Automatic 2D Hand Tracking in Video Sequences

In gesture and sign language video sequences, hand motion tends to be rapid, and hands frequently appear in front of each other or in front of the face. Thus, hand location is often ambiguous, and naive color-based hand tracking is insufficient. To improve tracking accuracy, some methods employ a prediction-update framework, but such methods require careful initialization of model parameters, and tend to drift and lose track in extended sequences. In this paper, a temporal filtering framework for hand tracking is proposed that can initialize and reset itself without human intervention. In each frame, simple features like color and motion residue are exploited to identify multiple candidate hand locations. The temporal filter then uses the Viterbi algorithm to select among the candidates from frame to frame. The resulting tracking system can automatically identify video trajectories of unambiguous hand motion, and detect frames where tracking becomes ambiguous because of occlusions or overlaps. Experiments on video sequences of several hundred frames in duration demonstrate the system's ability to track hands robustly, to detect and handle tracking ambiguities, and to extract the trajectories of unambiguous hand motion.

Handsignals Recognition From Video Using 3D Motion Capture Data

Hand signals are commonly used in applications such as giving instructions to a pilot for airplane take off or direction of a crane operator by a foreman on the ground. A new algorithm for recognizing hand signals from a single camera is proposed. Typically, tracked 2D feature positions of hand signals are matched to 2D training images. In contrast, our approach matches the 2D feature positions to an archive of 3D motion capture sequences. The method avoids explicit reconstruction of the 3D articulated motion from 2D image features. Instead, the matching between the 2D and 3D sequence is done by backprojecting the 3D motion capture data onto 2D. Experiments demonstrate the effectiveness of the approach in an example application: recognizing six classes of basketball referee hand signals in video.

Modal Matching for Correspondence and Recognition

Modal matching is a new method for establishing correspondences and computing canonical descriptions. The method is based on the idea of describing objects in terms of generalized symmetries, as defined by each object's eigenmodes. The resulting modal description is used for object recognition and categorization, where shape similarities are expressed as the amounts of modal deformation energy needed to align the two objects. In general, modes provide a global-to-local ordering of shape deformation and thus allow for selecting which types of deformations are used in object alignment and comparison. In contrast to previous techniques, which required correspondence to be computed with an initial or prototype shape, modal matching utilizes a new type of finite element formulation that allows for an object's eigenmodes to be computed directly from available image information. This improved formulation provides greater generality and accuracy, and is applicable to data of any dimensionality. Correspondence results with 2-D contour and point feature data are shown, and recognition experiments with 2-D images of hand tools and airplanes are described.

Automatic Detection of Relevant Head Gestures in American Sign Language Communication

An automated system for detection of head movements is described. The goal is to label relevant head gestures in video of American Sign Language (ASL) communication. In the system, a 3D head tracker recovers head rotation and translation parameters from monocular video. Relevant head gestures are then detected by analyzing the length and frequency of the motion signal's peaks and valleys. Each parameter is analyzed independently, due to the fact that a number of relevant head movements in ASL are associated with major changes around one rotational axis. No explicit training of the system is necessary. Currently, the system can detect "head shakes." In experimental evaluation, classification performance is compared against ground-truth labels obtained from ASL linguists. Initial results are promising, as the system matches the linguists' labels in a significant number of cases.

Indexing Methods for Efficient Multiclass Recognition

Many real world image analysis problems, such as face recognition and hand pose estimation, involve recognizing a large number of classes of objects or shapes. Large margin methods, such as AdaBoost and Support Vector Machines (SVMs), often provide competitive accuracy rates, but at the cost of evaluating a large number of binary classifiers, thus making it difficult to apply such methods when thousands or millions of classes need to be recognized. This thesis proposes a filter-and-refine framework, whereby, given a test pattern, a small number of candidate classes can be identified efficiently at the filter step, and computationally expensive large margin classifiers are used to evaluate these candidates at the refine step. Two different filtering methods are proposed, ClassMap and OVA-VS (One-vs.-All classification using Vector Search). ClassMap is an embedding-based method, works for both boosted classifiers and SVMs, and tends to map the patterns and their associated classes close to each other in a vector space. OVA-VS maps OVA classifiers and test patterns to vectors based on the weights and outputs of weak classifiers of the boosting scheme. At runtime, finding the strongest-responding OVA classifier becomes a classical vector search problem, where well-known methods can be used to gain efficiency. In our experiments, the proposed methods achieve significant speed-ups, in some cases up to two orders of magnitude, compared to exhaustive evaluation of all OVA classifiers. This was achieved in hand pose recognition and face recognition systems where the number of classes ranges from 535 to 48,600.

