三维场景点云理解与重建技术

3维场景理解与重建技术能够使计算机对真实场景进行高精度复现并引导机器以3维空间的思维理解整个真实世界,从而使机器拥有足够智能参与到真实世界的生产与建设,并能通过场景的模拟为人类的决策和生活提供服务。3维场景理解与重建技术主要包含场景点云特征提取、扫描点云配准与融合、场景理解与语义分割、扫描物体点云补全与细粒度重建等,在处理真实扫描场景时,受到扫描设备、角度、距离以及场景复杂程度的影响,对技术的精准度和稳定性提出了更高的要求,相关的技术也十分具有挑战性。其中,原始扫描点云特征提取与配准融合旨在将同场景下多个扫描区域进行特征匹配,从而融合得到完整的场景点云,是理解与重建技术的基石;场景点云的理解与语义分割的目的在于对场景模型进行整体感知并根据语义特征划分为功能性物体甚至是部件的点云,是整套技术的核心组成部分;后续的物体点云细粒度补全主要研究扫描物体的结构恢复和残缺部分补全,是场景物体点云细粒度重建的关键性技术。本文围绕上述系列技术,详细分析了基于3维点云的场景理解与重建技术相关的应用领域和研究方向,归结总结了国内外的前沿进展与研究成果,对未来的研究方向和技术发展进行了展望。     

Table structure understanding and its performance evaluation

This paper presents a table structure understanding algorithm designed using optimization methods. The algorithm is probability based, where the probabilities are estimated from geometric measurements made on the various entities in a large training set. The methodology includes a global parameter optimization scheme, a novel automatic table ground truth generation system and a table structure understanding performance evaluation protocol. With a document data set having 518 table and 10,934 cell entities, it performed at the 96.76% accuracy rate on the cell level and 98.32% accuracy rate on the table level.     

An experimental evaluation of simplicity in rule learning

While recent research on rule learning has focused largely on finding highly accurate hypotheses, we evaluate the degree to which these hypotheses are also simple, that is small. To realize this, we compare well-known rule learners, such as CN2, RIPPER, PART, FOIL and C5.0 rules, with the benchmark system SL² that explicitly aims at computing small rule sets with few literals. The results show that it is possible to obtain a similar level of accuracy as state-of-the-art rule learners using much smaller rule sets.     

Photorealistic Scene Reconstruction by Voxel Coloring

A novel scene reconstruction technique is presented, different from previous approaches in its ability to cope with large changes in visibility and its modeling of intrinsic scene color and texture information. The method avoids image correspondence problems by working in a discretized scene space whose voxels are traversed in a fixed visibility ordering. This strategy takes full account of occlusions and allows the input cameras to be far apart and widely distributed about the environment. The algorithm identifies a special set of invariant voxels which together form a spatial and photometric reconstruction of the scene, fully consistent with the input images. The approach is evaluated with images from both inward-facing and outward-facing cameras.     

Consistent Scene Editing by Progressive Difference Images

Even though much research was dedicated to the acceleration of consistent, progressive light transport simulations, the computation of fully converged images is still very time‐consuming. This is problematic, as for the practical use in production pipelines, the rapid editing of lighting effects is important. While previous approaches restart the simulation with every scene manipulation, we make use of the coherence between frames before and after a modification in order to accelerate convergence of the context that remained similar. This is especially beneficial if a scene is edited that has already been converging for a long time, because much of the previous result can be reused, e.g., sharp caustics cast or received by the unedited scene parts. In its essence, our method performs the scene modification stochastically by predicting and accounting for the difference image. In addition, we employ two heuristics to handle cases in which stochastic removal is likely to lead to strong noise. Typical scene interactions can be broken down into object adding and removal, material substitution, camera movement and light editing, which we all examine in a number of test scenes both qualitatively and quantitatively. As we focus on caustics, we chose stochastic progressive photon mapping as the underlying light transport algorithm. Further, we show preliminary results of bidirectional path tracing and vertex connection and merging.     

Performance evaluation of rule grouping on a real-time expertsystem architecture

Uses a Markov process to model a real-time expert system architecture characterized by message passing and event-driven scheduling. The model is applied to the performance evaluation of rule grouping for real-time expert systems running on this architecture. An optimizing algorithm based on Kernighan-Lin heuristic graph partitioning for the real-time architecture is developed and a demonstration system based on the model and algorithm has been developed and tested on a portion of the advanced GPS receiver (AGR) and manned manoeuvring unit (MMU) knowledge bases     

Scene graph generation by multi-level semantic tasks

Understanding scene image includes detecting and recognizing objects, estimating the interaction relationships of the detected objects, and describing image regions with sentences. However, since the complexity and variety of scene image, existing methods take object detection or vision relationship estimate as the research targets in scene understanding, and the obtained results are not satisfactory. In this work, we propose a Multi-level Semantic Tasks Generation Network (MSTG) to leverage mutual connections across object detection, visual relationship detection and image captioning, to solve jointly and improve the accuracy of the three vision tasks and achieve the more comprehensive and accurate understanding of scene image. The model uses a message pass graph to mutual connections and iterative updates across the different semantic features to improve the accuracy of scene graph generation, and introduces a fused attention mechanism to improve the accuracy of image captioning while using the mutual connections and refines of different semantic features to improve the accuracy of object detection and scene graph generation. Experiments on Visual Genome and COCO datasets indicate that the proposed method can jointly learn the three vision tasks to improve the accuracy of those visual tasks generation.

