Uncertainty Propagation in Model-Based Recognition

Robust recognition systems require a careful understanding of the effects of error in sensed features. In model-based recognition, matches between model features and sensed image features typically are used to compute a model pose and then project the unmatched model features into the image. The error in the image features results in uncertainty in the projected model features. We first show how error propagates when poses are based on three pairs of 3D model and 2D image points. In particular, we show how to simply and efficiently compute the distributed region in the image where an unmatched model point might appear, for both Gaussian and bounded error in the detection of image points, and for both scaled-orthographic and perspective projection models. Next, we provide geometric and experimental analyses to indicate when this linear approximation will succeed and when it will fail. Then, based on the linear approximation, we show how we can utilize Linear Programming to compute bounded propagated error regions for any number of initial matches. Finally, we use these results to extend, from two-dimensional to three-dimensional objects, robust implementations of alignment, interpretation-tree search, and transformation clustering.     

Minimal Decomposition of Model-Based Invariants

Model-based invariants are relations between model parameters and image measurements, which are independent of the imaging parameters. Such relations are true for all images of the model. Here we describe an algorithm which, given L independent model-based polynomial invariants describing some shape, will provide a linear re-parameterization of the invariants. This re-parameterization has the properties that: (i) it includes the minimal number of terms, and (ii) the shape terms are the same in all the model-based invariants. This final representation has 2 main applications: (1) it gives new representations of shape in terms of hyperplanes, which are convenient for object recognition; (2) it allows the design of new linear shape from motion algorithms. In addition, we use this representation to identify object classes that have universal invariants.     

Curve and Surface Duals and the Recognition of Curved 3D Objects from their Silhouettes

This article addresses the problem of recognizing a solid bounded by a smooth surface in a single image. The proposed approach is based on a new representation for two- and three-dimensional shapes, called their signature, that exploits the close relationship between the dual of a surface and the dual of its silhouette in weak-perspective images. Objects are modeled by rotating them in front of a camera without any knowledge of or constraints on their motion. The signatures of their silhouettes are concatenated into a single object signature. To recognize an object from novel viewpoint other than those used during modeling, the signature of the contours extracted from a test photograph is matched to the signatures of all modeled objects signatures. This approach has been implemented, and recognition examples are presented.     

Probabilistic Models of Appearance for 3-D Object Recognition

We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses probability distributions to describe the range of possible variation in the object's appearance. These distributions are organized on two levels. Large variations are handled by partitioning training images into clusters corresponding to distinctly different views of the object. Within each cluster, smaller variations are represented by distributions characterizing uncertainty in the presence, position, and measurements of various discrete features of appearance. Many types of features are used, ranging in abstraction from edge segments to perceptual groupings and regions. A matching procedure uses the feature uncertainty information to guide the search for a match between model and image. Hypothesized feature pairings are used to estimate a viewpoint transformation taking account of feature uncertainty. These methods have been implemented in an object recognition system, OLIVER. Experiments show that OLIVER is capable of learning to recognize complex objects in cluttered images, while acquiring models that represent those objects using relatively few views.     

基于隐含多项式曲线欧氏不变量物体识别

目标物体的识别和匹配在计算机视觉、图像视频压缩与传输中都有重要应用。隐含多项式曲线对物体有良好的描述能力,用它识别和匹配目标物体是很有效的。文章给出了任意次隐含多项式曲线欧氏几何不变量的计算方法,理论证明这些不变量是完全独立的并且是完备的。文中的实验证明基于这些欧氏不变量能较好地识别发生欧氏变换的目标物体。     

3D Object Recognition in Cluttered Environments by Segment-Based Stereo Vision

We propose a new method for 3D object recognition which uses segment-based stereo vision. An object is identified in a cluttered environment and its position and orientation (6 dof) are determined accurately enabling a robot to pick up the object and manipulate it. The object can be of any shape (planar figures, polyhedra, free-form objects) and partially occluded by other objects. Segment-based stereo vision is employed for 3D sensing. Both CAD-based and sensor-based object modeling subsystems are available. Matching is performed by calculating candidates for the object position and orientation using local features, verifying each candidate, and improving the accuracy of the position and orientation by an iteration method. Several experimental results are presented to demonstrate the usefulness of the proposed method.     

Probabilistic 3D Object Recognition

A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and ratios of lengths by tracing iso-angle and iso-ratio curves on the viewing sphere. The model also accounts for various types of uncertainty in the input such as incomplete and inexact edge detection. For each match hypothesis the pose of the object and the pose uncertainty which is due to the uncertainty in vertex position are recovered. This is used to find sets of hypotheses which reinforce each other by matching features of the same object with compatible uncertainty regions. A probabilistic expression is used to rank these hypothesis sets. The hypothesis sets with the highest rank are output. The algorithm has been fully implemented, and tested on real images.     

利用单个透视投影识别空间多边形

本文提出一种利用单个透视投影识别空间多边形的方法.空间多边形的识别依据于在透视投影下的基本不变量:交比.提出了使用交比描绘多边形的形状.该描绘子的基本特点具有在透视投影下观点不变性质,因此这种方法可直接应用到机器人视觉技术中.     

