Range Flow Estimation

We discuss the computation of the instantaneous 3D displacement vector fields of deformable surfaces from sequences of range data. We give a novel version of the basic motion constraint equation that can be evaluated directly on the sensor grid. The various forms of the aperture problem encountered are investigated and the derived constraint solutions are solved in a total least squares (TLS) framework. We propose a regularization scheme to compute dense full flow fields from the sparse TLS solutions. The performance of the algorithm is analyzed quantitatively for both synthetic and real data. Finally we apply the method to compute the 3D motion field of living plant leaves.     

Face Detection: A Survey

In this paper we present a comprehensive and critical survey of face detection algorithms. Face detection is a necessary first-step in face recognition systems, with the purpose of localizing and extracting the face region from the background. It also has several applications in areas such as content-based image retrieval, video coding, video conferencing, crowd surveillance, and intelligent human–computer interfaces. However, it was not until recently that the face detection problem received considerable attention among researchers. The human face is a dynamic object and has a high degree of variability in its apperance, which makes face detection a difficult problem in computer vision. A wide variety of techniques have been proposed, ranging from simple edge-based algorithms to composite high-level approaches utilizing advanced pattern recognition methods. The algorithms presented in this paper are classified as either feature-based or image-based and are discussed in terms of their technical approach and performance. Due to the lack of standardized tests, we do not provide a comprehensive comparative evaluation, but in cases where results are reported on common datasets, comparisons are presented. We also give a presentation of some proposed applications and possible application areas.     

An Algebraic Approach to Camera Self-Calibration

This paper describes a new self-calibration method for a single camera undergoing general motions. It has the following main contributions. First, we establish new constraints which relate the intrinsic parameters of the camera to the rotational part of the motions. This derivation is purely algebraic. We propose an algorithm which simultaneously solves for camera calibration and the rotational part of motions. Second, we provide a comparison between the developed method and a Kruppa equation-based method. Extensive experiments on both synthetic and real image data show the reliability and outperformance of the proposed method. The practical contribution of the method is its interesting convergence property compared with that of the Kruppa equations method.     

Three-Class Markovian Segmentation of High-Resolution Sonar Images

This paper presents an original method for analyzing, in an unsupervised way, images supplied by high resolution sonar. We aim at segmenting the sonar image into three kinds of regions: echo areas (due to the reflection of the acoustic wave on the object), shadow areas (corresponding to a lack of acoustic reverberation behind an object lying on the sea-bed), and sea-bottom reverberation areas. This unsupervised method estimates the parameters of noise distributions, modeled by a Weibull probability density function (PDF), and the label field parameters, modeled by a Markov random field (MRF). For the estimation step, we adopt a maximum likelihood technique for the noise model parameters and a least-squares method to estimate the MRF prior model. Then, in order to obtain an accurate segmentation map, we have designed a two-step process that finds the shadow and the echo regions separately, using the previously estimated parameters. First, we introduce a scale-causal and spatial model called SCM (scale causal multigrid), based on a multigrid energy minimization strategy, to find the shadow class. Second, we propose a MRF monoscale model using a priori information (at different level of knowledge) based on physical properties of each region, which allows us to distinguish echo areas from sea-bottom reverberation. This technique has been successfully applied to real sonar images and is compatible with automatic processing of massive amounts of data.     

3D Articulated Models and Multiview Tracking with Physical Forces

We present a method for automatically estimating the motion of an articulated object filmed by two or more fixed cameras. We focus our work on the case where the quality of the images is poor, and where only an approximation of a geometric model of the tracked object is available. Our technique uses physical forces applied to each rigid part of a kinematic 3D model of the object we are tracking. These forces guide the minimization of the differences between the pose of the 3D model and the pose of the real object in the video images. We use a fast recursive algorithm to solve the dynamical equations of motion of any 3D articulated model. We explain the key parts of our algorithms: how relevant information is extracted from the images, how the forces are created, and how the dynamical equations of motion are solved. A study of what kind of information should be extracted in the images and of when our algorithms fail is also presented. Finally we present some results about the tracking of a person. We also show the application of our method to the tracking of a hand in sequences of images, showing that the kind of information to extract from the images depends on their quality and of the configuration of the cameras.     

