A CAD Model Based System for Object Recognition

3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major components, namely: an object modeller and a system that performs the matching of stored representations to those derived from the sensed image. The performance of systems wherein the construction of object models is done by training from one or more images of the objects, has not been very satisfactory. Although objects used in a robotic workcell or in assembly processes have been designed using a CAD system, the vision systems used for recognition of these objects are independent of the CAD database. This paper proposes a scheme for interfacing the CAD database of objects and the computer vision processes used for recognising these objects. CAD models of objects are processed to generate vision oriented features that appear in the different views of the object and the same features are extracted from images of the object to identify the object and its pose.     

Some experiments on the detection of three-dimensional motion of rigid objects in blocks world

The present paper describes some major steps in our experiment of a two-frame based approach analysis. Its application deals with 3-D time-varing scene analysis. The entire analysis process can be divided into several major steps. Here, we are concerned with four main steps: preprocessing, knowledge representation, features matching and motion estimation. The work is directly related to the problem encountered by researchers in machine intelligence area where a vision system is indispensable. For each step, experimental results are given to illustrate the performance of the algorithms of processing. Furthermore, the implemented algorithms provide somewhat versatility and flexibility in the sense that they can be applied to other tasks of scene analysis, such as: stereo vision, object recognition and dynamic scene segmentation since the problem in determining the movement of an object using successive images is similar in many ways to the problem met in optic flow analysis and stereopsis. Finally, it should be pointed out that a vision system can be easily built when combining all of these available algorithms.     

A model-based vision system for industrial parts using a small computer

A model-based vision system has been successfully implemented in a small computer environment. This approach uses a basic solid modeling system to develop three-dimensional models of mechanical parts. From those models, two-dimensional projections are taken for every stable state of the object, with many orientations around the object's vertical axis for each stable state. These two-dimensional projections are treated as synthetic binary images, from which a variety of features may be measured and extracted. A similar procedure is used for a binary image of an object from a real scene, and features are also extracted for that image. A simple matching procedures uses the model-based feature sets to determine the real object's stable state position and orientation. This paper describes the system in detail and shows examples of its use.     

Distinctive Image Features from Scale-Invariant Keypoints

This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.     

Just-in-time landmarks recognition

Human beings act mysteriously well on object recognition tasks; they perceive images by sensors and convey information that is processed in parallel in the brain. To some extent, massively parallel computers offer a natural support for similar tasks, since the detection of an object in a scene can be performed by repeating the same operations in different zones of the scene. Unfortunately, most parametric models, commonly used in computer vision, are not very suitable for complex matching operations that involve both noise and severe image distortions.In this paper we discuss an expectation-driven approach for object recognition where, on the basis of the shape of the object to be recognized, we select a few possible zones of the scene where attention will be focused (shape perception): then we examine the previously selected areas, tyring to confirm or reject hypotheses of objects, if any (object classification). We propose the use of an architecture that relies on neural networks for both shape perception and object classification. A vision system based on the discussed architectures has been tested on board a mobile robot as a support for its localization and navigation in indoor environments. The obtained results demonstrated good tolerance with respect to both noise and landmark distortions, allowing the robot to perform its task “just-in-time”. The proposed approach has also been tested on a massively parallel architecture, with promising performance.     

Robust object recognition with cortex-like mechanisms

We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex     

A neural network approach to CSG-based 3-D object recognition

Describes the recognition subsystem of a computer vision system based on constructive solid geometry (CSG) representation scheme. Instead of using the conventional CSG trees to represent objects, the proposed system uses an equivalent representation scheme-precedence graphs-for object representation. Each node in the graph represents a primitive volume and each are between two nodes represents the relation between them. Object recognition is achieved by matching the scene precedence graph to the model precedence graph. A constraint satisfaction network is proposed to implement the matching process. The energy function associated with the network is used to enforce the matching constraints including match validity, primitive similarity, precedence graph preservation, and geometric structure preservation. The energy level is at its minimum only when the optimal match is reached. Experimental results on several range images are presented to demonstrate the proposed approach     

用于遥感图像人造目标识别的三维建模方法研究

该文研究了用于遥感图像人造地物目标识别的三维建模方法,文中分析了识别任务的特点,比较了一般的建模方法,介绍了一种基于广义锥思想的几何表示方法,并利用面向对象的技术来表示模型内部数据及其操作。     

Thermophysical algebraic invariants from infrared imagery forobject recognition

An important issue in developing a model-based vision system is the specification of features that are invariant to viewing and scene conditions and also specific, i.e., the feature must have different values for different classes of objects. We formulate a new approach for establishing invariant features. Our approach is unique in the field since it considers not just surface reflection and surface geometry in the specification of invariant features, but it also takes into account internal object composition and state which affect images sensed in the nonvisible spectrum. A new type of invariance called thermophysical invariance is defined. Features are defined such that they are functions of only the thermophysical properties of the imaged objects. The approach is based on a physics-based model that is derived from the principle of the conservation of energy applied at the surface of the imaged object     

Context-based vision: recognizing objects using information fromboth 2D and 3D imagery

