The Specialized Mappings Architecture

A probabilistic, nonlinear supervised learning model is proposed: the Specialized Mappings Architecture (SMA). The SMA employs a set of several forward mapping functions that are estimated automatically from training data. Each specialized function maps certain domains of the input space (e.g., image features) onto the output space (e.g., articulated body parameters). The SMA can model ambiguous, one-to-many mappings that may yield multiple valid output hypotheses. Once learned, the mapping functions generate a set of output hypotheses for a given input via a statistical inference procedure. The SMA inference procedure incorporates an inverse mapping or feedback function in evaluating the likelihood of each of the hypothesis. Possible feedback functions include computer graphics rendering routines that can generate images for given hypotheses. The SMA employs a variant of the Expectation-Maximization algorithm for simultaneous learning of the specialized domains along with the mapping functions, and approximate strategies for inference. The framework is demonstrated in a computer vision system that can estimate the articulated pose parameters of a human’s body or hands, given silhouettes from a single image. The accuracy and stability of the SMA are also tested using synthetic images of human bodies and hands, where ground truth is known.

Specialized Mappings Architecture with Applications to Vision-based Estimation of Articulated Body Pose

A fundamental task of vision systems is to infer the state of the world given some form of visual observations. From a computational perspective, this often involves facing an ill-posed problem; e.g., information is lost via projection of the 3D world into a 2D image. Solution of an ill-posed problem requires additional information, usually provided as a model of the underlying process. It is important that the model be both computationally feasible as well as theoretically well-founded. In this thesis, a probabilistic, nonlinear supervised computational learning model is proposed: the Specialized Mappings Architecture (SMA). The SMA framework is demonstrated in a computer vision system that can estimate the articulated pose parameters of a human body or human hands, given images obtained via one or more uncalibrated cameras. The SMA consists of several specialized forward mapping functions that are estimated automatically from training data, and a possibly known feedback function. Each specialized function maps certain domains of the input space (e.g., image features) onto the output space (e.g., articulated body parameters). A probabilistic model for the architecture is first formalized. Solutions to key algorithmic problems are then derived: simultaneous learning of the specialized domains along with the mapping functions, as well as performing inference given inputs and a feedback function. The SMA employs a variant of the Expectation-Maximization algorithm and approximate inference. The approach allows the use of alternative conditional independence assumptions for learning and inference, which are derived from a forward model and a feedback model. Experimental validation of the proposed approach is conducted in the task of estimating articulated body pose from image silhouettes. Accuracy and stability of the SMA framework is tested using artificial data sets, as well as synthetic and real video sequences of human bodies and hands.

Estimating Human Body Pose from a Single Image via the Specialized Mappings Architecture

A non-linear supervised learning architecture, the Specialized Mapping Architecture (SMA) and its application to articulated body pose reconstruction from single monocular images is described. The architecture is formed by a number of specialized mapping functions, each of them with the purpose of mapping certain portions (connected or not) of the input space, and a feedback matching process. A probabilistic model for the architecture is described along with a mechanism for learning its parameters. The learning problem is approached using a maximum likelihood estimation framework; we present Expectation Maximization (EM) algorithms for two different instances of the likelihood probability. Performance is characterized by estimating human body postures from low level visual features, showing promising results.

3D Hand Pose Reconstruction Using Specialized Mappings

A system for recovering 3D hand pose from monocular color sequences is proposed. The system employs a non-linear supervised learning framework, the specialized mappings architecture (SMA), to map image features to likely 3D hand poses. The SMA's fundamental components are a set of specialized forward mapping functions, and a single feedback matching function. The forward functions are estimated directly from training data, which in our case are examples of hand joint configurations and their corresponding visual features. The joint angle data in the training set is obtained via a CyberGlove, a glove with 22 sensors that monitor the angular motions of the palm and fingers. In training, the visual features are generated using a computer graphics module that renders the hand from arbitrary viewpoints given the 22 joint angles. We test our system both on synthetic sequences and on sequences taken with a color camera. The system automatically detects and tracks both hands of the user, calculates the appropriate features, and estimates the 3D hand joint angles from those features. Results are encouraging given the complexity of the task.

Deanonymizing Users of the SafeWeb Anonymizing Service

The SafeWeb anonymizing system has been lauded by the press and loved by its users; self-described as "the most widely used online privacy service in the world," it served over 3,000,000 page views per day at its peak. SafeWeb was designed to defeat content blocking by firewalls and to defeat Web server attempts to identify users, all without degrading Web site behavior or requiring users to install specialized software. In this article we describe how these fundamentally incompatible requirements were realized in SafeWeb's architecture, resulting in spectacular failure modes under simple JavaScript attacks. These exploits allow adversaries to turn SafeWeb into a weapon against its users, inflicting more damage on them than would have been possible if they had never relied on SafeWeb technology. By bringing these problems to light, we hope to remind readers of the chasm that continues to separate popular and technical notions of security.