A Real-Time Approach to the Spotting, Representation, and Recognition of Hand Gestures for Human–Computer Interaction

Aiming at the use of hand gestures for human–computer interaction, this paper presents a real-time approach to the spotting, representation, and recognition of hand gestures from a video stream. The approach exploits multiple cues including skin color, hand motion, and shape. Skin color analysis and coarse image motion detection are joined to perform reliable hand gesture spotting. At a higher level, a compact spatiotemporal representation is proposed for modeling appearance changes in image sequences containing hand gestures. The representation is extracted by combining robust parameterized image motion regression and shape features of a segmented hand. For efficient recognition of gestures made at varying rates, a linear resampling technique for eliminating the temporal variation (time normalization) while maintaining the essential information of the original gesture representations is developed. The gesture is then classified according to a training set of gestures. In experiments with a library of 12 gestures, the recognition rate was over 90%. Through the development of a prototype gesture-controlled panoramic map browser, we demonstrate that a vocabulary of predefined hand gestures can be used to interact successfully with applications running on an off-the-shelf personal computer equipped with a home video camera.     

Encoding Linear Logic with Interaction Combinators

The purpose of this paper is to demonstrate how Lafont's interaction combinators, a system of three symbols and six interaction rules, can be used to encode linear logic. Specifically, we give a translation of the multiplicative, exponential, and additive fragments of linear logic together with a strategy for cut-elimination which can be faithfully simulated. Finally, we show briefly how this encoding can be used for evaluating λ-terms. In addition to offering a very simple, perhaps the simplest, system of rewriting for linear logic and the λ-calculus, the interaction net implementation that we present has been shown by experimental testing to offer a good level of sharing in terms of the number of cut-elimination steps (resp. β-reduction steps). In particular it performs better than all extant finite systems of interaction nets.     

Tracking of Human Limbs by Multiocular Vision

This article proposes a method for the tracking of human limbs from multiocular sequences of perspective images. These limbs and the associated articulations must first be modelled. During the learning stage, we model the texture linked to the limbs. The lack of characteristic points on the skin is compensated by the wearing of nonrepetitive texture tights. The principle of the method is based on the interpretation of image textured patterns as the 3D perspective projections of points of the textured articulated model. An iterative Levenberg–Marquardt process is used to compute the model pose in accordance with the analyzed image. The calculated attitude is filtered (Kalman filter) to predict the model pose in the following image of the sequence. The image patterns are extracted locally according to the textured articulated model in the predicted attitude. Tracking experiments, illustrated in this paper by cycling sequences, demonstrate the validity of the approach.     

Decidability for Left-Linear Growing Term Rewriting Systems

A term rewriting system is called growing if each variable occurring on both the left-hand side and the right-hand side of a rewrite rule occurs at depth zero or one in the left-hand side. Jacquemard showed that the reachability and the sequentiality of linear (i.e., left-right-linear) growing term rewriting systems are decidable. In this paper we show that Jacquemard's result can be extended to left-linear growing rewriting systems that may have right-nonlinear rewrite rules. This implies that the reachability and the joinability of some class of right-linear term rewriting systems are decidable, which improves the results for right-ground term rewriting systems by Oyamaguchi. Our result extends the class of left-linear term rewriting systems having a decidable call-by-need normalizing strategy. Moreover, we prove that the termination property is decidable for almost orthogonal growing term rewriting systems.     

Cooperative Stereo–Motion: Matching and Reconstruction

One of the most interesting goals of computer vision is the 3D structure recovery of scenes. Traditionally, two cues are used: structure from motion and structure from stereo, two subfields with complementary sets of assumptions and techniques. This paper introduces a new general framework of cooperation between stereo and motion. This framework combines the advantages of both cues: (i) easy correspondence from motion and (ii) accurate 3D reconstruction from stereo. First, we show how the stereo matching can be recovered from motion correspondences using only geometric constraints. Second, we propose a method of 3D reconstruction of both binocular and monocular features using all stereo pairs in the case of a calibrated stereo rig. Third, we perform an analysis of the performance of the proposed framework as well as a comparison with an affine method. Experiments involving real and synthetic stereo pairs indicate that rich and reliable information can be derived from the proposed framework. They also indicate that robust 3D reconstruction can be obtained even with short image sequences.     

Robust Detection of Degenerate Configurations while Estimating the Fundamental Matrix

We present a new method for the detection of multiple solutions or degeneracy when estimating thefundamental matrix, with specific emphasis on robustness to data contamination (mismatches). The fundamental matrix encapsulates all the information on camera motion and internal parameters available from image feature correspondences between two views. It is often used as a first step in structure from motion algorithms. If the set of correspondences is degenerate, then this structure cannot be accurately recovered and many solutions explain the data equally well. It is essential that we are alerted to such eventualities. As current feature matchers are very prone to mismatching the degeneracy detection method must also be robust to outliers.In this paper a definition of degeneracy is given and all two-view nondegenerate and degenerate cases are catalogued in a logical way by introducing the language of varieties from algebraic geometry. It is then shown how each of the cases can be robustly determined from image correspondences via a scoring function we develop. These ideas define a methodology which allows the simultaneous detection of degeneracy and outliers. The method is called PLUNDER-DL and is a generalization of the robust estimator RANSAC.The method is evaluated on many differing pairs of real images. In particular it is demonstrated that proper modeling of degeneracy in the presence of outliers enables the detection of mismatches which would otherwise be missed. All processing including point matching, degeneracy detection, and outlier detection is automatic.     

