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.

On the Relationship Between File Sizes, Transport Protocols, and Self-Similar Network Traffic

Recent measurements of local-area and wide-area traffic have shown that network traffic exhibits variability at a wide range of scales self-similarity. In this paper, we examine a mechanism that gives rise to self-similar network traffic and present some of its performance implications. The mechanism we study is the transfer of files or messages whose size is drawn from a heavy-tailed distribution. We examine its effects through detailed transport-level simulations of multiple TCP streams in an internetwork. First, we show that in a "realistic" client/server network environment i.e., one with bounded resources and coupling among traffic sources competing for resources the degree to which file sizes are heavy-tailed can directly determine the degree of traffic self-similarity at the link level. We show that this causal relationship is not significantly affected by changes in network resources (bottleneck bandwidth and buffer capacity), network topology, the influence of cross-traffic, or the distribution of interarrival times. Second, we show that properties of the transport layer play an important role in preserving and modulating this relationship. In particular, the reliable transmission and flow control mechanisms of TCP (Reno, Tahoe, or Vegas) serve to maintain the long-range dependency structure induced by heavy-tailed file size distributions. In contrast, if a non-flow-controlled and unreliable (UDP-based) transport protocol is used, the resulting traffic shows little self-similar characteristics: although still bursty at short time scales, it has little long-range dependence. If flow-controlled, unreliable transport is employed, the degree of traffic self-similarity is positively correlated with the degree of throttling at the source. Third, in exploring the relationship between file sizes, transport protocols, and self-similarity, we are also able to show some of the performance implications of self-similarity. We present data on the relationship between traffic self-similarity and network performance as captured by performance measures including packet loss rate, retransmission rate, and queueing delay. Increased self-similarity, as expected, results in degradation of performance. Queueing delay, in particular, exhibits a drastic increase with increasing self-similarity. Throughput-related measures such as packet loss and retransmission rate, however, increase only gradually with increasing traffic self-similarity as long as reliable, flow-controlled transport protocol is used.

Safe Composition of Web Communication Protocols for Extensible Edge Services

As new multi-party edge services are deployed on the Internet, application-layer protocols with complex communication models and event dependencies are increasingly being specified and adopted. To ensure that such protocols (and compositions thereof with existing protocols) do not result in undesirable behaviors (e.g., livelocks) there needs to be a methodology for the automated checking of the "safety" of these protocols. In this paper, we present ingredients of such a methodology. Specifically, we show how SPIN, a tool from the formal systems verification community, can be used to quickly identify problematic behaviors of application-layer protocols with non-trivial communication models—such as HTTP with the addition of the "100 Continue" mechanism. As a case study, we examine several versions of the specification for the Continue mechanism; our experiments mechanically uncovered multi-version interoperability problems, including some which motivated revisions of HTTP/1.1 and some which persist even with the current version of the protocol. One such problem resembles a classic degradation-of-service attack, but can arise between well-meaning peers. We also discuss how the methods we employ can be used to make explicit the requirements for hardening a protocol's implementation against potentially malicious peers, and for verifying an implementation's interoperability with the full range of allowable peer behaviors.

Declarative Transport: No More Transport Protocols to Design, Only Policies to Specify

Transport protocols are an integral part of the inter-process communication (IPC) service used by application processes to communicate over the network infrastructure. With almost 30 years of research on transport, one would have hoped that we have a good handle on the problem. Unfortunately, that is not true. As the Internet continues to grow, new network technologies and new applications continue to emerge putting transport protocols in a never-ending flux as they are continuously adapted for these new environments. In this work, we propose a clean-slate transport architecture that renders all possible transport solutions as simply combinations of policies instantiated on a single common structure. We identify a minimal set of mechanisms that once instantiated with the appropriate policies allows any transport solution to be realized. Given our proposed architecture, we contend that there are no more transport protocols to design—only policies to specify. We implement our transport architecture in a declarative language, Network Datalog (NDlog), making the specification of different transport policies easy, compact, reusable, dynamically configurable and potentially verifiable. In NDlog, transport state is represented as database relations, state is updated/queried using database operations, and transport policies are specified using declarative rules. We identify limitations with NDlog that could potentially threaten the correctness of our specification. We propose several language extensions to NDlog that would significantly improve the programmability of transport policies.

