Hierarchical directory-based shared memory architecture

We describe the design of a directory-based shared memory architecture on a hierarchical network of hypercubes. The distributed directory scheme comprises two separate hierarchical networks for handling cache requests and transfers. Further, the scheme assumes a single address space and each processing element views the entire network as contiguous memory space. The size of individual directories stored at each node of the network remains constant throughout the network. Although the size of the directory increases with the network size, the architecture is scalable. The results of the analytical studies demonstrate superior performance characteristics of our scheme compared with those of other schemes.

High accuracy context recovery using clustering mechanisms

This paper examines the recovery of user context in indoor environmnents with existing wireless infrastructures to enable assistive systems. We present a novel approach to the extraction of user context, casting the problem of context recovery as an unsupervised, clustering problem. A well known density-based clustering technique, DBSCAN, is adapted to recover user context that includes user motion state, and significant places the user visits from WiFi observations consisting of access point id and signal strength. Furthermore, user rhythms or sequences of places the user visits periodically are derived from the above low level contexts by employing state-of-the-art probabilistic clustering technique, the Latent Dirichiet Allocation (LDA), to enable a variety of application services. Experimental results with real data are presented to validate the proposed unsupervised learning approach and demonstrate its applicability.

Pedestrian detection for mobile bus surveillance

In this paper, we present a system for pedestrian detection involving scenes captured by mobile bus surveillance cameras in busy city streets. Our approach integrates scene localization, foreground and background separation, and pedestrian detection modules into a unified detection framework. The scene localization module performs a two stage clustering of the video data. In the first stage, SIFT Homography is applied to cluster frames in terms of their structural similarities and second stage further clusters these aligned frames in terms of lighting. This produces clusters of images which are differential in viewpoint and lighting. A kernel density estimation (KDE) method for colour and gradient foreground-background separation are then used to construct background model for each image cluster which is subsequently used to detect all foreground pixels. Finally, using a hierarchical template matching approach, pedestrians can be identified. We have tested our system on a set of real bus video datasets and the experimental results verify that our system works well in practice.

Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model

Directly modeling the inherent hierarchy and shared structures of human behaviors, we present an application of the hierarchical hidden Markov model (HHMM) for the problem of activity recognition. We argue that to robustly model and recognize complex human activities, it is crucial to exploit both the natural hierarchical decomposition and shared semantics embedded in the movement trajectories. To this end, we propose the use of the HHMM, a rich stochastic model that has been recently extended to handle shared structures, for representing and recognizing a set of complex indoor activities. Furthermore, in the need of real-time recognition, we propose a Rao-Blackwellised particle filter (RBPF) that efficiently computes the filtering distribution at a constant time complexity for each new observation arrival. The main contributions of this paper lie in the application of the shared-structure HHMM, the estimation of the model's parameters at all levels simultaneously, and a construction of an RBPF approximate inference scheme. The experimental results in a real-world environment have confirmed our belief that directly modeling shared structures not only reduces computational cost, but also improves recognition accuracy when compared with the tree HHMM and the flat HMM.

Automatically learning structural units in educational videos with the hierarchical hidden Markov models

In this paper we present a coherent approach using the hierarchical HMM with shared structures to extract the structural units that form the building blocks of an education/training video. Rather than using hand-crafted approaches to define the structural units, we use the data from nine training videos to learn the parameters of the HHMM, and thus naturally extract the hierarchy. We then study this hierarchy and examine the nature of the structure at different levels of abstraction. Since the observable is continuous, we also show how to extend the parameter learning in the HHMM to deal with continuous observations.

Hierarchical hidden Markov models with general state hierarchy

The hierarchical hidden Markov model (HHMM) is an extension of the hidden Markov model to include a hierarchy of the hidden states. This form of hierarchical modeling has been found useful in applications such as handwritten character recognition, behavior recognition, video indexing, and text retrieval. Nevertheless, the state hierarchy in the original HHMM is restricted to a tree structure. This prohibits two different states from having the same child, and thus does not allow for sharing of common substructures in the model. In this paper, we present a general HHMM in which the state hierarchy can be a lattice allowing arbitrary sharing of substructures. Furthermore, we provide a method for numerical scaling to avoid underflow, an important issue in dealing with long observation sequences. We demonstrate the working of our method in a simulated environment where a hierarchical behavioral model is automatically learned and later used for recognition.

Hierarchical topical segmentation in instructional films based on cinematic expressive functions

In this paper, we propose a novel solution for segmenting an instructional video into hierarchical topical sections. Incorporating the knowledge of education-oriented film theory with our previous study of expressive functions namely the content density and the thematic functions, we develop an algorithm to effectively structuralize an instructional video into a two-tiered hierarchy of topical sections at the main and sub-topic levels. Our experimental results on a set of ten industrial instructional videos demonstrate the validity of the detection scheme.