Combining Textual and Visual Cues for Content-based Image Retrieval on the World Wide Web

Some WWW image engines allow the user to form a query in terms of text keywords. To build the image index, keywords are extracted heuristically from HTML documents containing each image, and/or from the image URL and file headers. Unfortunately, text-based image engines have merely retro-fitted standard SQL database query methods, and it is difficult to include images cues within such a framework. On the other hand, visual statistics (e.g., color histograms) are often insufficient for helping users find desired images in a vast WWW index. By truly unifying textual and visual statistics, one would expect to get better results than either used separately. In this paper, we propose an approach that allows the combination of visual statistics with textual statistics in the vector space representation commonly used in query by image content systems. Text statistics are captured in vector form using latent semantic indexing (LSI). The LSI index for an HTML document is then associated with each of the images contained therein. Visual statistics (e.g., color, orientedness) are also computed for each image. The LSI and visual statistic vectors are then combined into a single index vector that can be used for content-based search of the resulting image database. By using an integrated approach, we are able to take advantage of possible statistical couplings between the topic of the document (latent semantic content) and the contents of images (visual statistics). This allows improved performance in conducting content-based search. This approach has been implemented in a WWW image search engine prototype.

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.

Cuckoo: a Language for Implementing Memory- and Thread-safe System Services

This paper is centered around the design of a thread- and memory-safe language, primarily for the compilation of application-specific services for extensible operating systems. We describe various issues that have influenced the design of our language, called Cuckoo, that guarantees safety of programs with potentially asynchronous flows of control. Comparisons are drawn between Cuckoo and related software safety techniques, including Cyclone and software-based fault isolation (SFI), and performance results suggest our prototype compiler is capable of generating safe code that executes with low runtime overheads, even without potential code optimizations. Compared to Cyclone, Cuckoo is able to safely guard accesses to memory when programs are multithreaded. Similarly, Cuckoo is capable of enforcing memory safety in situations that are potentially troublesome for techniques such as SFI.

Learning Embeddings for Indexing, Retrieval, and Classification, with Applications to Object and Shape Recognition in Image Databases

Nearest neighbor retrieval is the task of identifying, given a database of objects and a query object, the objects in the database that are the most similar to the query. Retrieving nearest neighbors is a necessary component of many practical applications, in fields as diverse as computer vision, pattern recognition, multimedia databases, bioinformatics, and computer networks. At the same time, finding nearest neighbors accurately and efficiently can be challenging, especially when the database contains a large number of objects, and when the underlying distance measure is computationally expensive. This thesis proposes new methods for improving the efficiency and accuracy of nearest neighbor retrieval and classification in spaces with computationally expensive distance measures. The proposed methods are domain-independent, and can be applied in arbitrary spaces, including non-Euclidean and non-metric spaces. In this thesis particular emphasis is given to computer vision applications related to object and shape recognition, where expensive non-Euclidean distance measures are often needed to achieve high accuracy. The first contribution of this thesis is the BoostMap algorithm for embedding arbitrary spaces into a vector space with a computationally efficient distance measure. Using this approach, an approximate set of nearest neighbors can be retrieved efficiently - often orders of magnitude faster than retrieval using the exact distance measure in the original space. The BoostMap algorithm has two key distinguishing features with respect to existing embedding methods. First, embedding construction explicitly maximizes the amount of nearest neighbor information preserved by the embedding. Second, embedding construction is treated as a machine learning problem, in contrast to existing methods that are based on geometric considerations. The second contribution is a method for constructing query-sensitive distance measures for the purposes of nearest neighbor retrieval and classification. In high-dimensional spaces, query-sensitive distance measures allow for automatic selection of the dimensions that are the most informative for each specific query object. It is shown theoretically and experimentally that query-sensitivity increases the modeling power of embeddings, allowing embeddings to capture a larger amount of the nearest neighbor structure of the original space. The third contribution is a method for speeding up nearest neighbor classification by combining multiple embedding-based nearest neighbor classifiers in a cascade. In a cascade, computationally efficient classifiers are used to quickly classify easy cases, and classifiers that are more computationally expensive and also more accurate are only applied to objects that are harder to classify. An interesting property of the proposed cascade method is that, under certain conditions, classification time actually decreases as the size of the database increases, a behavior that is in stark contrast to the behavior of typical nearest neighbor classification systems. The proposed methods are evaluated experimentally in several different applications: hand shape recognition, off-line character recognition, online character recognition, and efficient retrieval of time series. In all datasets, the proposed methods lead to significant improvements in accuracy and efficiency compared to existing state-of-the-art methods. In some datasets, the general-purpose methods introduced in this thesis even outperform domain-specific methods that have been custom-designed for such datasets.

