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

Unsupervised monocular depth estimation algorithm based on deep learning

A technology of depth estimation and deep learning, applied in neural learning methods, computing, computer components, etc., can solve problems such as the impact of prediction accuracy

Pending Publication Date: 2020-10-16
SOUTHEAST UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this type of method needs to assume that there is only camera motion in the scene, that is, the existence of moving targets such as vehicles and pedestrians is ignored.
When there are a large number of moving objects in the scene, the prediction accuracy of such methods will be greatly affected

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
  • Unsupervised monocular depth estimation algorithm based on deep learning
  • Unsupervised monocular depth estimation algorithm based on deep learning
  • Unsupervised monocular depth estimation algorithm based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The technical solution of the present invention will be further described in conjunction with the accompanying drawings and embodiments.

[0058] see figure 1 , the algorithm model of the present invention consists of three parts: depth network DepthNet, camera pose network PoseNet and optical flow network FlowNet. The depth network DepthNet outputs a depth image with the same resolution as the monocular input image, and the depth value is expressed in grayscale. The camera pose network PoseNet is used to estimate the pose transformation of the camera in three-dimensional space between adjacent frame images, and the light The flow network FlowNet is used to estimate the full optical flow between adjacent frame images, figure 2 It is the generation confrontation network structure of the optical flow network FlowNet.

[0059] Based on the above model, the present invention designs an unsupervised monocular depth estimation algorithm based on deep learning. By comparing...

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 an unsupervised monocular depth estimation algorithm based on deep learning. Through comparing the difference between the optical flow generated by the motion of the camera andthe all-optical flow, the detection of the moving target in the scene is realized; finally, the depth estimation effect of the algorithm is improved. According to the method, under the condition thata training label is not needed, for a moving monocular camera video, unsupervised estimation of a depth image, a camera pose and a moving optical flow can be achieved at the same time, the predictionprecision of the three tasks is excellent, and the precision and robustness of the algorithm are effectively enhanced by detecting a dynamic target in a scene.

Description

technical field [0001] The invention relates to a monocular depth estimation algorithm, in particular to an unsupervised monocular depth estimation algorithm based on deep learning. Background technique [0002] Computer vision uses computers to simulate human visual functions, enabling computers to have the human-like ability to recognize real three-dimensional scenes from two-dimensional plane images, including understanding and recognizing information such as content, movement and structure in the scene. However, due to the lack of depth information in three-dimensional space during the imaging process of planar images, the technology based on two-dimensional images has some inherent defects. Therefore, how to reconstruct the three-dimensional information of the scene from a single or multiple images, that is, depth estimation, has become a very important basic topic in the field of computer vision. Depth refers to the distance from a point in the scene to the plane wher...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/088G06V20/40G06F18/214
Inventor 王腾高昊昇薛磊
Owner SOUTHEAST UNIV
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