Assigning Types to Processes

In wide area distributed systems it is now common for higher-order code to be transferred from one domain to another; the receiving host may initialise parameters and then execute the code in its local environment. In this paper we propose a fine-grained typing system for a higher-order π-calculus which can be used to control the effect of such migrating code on local environments. Processes may be assigned different types depending on their intended use. This is in contrast to most of the previous work on typing processes where all processes are typed by a unique constant type, indicating essentially that they are well typed relative to a particular environment. Our fine-grained typing facilitates the management of access rights and provides host protection from potentially malicious behaviour. Our process type takes the form of an interface limiting the resources to which it has access and the types at which they may be used. Allowing resource names to appear both in process types and process terms, as interaction ports, complicates the typing system considerably. For the development of a coherent typing system, we use a kinding technique, similar to that used by the subtyping of the system F, and order-theoretic properties of our subtyping relation. Various examples of this paper illustrate the usage of our fine-grained process types in distributed systems.     

Communication Complexity Method for Measuring Nondeterminism in Finite Automata

While deterministic finite automata seem to be well understood, surprisingly many important problems concerning nondeterministic finite automata (nfa's) remain open. One such problem area is the study of different measures of nondeterminism in finite automata and the estimation of the sizes of minimal nondeterministic finite automata. In this paper the concept of communication complexity is applied in order to achieve progress in this problem area. The main results are as follows:1. Deterministic communication complexity provides lower bounds on the size of nfa's with bounded unambiguity. Applying this fact, the proofs of several results about nfa's with limited ambiguity can be simplified and presented in a uniform way.2. There is a family of languages KON_k² with an exponential size gap between nfa's with polynomial leaf number/ambiguity and nfa's with ambiguity k. This partially provides an answer to the open problem posed by B. Ravikumar and O. Ibarra (1989, SIAM J. Comput.18, 1263–1282) and H. Leung (1998, SIAM J. Comput.27, 1073–1082).     

Simulation Preorder over Simple Process Algebras

We consider the problem of simulation preorder/equivalence between infinite-state processes and finite-state ones. First, we describe a general method how to utilize the decidability of bisimulation problems to solve (certain instances of) the corresponding simulation problems. For certain process classes, the method allows us to design effective reductions of simulation problems to their bisimulation counterparts and some new decidability results for simulation have already been obtained in this way. Then we establish the decidability border for the problem of simulation preorder/equivalence between infinite-state processes and finite-state ones w.r.t. the hierarchy of process rewrite systems. In particular, we show that simulation preorder (in both directions) and simulation equivalence are decidable in EXPTIME between pushdown processes and finite-state ones. On the other hand, simulation preorder is undecidable between PA and finite-state processes in both directions. These results also hold for those PA and finite-state processes which are deterministic and normed, and thus immediately extend to trace preorder. Regularity (finiteness) w.r.t. simulation and trace equivalence is also shown to be undecidable for PA. Finally, we prove that simulation preorder (in both directions) and simulation equivalence are intractable between all classes of infinite-state systems (in the hierarchy of process rewrite systems) and finite-state ones. This result is obtained by showing that the problem whether a BPA (or BPP) process simulates a finite-state one is PSPACE-hard and the other direction is co -hard; consequently, simulation equivalence between BPA (or BPP) and finite-state processes is also co -hard.     

Attentional Scene Segmentation: Integrating Depth and Motion

We present an approach to attention in active computer vision. The notion of attention plays an important role in biological vision. In recent years, and especially with the emerging interest in active vision, computer vision researchers have been increasingly concerned with attentional mechanisms as well. The basic principles behind these efforts are greatly influenced by psychophysical research. That is the case also in the work presented here, which adapts to the model of Treisman (1985, Comput. Vision Graphics Image Process. Image Understanding31, 156–177), with an early parallel stage with preattentive cues followed by a later serial stage where the cues are integrated. The contributions in our approach are (i) the incorporation of depth information from stereopsis, (ii) the simple implementation of low level modules such as disparity and flow by local phase, and (iii) the cue integration along pursuit and saccade mode that allows us a proper target selection based on nearness and motion. We demonstrate the technique by experiments in which a moving observer selectively masks out different moving objects in real scenes.     