Preferential Field Coverage Through Detour-Based Mobility Coordination

Controlling the mobility pattern of mobile nodes (e.g., robots) to monitor a given field is a well-studied problem in sensor networks. In this setup, absolute control over the nodes’ mobility is assumed. Apart from the physical ones, no other constraints are imposed on planning mobility of these nodes. In this paper, we address a more general version of the problem. Specifically, we consider a setting in which mobility of each node is externally constrained by a schedule consisting of a list of locations that the node must visit at particular times. Typically, such schedules exhibit some level of slack, which could be leveraged to achieve a specific coverage distribution of a field. Such a distribution defines the relative importance of different field locations. We define the Constrained Mobility Coordination problem for Preferential Coverage (CMC-PC) as follows: given a field with a desired monitoring distribution, and a number of nodes n, each with its own schedule, we need to coordinate the mobility of the nodes in order to achieve the following two goals: 1) satisfy the schedules of all nodes, and 2) attain the required coverage of the given field. We show that the CMC-PC problem is NP-complete (by reduction to the Hamiltonian Cycle problem). Then we propose TFM, a distributed heuristic to achieve field coverage that is as close as possible to the required coverage distribution. We verify the premise of TFM using extensive simulations, as well as taxi logs from a major metropolitan area. We compare TFM to the random mobility strategy—the latter provides a lower bound on performance. Our results show that TFM is very successful in matching the required field coverage distribution, and that it provides, at least, two-fold query success ratio for queries that follow the target coverage distribution of the field.

Object Matching in Distributed Video Surveillance Systems by LDA-Based Appearance Descriptors

Establishing correspondences among object instances is still challenging in multi-camera surveillance systems, especially when the cameras’ fields of view are non-overlapping. Spatiotemporal constraints can help in solving the correspondence problem but still leave a wide margin of uncertainty. One way to reduce this uncertainty is to use appearance information about the moving objects in the site. In this paper we present the preliminary results of a new method that can capture salient appearance characteristics at each camera node in the network. A Latent Dirichlet Allocation (LDA) model is created and maintained at each node in the camera network. Each object is encoded in terms of the LDA bag-of-words model for appearance. The encoded appearance is then used to establish probable matching across cameras. Preliminary experiments are conducted on a dataset of 20 individuals and comparison against Madden’s I-MCHR is reported.

A Performance Evaluation of Hyper Text Transfer Protocols

Version 1.1 of the Hyper Text Transfer Protocol (HTTP) was principally developed as a means for reducing both document transfer latency and network traffic. The rationale for the performance enhancements in HTTP/1.1 is based on the assumption that the network is the bottleneck in Web transactions. In practice, however, the Web server can be the primary source of document transfer latency. In this paper, we characterize and compare the performance of HTTP/1.0 and HTTP/1.1 in terms of throughput at the server and transfer latency at the client. Our approach is based on considering a broader set of bottlenecks in an HTTP transfer; we examine how bottlenecks in the network, CPU, and in the disk system affect the relative performance of HTTP/1.0 versus HTTP/1.1. We show that the network demands under HTTP/1.1 are somewhat lower than HTTP/1.0, and we quantify those differences in terms of packets transferred, server congestion window size and data bytes per packet. We show that when the CPU is the bottleneck, there is relatively little difference in performance between HTTP/1.0 and HTTP/1.1. Surprisingly, we show that when the disk system is the bottleneck, performance using HTTP/1.1 can be much worse than with HTTP/1.0. Based on these observations, we suggest a connection management policy for HTTP/1.1 that can improve throughput, decrease latency, and keep network traffic low when the disk system is the bottleneck.

