Multi-scale enhanced monocular depth estimation method

A depth estimation, multi-scale technology, applied in the computer vision field of deep learning, which can solve the problems of low accuracy of monocular depth estimation, low accuracy of depth map, and easy loss of intermediate layer feature information.

Active Publication Date: 2021-05-11
UNIV OF SHANGHAI FOR SCI & TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the monocular depth estimation methods based on deep learning, in order to improve the receptive field of the monocular depth estimation network, most of the CNNs used are obtained through repeated stacking of long-range dependency capture and backpropagation. When transmitting information back and forth over a long distance,

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
  • Multi-scale enhanced monocular depth estimation method
  • Multi-scale enhanced monocular depth estimation method
  • Multi-scale enhanced monocular depth estimation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0067] The monocular depth estimation framework mentioned in this example is configured with two NVDIATitian Xp GPU hardware. The operating system used in this experiment is Windows, the deep learning framework is PyTorch, and the batch size is set to 4.

[0068] The data used in this embodiment is the NYU DepthV2 data set, which consists of 1449 pairs of RGB images and their corresponding images with depth information. In this embodiment, the officially divided training set and test set are used. Among them, 249 scenes are used as training set and 215 scenes are used as test set.

[0069] In addition, in order to improve the training speed of the model, the feature extraction part of the network framework (ABMN) proposed in this embodiment uses ImageNet[pre-trained parameters to initialize the front-end network, and uses the SGD optimizer to set the learning rate to is 0.0001, the momentum momentum is set to 0.9, and the weight decay weight_decay is set to 0.0005.

[0070] ...

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 multi-scale enhanced monocular depth estimation method, which comprises the following steps: step 1, inputting a single RGB image, and then performing multi-scale feature extraction on the RGB image by adopting a context and receptive field enhanced high-resolution network CRE-HRNet to obtain a high-resolution first image; step 2, using a residual error expansion convolution unit of a receptive field enhancement module to carry out expansion convolution on the first depth image to obtain a second image; and step 3, capturing long-distance pixel points of the second depth image by using a weighted non-local neighborhood module to obtain a depth image. According to the method provided by the invention, the monocular depth estimation precision is high on the basis of obtaining the feature information of the intermediate layer.

Description

technical field [0001] The invention belongs to the field of computer vision of deep learning, and in particular relates to a multi-scale enhanced monocular depth estimation method. Background technique [0002] Image-based depth information estimation refers to learning the three-dimensional information of the scene from a single or multiple two-dimensional images, aiming to predict the pixel depth of the image, and the estimated depth map can be applied to intelligent robots and scene reconstruction , semantic segmentation, unmanned driving and other fields, has important research significance and application value, and is an important research issue in the field of computer vision. Among them, estimating the depth information from a single image is also called monocular depth estimation, because it only needs a single image to achieve depth estimation, which is more portable than the multiple images required by the multi-view method, but because The single image may be t...

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): G06T7/55G06T5/50
CPCG06T7/55G06T5/50G06T2207/20081
Inventor 宁悦王文举
Owner UNIV OF SHANGHAI FOR SCI & TECH
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