融合信息化边界和多模态特征的室内空间布局估计  

Indoor spatial layout estimation using informative edges and multi-modality features

作　　者：刘天亮[1] 陆泮宇 戴修斌[1] 刘峰[1] 罗杰波 LIU Tianliang;LU Panyu;DAI Xiubin;LIU Feng;LUO Jiebo(Jiangsu Provincial Key Lab of Image Processing and Image Communication,Nanjing University of Posts and Telecommunications,Nanjing 210003;Department of Computer Science,University of Rochester,Rochester 14627,USA)

机构地区：[1]南京邮电大学江苏省图像处理与图像通信重点实验室,南京210003 [2]罗彻斯特大学计算机科学系,美国罗彻斯特14627

出　　处：《南京信息工程大学学报（自然科学版）》2019年第6期735-742,共8页Journal of Nanjing University of Information Science & Technology（Natural Science Edition）

基　　金：国家自然科学基金(61001152,31200747,61071091,61071166,61172118);江苏省自然科学基金(BK2012437);南京邮电大学校级科研基金(NY214037);国家留学基金(201208320219)

摘　　要：为感知室内空间布局,提出一种基于信息化边界和多模态特征的场景布局估计方法.首先,采用VGG-16全卷积神经网络预测蕴含空间布局先验的信息化边界图.其次,采用Canny边缘检测和投票策略估计水平和竖直方向消失点,从消失点等角度间隔引出射线细采样信息化边界能量高的区域.接着,采用VGG空间多尺度卷积神经网络估计几何深度和法向特征.然后,积分几何求和候选布局多边形中多模特征描述一元共生,候选布局的表面法向平滑和位置关系确定二元标记约束.最后,采用结构化支持向量机学习模型,最大布局候选得分以推理布局.实验结果表明,与经典方法相比,本估计方法可以有效改善布局的完整度.To perceive indoor spatial layout,we present a scene layout estimation method based on informative edges and multi-modality features.First,the VGG-16 full convolutional neural network is applied to predict informative edge map with the prior of spatial layout.Then,Canny edge detection and voting strategy are utilized to estimate the horizontal and vertical vanishing points,while the rays led at equal intervals from the given vanishing points finely resample the divided regions with high informative edge energies for the layout candidates.Next,the spatial multi-scaled VGG-16-based convolutional neural network is adopted to estimate the related geometric depth and normal vectors on the scene surfaces.And then,integral geometry is applied to accumulate the multi-model regional features as unary occurrence potential in the polygons of candidate layouts,and the pairwise label constrains are reflected by surface normal smooth and the location relationship of candidate layouts.Finally,the mode parameters can be learned by structural SVM learning,and the scene layout can be inferred by maximizing the related scores of the layout candidates.Experimental results show that,compared with traditional methods,this proposed estimation method can effectively improve the completeness of the resulting spatial layouts.

关 键 词：空间布局 卷积神经网络 场景理解 信息化边界 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]