An Invariant Representation for Matching Trajectories across Uncalibrated Video Streams

We introduce a view-point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on a surface that can be locally approximated with a plane. Raw trajectory data is first locally approximated with a cubic spline via least squares fitting. For each sampled point of the obtained curve, a projective invariant feature is computed using a small number of points in its neighborhood. The resulting sequence of invariant features computed along the entire trajectory forms the view invariant descriptor of the trajectory itself. Time parametrization has been exploited to compute cross ratios without ambiguity due to point ordering. Similarity between descriptors of different trajectories is measured with a distance that takes into account the statistical properties of the cross ratio, and its symmetry with respect to the point at infinity. In experiments, an overall correct classification rate of about 95% has been obtained on a dataset of 58 trajectories of players in soccer video, and an overall correct classification rate of about 80% has been obtained on matching partial segments of trajectories collected from two overlapping views of outdoor scenes with moving people and cars.

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.

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.

Cortical Learning of Recognition Categories: A Resolution of the Exemplar Vs. Prototype Debate

Do humans and animals learn exemplars or prototypes when they categorize objects and events in the world? How are different degrees of abstraction realized through learning by neurons in inferotemporal and prefrontal cortex? How do top-down expectations influence the course of learning? Thirty related human cognitive experiments (the 5-4 category structure) have been used to test competing views in the prototype-exemplar debate. In these experiments, during the test phase, subjects unlearn in a characteristic way items that they had learned to categorize perfectly in the training phase. Many cognitive models do not describe how an individual learns or forgets such categories through time. Adaptive Resonance Theory (ART) neural models provide such a description, and also clarify both psychological and neurobiological data. Matching of bottom-up signals with learned top-down expectations plays a key role in ART model learning. Here, an ART model is used to learn incrementally in response to 5-4 category structure stimuli. Simulation results agree with experimental data, achieving perfect categorization in training and a good match to the pattern of errors exhibited by human subjects in the testing phase. These results show how the model learns both prototypes and certain exemplars in the training phase. ART prototypes are, however, unlike the ones posited in the traditional prototype-exemplar debate. Rather, they are critical patterns of features to which a subject learns to pay attention based on past predictive success and the order in which exemplars are experienced. Perturbations of old memories by newly arriving test items generate a performance curve that closely matches the performance pattern of human subjects. The model also clarifies exemplar-based accounts of data concerning amnesia.

Integrating Symbolic and Neural Processing in a Self-Organizing Architechture for Pattern Recognition and Prediction

British Petroleum (89A-1204); Defense Advanced Research Projects Agency (N00014-92-J-4015); National Science Foundation (IRI-90-00530); Office of Naval Research (N00014-91-J-4100); Air Force Office of Scientific Research (F49620-92-J-0225)

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.

Learning Temporal Contexts and Priming-Preparation Modes for Pattern Recognition

The system presented here is based on neurophysiological and electrophysiological data. It computes three types of increasingly integrated temporal and probability contexts, in a bottom-up mode. To each of these contexts corresponds an increasingly specific top-down priming effect on lower processing stages, mostly pattern recognition and discrimination. Contextual learning of time intervals, events' temporal order or sequential dependencies and events' prior probability results from the delivery of large stimuli sequences. This learning gives rise to emergent properties which closely match the experimental data.

A Neural Pattern Generator that Exhibits Arousal-Dependant Human Gait Transitions

A neural pattern generator based upon a non-linear cooperative-competitive feedback neural network is presented. It can generate the two standard human gaits: the walk and the run. A scalar arousal or GO signal causes a bifurcation from one gait to the next. Although these two gaits are qualitatively different, they both have the same limb order and may exhibit oscillation frequencies that overlap. The model simulates the walk and the run via qualitatively different waveform shapes. The fraction of cycle that activity is above threshold distinguishes the two gaits, much as the duty cycles of the feet are longer in the walk than in the run.