Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A depth prediction method of monocular image based on neural network

A neural network and prediction method technology, applied in the field of image depth prediction, which can solve the problem of not fully considering global and local features.

Active Publication Date: 2019-03-12
ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above methods do not fully consider the global and local features, so there is still room for improvement in the accuracy of depth prediction

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 depth prediction method of monocular image based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described in detail below with reference to the embodiments of the accompanying drawings.

[0027] The present invention proposes a neural network-based monocular image depth prediction method, and its overall implementation block diagram is as follows: figure 1 As shown, it includes two processes: training phase and testing phase;

[0028] The specific steps of the training phase process are:

[0029] Step 1_1: Select Q original monocular images and the real depth image corresponding to each original monocular image, and form a training set, and mark the qth original monocular image in the training set as {I q (i,j)}, compare the training set with {I q (i,j)} The corresponding real depth image is denoted as Among them, Q is a positive integer, Q≥200, if Q=4000, q is a positive integer, 1≤q≤Q, 1≤i≤W, 1≤j≤H, W represents {I q (i,j)} and The width of , H represents {I q (i,j)} and height, I q (i,j) means {I q (i,j)} The pi...

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 monocular image depth prediction method based on a neural network, It is constructed to include an input layer, the neural network of hidden layer and output layer, the hidden layer includes an encoding and decoding network framework, The coding network framework consists of five neural network blocks, 1 inference layer and 1 connection layer, The first and second neuralnetwork blocks are composed of two convolution layers and one maximum pool layer, The third to fifth neural network blocks are composed of three convolution layers and one maximum pool layer, The inference layer consists of two perforated convolutional neural networks. The decoding network framework consists of five neural network blocks, five connection layers and four independent bilinear upsampling layers. Each neural network block consists of one convolutional layer and one bilinear upsampling layer. The monocular images in the training set are input to the neural network for training. When testing, the predicted monocular image is input into the neural network model to predict, and the predicted depth image is obtained. The advantages are high prediction accuracy and low computationalcomplexity.

Description

technical field [0001] The invention relates to an image depth prediction technology, in particular to a neural network-based monocular image depth prediction method. Background technique [0002] With the rapid development of machine learning, it has become possible for machines to imitate humans to estimate the distance of objects from images to a certain extent, that is, machines can predict the depth of a single image and obtain a depth map to a certain extent. Depth maps are widely used in 3D reconstruction, robot navigation and other fields. At the same time, depth maps are helpful in computer vision fields such as detection and segmentation because they provide information about the distance of objects. Depth maps are currently mainly derived from different types of depth cameras. However, depth cameras have limitations in application due to their shortcomings such as high price and low portability. However, the cost of depth information extracted by monocular vision ...

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): G06T7/50G06N3/04G06N3/08
CPCG06N3/08G06T7/50G06T2207/20084G06T2207/20081G06N3/045
Inventor 周武杰潘婷顾鹏笠张宇来向坚邱薇薇周扬
Owner ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com