Recursive Estimation of Motion and Planar Structure

A specialized formulation of Azarbayejani and Pentland's framework for recursive recovery of motion, structure and focal length from feature correspondences tracked through an image sequence is presented. The specialized formulation addresses the case where all tracked points lie on a plane. This planarity constraint reduces the dimension of the original state vector, and consequently the number of feature points needed to estimate the state. Experiments with synthetic data and real imagery illustrate the system performance. The experiments confirm that the specialized formulation provides improved accuracy, stability to observation noise, and rate of convergence in estimation for the case where the tracked points lie on a plane.

Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions

A learning based framework is proposed for estimating human body pose from a single image. Given a differentiable function that maps from pose space to image feature space, the goal is to invert the process: estimate the pose given only image features. The inversion is an ill-posed problem as the inverse mapping is a one to many process. Hence multiple solutions exist, and it is desirable to restrict the solution space to a smaller subset of feasible solutions. For example, not all human body poses are feasible due to anthropometric constraints. Since the space of feasible solutions may not admit a closed form description, the proposed framework seeks to exploit machine learning techniques to learn an approximation that is smoothly parameterized over such a space. One such technique is Gaussian Process Latent Variable Modelling. Scaled conjugate gradient is then used find the best matching pose in the space of feasible solutions when given an input image. The formulation allows easy incorporation of various constraints, e.g. temporal consistency and anthropometric constraints. The performance of the proposed approach is evaluated in the task of upper-body pose estimation from silhouettes and compared with the Specialized Mapping Architecture. The estimation accuracy of the Specialized Mapping Architecture is at least one standard deviation worse than the proposed approach in the experiments with synthetic data. In experiments with real video of humans performing gestures, the proposed approach produces qualitatively better estimation results.

A Customizable Camera-based Human Computer Interaction System Allowing People With Disabilities Autonomous Hands Free Navigation of Multiple Computing Task

Many people suffer from conditions that lead to deterioration of motor control and makes access to the computer using traditional input devices difficult. In particular, they may loose control of hand movement to the extent that the standard mouse cannot be used as a pointing device. Most current alternatives use markers or specialized hardware to track and translate a user's movement to pointer movement. These approaches may be perceived as intrusive, for example, wearable devices. Camera-based assistive systems that use visual tracking of features on the user's body often require cumbersome manual adjustment. This paper introduces an enhanced computer vision based strategy where features, for example on a user's face, viewed through an inexpensive USB camera, are tracked and translated to pointer movement. The main contributions of this paper are (1) enhancing a video based interface with a mechanism for mapping feature movement to pointer movement, which allows users to navigate to all areas of the screen even with very limited physical movement, and (2) providing a customizable, hierarchical navigation framework for human computer interaction (HCI). This framework provides effective use of the vision-based interface system for accessing multiple applications in an autonomous setting. Experiments with several users show the effectiveness of the mapping strategy and its usage within the application framework as a practical tool for desktop users with disabilities.

AIRSTREAM: A Neural Network Model of Auditory Scene Analysis and Source Segregation

Multiple sound sources often contain harmonics that overlap and may be degraded by environmental noise. The auditory system is capable of teasing apart these sources into distinct mental objects, or streams. Such an "auditory scene analysis" enables the brain to solve the cocktail party problem. A neural network model of auditory scene analysis, called the AIRSTREAM model, is presented to propose how the brain accomplishes this feat. The model clarifies how the frequency components that correspond to a give acoustic source may be coherently grouped together into distinct streams based on pitch and spatial cues. The model also clarifies how multiple streams may be distinguishes and seperated by the brain. Streams are formed as spectral-pitch resonances that emerge through feedback interactions between frequency-specific spectral representaion of a sound source and its pitch. First, the model transforms a sound into a spatial pattern of frequency-specific activation across a spectral stream layer. The sound has multiple parallel representations at this layer. A sound's spectral representation activates a bottom-up filter that is sensitive to harmonics of the sound's pitch. The filter activates a pitch category which, in turn, activate a top-down expectation that allows one voice or instrument to be tracked through a noisy multiple source environment. Spectral components are suppressed if they do not match harmonics of the top-down expectation that is read-out by the selected pitch, thereby allowing another stream to capture these components, as in the "old-plus-new-heuristic" of Bregman. Multiple simultaneously occuring spectral-pitch resonances can hereby emerge. These resonance and matching mechanisms are specialized versions of Adaptive Resonance Theory, or ART, which clarifies how pitch representations can self-organize durin learning of harmonic bottom-up filters and top-down expectations. The model also clarifies how spatial location cues can help to disambiguate two sources with similar spectral cures. Data are simulated from psychophysical grouping experiments, such as how a tone sweeping upwards in frequency creates a bounce percept by grouping with a downward sweeping tone due to proximity in frequency, even if noise replaces the tones at their interection point. Illusory auditory percepts are also simulated, such as the auditory continuity illusion of a tone continuing through a noise burst even if the tone is not present during the noise, and the scale illusion of Deutsch whereby downward and upward scales presented alternately to the two ears are regrouped based on frequency proximity, leading to a bounce percept. Since related sorts of resonances have been used to quantitatively simulate psychophysical data about speech perception, the model strengthens the hypothesis the ART-like mechanisms are used at multiple levels of the auditory system. Proposals for developing the model to explain more complex streaming data are also provided.

