Augmented reality is the merging of synthetic sensory information into a user's perception of a real environment. As one of the most important tasks in augmented scene modeling, terrain simplification research has...Augmented reality is the merging of synthetic sensory information into a user's perception of a real environment. As one of the most important tasks in augmented scene modeling, terrain simplification research has gained more and more attention. In this paper, we mainly focus on point selection problem in terrain simplification using triangulated irregular network. Based on the analysis and comparison of traditional importance measures for each input point, we put forward a new importance measure based on local entropy. The results demonstrate that the local entropy criterion has a better performance than any traditional methods. In addition, it can effectively conquer the 'short-sight' problem associated with the traditional methods.展开更多
Image-based 3D modeling is an effective method for reconstructing large-scale scenes,especially city-level scenarios.In the image-based modeling pipeline,obtaining a watertight mesh model from a noisy multi-view stere...Image-based 3D modeling is an effective method for reconstructing large-scale scenes,especially city-level scenarios.In the image-based modeling pipeline,obtaining a watertight mesh model from a noisy multi-view stereo point cloud is a key step toward ensuring model quality.However,some state-of-the-art methods rely on the global Delaunay-based optimization formed by all the points and cameras;thus,they encounter scaling problems when dealing with large scenes.To circumvent these limitations,this study proposes a scalable pointcloud meshing approach to aid the reconstruction of city-scale scenes with minimal time consumption and memory usage.Firstly,the entire scene is divided along the x and y axes into several overlapping chunks so that each chunk can satisfy the memory limit.Then,the Delaunay-based optimization is performed to extract meshes for each chunk in parallel.Finally,the local meshes are merged together by resolving local inconsistencies in the overlapping areas between the chunks.We test the proposed method on three city-scale scenes with hundreds of millions of points and thousands of images,and demonstrate its scalability,accuracy,and completeness,compared with the state-of-the-art methods.展开更多
Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes,there still exist some challenges in the debris recognition of terrain data.Compared with hundreds of thousands of i...Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes,there still exist some challenges in the debris recognition of terrain data.Compared with hundreds of thousands of indoor point clouds,the amount of terrain point cloud is up to millions.Apart from that,terrain point cloud data obtained from remote sensing is measured in meters,but the indoor scene is measured in centimeters.In this case,the terrain debris obtained from remote sensing mapping only have dozens of points,which means that sufficient training information cannot be obtained only through the convolution of points.In this paper,we build multi-attribute descriptors containing geometric information and color information to better describe the information in low-precision terrain debris.Therefore,our process is aimed at the multi-attribute descriptors of each point rather than the point.On this basis,an unsupervised classification algorithm is proposed to divide the point cloud into several terrain areas,and regard each area as a graph vertex named super point to form the graph structure,thus effectively reducing the number of the terrain point cloud from millions to hundreds.Then we proposed a graph convolution network by employing PointNet for graph embedding and recurrent gated graph convolutional network for classification.Our experiments show that the terrain point cloud can reduce the amount of data from millions to hundreds through the super point graph based on multi-attribute descriptor and our accuracy reached 91.74%and the IoU reached 94.08%,both of which were significantly better than the current methods such as SEGCloud(Acc:88.63%,IoU:89.29%)and PointCNN(Acc:86.35,IoU:87.26).展开更多
Large-scale virtual scene exploration is still a challenging task. The novice users caneasily get distracted and disorientated, which results in being lost in space. Assistedcamera control technology is the most effec...Large-scale virtual scene exploration is still a challenging task. The novice users caneasily get distracted and disorientated, which results in being lost in space. Assistedcamera control technology is the most effective solution for virtual environment exploration problems which requires viewpoint computation and path planning. In this paper,a novel approach for large-scale virtual scene based on viewpoint scoring is proposed.First, the scene was adaptively divided into several meaningful and easily analyzedsubregions according to the optimal view distance criterion. Second, a novel viewpointscoring method based on visual perception and information entropy fusion was developed for optimal viewpoint determination and greedy N-Best viewpoint selection algorithm was utilized for visual perceptibility calculation. Then evolutionary programmingapproach for the Traveling Salesman problem was applied for intra-subregion and intersubregion exploring path optimization. Finally, the Cubic Hermite Curve was introduced to smoothen the inflection point on the exploration path. The experimental resultsdemonstrate that the proposed method can effectively generate an automatic smooth,informative, aesthetic and non-intersecting path, with the characteristics of good exploring comfort, strong immersion and high scene information perception.展开更多
基金This paper is supported by the State Key Laboratory for Image Processing & Intelligent Control (No. TKLJ9903) National Defe
文摘Augmented reality is the merging of synthetic sensory information into a user's perception of a real environment. As one of the most important tasks in augmented scene modeling, terrain simplification research has gained more and more attention. In this paper, we mainly focus on point selection problem in terrain simplification using triangulated irregular network. Based on the analysis and comparison of traditional importance measures for each input point, we put forward a new importance measure based on local entropy. The results demonstrate that the local entropy criterion has a better performance than any traditional methods. In addition, it can effectively conquer the 'short-sight' problem associated with the traditional methods.