     

Rough-fuzzy MLP: modular evolution, rule generation, and evaluation

A methodology is described for evolving a Rough-fuzzy multi layer perceptron with modular concept using a genetic algorithm to obtain a structured network suitable for both classification and rule extraction. The modular concept, based on "divide and conquer" strategy, provides accelerated training and a compact network suitable for generating a minimum number of rules with high certainty values. The concept of variable mutation operator is introduced for preserving the localized structure of the constituting knowledge-based subnetworks, while they are integrated and evolved. Rough set dependency rules are generated directly from the real valued attribute table containing fuzzy membership values. Two new indices viz., "certainty" and "confusion" in a decision are defined for evaluating quantitatively the quality of rules. The effectiveness of the model and the rule extraction algorithm is extensively demonstrated through experiments alongwith comparisons.     

On the convergence of a rule by Monegato for the numerical evaluation of Cauchy principal value integrals

In this paper the authors examine the convergence of an interpolatory type quadrature rule proposed by G. Monegato for the evaluation of Cauchy principal value integrals. A convergence theorem is given for a large class of functions and some estimates of the remainder are established.     

Outdoor Scene Classification by a Neural Tree-Based Approach

This paper describes a Neural Tree (NT) based system for outdoor scene classification. A new NT classifier with backtracking capabilities is employed at different levels of the system architecture. First, it is used to obtain a rough interpretation of the scene by classifying each image pixel into multiple classes of static background objects, e.g. road, sky, vegetation, or into one generic class representing moving objects, e.g. vehicles, pedestrians. Then it is applied to obtain a more accurate scene interpretation by classifying all detected mobile objects into multiple classes, e.g. cars, lorries, buses, and also estimating their pose. Experiments have been performed on a large set of optical and infrared images. System performances are tested on both clean and noisy data, and comparative studies with other classifiers (i.e. a multi-layer perceptron, a binary decision tree, a standard NT and a bank of neural networks) and with other scene classification methods are carried out. Receiveed: 29 May 1998?,Received in revised form: 13 November 1998?Accepted: 15 December 1998     

用3DSMAX打造瀑布景观

Discreet公司推出的3DSMAX是全球应用非常广泛的三维设计软件，它广泛应用于建筑装潢设计，工业产品造型设计，影视特技、片头、广告设计以及三维动画设计。本文利用3DSMAX制作了一个虚拟的瀑布三维景观，整个制作过程循序渐进即遵从了三维设计的一般过程．又能从中了解到3DSMAX某些角度的相关知识。     

用3DS MAX 打造瀑布景观

Discreet公司推出的3DS MAx是全球应用非常广泛的三维设计软件,它广泛应用于连筑装潢设计,工业产品造型设计,影视特技、片头、广告设计以及三维动画设计.本文利用3DS MAX制作了一个虚拟的瀑布三维景观,整个制作过程循序新选即遵从了三维设计的一般过程,又能从中了解到3DS MAX某些角度的相关知识.     

语音交互创建英语教学情景

主要介绍了如何利用语音交互技术来创建英语教学情景,并就其支持技术：语音识别、语音合成进行了探讨。     

视景仿真系统中动力模型与场景控制的实现

对汽车动力模型的建立与场景控制的设计做了简单的介绍,描述了在视景仿真系统中如何建立汽车动力模型以及对系统中汽车模型的前进、后退、方向转变、遇到雾和阳光的强弱等场景控制的实现。     

虚拟现实建立动态场景的研究

随着虚拟现实技术的发展,对虚拟现实场景不仅要求有逼真的效果,同时还要求有生动的交互功能,而VRML(Vitual Reality Modeling Language)与Java的结合是目前常用的交互式虚拟现实技术。文章系统介绍了虚拟现实建模语言VRML,采用JAVA做为脚本建立动态场景的原因并具体介绍了VRML与Java结合建立动态交互场景的两种方式,以及JSAI和EAI的区别。     

Scene analysis by integrating primitive segmentation andassociative memory

Scene analysis is a major aspect of perception and continues to challenge machine perception. This paper addresses the scene-analysis problem by integrating a primitive segmentation stage with a model of associative memory. The model is a multistage system that consists of an initial primitive segmentation stage, a multimodule associative memory, and a short-term memory (STM) layer. Primitive segmentation is performed by a locally excitatory globally inhibitory oscillator network (LEGION), which segments the input scene into multiple parts that correspond to groups of synchronous oscillations. Each segment triggers memory recall and multiple recalled patterns then interact with one another in the STM layer. The STM layer projects to the LEGION network, giving rise to memory-based grouping and segmentation. The system achieves scene analysis entirely in phase space, which provides a unifying mechanism for both bottom-up analysis and top-down analysis. The model is evaluated with a systematic set of three-dimensional (3-D) line drawing objects, which are arranged in an arbitrary fashion to compose input scenes that allow object occlusion. Memory-based organization is responsible for a significant improvement in performance. A number of issues are discussed, including input-anchored alignment, top-down organization, and the role of STM in producing context sensitivity of memory recall.     

虚拟现实建立动态场景的研究

随着虚拟现实技术的发展，对虚拟现实场景不仅要求有逼真的效果，同时还要求有生动的交互功能，而VRML（Vitual Reality Modeling Language）与Java的结合是目前常用的交互式虚拟现实技术。文章系统介绍了虚拟现实建模语言VRML，采用JAVA做为脚本建立动态场景的原因并具体介绍了VRML与Java结合建立动态交互场景的两种方式，以及JSAI和EAI的区别。