结合注意力与无监督深度学习的单目深度估计

岑仕杰; 何元烈; 陈小聪

doi:10.12052/gdutxb.190140

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

结合注意力与无监督深度学习的单目深度估计

更新时间：2026-05-27

- 结合注意力与无监督深度学习的单目深度估计
- A Monocular Depth Estimation Combined with Attention and Unsupervised Deep Learning
- 广东工业大学学报 2020年37卷第4期页码：35-41
- 作者机构：
  
  广东工业大学计算机学院,广东,广州,510006
- 作者简介：
  
  岑仕杰(1992–)，男，硕士研究生. 主要研究方向为计算机视觉、深度学习和深度估计
  何元烈(1976–)，男，副教授. 主要研究方向为计算机视觉、深度学习和智能机器人，E-mail:heyuanlie@163.com
- 基金信息：
  
  国家自然科学基金资助项目(61876043)
- DOI：10.12052/gdutxb.190140
  中图分类号： TP249
- 网络首发：2020-07-11，
  
  纸质出版：2020
- 稿件说明：
移动端阅览
岑仕杰, 何元烈, 陈小聪. 结合注意力与无监督深度学习的单目深度估计[J]. 广东工业大学学报, 2020, 37(4): 35-41.

Cen Shi-jie, He Yuan-lie, Chen Xiao-cong. A Monocular Depth Estimation Combined with Attention and Unsupervised Deep Learning[J]. 2020, 37(4): 35-41.
岑仕杰, 何元烈, 陈小聪. 结合注意力与无监督深度学习的单目深度估计[J]. 广东工业大学学报, 2020, 37(4): 35-41. DOI： 10.12052/gdutxb.190140.

Cen Shi-jie, He Yuan-lie, Chen Xiao-cong. A Monocular Depth Estimation Combined with Attention and Unsupervised Deep Learning[J]. 2020, 37(4): 35-41. DOI： 10.12052/gdutxb.190140.

摘要

针对当前的无监督单目深度估计方法边界模糊的问题

提出了一种基于双重注意力模块的网络架构。这种架构能有效利用图像特征的远程上下文信息解决深度估计中的边界模糊问题。整个框架使用基于视图合成的无监督方法训练

模型框架包括深度估计网络与位姿估计网络

同步估计深度和相机位姿变换。双重注意力模块嵌入在深度估计网络中

包含位置注意力模块和通道注意力模块

能表示远程空间位置和不同特征图间的上下文信息

从而使网络估计出细节更好的深度信息。在KITTI数据集以及Make3D数据集上的实验结果表明

本文的方法能有效提高单目深度估计的精度和解决深度估计边界模糊问题。

Abstract

To solve the problem of boundary blurring of current unsupervised monocular depth estimation method

a network architecture is proposed based on dual attention module. This architecture can effectively solve the problem of boundary blurring of depth estimation by using long-range context information of image features. The model framework that includes depth estimation network and pose estimation network is trained by an unsupervised method based on view synthesis and estimation depth and camera pose transformation at the same time. The dual attention module is embedded in the depth estimation network

including position attention module and channel attention module. This module can represent the long-range spatial location and the context information between different feature maps

so that the network can estimate the depth information with better details. The experimental results on the KITTI dataset and the Make3D dataset show that our method can effectively improve the accuracy of the monocular depth estimation and can solve the depth estimation boundary blur problem.

关键词

Keywords

references

ZHU F L, ZENG B, CAO J. Parallel optimization and implementation of SLAM algorithm based on particle filter [J]. Journal of Guangdong University of Technology, 2017, 34(2): 92-96.

XIE J, GIRSHICK R, FARHADI A. Deep3D: Fully automatic 2D-to-3D video conversion with deep convolutional neural networks[C]//European Conference on Computer Vision. Amsterdam: Springer, 2016: 842-857.

GARG R, BG V K, CARNEIRO G, et al. Unsupervised CNN for single view depth estimation: Geometry to the Rescue[C]//European Conference on Computer Vision. Amsterdam: Springer, 2016: 740-756.

GODARD C, AODHA O M, BROSTOW G J. Unsupervised monocular depth estimation with left-right consistency[C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6602-6611.

ZHOU T H, BROWN M, SNAVELY N, et al. Unsupervised learning of depth and ego-motion from video[C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6612-6619.

MAHJOURIAN R, WICKE M, ANGELOVA A, et al. Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 5667-5675.

YIN Z C, SHI J P. GeoNet: unsupervised learning of dense depth, optical flow and camera pose[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 1983-1992.

HUANG J, LEE A B, Mumford D. Statistics of range images[C]//Proceedings IEEE Conference on Computer Vision and Pattern Recog-nition. Hilton Head Island: IEEE, 2000: 324-331.

FU J, LIU J, TIAN H, et al. Dual attention network for scene segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 3146-3154.

HE K, ZHANNG X, REN S, et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770-778.

WANG Z, BOVIK A C, SHEIKH H R, et al . Image quality assessment: from error visibility to structural similarity [J ] . IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

GODARD C, AODHA O M, BROSTOW G J, et al. Digging into self-supervised monocular depth estimation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 3828-3838.

EIGEN D, PUHRSCH C, FERGUS R. Depth map prediction from a single image using a multiscale deep network[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT press, 2014: 2366-2374

LIU F, SHEN C, LIN G, et al . Learning depth from single monocular images using deep convolutional neural fields [J ] . IEEE Transactions on Pattern Analysis Machine Intelligence, 2015, 38(10): 2024-2039.

ZOU Y, LUO Z, HUANG J, et al. DF-Net: unsupervised joint learning of depth and flow using cross-task consistency[C]//European Conference on Computer Vision. Munich: Springer International Publishing, 2018: 38-55.

RANJAN A, JAMPANI V, BALLES L, et al. Adversarial collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 12240-12249.

BIAN J, LI Z, WANG N, et al. Unsupervised scale-consistent depth and ego-motion learning from monocular video[C]//Proceedings of the 32th International Conference on Neural Information Processing Systems. Vancouver: MIT press, 2019: 35-45.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于注意力机制的无监督GAN多聚焦图像融合

面向电力场景图像的动态自适应增量目标检测DA-IOD算法

基于域不变判别特征学习的深子域自适应方法

基于主动学习和视觉状态空间模型的热点检测器

基于AAGV-YOLOX模型的输电线路异物检测研究