In recent days, applications using 3d animation models are increasing. Since the 3d animation model contains a huge amount of information, data compression is needed for efficient storage or transmission. Although the...
详细信息
ISBN:
(纸本)0819439886
In recent days, applications using 3d animation models are increasing. Since the 3d animation model contains a huge amount of information, data compression is needed for efficient storage or transmission. Although there have been various proposals for 3d model coding, most works have considered only static connectivity and geometry information. Only a few studies have been presented for 3d animation models. This paper presents a coding scheme for 3d animation models using a new 3dsegmentation algorithm. For an accurate segmentation, we take advantage of temporal coherence in the generic animated3d model. After the motion vector of each vertex is mapped onto the surface of the unit sphere in the spherical coordinate system, we partition the surface of the sphere equally to have the same area. We then reconstruct in-between 3d models using the reconstructed key frame and an affine motion model for each segmented unit.
This paper presents a novel objectsegmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately confor...
详细信息
This paper presents a novel objectsegmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately conform to the physical object boundaries in the scene. Next, we propose a novel perceptual grouping algorithm based on local cues (e.g., 3d proximity, co-planarity, and shape convexity) to merge these regions into object hypotheses. Our extensive experimental evaluations demonstrate that our objectsegmentation results are superior compared to the state-of-the-art methods.
data segmentation andobject rendering is required for localization super-resolution microscopy, fluorescent photoactivation localization microscopy (FPALM), anddirect stochastic optical reconstruction microscopy (dS...
详细信息
data segmentation andobject rendering is required for localization super-resolution microscopy, fluorescent photoactivation localization microscopy (FPALM), anddirect stochastic optical reconstruction microscopy (dSTORM). We developed and validated methods for segmenting objects based on delaunay triangulation in 3d space, followed by facet culling. We applied them to visualize mitochondrial nucleoids, which confine dNA in complexes with mitochondrial (mt) transcription factor A (TFAM) and gene expression machinery proteins, such as mt single-stranded-dNA-binding protein (mtSSB). Eos2-conjugated TFAM visualized nucleoids in HepG2 cells, which was compared with dSTORM 3d-immunocytochemistry of TFAM, mtSSB, or dNA. The localized fluorophores of FPALM/dSTORM data were segmented using delaunay triangulation into polyhedron models and by principal component analysis (PCA) into general PCA ellipsoids. The PCA ellipsoids were normalized to the smoothed volume of polyhedrons or by the net unsmootheddelaunay volume and remodeled into rotational ellipsoids to obtain models, termeddVRE. The most frequent size of ellipsoid nucleoid model imaged via TFAM was 35 x 45 x 95 nm;or 35 x 45 x 75 nm for mtdNA cores;and 25 x 45 x 100 nm for nucleoids imaged via mtSSB. Nucleoids encompasseddifferent point density and wide size ranges, speculatively due to different activity stemming from different TFAM/mtdNA stoichiometry/density. Considering twofold lower axial vs. lateral resolution, only bulky dVRE models with an aspect ratio > 3 and tilted toward the xy-plane were considered as two proximal nucleoids, suspicious occurring after division following mtdNA replication. The existence of proximal nucleoids in mtdNA-dSTORM 3d images of mtdNA "doubling"-supported possible direct observations of mt nucleoiddivision after mtdNA replication.
The problem of how to arrive at an appropriate 3d-segmentation of a scene remains difficult. While current state-of-the-art methods continue to gradually improve in benchmark performance, they also grow more and more ...
详细信息
ISBN:
(纸本)9781479951178
The problem of how to arrive at an appropriate 3d-segmentation of a scene remains difficult. While current state-of-the-art methods continue to gradually improve in benchmark performance, they also grow more and more complex, for example by incorporating chains of classifiers, which require training on large manually annotateddata-sets. As an alternative to this, we present a new, efficient learning-and model-free approach for the segmentation of 3d point clouds into object parts. The algorithm begins by decomposing the scene into an adjacency-graph of surface patches based on a voxel grid. Edges in the graph are then classified as either convex or concave using a novel combination of simple criteria which operate on the local geometry of these patches. This way the graph is divided into locally convex connected subgraphs, which - with high accuracy -represent object parts. Additionally, we propose a novel depth dependent voxel grid to deal with the decreasing point-density at far distances in the point clouds. This improves segmentation, allowing the use of fixed parameters for vastly different scenes. The algorithm is straightforward to implement and requires no training data, while nevertheless producing results that are comparable to state-of-the-art methods which incorporate high-level concepts involving classification, learning and model fitting.
due to the advantages of 3d point clouds over 2d optical images, the related researches on scene understanding in 3d point clouds have been increasingly attracting wide attention from academy and industry. However, ma...
详细信息
due to the advantages of 3d point clouds over 2d optical images, the related researches on scene understanding in 3d point clouds have been increasingly attracting wide attention from academy and industry. However, many 3d scene understanding methods largely require abundant supervised information for training a data-driven model. The acquisition of such supervised information relies on manual annotations which are laborious and arduous. Therefore, to mitigate such manual efforts for annotating training samples, this paper studies a unified neural network to segment 3dobjects out of point clouds interactively. Particularly, to improve the segmentation performance on the accurate objectsegmentation, the boundary information of 3dobjects in point clouds are encoded as a boundary energy term in the Markov Random Field (MRF) model. Moreover, the MRF model with the boundary energy term is naturally integrated with the Graphical Neural Network (GNN) to obtain a compact representation for generating the boundary-preserved3dobjects. The proposed method is evaluated on two point clouds datasets obtained from different types of laser scanning systems, i.e. terrestrial laser scanning system and mobile laser scanning system. Comparative experiments show that the proposed method is superior and effective in 3dobjects segmentation in different point-cloud scenarios.
暂无评论