3D scene analysis from a single range image through occlusion graphs

This paper presents a new strategy to extract knowledge about the objects and their relative location in a complex scene when a single range image is taken. The analysis process is based on a range data distributed segmentation technique, which separates the components of the scene, and on a silhouette segmentation method, which classified the silhouette in real (non occluded) and false (occluded) parts. Finally, an occlusion graph provides a compact representation about the layout and relationship of the objects in the scene. This information is essential before higher level tasks in complex scenes – like recognition, understanding and robot interaction – are carried out. An extensive experimentation has been accomplished under real conditions in scenes of up to 12 objects yielding a very good performance. The experiments and results carried out validate the goodness of this approach in 3D environments.     

具有强鲁棒性的三维对象多视变分分割方法

针对校准摄像机采集系列图像的三维分割重构问题,提出了一种新的面向概率描述的变分方法。首先,计算系列图像的极大似然曲面,可重构与分割保持一致的三维曲面;接着,融合联合概率,可重构目标对象及图像背景的平均强度及标准差;最后,采用水平集框架,可实现对曲面能量方程的数值模拟。该方法适用于复杂拓扑结构重构及噪声数据处理。实验结果表明,该方法实用性好,鲁棒性强,对任意三维对象的分割重构效果较形状雕刻方法及体视分割方法理想。     

三维激光扫描表面数据区域分割

针对现有三维激光扫描数据区域分割算法受原始碎片表面粗糙度影响较大且只适用于形状较规则、表面较平坦及断裂面较少的物体这一问题,提出了区域膨胀策略的三维扫描表面数据区域分割算法,该算法将三维激光扫描表面数据分割成若干个具有相同法矢方向的区域。首先将三维扫描表面数据转化为三维网格模型;然后利用同一区域中相邻网格具有相似法线方向这一性质,使用区域膨胀策略生成若干获选表面区域;最后通过去除候选区域中的噪声区域得到最终表面区域分割结果。通过实物表面扫描数据对上述算法进行仿真验证,结果表明该算法可对三维表面扫描数据进行有效的区域分割。     

3D object segmentation using B-Surface

3D object segmentation is important in computer vision such as target detection in biomedical image analysis. A new method, called B-Surface algorithm, is generated for 3D object segmentation. An improved 3D external force field combined with the normalized GVF is utilized. After the initialization of a surface model near the target, B-Surface starts to deform to locate the boundary of the object. First, it overcomes the difficulty that comes from analyzing 3D volume image slice by slice. And the speed of B-Surface deformation is enhanced since the internal forces are not needed to compute in every iteration deformation step. Next, the normal at every surface point can be calculated easily since B-Surface is a continuous deformable model. And it has the ability to achieve high compression ratio (ratio of data to parameters) by presenting the whole surface with only a relatively small number of control points. Experimental results and analysis are presented in this paper. We can see that the B-Surface algorithm can find the surface of the target efficiently.     

Multi-object reconstruction from dynamic scenes: An object-centered approach

In this paper, we present a new framework for three-dimensional (3D) reconstruction of multiple rigid objects from dynamic scenes. Conventional 3D reconstruction from multiple views is applicable to static scenes, in which the configuration of objects is fixed while the images are taken. In our framework, we aim to reconstruct the 3D models of multiple objects in a more general setting where the configuration of the objects varies among views. We solve this problem by object-centered decomposition of the dynamic scenes using unsupervised co-recognition approach. Unlike conventional motion segmentation algorithms that require small motion assumption between consecutive views, co-recognition method provides reliable accurate correspondences of a same object among unordered and wide-baseline views. In order to segment each object region, we benefit from the 3D sparse points obtained from the structure-from-motion. These points are reliable and serve as automatic seed points for a seeded-segmentation algorithm. Experiments on various real challenging image sequences demonstrate the effectiveness of our approach, especially in the presence of abrupt independent motions of objects.     

A multi-plane approach for text segmentation of complex document images

This study presents a new method, namely the multi-plane segmentation approach, for segmenting and extracting textual objects from various real-life complex document images. The proposed multi-plane segmentation approach first decomposes the document image into distinct object planes to extract and separate homogeneous objects including textual regions of interest, non-text objects such as graphics and pictures, and background textures. This process consists of two stages—localized histogram multilevel thresholding and multi-plane region matching and assembling. Then a text extraction procedure is applied on the resultant planes to detect and extract textual objects with different characteristics in the respective planes. The proposed approach processes document images regionally and adaptively according to their respective local features. Hence detailed characteristics of the extracted textual objects, particularly small characters with thin strokes, as well as gradational illuminations of characters, can be well-preserved. Moreover, this way also allows background objects with uneven, gradational, and sharp variations in contrast, illumination, and texture to be handled easily and well. Experimental results on real-life complex document images demonstrate that the proposed approach is effective in extracting textual objects with various illuminations, sizes, and font styles from various types of complex document images.     

