated; and through the use of a large amount of image and depth information, training and learning are carried out so as to obtain a disparity data model of the binocular image, and after the actual acquisition of the binocular information and according to the training model, it is possible to rapidly and accurately obtain the stereoscopic information of the current scene so as to successfully obtain the depth. The method transfers calculation amount from depth obtaining to the training process, and the hardware is light in weight without the need of laser and energy. Cost-effective and simple to use, the method can be conveniently expanded. The method does not actively emit energy and is suitable for scenes both indoors and outdoors.

Description

technical field [0001] The invention belongs to the technical field of stereo vision, and in particular relates to a binocular vision depth information acquisition method based on deep learning. Background technique [0002] In recent years, depth information has gained more and more applications in sensors. The technologies for obtaining depth information mainly include binocular stereo matching, TOF (Time of Flight, time of flight), monocular structured light, laser radar and other technologies. These technologies can add additional depth information to the sensor, and have a wide range of applications in image recognition and processing, scene understanding, VR, AR, and robotics. However, the mainstream products currently on the market still have their own scope of use and limitations. For example, Microsoft's Kinect (TOF) can only be used indoors and outdoor scenes with limited light, and the distance is limited; monocular structured light technology needs to emit acti...

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 Applications(China)
IPC IPC(8): G06T7/80G06T7/593
CPCG06T2207/20081
Inventor 时岭高勇
Owner HANGZHOU LANXIN 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
Eureka Blog
Learn More
PatSnap group products