基于注意力机制和可分离卷积的双目立体匹配算法

郑秋梅; 温阳; 王风华

Chinese

您当前的位置：

首页 >

文章列表页 >

基于注意力机制和可分离卷积的双目立体匹配算法

更新时间：2026-09-04

- 基于注意力机制和可分离卷积的双目立体匹配算法
- Stereo matching based on attention mechanism and separable convolution
- 微电子学与计算机 2021年38卷第5期页码：42-47
- 作者机构：
  
  中国石油大学(华东) 计算机科学与技术学院,山东,青岛,266580
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61305008中央高校基本科研业务费专项资助 19CX02030A
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
郑秋梅, 温阳, 王风华. 基于注意力机制和可分离卷积的双目立体匹配算法[J]. 微电子学与计算机, 2021, 38(5): 42-47.

ZHENG Qiu-mei, WEN Yang, WANG Feng-hua. Stereo matching based on attention mechanism and separable convolution[J]. 2021, 38(5): 42-47.
郑秋梅, 温阳, 王风华. 基于注意力机制和可分离卷积的双目立体匹配算法[J]. 微电子学与计算机, 2021, 38(5): 42-47. DOI：

ZHENG Qiu-mei, WEN Yang, WANG Feng-hua. Stereo matching based on attention mechanism and separable convolution[J]. 2021, 38(5): 42-47. DOI：

摘要

针对当前基于卷积神经网络的双目立体匹配算法需要较高的特征提取能力且网络的参数量过多的问题，提出一种基于注意力机制的立体匹配网络，在特征提取阶段采用改进后的通道注意力机制根据通道内所含的信息进行特征加权，同时采用改进的空间金字塔结构实现多尺度特征提取，以提高网络的特征提取能力；设计3D注意力模块和3D可分离卷积进行视差计算，相比于标准卷积不仅可以降低网络的计算参数同时增加了通道维数可以保证匹配精度.最后，在Scene Flow数据集、KITTI 2012数据集和KITTI 2015数据集上进行评估，实验表明，本文的网络模型在保证匹配精度的同时有效减少网络的计算参数.

Abstract

To improve the feature extraction capability of current stereo matching network and reduce the parameter

the multi-scale context attention network for stereo matching network is proposed. In the feature extraction stage

the improvedchannel-wise attention mechanism is used to weight the features based on the information contained in the channel

and the improved spatial pyramid structure is used to achieve multi-scale feature extraction to improve the networks feature extraction ability.A three-dimensional attention module and a three-dimensional separable convolution for disparity calculation.Compared with the standard convolution

the computational parameters of the network can be reduced and the channel dimension can be increased to ensure the matching accuracy. Experiments on Scene Flow datasets

KITTI 2012 datasets and KITTI 2015 datasets show that the network model in this paper can effectively reduce the calculation parameters of the network while ensuring matching accuracy.

关键词

Keywords

references

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010.

KANG J H, CHEN L, DENG F, et al. Context pyramidal network for stereo matching regularized by disparity gradients[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 157: 201-215. DOI:10.1016/j.isprsjprs. 2019.09.012.

HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1026-1034. DOI: 10.1109/ICCV.2015.123.

CHEN X Z, KUNDU K, ZHU Y K, et al. 3D object proposals for accurate object class detection[J]. Proceedings of the 28th International Conference on Neural Information Processing Systems, 2015(1): 424-432. DOI: 424

NGUYENT P, JEONJ W. Wide context learning network for stereo matching[J]. Signal Processing: Image Communication, 2019(78): 263-273. DOI:10.1016/j.image.2019.07.008.

PANG J H, SUN W X, REN JS J, et al. Cascade residual learning: a two-stage convolutional neural network for stereo matching[C]//2017 IEEE International Conference on Computer Vision Workshops (ICCVW). Venice, Italy: IEEE, 2017: 878-886. DOI: 10.1109/ICCVW.2017.108.

MAYER N, ILG E, HAUSSER P, et al. A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 4040-4048. DOI: 10.1109/CVPR.2016.438.

GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, 2010: 315-323.

SONG T, KIM Y, OH C, et al. Simultaneous deep stereo matching and dehazing with feature attention[J]. International Journal of Computer Vision, 2020, 128(4): 799-817. DOI:10.1007/s11263-020-01294-2.

HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023. DOI:10.1109/TPAMI.2019.2913372.

CHANG J R, CHEN Y S. Pyramid stereo matching network[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE, 2018: 5410-5418. DOI: 10.1109/CVPR.2018.00567.

CHEN L C, PAPANDREOU G, KOKKINOS I. DeepLab: semantic image segmentation with deep convolutional nets, atrousconvolution, and fully connectedCRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848. DOI:10.1109/TPAMI.2017.2699184.

MENZE M, GEIGER A. Object scene flow for autonomous vehicles[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE, 2015: 3061-3070. DOI: 10.1109/CVPR.2015.7298925.

LI X, WANG W H, HU X L, et al. Selective kernel networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach: IEEE, 2019: 510-519. DOI: 10.1109/CVPR.2019.00060.

KENDALL A, MARTIROSYAN H, DASGUPTA S, et al. End-to-end learning of geometry and context for deep stereo regression[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017: 66-75. DOI: 10.1109/ICCV.2017.17.

LIU R C, JIANG D W, ZHANG LL, et al. Deep depthwise separable convolutional network for change detection in optical aerial images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020(13): 1109-1118. DOI:10. 1109/JSTARS.2020.2974276.

GEIGER A, LENZ P, URTASUN R. Are we ready for autonomous driving? The KITTI vision benchmark suite[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, RI, USA: IEEE, 2012: 3354-3361. DOI: 10.1109/CVPR.2012.6248074.

HOWARD A G, ZHU M L, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[C]//Proceedings of Computer Vision and Pattern Recognition. 2017.

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

一种基于Zynq的ROS软硬件协同计算架构设计与实现

基于图像分割的改进立体匹配算法

基于区域深度特征的人头检测方法

结合图像梯度和亮度的并行信任传播算法

基于相位相关的图像三维重建算法