Object recognition requires robust and stable features that are unique in feature space. Lie group analysis provides a constructive procedure to determine such features, called invariants, when they exist. Absolute invariants are rare in general, so quasi-invariants relax the restrictions required for absolute invariants and, potentially, can be just as useful in real-world applications. The paper develops the concept of a dominant-subspace invariant, a particular type of quasi-invariant, using the theory of Lie groups. A constructive algorithm is provided that fundamentally seeks to determine an integral submanifold which, in practice, is a good approximation to the orbit of the Lie group action. This idea is applied to the long-wave infrared problem and experimental results are obtained supporting the approach. Other application areas are cited.

In face recognition literature, holistic template matching systems and geometrical local feature based systems have been pursued. In the holistic approach, PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) are popular ones. More recently, the combination of PCA and LDA has been proposed as a superior alternative over pure PCA and LDA. In this paper, we illustrate the rationales behind these methods and the pros and cons of applying them to pattern classification task. A theoretical performance analysis of LDA suggests applying LDA over the principal components from the original signal space or the subspace. The improved performance of this combined approach is demonstrated through experiments conducted on both simulated data and real data.

In face recognition literature, major approaches based on holistic templates and geometrical local features have been taken. Both approaches have certain advantages and disadvantages. We explore a method which integrates the above two approaches. Among many specific systems, we select LDA (linear discriminant analysis) and MPF (matching pursuit filter) as the representative from the first type approach and the second type approach respectively. We treat MPF as the feature representation of the original input and LDA as the pattern classifier. We compare the performances of MPF system, LDA system and the hybrid LDA-MPF system for face 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.

The fusion of multiple imaging modalities offers many advantages over the analysis, separately, of the individual sensory modalities. In this paper we present a unique approach to the integrated analysis of disparate sources of imagery for object recognition. The approach is based on physics-based modeling of the image generation mechanisms. Such models make possible features that are physically meaningful and have an improved capacity to differentiate between multiple classes of objects. We illustrate the use of physics-based approach to develop multisensory vision systems for different object recognition application domains. The paper discusses the integration of different suites of sensors, the integration of image-derived information with model-derived information and the physics-based simulation of multisensory imagery.

We previously formulated a new approach for computing invariant features from infrared (IR) images. That 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 thermal state that affect images sensed in the nonvisible spectrum. In this paper, we extend the thermophysical algebraic invariance (TAI) formulation for the interpretation of uncalibrated infrared imagery and further reduce the information that is required to be known about the environment. Features are defined such that they are functions of only the thermophysical properties of the imaged objects. In addition, we show that the distribution of the TAI features can be accurately modeled by symmetric alpha-stable models. This approach is shown to yield robust classifier performance. Results on ground truth data and real infrared imagery are presented. The application of this scheme for site change detection is discussed.

Although many algorithms have been developed for motion estimation from range images, none are suited for use with scanning laser sensors. In this paper, the feature-based motion transformation model is restated to incorporate the nonzero pixel sampling rate of laser range cameras and a novel iterative, linear, feature-based technique for determining the 3D motion transformation of moving objects is developed using this new model. A technique is then presented which employs the motion recovered using the iterative algorithm to remove the structural distortion of the object in the range map. The performance of the motion recovery method is verified using simulated and experimental data.

Since the analytical expressions for the representation of nonrigid object structure and motion are severely underconstrained, current techniques for nonrigid object manipulation employ physical object models known prior to sensing. Recently, however, psychophysical studies have revealed that humans are able to discover proper motor coordination skills through sensory input without the use of previously known physical models. In this paper, a robust, discovery-driven, vision-based robotic manipulation algorithm for nonrigid objects, based on the novel concept of relative elasticity, is developed which requires the use of no a priori physical models. The manipulation technique is also experimentally verified on different flexible linear objects.

This paper analyses the performance of cepstral approaches for solving the stereo correspondence problem. A quantitative analysis of the effects of noise, foreshortening differences, and photometric variations on existing cepstral correspondence techniques is presented. A modified approach that is less sensitive to these effects is developed for textured scenes, and analytical arguments for its robustness are developed. The results of a comparative study of the new cepstral technique, the original cepstral algorithm and the cross-correlation approach are shown and discussed. The performance of the new method is experimentally verified on textured surfaces.

An innovative technique for rigid body motion estimation for use with sequential, time-of-flight laser radar scanners is presented. The method is an iterative, linear, feature-based approach which uses the non-zero image acquisition time constraint to accurately recover the motion parameters from the distorted structure of the 3-D range maps. The performance of the technique is experimentally verified using computer simulations.>

This paper describes the design of a binocular stereo system called CCLPS (Computerized Coal Profiling System) that provides dense, accurate disparity maps of coal as it is being transported in open rail cars. After a quantitative analysis of previously developed cepstral correspondence techniques which highlights the shortcomings of the cepstrum's matching ability in the presence of random noise and severe foreshortening distortion, we present a modified power cepstral approach that is less sensitive to these effects, along with analytical arguments verifying its robustness. The design of the CCLPS system is then discussed in detail and its performance is verified.>

A qualitative analysis of the effects of noise, foreshortening, and photometric variations on cepstral correspondence methods is presented. A modified approach that is less sensitive to these effects is developed, and analytical arguments for its robustness are given. The performance of the improved method is experimentally verified on real data.>

A unified approach for modeling objects which are imaged by thermal (infrared) and visual cameras is presented. The model supports the generation of both infrared (8 mu m-12 mu m wavelength) images and monochrome visual images under different viewing and ambient-scene conditions. A modified octree data structure is used for object modeling. The octree serves two different purposes: surface information encoded in boundary nodes and efficient tree-traversal algorithms facilitate the generation of monochrome visual images; and the compact volumetric representation facilitates simulation of heat flow in the object which gives rise to surface temperature variation, which in turn is used to synthesize the thermal image. The detailed object model allows for more accurate prediction of thermal and visual images of objects. It also predicts the values of discriminatory features used in classification. The model developed is designed to be used in a model-based vision system which uses a hypothesize-and-verify strategy to interpret thermal and visual images of scenes. Several blocks-world examples are presented to show typical images generated by the approach.>

After a brief summary of range acquisition techniques, some of the progress made with three-dimensional data in the field of computer vision is examined. The present state of three-dimensional object recognition using range data is surveyed. Some work involving three-dimensional object recognition using intensity images is also included when it is applicable to, or extendable to, recognition with range data.>

A novel technique is presented for automated image analysis. Information from thermal and visual imagery is fused for classifying objects in outdoor scenes. Pixel-level information fusion yields a feature based on the lumped thermal capacitance of the objects. Region-level fusion using a decision tree classifier categorizes imaged objects as being either vegetation, building, pavement, or a vehicle.>

An approach for computer perception of outdoor scenes is presented. The approach is based on integrating information extracted from thermal images and visual images, which provides information not available by processing either type of image alone. The thermal image is analyzed to provide estimates of surface temperature. The visual image provides surface absorptivity and relative orientation. These parameters are used together to provide estimates of heat fluxes at the surfaces of viewed objects. The thermal behavior of scene objects is described in terms of surface heat fluxes. Features based on estimated values of surface heat fluxes are shown to be more meaningful and specific in distinguishing scene components.>

Recent developments are reviewed in the computation of motion and structure of objects in a scene from a sequence of images. Two distinct paradigms are highlighted: (i) the feature-based approach and (ii) the optical-flow-based approach. The comparative merits/demerits of these approaches are discussed. The current status of research in these areas is reviewed and future research directions are indicated.>