Polyhedral Object Localization in an Image by Referencing to a Single Model View

Identifying a three-dimensional (3D) object in an image is traditionally dealt with by referencing to a 3D model of the object. In the last few years there has been a growing interest of using not a 3D shape but multiple views of the object as the reference. This paper attempts a further step in the direction, using not multiple views but a single clean view as the reference model. The key issue is how to establish correspondences from the model view where the boundary of the object is explicitly available, to the scene view where the object can be surrounded by various distracting entities and its boundary disturbed by noise. We propose a solution to the problem, which is based upon a mechanism of predicting correspondences from just four particular initial point correspondences. The object is required to be polyhedral or near-polyhedral. The correspondence mechanism has a computational complexity linear with respect to the total number of visible corners of the object in the model view. The limitation of the mechanism is also analyzed thoroughly in this paper. Experimental results over real images are presented to illustrate the performance of the proposed solution.     

A Similarity-Based Aspect-Graph Approach to 3D Object Recognition

This paper describes a view-based method for recognizing 3D objects from 2D images. We employ an aspect-graph structure, where the aspects are not based on the singularities of visual mapping but are instead formed using a notion of shape similarity between views. Specifically, the viewing sphere is endowed with a metric of dis-similarity for each pair of views and the problem of aspect generation is viewed as a segmentation of the viewing sphere into homogeneous regions. The viewing sphere is sampled at regular (5 degree) intervals and the similarity metric is used in an iterative procedure to combine views into aspects with a prototype representing each aspect. This is done in a region-growing regime which stands in contrast to the usual edge detection styles to computing the aspect graph. The aspect growth is constrained such that two aspects of an object remain distinct under the given similarity metric. Once the database of 3D objects is organized as a set of aspects, and prototypes for these aspects for each object, unknown views of database objects are compared with the prototypes and the results are ordered by similarity. We use two similarity metrics for shape, one based on curve matching and the other based on matching shock graphs, which for a database of 64 objects and unknown views of objects from the database give a recall rate of (90.3%, 74.2%, 59.7%) and (95.2%, 69.0%, 57.5%), respectively, for the top three matches; cumulative recall rate based on the top three matches is 98% and 100%, respectively. The result of indexing unknown views of objects not in the database also produce intuitive matches. We also develop a hierarchical indexing scheme to prune unlikely objects at an early stage to improve the efficiency of indexing, resulting in savings of 35% at the top level and of 55% at the next level, cumulatively.     

基于单目计算机视觉的目标跟踪与识别方法讨论

通过实验,对几种常用的图像处理方法在单目计算机视觉下进行目标的跟踪与识别,并进行对比,总结出各方法在不同场景中的处理效果,并提出了相应的使用建议.     

不变矩稳定性及基于多级特征模型的目标识别研究

从成像过程和实际应用角度研究影响目标不变矩稳定性的各种因素,包括有限观测区域、高斯模糊和离散化处理以及在这些因素影响下不变矩的变化规律和误差．理论分析和实验还证明各不变矩自身的稳定特性不仅与阶数而且与其次数有关．这些研究和分析表明建立多尺度目标特征模型的必要性,可为不变矩在实际成像识别系统中正确有效地应用提供重要的理论和实验依据．     

Invariants of Families of Coplanar Conics and Their Applications to Object Recognition

This paper presents mutual invariants of families ofcoplanar conics. These invariants are compared with the use ofinvariants of two conics and a case is presented where the proposedinvariants have a greater discriminating power than the previouslyused invariants. The use of invariants for two conics is extended toany number of coplanar conics. A lambda-matrix is associated witheach family of coplanar conics. The use of lambda-matrices isextended from the single variable polynomial to multi-variablepolynomials. The Segre characteristic and other invariants of thelambda-matrix are used as invariants of the family of conics.     

VC-Dimension Analysis of Object Recognition Tasks

We analyze the amount of data needed to carry out various model-based recognition tasks in the context of a probabilistic data collection model. We focus on objects that may be described as semi-algebraic subsets of a Euclidean space. This is a very rich class that includes polynomially described bodies, as well as polygonal objects, as special cases. The class of object transformations considered is wide, and includes perspective and affine transformations of 2D objects, and perspective projections of 3D objects.We derive upper bounds on the number of data features (associated with non-zero spatial error) which provably suffice for drawing reliable conclusions. Our bounds are based on a quantitative analysis of the complexity of the hypotheses class that one has to choose from. Our central tool is the VC-dimension, which is a well-studied parameter measuring the combinatorial complexity of families of sets. It turns out that these bounds grow linearly with the task complexity, measured via the VC-dimension of the class of objects one deals with. We show that this VC-dimension is at most logarithmic in the algebraic complexity of the objects and in the cardinality of the model library.Our approach borrows from computational learning theory. Both learning and recognition use evidence to infer hypotheses but as far as we know, their similarity was not exploited previously. We draw close relations between recognition tasks and a certain learnability framework and then apply basic techniques of learnability theory to derive our sample size upper bounds. We believe that other relations between learning procedures and visual tasks exist and hope that this work will trigger further fruitful study along these lines.     

