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.     

基于上下文相似度的对象识别模型的研究

对象识别是数据集成的一个重要问题,针对学术领域的对象集成问题,提出一个基于上下文环境的对象识别模型。利用作者名字的上下文环境,包括合作者、国际会议、论文时间、论文标题4维信息对作者进行对象识别。通过计算两个表象每一维信息的相似程度,采用感知器模型对于少量的专家标注的学习用例进行学习从而获得每一维合适的权重以及对应的阈值,最后利用构造的模型进行准确预测。实验结果表明该模型具有较高的可用性。     

Using natural class hierarchies in multi-class visual classification

We address the problem of computationally efficient visual classification of objects, and propose a system for solving multi-class problems in domains that have inherent hierarchic structure, such as subclass-superclass-relationships based on visual similarity. Class relationships are used at runtime to select the computationally simplest feature space that allows classification at high level of confidence for each example view. Classification accuracies can then be further improved using rank-order voting over multiple views. Our experimental results show that our system compares favorably to previously published results using a demanding benchmark. The results support the hypothesis that class hierarchies based on visual similarities are feasible and useful in controlling the accuracy vs. speed tradeoffs in classification.     

Contextual Priming for Object Detection

There is general consensus that context can be a rich source of information about an object's identity, location and scale. In fact, the structure of many real-world scenes is governed by strong configurational rules akin to those that apply to a single object. Here we introduce a simple framework for modeling the relationship between context and object properties based on the correlation between the statistics of low-level features across the entire scene and the objects that it contains. The resulting scheme serves as an effective procedure for object priming, context driven focus of attention and automatic scale-selection on real-world scenes.     

Generalization to Novel Views: Universal,Class-based,and Model-based Processing

A major problem in object recognition is that a novel image of a given object can be different from all previously seen images. Images can vary considerably due to changes in viewing conditions such as viewing position and illumination. In this paper we distinguish between three types of recognition schemes by the level at which generalization to novel images takes place: universal, class, and model-based. The first is applicable equally to all objects, the second to a class of objects, and the third uses known properties of individual objects. We derive theoretical limitations on each of the three generalization levels. For the universal level, previous results have shown that no invariance can be obtained. Here we show that this limitation holds even when the assumptions made on the objects and the recognition functions are relaxed. We also extend the results to changes of illumination direction. For the class level, previous studies presented specific examples of classes of objects for which functions invariant to viewpoint exist. Here, we distinguish between classes that admit such invariance and classes that do not. We demonstrate that there is a tradeoff between the set of objects that can be discriminated by a given recognition function and the set of images from which the recognition function can recognize these objects. Furthermore, we demonstrate that although functions that are invariant to illumination direction do not exist at the universal level, when the objects are restricted to belong to a given class, an invariant function to illumination direction can be defined. A general conclusion of this study is that class-based processing, that has not been used extensively in the past, is often advantageous for dealing with variations due to viewpoint and illuminant changes.     

三维物体识别研究进展

出于工业和医疗等领域大量现实应用的需要,如今三维物体识别已成为一个很活跃的研究领域。一般来说,三维物体识别系统可以通过两个阶段的处理来完成三维物体的识别和定位,首先用传感器获取的场景输入数据来得到场景的表达;然后将它与数据库中存储的物体表达相匹配。为了推动该领域研究进一步发展,因而对近１０ａ年中该识别过程中必须解决的感传器类型、三维物体表达方法和匹配策略等３个方面问题的研究成果进行了综述,对主要方法进行分类和总结;并提出了一些三维视觉系统中还需要深入研究的问题,包括对所研究物体形状的限制、复杂背景的影响和表达以及识别中的“整体和局部”的矛盾等。     

基于判别性局部联合稀疏模型的多任务跟踪

目标表观建模是基于稀疏表示的跟踪方法的研究重点, 针对这一问题, 提出一种基于判别性局部联合稀疏表示的目标表观模型, 并在粒子滤波框架下提出一种基于该模型的多任务跟踪方法(Discriminative local joint sparse appearance model based multitask tracking method, DLJSM).该模型为目标区域内的局部图像分别构建具有判别性的字典, 从而将判别信息引入到局部稀疏模型中, 并对所有局部图像进行联合稀疏编码以增强结构性.在跟踪过程中, 首先对目标表观建立上述模型; 其次根据目标表观变化的连续性对采样粒子进行初始筛选以提高算法的效率; 然后求解剩余候选目标状态的联合稀疏编码, 并定义相似性函数衡量候选状态与目标模型之间的相似性; 最后根据最大后验概率估计目标当前的状态.此外, 为了避免模型频繁更新而引入累积误差, 本文采用每5帧判断一次的方法, 并在更新时保留首帧信息以减少模型漂移.实验测试结果表明DLJSM方法在目标表观发生巨大变化的情况下仍然能够稳定准确地跟踪目标, 与当前最流行的13种跟踪方法的对比结果验证了DLJSM方法的高效性.     

What Is the Set of Images of an Object Under All Possible Illumination Conditions?

The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then–in theory–the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, we consider only the set of images of an object under variable illumination, including multiple, extended light sources and shadows. We prove that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IRⁿ and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IRⁿ. Extensions of these results to color images are presented. These results immediately suggest certain approaches to object recognition. Throughout, we present results demonstrating the illumination cone representation.

     

DISCOV: A Framework for Discovering Objects in Video

This paper presents a probabilistic framework for discovering objects in video. The video can switch between different shots, the unknown objects can leave or enter the scene at multiple times, and the background can be cluttered. The framework consists of an appearance model and a motion model. The appearance model exploits the consistency of object parts in appearance across frames. We use maximally stable extremal regions as observations in the model and hence provide robustness to object variations in scale, lighting and viewpoint. The appearance model provides location and scale estimates of the unknown objects through a compact probabilistic representation. The compact representation contains knowledge of the scene at the object level, thus allowing us to augment it with motion information using a motion model. This framework can be applied to a wide range of different videos and object types, and provides a basis for higher level video content analysis tasks. We present applications of video object discovery to video content analysis problems such as video segmentation and threading, and demonstrate superior performance to methods that exploit global image statistics and frequent itemset data mining techniques.