多特征和SVM相融合的三维物体识别方法

研究三维物体识别问题,摄像机从不同角度拍摄三维物体,获取的三维物体图像变化比较大,传统方法采用单一特征或简单多特征难以正确描述三维物体,导致三维物体识别的准确率较低.为了提高三维物体识别准确率,提出一种多特征和支持向量机相融合的三维物体识别方法.首先分别提取三维物体的颜色特征、纹理特征和不变矩特征,然后采用主成分分析消除各特征间的冗余信息,最后采用支持向量机建立三维物体识别模型.采用三维物体图像数据库COIL-100进行测试实验,结果表明,相对于传统识别方法,改进方法不仅提高了三维物体识别准确率,同时加快识别速度,为三维物体识别提供了一种新的识别方法.     

面向散乱数据点的超二次曲面建模与识别综述

在深度图像处理中,针对散乱的数据点进行三维建模与识别研究更具一般性,它是计算机视觉领域中的一个研究热点。通过阐述超二次曲面建模、分割与识别理论和方法的研究进展,以及演化计算在三维建模与识别中的应用,针对离散不规则三维数据点的特性,分析了超二次曲面参数拟合、多物体场景分割、部件识别存在的问题,提出进一步研究扩展超二次曲面的表达能力,利用的超二次曲面作为基元部件对场景进行建模与分割,并将群体并行演化以及关系匹配理论引入到超二次曲面建模与识别中,其目的在于探求一种高效实用的三维建模与识别方案。     

环视图表示下的无监督三维物体检索

为了解决基于多视图的三维物体检索方法过度依赖基于人工标注的有监督训练的问题,提出了一种基于环视图的无监督三维物体检索算法.首先,训练面向多圈环视图的无监督深度网络模型,通过随机数据混合增强学习不同形状之间的内在联系;其次,基于最优匹配方法计算物体间的相似性,其中,最优匹配是利用2个物体环视图间最小距离的平均值计算得到;...     

建立Avatar感知能力与自主行为选择模型的新方法

在人脸重构系统与智能虚拟环境系统的研究基础上,提出了一种基于Agent的建立虚拟人感知能力与行为选择模型的新方法。该方法把虚拟人(Avatar)当成一个Agent,它在虚拟场景中能够识别三维物体以及利用传感器计算物体的运动方向。Avatar的行走采用骨架模型来进行仿真,并且其行走行为由七个基本动作行为组成。实验结果显示新方法是具有较好的效果。     

基于形态和约束结构的几何哈希法

几何哈希法,作为一种有效的模型搜索算法,在物体识别中有着重要的应用。现有的几何哈希法仅适合于仿射变换下的二维景物识别,论文提出了适合透视投影变换下三维物体识别的几何哈希方法。该方法利用物体的三维形态和物体中具有射影不变量的几何约束结构来构造哈希表。一方面,几何约束结构提供了物体模型的索引功能;另一方面,物体的三维形态提供了物体成像位姿的有关信息,使后续的匹配验证得以简化。实验中使用人造物体对该方法进行了验证,实验表明该方法正确有效。     

基于多视角距离图象的三维物体建模及其在识别中的应用

模型的表示和构建是基于距离图象三维物体识别技术中的关键模块之一.针对已有方法 存在的若干问题,提出一个新的综合多个视角距离图象的三维物体模型表示策略和增量式的 模型习得算法,并将该模型表示用于三维物体识别中.实验结果验证了算法的有效性.     

基于形态及受约束结构的三维物体建模方法

文中提出一种基于物体形态及受约束结构的三维物体建模方法,该方法利用具有透视不变性的三维结构来表达物体的各个形态。利用该表达方法可以使机器视觉系统在用单幅灰度图像识别物体时,在模型索引阶段避开求解物体位姿、摄像机参数、特征对应等复杂问题,从而实现先索引后匹配的识别策略,提高识别物体的实时性。文中首先论述了透视不变性和具有透视不变性的受约束结构的基本概念;其次,给出了用受约束结构进行三维物体建模的一般方法和应用实例;最后,指出了这种方法的不足和进一步的研究方向。     

基于随机森林的三维人造模型前朝向识别算法

三维模型前朝向的识别是场景合成与重建的基础.针对现有三维模型前朝向识别算法依赖于模型在场景中上下文关系、计算过程复杂等问题,提出一种基于随机森林的三维人造模型前朝向识别算法.首先通过模型简化和计算模型方向包围盒得到候选面;然后基于物体功能设计和心理学等对模型进行形状分析,为候选面提取一组与之相关联的特征;最后利用随机森林理论训练前朝向判别分类器,实现对模型的前朝向识别.实验结果表明,该算法对模型前朝向识别正确率达到80%,能够很好地处理室内场景绝大种类模型,包括目前方法计算错误的模型.     

