检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:覃业宝 孙炜[1,3] 范诗萌 张星 刘剑 Qin Yebao;Sun Wei;Fan Shimeng;Zhang Xing;Liu Jian(School of Electrical and Information Engineering,Hunan University,Changsha 410082,China;State Key Laboratory of Advanced Vehicle Design and Manufacturing,Hunan University,Changsha 410082,China;Shenzhen Research Institute,Hunan University,Shenzhen 518000,China)
机构地区:[1]湖南大学电气与信息工程学院,长沙410082 [2]湖南大学汽车车身先进设计制造国家重点实验室,长沙410082 [3]湖南大学深圳研究院,深圳518000
出 处:《电子测量与仪器学报》2023年第8期30-39,共10页Journal of Electronic Measurement and Instrumentation
基 金:国家自然科学基金(U22A2059);深圳科技计划项目(2021Szvup035);湖南大学汽车车身先进设计制造国家重点实验室自主研究项目;电子制造业智能机器人技术湖南省重点实验室开放课题项目资助。
摘 要:针对当前视差估计网络在将视差转换成深度时,存在深度精度受相机参数影响,且在远距离处产生深度精度急剧下降的问题,提出一种全距离深度平衡立体匹配网络(FRDBNet)。首先构建深度代价体,使网络学习到全距离深度的概率分布,进行深度回归直接生成深度;然后采用视差与深度损失融合的训练策略使网络同时关注远中近三分段全距离的深度估计;最后,基于初始视差右图对应点7邻域特征设计视差优化模块进一步提高网络的深度估计精度。在大型真实驾驶场景Driving Stereo数据集上的实验表明,针对全距离[1,100]m的深度估计,FRDBNet在[1,30]m近距离、[30,60]m中距离和[60,100]m远距离处深度精度相比CVPR2022性能表现优越的ACVNet分别提高10.38%、15.11%和20.35%,达到了良好的深度精度平衡。In view of the problem that depth accuracy is affected by camera parameters when disparity is converted into depth in the current disparity estimation network,and depth accuracy decreases sharply at long distance,a full range depth balanced stereo matching network(FRDBNet)is proposed.Firstly,the depth cost volume is constructed to make the network learn the probability distribution of the full distance depth,and the depth is directly generated by depth regression.Then,the training strategy of disparity and depth loss fusion is used to make the network pay attention to the depth estimation of the long,middle and near three segments distance at the same time.Finally,a disparity optimization module is designed based on the seven neighborhood features corresponding to the original disparity right map to further improve the depth estimation accuracy of the network.Experiments on the DrivingStereo dataset of large real-world driving scenarios show that for the full distance[1,100]m depth estimation,the depth accuracy of FRDBNet at[1,30]m short distance,[30,60]m middle distance and[60,100]m long distance is 10.38%,15.11%and 20.35%higher than that of ACVNet with superior performance of CVPR2022,respectively,achieving a good balance of depth accuracy.
关 键 词:立体匹配 深度代价体 视差与深度损失融合 7邻域特征 视差优化 深度精度
分 类 号:TP391[自动化与计算机技术—计算机应用技术] TN98[自动化与计算机技术—计算机科学与技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.200