Vector Associative Maps: Unsupervised Real-time Error-based Learning and Control of Movement Trajectories

This article describes neural network models for adaptive control of arm movement trajectories during visually guided reaching and, more generally, a framework for unsupervised real-time error-based learning. The models clarify how a child, or untrained robot, can learn to reach for objects that it sees. Piaget has provided basic insights with his concept of a circular reaction: As an infant makes internally generated movements of its hand, the eyes automatically follow this motion. A transformation is learned between the visual representation of hand position and the motor representation of hand position. Learning of this transformation eventually enables the child to accurately reach for visually detected targets. Grossberg and Kuperstein have shown how the eye movement system can use visual error signals to correct movement parameters via cerebellar learning. Here it is shown how endogenously generated arm movements lead to adaptive tuning of arm control parameters. These movements also activate the target position representations that are used to learn the visuo-motor transformation that controls visually guided reaching. The AVITE model presented here is an adaptive neural circuit based on the Vector Integration to Endpoint (VITE) model for arm and speech trajectory generation of Bullock and Grossberg. In the VITE model, a Target Position Command (TPC) represents the location of the desired target. The Present Position Command (PPC) encodes the present hand-arm configuration. The Difference Vector (DV) population continuously.computes the difference between the PPC and the TPC. A speed-controlling GO signal multiplies DV output. The PPC integrates the (DV)·(GO) product and generates an outflow command to the arm. Integration at the PPC continues at a rate dependent on GO signal size until the DV reaches zero, at which time the PPC equals the TPC. The AVITE model explains how self-consistent TPC and PPC coordinates are autonomously generated and learned. Learning of AVITE parameters is regulated by activation of a self-regulating Endogenous Random Generator (ERG) of training vectors. Each vector is integrated at the PPC, giving rise to a movement command. The generation of each vector induces a complementary postural phase during which ERG output stops and learning occurs. Then a new vector is generated and the cycle is repeated. This cyclic, biphasic behavior is controlled by a specialized gated dipole circuit. ERG output autonomously stops in such a way that, across trials, a broad sample of workspace target positions is generated. When the ERG shuts off, a modulator gate opens, copying the PPC into the TPC. Learning of a transformation from TPC to PPC occurs using the DV as an error signal that is zeroed due to learning. This learning scheme is called a Vector Associative Map, or VAM. The VAM model is a general-purpose device for autonomous real-time error-based learning and performance of associative maps. The DV stage serves the dual function of reading out new TPCs during performance and reading in new adaptive weights during learning, without a disruption of real-time operation. YAMs thus provide an on-line unsupervised alternative to the off-line properties of supervised error-correction learning algorithms. YAMs and VAM cascades for learning motor-to-motor and spatial-to-motor maps are described. YAM models and Adaptive Resonance Theory (ART) models exhibit complementary matching, learning, and performance properties that together provide a foundation for designing a total sensory-cognitive and cognitive-motor autonomous system.

Equilibria and Dynamics of a Neural Network Model for Opponent Muscle Control

One of the advantages of biological skeleto-motor systems is the opponent muscle design, which in principle makes it possible to achieve facile independent control of joint angle and joint stiffness. Prior analysis of equilibrium states of a biologically-based neural network for opponent muscle control, the FLETE model, revealed that such independent control requires specialized interneuronal circuitry to efficiently coordinate the opponent force generators. In this chapter, we refine the FLETE circuit variables specification and update the equilibrium analysis. We also incorporate additional neuronal circuitry that ensures efficient opponent force generation and velocity regulation during movement.

Normal and Amnesis Learning, Recognition, and Memory by a Neural Model of Cortico-Hippocampal Interactions

The processes by which humans and other primates learn to recognize objects have been the subject of many models. Processes such as learning, categorization, attention, memory search, expectation, and novelty detection work together at different stages to realize object recognition. In this article, Gail Carpenter and Stephen Grossberg describe one such model class (Adaptive Resonance Theory, ART) and discuss how its structure and function might relate to known neurological learning and memory processes, such as how inferotemporal cortex can recognize both specialized and abstract information, and how medial temporal amnesia may be caused by lesions in the hippocampal formation. The model also suggests how hippocampal and inferotemporal processing may be linked during recognition learning.