优化的PCNN自适应三维图像分割算法*

脉冲耦合神经网络(pulse coupled neural network,PCNN)对图像分割具有天然的优势,但是传统的PCNN模型参数难以确定,且算法耗时多。对多种PCNN模型进行研究改进,并利用统计学知识提出了一种精简高效的自适应三维分割算法。将其用于脑部磁共振成像(magnetic resonance imaging,MRI)图像的分割,把脑组织分成白质、灰质和脑脊液。与标准PCNN、传统的Otsu阈值方法、SPM8工具箱及专家手动分割结果的对比实验表明,该自适应算法具有精确性、高效性。     

Building 3D anatomical scenes on the Web

We propose a new service for building user‐defined 3D anatomical structures on the Web. The Web server is connected to a database storing more than 1000 3D anatomical models reconstructed from the Visible Human. Users may combine existing models as well as planar oblique slices in order to create their own structured anatomical scenes. Furthermore, they may record sequences of scene construction and visualization actions. These actions enable the server to construct high‐quality video animations, downloadable by the user. Professionals and students in anatomy, medicine and related disciplines are invited to use the server and create their own anatomical scenes. Copyright © 2002 John Wiley & Sons, Ltd.     

A multi-scale 3D Otsu thresholding algorithm for medical image segmentation

Thresholding technique is one of the most imperative practices to accomplish image segmentation. In this paper, a novel thresholding algorithm based on 3D Otsu and multi-scale image representation is proposed for medical image segmentation. Considering the high time complexity of 3D Otsu algorithm, an acceleration variant is invented using dimension decomposition rule. In order to reduce the effects of noises and weak edges, multi-scale image representation is brought into the segmentation algorithm. The whole segmentation algorithm is designed as an iteration procedure. In each iteration, the image is segmented by the efficient 3D Otsu, and then it is filtered by a fast local Laplacian filtering to get a smoothed image which will be input into the next iteration. Finally, the segmentation results are pooled to get a final segmentation using majority voting rules. The attractive features of the algorithm are that its segmentation results are stable, it is robust to noises and it holds for both bi-level and multi-level thresholding cases. Experiments on medical MR brain images are conducted to demonstrate the effectiveness of the proposed method. The experimental results indicate that the proposed algorithm is superior to the other multilevel thresholding algorithms consistently.     

结合图像分割和点云分割的障碍物检测算法

针对单目图像检测障碍物的低可靠性和当前双目视觉检测障碍物的局限性的问题,提出一种结合图像分割和点云分割技术的双目视觉障碍物检测方法。通过设定检测深度范围,分割障碍物点云与道路点云;采用将分割出的障碍物点云对应的视差图与图像分割得到的子图进行比较的策略,有效解决对不同深度、倾斜面和不规则障碍物检测效果差的问题。通过实验验证了在获得稀疏三维点云的情况下,该方法对障碍物的检测具有较好的鲁棒性。     

3D-BSNet:双边特征和相似度量的点云实例分割网络

针对现有的三维分割方法在挖掘点云特征时,会忽略几何特征有效利用的问题,提出双边特征和相似度量的点云实例分割网络3D-BSNet（3D-bilateral feature and similarity measure network）。该网络主要由双边特征学习和轻量级相似度量两部分组成。首先提出一种包含基于子流形稀疏卷积的3D-UNet和多层感知机的双边特征提取模块,用于提取经过体素化处理的点云数据的语义特征和几何特征;然后设计一种结合通道维度和空间维度的双边注意力机制,用于减少双边特征聚合过程中产生的信息损失;最后开发一种轻量级相似度量模块,获取高维嵌入特征空间中邻近点云之间的相似性,并生成细粒度实例分割结果。实验表明,3D-BSNet在S3DIS和Scannet（v2）数据集上的多指标综合表现优越,其中在Scannet（v2）上的平均精确率比 SSTNet 提高了3.3%,有效提高了室内场景三维实例分割的精度。     

A semi-interactive panorama based 3D reconstruction framework for indoor scenes

We present a semi-interactive method for 3D reconstruction specialized for indoor scenes which combines computer vision techniques with efficient interaction. We use panoramas, popularly used for visualization of indoor scenes, but clearly not able to show depth, for their great field of view, as the starting point. Exploiting user defined knowledge, in term of a rough sketch of orthogonality and parallelism in scenes, we design smart interaction techniques to semi-automatically reconstruct a scene from coarse to fine level. The framework is flexible and efficient. Users can build a coarse walls-and-floor textured model in five mouse clicks, or a detailed model showing all furniture in a couple of minutes interaction. We show results of reconstruction on four different scenes. The accuracy of the reconstructed models is quite high, around 1% error at full room scale. Thus, our framework is a good choice for applications requiring accuracy as well as application requiring a 3D impression of the scene.     