Hierarchical monitoring of people's behaviors in complex environments using multiple cameras

We present a distributed, surveillance system that works in large and complex indoor environments. To track and recognize behaviors of people, we propose the use of the Abstract Hidden Markov Model (AHMM), which can be considered as an extension of the Hidden Markov Model (HMM), where the single Markov chain in the HMM is replaced by a hierarchy of Markov policies. In this policy hierarchy, each behavior can be represented as a policy at the corresponding level of abstraction. The noisy observations are handled in the same way as an HMM and an efficient Rao-Blackwellised particle filter method is used to compute the probabilities of the current policy at different levels of the hierarchy The novelty of the paper lies in the implementation of a scalable framework in the context of both the scale of behaviors and the size of the environment, making it ideal for distributed surveillance. The results of the system demonstrate the ability to answer queries about people's behaviors at different levels of details using multiple cameras in a large and complex indoor environment.

Hierarchical recognition of intentional human gestures for sports video annotation

We present a novel technique for the recognition of complex human gestures for video annotation using accelerometers and the hidden Markov model. Our extension to the standard hidden Markov model allows us to consider gestures at different levels of abstraction through a hierarchy of hidden states. Accelerometers in the form of wrist bands are attached to humans performing intentional gestures, such as umpires in sports. Video annotation is then performed by populating the video with time stamps indicating significant events, where a particular gesture occurs. The novelty of the technique lies in the development of a probabilistic hierarchical framework for complex gesture recognition and the use of accelerometers to extract gestures and significant events for video annotation.

Content structure discovery in educational videos using shared structures in the hierarchical hidden Markov models

In this paper, we present an application of the hierarchical HMM for structure discovery in educational videos. The HHMM has recently been extended to accommodate the concept of shared structure, ie: a state might multiply inherit from more than one parents. Utilising the expressiveness of this model, we concentrate on a specific class of video -educational videos - in which the hierarchy of semantic units is simpler and clearly defined in terms of topics and its subunits. We model the hierarchy of topical structures by an HHMM and demonstrate the usefulness of the model in detecting topic transitions.

Hierarchical representation for spatial knowledge

One of the fundamental issues in building autonomous agents is to be able to sense, represent and react to the world. Some of the earlier work [Mor83, Elf90, AyF89] has aimed towards a reconstructionist approach, where a number of sensors are used to obtain input that is used to construct a model of the world that mirrors the real world. Sensing and sensor fusion was thus an important aspect of such work. Such approaches have had limited success, and some of the main problems were the issues of uncertainty arising from sensor error and errors that accumulated in metric, quantitative models. Recent research has therefore looked at different ways of examining the problems. Instead of attempting to get the most accurate and correct model of the world, these approaches look at qualitative models to represent the world, which maintain relative and significant aspects of the environment rather than all aspects of the world. The relevant aspects of the world that are retained are determined by the task at hand which in turn determines how to sense. That is, task directed or purposive sensing is used to build a qualitative model of the world, which though inaccurate and incomplete is sufficient to solve the problem at hand. This paper examines the issues of building up a hierarchical knowledge representation of the environment with limited sensor input that can be actively acquired by an agent capable of interacting with the environment. Different tasks require different aspects of the environment to be abstracted out. For example, low level tasks such as navigation require aspects of the environment that are related to layout and obstacle placement. For the agent to be able to reposition itself in an environment, significant features of spatial situations and their relative placement need to be kept. For the agent to reason about objects in space, for example to determine the position of one object relative to another, the representation needs to retain information on relative locations of start and finish of the objects, that is endpoints of objects on a grid. For the agent to be able to do high level planning, the agent may need only the relative position of the starting point and destination, and not the low level details of endpoints, visual clues and so on. This indicates that a hierarchical approach would be suitable, such that each level in the hierarchy is at a different level of abstraction, and thus suitable for a different task. At the lowest level, the representation contains low level details of agent's motion and visual clues to allow the agent to navigate and reposition itself. At the next level of abstraction the aspects of the representation allow the agent to perform spatial reasoning, and finally the highest level of abstraction in the representation can be used by the agent for high level planning.

Hierarchical semi-markov conditional random fields for recursive sequential data

Inspired by the hierarchical hidden Markov models (HHMM), we present the hierarchical semi-Markov conditional random field (HSCRF), a generalisation of embedded undirected Markov chains to model complex hierarchical, nested Markov processes. It is parameterised in a discriminative framework and has polynomial time algorithms for learning and inference. Importantly, we develop efficient algorithms for learning and constrained inference in a partially-supervised setting, which is important issue in practice where labels can only be obtained sparsely. We demonstrate the HSCRF in two applications: (i) recognising human activities of daily living (ADLs) from indoor surveillance cameras, and (ii) noun-phrase chunking. We show that the HSCRF is capable of learning rich hierarchical models with reasonable accuracy in both fully and partially observed data cases.