Results from an ongoing project concerned with recognizing objects in complex scene domains, especially in the domain that includes the natural outdoor world, are described. Traditional machine recognition paradigms assume either that all objects of interest are definable by a relatively small number of explicit shape models or that all objects of interest have characteristic, locally measurable features. The failure of both assumptions has a dramatic impact on the form of an acceptable architecture for an object recognition system. In this work, the use of the contextual information is a central issue, and a system is explicitly designed to identify and use context as an integral part of recognition that eliminates the traditional dependence on stored geometric models and universal image partitioning algorithms. This paradigm combines the results of many simple procedures that analyze monochrome, color, stereo, or 3D range images. Interpreting the results along with relevant contextual knowledge makes it possible to achieve a reliable recognition result, even when using imperfect visual procedures. Initial experimentation with the system on ground-level outdoor imagery has demonstrated competence beyond what is attainable with other vision systems     

Building extraction based on stereo analysis of high-resolution SAR images taken from orthogonal aspect directions

In this paper high-resolution SAR images of an urban scene are analyzed in order to infer buildings and their heights from the different layover effects in perpendicular taken views. Due to the strong dependence of the appearance of objects on the lighting and viewing direction, it is unlikely that a simple image-matching method would succeed. Instead, higher level object matching is proposed. Here, a knowledge-based approach is applied, a production system. The images are analyzed separately for the presence of certain object groups and their characteristics frequently appearing on buildings, such as salient rows, rectangular structures, or symmetries. The stereo analysis is then accomplished locally by means of productions that combine and match these image objects and infer the height. The approach is tested using real SAR data of an urban scene.     

A Multibody Factorization Method for Independently Moving Objects

The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The more realistic case where an unknown number of objects move in the scene has received little attention, especially for its theoretical treatment. In this paper we present a new method for separating and recovering the motion and shape of multiple independently moving objects in a sequence of images. The method does not require prior knowledge of the number of objects, nor is dependent on any grouping of features into an object at the image level. For this purpose, we introduce a mathematical construct of object shapes, called the shape interaction matrix, which is invariant to both the object motions and the selection of coordinate systems. This invariant structure is computable solely from the observed trajectories of image features without grouping them into individual objects. Once the matrix is computed, it allows for segmenting features into objects by the process of transforming it into a canonical form, as well as recovering the shape and motion of each object. The theory works under a broad set of projection models (scaled orthography, paraperspective and affine) but they must be linear, so it excludes projective cameras.     

Application of differential geometry to recognize and locate partially occluded objects

A new method has been proposed to recognize and locate partially occluded two-dimensional rigid objects of a given scene. For this purpose we initially generate a set of local features of the shapes using the concept of differential geometry. Finally a computer vision scheme, based upon matching local features of the objects in a scene and the models which are considered as cognitive database, is described using hypothesis generation and verification of features for the best possible recognition.     

Visual learning and recognition of 3-d objects from appearance

The problem of automatically learning object models for recognition and pose estimation is addressed. In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. The appearance of an object in a two-dimensional image depends on its shape, reflectance properties, pose in the scene, and the illumination conditions. While shape and reflectance are intrinsic properties and constant for a rigid object, pose and illumination vary from scene to scene. A compact representation of object appearance is proposed that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a manifold. Given an unknown input image, the recognition system projects the image to eigenspace. The object is recognized based on the manifold it lies on. The exact position of the projection on the manifold determines the object's pose in the image.A variety of experiments are conducted using objects with complex appearance characteristics. The performance of the recognition and pose estimation algorithms is studied using over a thousand input images of sample objects. Sensitivity of recognition to the number of eigenspace dimensions and the number of learning samples is analyzed. For the objects used, appearance representation in eigenspaces with less than 20 dimensions produces accurate recognition results with an average pose estimation error of about 1.0 degree. A near real-time recognition system with 20 complex objects in the database has been developed. The paper is concluded with a discussion on various issues related to the proposed learning and recognition methodology.     

Scene Parsing Using Region-Based Generative Models

Semantic scene classification is a challenging problem in computer vision. In contrast to the common approach of using low-level features computed from the whole scene, we propose "scene parsing" utilizing semantic object detectors (e.g., sky, foliage, and pavement) and region-based scene-configuration models. Because semantic detectors are faulty in practice, it is critical to develop a region-based generative model of outdoor scenes based on characteristic objects in the scene and spatial relationships between them. Since a fully connected scene configuration model is intractable, we chose to model pairwise relationships between regions and estimate scene probabilities using loopy belief propagation on a factor graph. We demonstrate the promise of this approach on a set of over 2000 outdoor photographs, comparing it with existing discriminative approaches and those using low-level features     

Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes

We describe a flexible model for representing images of objects of a certain class, known a priori, such as faces, and introduce a new algorithm for matching it to a novel image and thereby perform image analysis. The flexible model, known as a multidimensional morphable model, is learned from example images of objects of a class. In this paper we introduce an effective stochastic gradient descent algorithm that automatically matches a model to a novel image. Several experiments demonstrate the robustness and the broad range of applicability of morphable models. Our approach can provide novel solutions to several vision tasks, including the computation of image correspondence, object verification and image compression.