Progressive 3D shape segmentation using online learning

In this article, we propose a progressive 3D shape segmentation method, which allows users to guide the segmentation with their interactions, and does segmentation gradually driven by their intents. More precisely, we establish an online framework for interactive 3D shape segmentation, without any boring collection preparation or training stages. That is, users can collect the 3D shapes while segment them, and the segmentation will become more and more precise as the accumulation of the shapes.Our framework uses Online Multi-Class LPBoost (OMCLP) to train/update a segmentation model progressively, which includes several Online Random forests (ORFs) as the weak learners. Then, it performs graph cuts optimization to segment the 3D shape by using the trained/updated segmentation model as the optimal data term. There exist three features of our framework. Firstly, the segmentation model can be trained gradually during the collection of the shapes. Secondly, the segmentation results can be refined progressively until users’ requirements are met. Thirdly, the segmentation model can be updated incrementally without retraining all shapes when users add new shapes. Experimental results demonstrate the effectiveness of our approach.     

A new image segmentation technique based on partition mode test

Image segmentation is one of the most important steps in a modern computerized machine vision system. This paper describes a simple, systematic one-pass image segmentation algorithm which is based on the partition mode test of pixels within a (2 × 2) window and assigning and updating label fields to the pixels of this window. A number of well chosen examples are shown to demonstrate the capabilities of the new algorithm.     

一种全自动的三维肺实质分割算法

精确的肺实质三维分割是对肺部病变进行计算机辅助检测或诊断的必要步骤,但复杂的胸部组织结构使得肺实质的精确分割变得较为困难。提出了一种结合阈值分割、区域增长、改进波阵面法等多种方法的全自动的三维肺实质分割方法。该方法使用计算机视觉及图像分析小组/国际肺癌早期行动计划（Computer Vision and Image Analysis Group/International Early Lung Cancer Action Program,VIA/I-ELCAP）和肺部图像数据库联盟（Lung Image Database Consortium,LIDC）提供的数据进行实验,结果证明这个方法能快速、精确地得到肺实质。     

Convex relaxation for a 3D spatiotemporal segmentation model using the primal-dual method

A method based on 3D videos is proposed for multi-target segmentation and tracking with a moving viewing system. A spatiotemporal energy functional is built up to perform motion segmentation and estimation simultaneously. To overcome the limitation of the local minimum problem with the level set method, a convex relaxation method is applied to the 3D spatiotemporal segmentation model. The relaxed convex model is independent of the initial condition. A primal-dual algorithm is used to improve computational efficiency. Several indoor experiments show the validity of the proposed method.     

Contour-based focus of attention mechanism to speed up object detection and labeling in 3D scenes

In this paper, a contour-based focus of attention approach is presented. Fast to compute, contour based features are extracted from 3D scenes and matched to model parts of objects. Local reference frames associated with the features induce a translation and rotation, resulting in a vote being cast for the presence of the object in a certain position within the scene. In these positions, HoG features are extracted and SVM classification is applied. Detection results and computation times are compared to those corresponding to a sliding window approach.     

基于OpenGVS的三维仿真软件的开发研究

视景仿真技术是在数值仿真的基础上以图形和动画来显示仿真的过程和结果，近年来视景仿真技术在军事领域上得到了广泛的应用。OpenGVS是专门用于实时3D图形开发的软件。该文在Multigen Creator 3D场景建模的基础上，采用OpenGVS来实现场景驱动，开发了一个导弹与飞机交战场景的仿真程序，并介绍了实现三维动画驱动时需要解决的几个关键问题，包括外部模型的导入，视点的选取，碰撞的检测，以及爆炸效果的产生等。这些技术的运用使得软件仿真的效果更加逼真。     

数据驱动的三维服装快速建模

提出一种数据驱动的三维服装快速建模方法,可以从样本中快速生成新的三维服装模型.首先,输入三维服装模型集,通过形状款式分析,对三维服装进行语义分割.其次,将分割后的三维服装部件模型聚类为四大类（上身、下身、袖子、配件）,构成三维服装部件库.然后,以服装部件模型的面积和边界周长比例为几何形状特征,定义度量服装部件重新组合的款式描述算子.最后,对三维服装部件模型聚类后的源模型进行优化,并通过自然拼接输出新的三维服装.实验结果表明,该方法提高了三维服装建模的效率,能较好地满足目前大规模三维服装数量的需求.