自动化学报2024，Vol.50Issue(8)：1631-1645,15.DOI:10.16383/j.aas.c230049
联合深度超参数卷积和交叉关联注意力的大位移光流估计
Large Displacement Optical Flow Estimation Jointing Depthwise Over-parameterized Convolution and Cross Correlation Attention
摘要
Abstract
To improve the computation accuracy and robustness of deep-learning based optical flow models under large displacement scenes,we propose an optical flow estimation method jointing depthwise over-parameterized con-volution and cross correlation attention.First,we construct a depthwise over-parameterized convolution model by combining the common convolution and depthwise convolution,which extracts more features and accelerates the convergence speed of optical flow network.This improves the optical flow accuracy without increasing computation complexity.Second,we exploit a feature extraction encoder based on cross correlation attention network,which ex-tracts multi-scale long distance context feature information by stack the attention layers to obtain a larger recept-ive field.This improves the robustness of optical flow estimation under large displacement scenes.Finally,a pyram-id residual iteration network by combing cross correlation attention and depthwise over-parameterized convolution is presented to improve the overall performance of optical flow estimation.We compare our method with the exist-ing representative approaches by using the MPI-Sintel and KITTI datasets.The experimental results demonstrate that the proposed method shows better optical flow estimation performance,especially achieves better computation accuracy and robustness under large displacement areas.关键词
光流/大位移/交叉关联注意力/深度超参数卷积/深度学习Key words
Optical flow/large displacement/cross correlation attention/depthwise over-parameterized convolution/deep learning引用本文复制引用
王梓歌,葛利跃,陈震,张聪炫,王子旭,舒铭奕..联合深度超参数卷积和交叉关联注意力的大位移光流估计[J].自动化学报,2024,50(8):1631-1645,15.基金项目
国家自然科学基金(62222206,62272209),江西省重大科技研发专项(20232ACC01007),江西省重点研发计划重点专项(20232BBE50006),江西省技术创新引导类计划项目(2021AEI91005),江西省教育厅科学技术项目(GJJ210910),江西省图像处理与模式识别重点实验室开放基金(ET202104413)资助Supported by National Natural Science Foundation of China(62222206,62272209),National Science and Technology Major Project of Jiangxi Province(20232ACC01007),Key Research and Development Program of Jiangxi Province(20232BBE50006),the Technological Innovation Guidance Program of Jiangxi Province(2021AEI91005),Science and Technology Program of Education Department of Jiangxi Province(GJJ210910),and the Open Fund of Jiangxi Key Laboratory for Image Processing and Pat-tern Recognition(ET202104413) （62222206,62272209）