Recognition without Correspondence using Multidimensional Receptive Field Histograms

The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represented by the joint statistics of such local neighborhood operators. As such, this represents a new class of appearance based techniques for computer vision. Based on joint statistics, the paper develops techniques for the identification of multiple objects at arbitrary positions and orientations in a cluttered scene. Experiments show that these techniques can identify over 100 objects in the presence of major occlusions. Most remarkably, the techniques have low complexity and therefore run in real-time.     

Covariant-Conics Decomposition of Quartics for 2D Shape Recognition and Alignment

This paper outlines a new geometric parameterization of 2D curves where parameterization is in terms of geometric invariants and parameters that determine intrinsic coordinate systems. This new approach handles two fundamental problems: single-computation alignment, and recognition of 2D shapes under Euclidean or affine transformations. The approach is model-based: every shape is first fitted by a quartic represented by a fourth degree 2D polynomial. Based on the decomposition of this equation into three covariant conics, we are able, in both the Euclidean and the affine cases, to define a unique intrinsic coordinate system for non-singular bounded quartics that incorporates usable alignment information contained in the polynomial representation, a complete set of geometric invariants, and thus an associated canonical form for a quartic. This representation permits shape recognition based on 11 Euclidean invariants, or 8 affine invariants. This is illustrated in experiments with real data sets.     

多事件学习方法及其在三维物体识别中的应用

该文首先介绍了计算机视觉研究领域新近提出的一种知识学习方法———多事件学习模型,简要说明了其研究思路、研究进展、计算方法以及在图像检索中的应用。其次,在简要回顾当前三维物体识别的研究进展和困难的基础上,提出了一种改进的多事件学习模型计算方法,并将其引入到三维物体识别的研究中,以有效简化三维物体的特征表达,提高识别效率。     

一种基于注意力机制的三维点云物体识别方法

三维点云数据通常具备无序排列的结构。在三维点云数据处理领域,深度学习模型通常会利用最大池化等对称操作来处理点云的排列不变性。最大池化方法一方面会破坏点云的信息结构,使得局部信息与全局信息难以交互。另一方面,最大池化方法对点云信息过度压缩,得到的特征对局部细节描述不足。针对上述问题,提出了AttentionPointNet的网络结构。该网络利用注意力机制,使每个点与点云其余部分进行特征交互,实现了局部与全局信息的综合。为降低最大池化造成的信息损失,提出了一种稀疏卷积方法来替代池化操作。这种方法利用大步长的稀疏卷积实现全局信息的提取。在ModelNet40数据集上,AttentionPointNet取得了87.2%的准确率。不使用池化层,完全采用卷积层实现的模型取得了86.2%的分类准确率。     

Point Signatures: A New Representation for 3D Object Recognition

Few systems capable of recognizing complex objects with free-form (sculptured) surfaces have been developed. The apparent lack of success is mainly due to the lack of a competent modelling scheme for representing such complex objects. In this paper, a new form of point representation for describing 3D free-form surfaces is proposed. This representation, which we call the point signature, serves to describe the structural neighbourhood of a point in a more complete manner than just using the 3D coordinates of the point. Being invariant to rotation and translation, the point signature can be used directly to hypothesize the correspondence to model points with similar signatures. Recognition is achieved by matching the signatures of data points representing the sensed surface to the signatures of data points representing the model surface.The use of point signatures is not restricted to the recognition of a single-object scene to a small library of models. Instead, it can be extended naturally to the recognition of scenes containing multiple partially-overlapping objects (which may also be juxtaposed with each other) against a large model library. No preliminary phase of segmenting the scene into the component objects is required. In searching for the appropriate candidate model, recognition need not proceed in a linear order which can become prohibitive for a large model library. For a given scene, signatures are extracted at arbitrarily spaced seed points. Each of these signatures is used to vote for models that contain points having similar signatures. Inappropriate models with low votes can be rejected while the remaining candidate models are ordered according to the votes they received. In this way, efficient verification of the hypothesized candidates can proceed by testing the most likely model first. Experiments using real data obtained from a range finder have shown fast recognition from a library of fifteen models whose complexities vary from that of simple piecewise quadric shapes to complicated face masks. Results from the recognition of both single-object and multiple-object scenes are presented.     

三维人脸识别研究综述

近二十多年来,虽然基于图像的人脸识别已取得很大进展,并可在约束环境下获得很好的识别性能,但仍受光照、姿态、表情等变化的影响很大,其本质原因在于图像是三维物体在二维空间的简约投影.因此,利用脸部曲面的显式三维表达进行人脸识别正成为近几年学术界的研究热点.文中分析了三维人脸识别的产生动机、概念与基本过程;根据特征形式,将三维人脸识别算法分为基于空域直接匹配、基于局部特征匹配、基于整体特征匹配三大类进行综述;对二维和三维的双模态融合方法进行分类阐述;列出了部分代表性的三维人脸数据库;对部分方法进行实验比较,并分析了方法有效性的原因;总结了目前三维人脸识别技术的优势与困难,并探讨了未来的研究趋势.