一种基于特征捆绑计算模型的物体识别方法

利用一种特征捆绑计算模型,以Gabor特征作为模型的初级特征,将相关统计量作为实现特征捆绑的基础,提出了一种物体识别方法.并实现了一组物体识别实验,结果显示,该方法能够进行较快速而准确地识别,说明了此方法和所使用的特征捆绑计算模型的有效性.     

基于四面体坐标系的三维变形方法及应用

为了直观、精确地控制模型的形变,提出一种基于自定义四面体坐标系的三维变形计算方法.首先从几何上给出四面体坐标系的定义,阐述并证明了其关于几何变换的一些性质,使得拓扑变形易于实现,并可应用在三维变形技术中;然后描述了基于四面体坐标系的2种三维变形算法:嵌入式变形与基于特征的精确变形算法.通过多个变形实例结果证明,该方法能够有效地实现物体的变形以及物体间的渐变.     

CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition

In computer vision fields, 3D object recognition is one of the most important tasks for many real-world applications. Three-dimensional convolutional neural networks (CNNs) have demonstrated their advantages in 3D object recognition. In this paper, we propose to use the principal curvature directions of 3D objects (using a CAD model) to represent the geometric features as inputs for the 3D CNN. Our framework, namely CurveNet, learns perceptually relevant salient features and predicts object class labels. Curvature directions incorporate complex surface information of a 3D object, which helps our framework to produce more precise and discriminative features for object recognition. Multitask learning is inspired by sharing features between two related tasks, where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification. Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification. We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs. A Cross-Stitch module was adopted to learn effective shared features across multiple representations. We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task.      

On the learning machine for three dimensional mapping

In this paper, we investigate the neural network with three-dimensional parameters for applications like 3D image processing, interpretation of 3D transformations, and 3D object motion. A 3D vector represents a point in the 3D space, and an object might be represented with a set of these points. Thus, it is desirable to have a 3D vector-valued neural network, which deals with three signals as one cluster. In such a neural network, 3D signals are flowing through a network and are the unit of learning. This article also deals with a related 3D back-propagation (3D-BP) learning algorithm, which is an extension of conventional back-propagation algorithm in the single dimension. 3D-BP has an inherent ability to learn and generalize the 3D motion. The computational experiments presented in this paper evaluate the performance of considered learning machine in generalization of 3D transformations and 3D pattern recognition.     

View-based virtual learning and recognition of 3D object using view model obtained by motion-stereo

View-based approach for learning and recognition of 3D object and its pose detection was proved to be affective and efficient, except its high learning cost. In this research, we propose a virtual learning approach which generates learning samples of views of an object from its 3D view model obtained by motion-stereo method. From the generated learning sample views, features of high-order autocorrelation are extracted, and discriminant feature spaces for object recognition and pose detection are built. Recognition experiments on real objects are carried out to show the effectiveness of the proposed method. Caihua Wang, Ph.D.: He received his B.S. in mathematics and M.E. in electronic engineering from Renmin University of China, Beijing, China in 1983 and 1986, and his Ph. D. from Shizuoka University, Hamamatsu, Japan in 1996. He is a JST domestic fellow and is doing his post doctoral research at Electrotechnical Laboratory. His research interests are computer vision and image processing. He is a member of IEICE and IPSJ. Katsuhiko Sakaue, Ph.D.: He received the B.E., M.E., and Ph.D. degrees all in electronic engineering from University of Tokyo, in 1976, 1978 and 1981, respectively. In 1981, he joined the Electrotechnical Laboratory, Ministry of International Trade and Industry, and engaged in researches in image processing and computer vision. He received the Encouragement Prize in 1979 from IEICE, and the Paper Award in 1985 from Information.     

Graph matching for object recognition and recovery

A robust skeleton-based graph matching method for object recognition and recovery applications is presented. The object model uses both a skeleton model and contour segment models, for object recognition and recovery. The presented skeleton-based shape matching method uses a combination of both structural and statistical methods that are applied in a sequential manner, which largely reduce the matching space when compared with previous works. This also provides a good alternate means to alleviate difficulties encountered in segmentation problems. Experiments of object recovery using real biomedical image samples have shown satisfactory results.     