基金This work was supported by the Natural Science Foundation of China(Nos.61632003,61873265)。
文摘Image-based 3D modeling is an effective method for reconstructing large-scale scenes,especially city-level scenarios.In the image-based modeling pipeline,obtaining a watertight mesh model from a noisy multi-view stereo point cloud is a key step toward ensuring model quality.However,some state-of-the-art methods rely on the global Delaunay-based optimization formed by all the points and cameras;thus,they encounter scaling problems when dealing with large scenes.To circumvent these limitations,this study proposes a scalable pointcloud meshing approach to aid the reconstruction of city-scale scenes with minimal time consumption and memory usage.Firstly,the entire scene is divided along the x and y axes into several overlapping chunks so that each chunk can satisfy the memory limit.Then,the Delaunay-based optimization is performed to extract meshes for each chunk in parallel.Finally,the local meshes are merged together by resolving local inconsistencies in the overlapping areas between the chunks.We test the proposed method on three city-scale scenes with hundreds of millions of points and thousands of images,and demonstrate its scalability,accuracy,and completeness,compared with the state-of-the-art methods.
基金This research was funded by grant from the Key Research and Development Program of Shaanxi Province(2018NY-127,2019ZDLNY07-02-01,2020NY-205)National Undergraduate Training Program for Innovation and entrepreneurship plan(S201910712240,X201910712080).
文摘Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes,there still exist some challenges in the debris recognition of terrain data.Compared with hundreds of thousands of indoor point clouds,the amount of terrain point cloud is up to millions.Apart from that,terrain point cloud data obtained from remote sensing is measured in meters,but the indoor scene is measured in centimeters.In this case,the terrain debris obtained from remote sensing mapping only have dozens of points,which means that sufficient training information cannot be obtained only through the convolution of points.In this paper,we build multi-attribute descriptors containing geometric information and color information to better describe the information in low-precision terrain debris.Therefore,our process is aimed at the multi-attribute descriptors of each point rather than the point.On this basis,an unsupervised classification algorithm is proposed to divide the point cloud into several terrain areas,and regard each area as a graph vertex named super point to form the graph structure,thus effectively reducing the number of the terrain point cloud from millions to hundreds.Then we proposed a graph convolution network by employing PointNet for graph embedding and recurrent gated graph convolutional network for classification.Our experiments show that the terrain point cloud can reduce the amount of data from millions to hundreds through the super point graph based on multi-attribute descriptor and our accuracy reached 91.74%and the IoU reached 94.08%,both of which were significantly better than the current methods such as SEGCloud(Acc:88.63%,IoU:89.29%)and PointCNN(Acc:86.35,IoU:87.26).
文摘Large-scale virtual scene exploration is still a challenging task. The novice users caneasily get distracted and disorientated, which results in being lost in space. Assistedcamera control technology is the most effective solution for virtual environment exploration problems which requires viewpoint computation and path planning. In this paper,a novel approach for large-scale virtual scene based on viewpoint scoring is proposed.First, the scene was adaptively divided into several meaningful and easily analyzedsubregions according to the optimal view distance criterion. Second, a novel viewpointscoring method based on visual perception and information entropy fusion was developed for optimal viewpoint determination and greedy N-Best viewpoint selection algorithm was utilized for visual perceptibility calculation. Then evolutionary programmingapproach for the Traveling Salesman problem was applied for intra-subregion and intersubregion exploring path optimization. Finally, the Cubic Hermite Curve was introduced to smoothen the inflection point on the exploration path. The experimental resultsdemonstrate that the proposed method can effectively generate an automatic smooth,informative, aesthetic and non-intersecting path, with the characteristics of good exploring comfort, strong immersion and high scene information perception.