Test Sets for the Universal and Existential Closure of Regular Tree Languages

Finite test sets are a useful tool for deciding the membership problem for the universal closure of a given tree language, that is, for deciding whether a term has all its ground instances in the given language. A uniform test set for the universal closure must serve the following purpose: In order to decide membership of a term, it is sufficient to check whether all its test set instances belong to the underlying language. A possible application, and our main motivation, is ground reducibility, an essential concept for many approaches to inductive reasoning. Ground reducibility modulo some rewrite system is membership in the universal closure of the set of reducible ground terms. Here, test sets always exist, and several algorithmic approaches are known. The resulting sets, however, are often unnecessarily large. In this paper we consider regular languages and linear closure operators. We prove that universal as well as existential closure, defined analogously, preserve regularity. By relating test sets to tree automata and to appropriate congruence relations, we show how to characterize, how to compute, and how to minimize ground and non-ground test sets. In particular, optimal solutions now replace previous ad hoc approximations for the ground reducibility problem.     

A Monadic Second-Order Definition of the Structure of Convex Hypergraphs

We consider finite hypergraphs with hyperedges defined as sets of vertices of unbounded cardinality. Each such hypergraph has a unique modular decomposition, which is a tree, the nodes of which correspond to certain subhypergraphs (induced by certain sets of vertices called strong modules) of the considered hypergraph. One can define this decomposition by monadic second-order (MS) logical formulas. Such a hypergraph is convex if the vertices are linearly ordered in such a way that the hyperedges form intervals. Our main result says that the unique linear order witnessing the convexity of a prime hypergraph (i.e., of one, the modular decomposition of which is trivial) can be defined in MS logic. As a consequence, we obtain that if a set of bipartite graphs that correspond (in the usual way) to convex hypergraphs has a decidable monadic second-order theory (which means that one can decide whether a given MS formula is satisfied in some graph of the set) then it has bounded clique-width. This yields a new case of validity of a conjecture which is still open.     

Optimal Robot Localization in Trees

The problem of localization, that is, of a robot finding its position on a map, is an important task for autonomous mobile robots. It has applications in numerous areas of robotics ranging from aerial photography to autonomous vehicle exploration. In this paper we present a new strategy LPS (Localize-by-Placement-Separation) for a robot to find its position on a map, where the map is represented as a geometric tree of bounded degree. Our strategy exploits to a high degree the self-similarities that may occur in the environment. We use the framework of competitive analysis to analyze the performance of our strategy. In particular, we show that the distance traveled by the robot is at most O( ) times longer than the shortest possible route to localize the robot, where n is the number of vertices of the tree. This is a significant improvement over the best known previous bound of O(n^2/3). Moreover, since there is a lower bound of Ω( ), our strategy is optimal up to a constant factor. Using the same approach we can also show that the problem of searching for a target in a geometric tree, where the robot is given a map of the tree and the location of the target but does not know its own position, can be solved by a strategy with a competitive ratio of O( ), which is again optimal up to a constant factor.     

Perceptual Organization Based Computational Model for Robust Segmentation of Moving Objects

The role of perceptual organization in motion analysis has heretofore been minimal. In this work we present a simple but powerful computational model and associated algorithms based on the use of perceptual organizational principles, such as temporal coherence (or common fate) and spatial proximity, for motion segmentation. The computational model does not use the traditional frame by frame motion analysis; rather it treats an image sequence as a single 3D spatio-temporal volume. It endeavors to find organizations in this volume of data over three levels—signal, primitive, and structural. The signal level is concerned with detecting individual image pixels that are probably part of a moving object. The primitive level groups these individual pixels into planar patches, which we call the temporal envelopes. Compositions of these temporal envelopes describe the spatio-temporal surfaces that result from object motion. At the structural level, we detect these compositions of temporal envelopes by utilizing the structure and organization among them. The algorithms employed to realize the computational model include 3D edge detection, Hough transformation, and graph based methods to group the temporal envelopes based on Gestalt principles. The significance of the Gestalt relationships between any two temporal envelopes is expressed in probabilistic terms. One of the attractive features of the adopted algorithm is that it does not require the detection of special 2D features or the tracking of these features across frames. We demonstrate that even with simple grouping strategies, we can easily handle drastic illumination changes, occlusion events, and multiple moving objects, without the use of training and specific object or illumination models. We present results on a large variety of motion sequences to demonstrate this robustness.