Spatiotemporal Gesture Segmentation

Spotting patterns of interest in an input signal is a very useful task in many different fields including medicine, bioinformatics, economics, speech recognition and computer vision. Example instances of this problem include spotting an object of interest in an image (e.g., a tumor), a pattern of interest in a time-varying signal (e.g., audio analysis), or an object of interest moving in a specific way (e.g., a human's body gesture). Traditional spotting methods, which are based on Dynamic Time Warping or hidden Markov models, use some variant of dynamic programming to register the pattern and the input while accounting for temporal variation between them. At the same time, those methods often suffer from several shortcomings: they may give meaningless solutions when input observations are unreliable or ambiguous, they require a high complexity search across the whole input signal, and they may give incorrect solutions if some patterns appear as smaller parts within other patterns. In this thesis, we develop a framework that addresses these three problems, and evaluate the framework's performance in spotting and recognizing hand gestures in video. The first contribution is a spatiotemporal matching algorithm that extends the dynamic programming formulation to accommodate multiple candidate hand detections in every video frame. The algorithm finds the best alignment between the gesture model and the input, and simultaneously locates the best candidate hand detection in every frame. This allows for a gesture to be recognized even when the hand location is highly ambiguous. The second contribution is a pruning method that uses model-specific classifiers to reject dynamic programming hypotheses with a poor match between the input and model. Pruning improves the efficiency of the spatiotemporal matching algorithm, and in some cases may improve the recognition accuracy. The pruning classifiers are learned from training data, and cross-validation is used to reduce the chance of overpruning. The third contribution is a subgesture reasoning process that models the fact that some gesture models can falsely match parts of other, longer gestures. By integrating subgesture reasoning the spotting algorithm can avoid the premature detection of a subgesture when the longer gesture is actually being performed. Subgesture relations between pairs of gestures are automatically learned from training data. The performance of the approach is evaluated on two challenging video datasets: hand-signed digits gestured by users wearing short sleeved shirts, in front of a cluttered background, and American Sign Language (ASL) utterances gestured by ASL native signers. The experiments demonstrate that the proposed method is more accurate and efficient than competing approaches. The proposed approach can be generally applied to alignment or search problems with multiple input observations, that use dynamic programming to find a solution.

SOVEREIGN: A Self-Organizing, Vision, Expectation, Recognition, Emotion, Intelligent, Goal-Oriented Navigation System

Both animals and mobile robots, or animats, need adaptive control systems to guide their movements through a novel environment. Such control systems need reactive mechanisms for exploration, and learned plans to efficiently reach goal objects once the environment is familiar. How reactive and planned behaviors interact together in real time, and arc released at the appropriate times, during autonomous navigation remains a major unsolved problern. This work presents an end-to-end model to address this problem, named SOVEREIGN: A Self-Organizing, Vision, Expectation, Recognition, Emotion, Intelligent, Goal-oriented Navigation system. The model comprises several interacting subsystems, governed by systems of nonlinear differential equations. As the animat explores the environment, a vision module processes visual inputs using networks that arc sensitive to visual form and motion. Targets processed within the visual form system arc categorized by real-time incremental learning. Simultaneously, visual target position is computed with respect to the animat's body. Estimates of target position activate a motor system to initiate approach movements toward the target. Motion cues from animat locomotion can elicit orienting head or camera movements to bring a never target into view. Approach and orienting movements arc alternately performed during animat navigation. Cumulative estimates of each movement, based on both visual and proprioceptive cues, arc stored within a motor working memory. Sensory cues are stored in a parallel sensory working memory. These working memories trigger learning of sensory and motor sequence chunks, which together control planned movements. Effective chunk combinations arc selectively enhanced via reinforcement learning when the animat is rewarded. The planning chunks effect a gradual transition from reactive to planned behavior. The model can read-out different motor sequences under different motivational states and learns more efficient paths to rewarded goals as exploration proceeds. Several volitional signals automatically gate the interactions between model subsystems at appropriate times. A 3-D visual simulation environment reproduces the animat's sensory experiences as it moves through a simplified spatial environment. The SOVEREIGN model exhibits robust goal-oriented learning of sequential motor behaviors. Its biomimctic structure explicates a number of brain processes which are involved in spatial navigation.