Instance-based object recognition in 3D point clouds using discriminative shape primitives

3D local shapes are a critical cue for object recognition in 3D point clouds. This paper presents an instance-based 3D object recognition method via informative and discriminative shape primitives. We propose a shape primitive model that measures geometrical informativity and discriminativity of 3D local shapes of an object. Discriminative shape primitives of the object are extracted automatically by model parameter optimization. We achieve object recognition from 2.5/3D scenes via shape primitive classification and recover the 3D poses of the identified objects simultaneously. The effectiveness and the robustness of the proposed method were verified on popular instance-based 3D object recognition datasets. The experimental results show that the proposed method outperforms some existing instance-based 3D object recognition pipelines in the presence of noise, varying resolutions, clutter and occlusion.     

Scalable representation for 3D object recognition using feature sharing and view clustering

Scalability is an important issue in object recognition as it reduces database storage and recognition time. In this paper, we propose a new scalable 3D object representation and a learning method to recognize many everyday objects. The key proposal for scalable object representation is to combine the concept of feature sharing with multi-view clustering in part-based object representation, in particular a common-frame constellation model (CFCM). In this representation scheme, we also propose a fully automatic learning method: appearance-based automatic feature clustering and sequential construction of clustered CFCMs from labeled multi-views and multiple objects. We evaluated the scalability of the proposed method to COIL-100 DB and applied the learning scheme to 112 objects with 620 training views. Experimental results show the scalable learning results in almost constant recognition performance relative to the number of objects.     

感知器残差网络和超限学习机融合的3D物体识别

目的 随着3D扫描技术和虚拟现实技术的发展,真实物体的3D识别方法已经成为研究的热点之一。针对现有基于深度学习的方法训练时间长,识别效果不理想等问题,提出了一种结合感知器残差网络和超限学习机（ELM）的3D物体识别方法。方法 以超限学习机的框架为基础,使用多层感知器残差网络学习3D物体的多视角投影特征,并利用提取的特征数据和已知的标签数据同时训练了ELM分类层、K最近邻（KNN）分类层和支持向量机（SVM）分类层识别3D物体。网络使用增加了多层感知器的卷积层替代传统的卷积层。卷积网络由改进的残差单元组成,包含多个卷积核个数恒定的并行残差通道,用于拟合不同数学形式的残差项函数。网络中半数卷积核参数和感知器参数以高斯分布随机产生,其余通过训练寻优得到。结果 提出的方法在普林斯顿3D模型数据集上达到了94.18%的准确率,在2D的NORB数据集上达到了97.46%的准确率。该算法在两个国际标准数据集中均取得了当前最好的效果。同时,使用超限学习机框架使得本文算法的训练时间比基于深度学习的方法减少了3个数量级。结论 本文提出了一种使用多视角图识别3D物体的方法,实验表明该方法比现有的ELM方法和深度学习等最新方法的识别率更高,抗干扰性更强,并且其调节参数少,收敛速度快。     

基于深度学习的三维数据分析理解方法研究综述

基于深度学习的三维数据分析理解是数字几何领域的一个研究热点.不同于基于深度学习的图像分析理解,基于深度学习的三维数据分析理解需要解决的首要问题是数据表达的多样性.相较于规则的二维图像,三维数据有离散表达和连续表达的方法,目前基于深度学习的相关工作多基于三维数据的离散表示,不同的三维数据表达方法与不同的数字几何处理任务对深度学习网络的要求也不同.本文首先汇总了常用的三维数据集与特定任务的评价指标,并分析了三维模型特征描述符.然后从特定任务出发,就不同的三维数据表达方式,对现有的基于深度学习的三维数据分析理解网络进行综述,对各类方法进行对比分析,并从三维数据表达方法的角度进一步汇总现有工作.最后基于国内外研究现状,讨论了亟待解决的挑战性问题,展望了未来发展的趋势.     

Aspect graph construction with noisy feature detectors

Many three-dimensional (3D) object recognition strategies use aspect graphs to represent objects in the model base. A crucial factor in the success of these object recognition strategies is the accurate construction of the aspect graph, its ease of creation, and the extent to which it can represent all views of the object for a given setup. Factors such as noise and nonadaptive thresholds may introduce errors in the feature detection process. This paper presents a characterization of errors in aspect graphs, as well as an algorithm for estimating aspect graphs, given noisy sensor data. We present extensive results of our strategies applied on a reasonably complex experimental set, and demonstrate applications to a robust 3D object recognition problem.