An Active Pattern Recognition Architecture for Mobile Robots

An active, attentionally-modulated recognition architecture is proposed for object recognition and scene analysis. The proposed architecture forms part of navigation and trajectory planning modules for mobile robots. Key characteristics of the system include movement planning and execution based on environmental factors and internal goal definitions. Real-time implementation of the system is based on space-variant representation of the visual field, as well as an optimal visual processing scheme utilizing separate and parallel channels for the extraction of boundaries and stimulus qualities. A spatial and temporal grouping module (VWM) allows for scene scanning, multi-object segmentation, and featural/object priming. VWM is used to modulate a tn~ectory formation module capable of redirecting the focus of spatial attention. Finally, an object recognition module based on adaptive resonance theory is interfaced through VWM to the visual processing module. The system is capable of using information from different modalities to disambiguate sensory input.

A Neural Theory of Visual Search: Recursive Attention to Segmentations and Surfaces

A neural theory is proposed in which visual search is accomplished by perceptual grouping and segregation, which occurs simultaneous across the visual field, and object recognition, which is restricted to a selected region of the field. The theory offers an alternative hypothesis to recently developed variations on Feature Integration Theory (Treisman, and Sato, 1991) and Guided Search Model (Wolfe, Cave, and Franzel, 1989). A neural architecture and search algorithm is specified that quantitatively explains a wide range of psychophysical search data (Wolfe, Cave, and Franzel, 1989; Cohen, and lvry, 1991; Mordkoff, Yantis, and Egeth, 1990; Treisman, and Sato, 1991).

Dynamic Binding of Visual Contours Without Temporal Coding

Recognition of objects in complex visual scenes is greatly simplified by the ability to segment features belonging to different objects while grouping features belonging to the same object. This feature-binding process can be driven by the local relations between visual contours. The standard method for implementing this process with neural networks uses a temporal code to bind features together. I propose a spatial coding alternative for the dynamic binding of visual contours, and demonstrate the spatial coding method for segmenting an image consisting of three overlapping objects.

A Neural Theory of Attentive Visual Search: Interactions of Boundary, Surface, Spatial, and Object Representations

Visual search data are given a unified quantitative explanation by a model of how spatial maps in the parietal cortex and object recognition categories in the inferotemporal cortex deploy attentional resources as they reciprocally interact with visual representations in the prestriate cortex. The model visual representations arc organized into multiple boundary and surface representations. Visual search in the model is initiated by organizing multiple items that lie within a given boundary or surface representation into a candidate search grouping. These items arc compared with object recognition categories to test for matches or mismatches. Mismatches can trigger deeper searches and recursive selection of new groupings until a target object io identified. This search model is algorithmically specified to quantitatively simulate search data using a single set of parameters, as well as to qualitatively explain a still larger data base, including data of Aks and Enns (1992), Bravo and Blake (1990), Chellazzi, Miller, Duncan, and Desimone (1993), Egeth, Viri, and Garbart (1984), Cohen and Ivry (1991), Enno and Rensink (1990), He and Nakayarna (1992), Humphreys, Quinlan, and Riddoch (1989), Mordkoff, Yantis, and Egeth (1990), Nakayama and Silverman (1986), Treisman and Gelade (1980), Treisman and Sato (1990), Wolfe, Cave, and Franzel (1989), and Wolfe and Friedman-Hill (1992). The model hereby provides an alternative to recent variations on the Feature Integration and Guided Search models, and grounds the analysis of visual search in neural models of preattentive vision, attentive object learning and categorization, and attentive spatial localization and orientation.