Peter Barrie

A pervasive gesture-driven augmented reality prototype using wireless sensor body area networks

This paper describes the prototype implementation of a pervasive, wearable augmented reality (AR) system based on a full body-motion-capture system using low-power wireless sensors. The system uses body motion to visualize and interact with virtual objects populating AR settings. Body motion is used to implement a whole body gesture-driven interface to manipulate the virtual objects. Gestures are mapped to correspondent behaviors for virtual objects, such as controlling the playback and volume of virtual audio players or displaying a virtual objects metadata.

Urban exploration using audio scents

We describe the design and evaluation of an audio-based mixed reality navigation system that uses the concept of audio scents for the implicit guidance of tourists and visitors of urban areas, as an alternative to turn-by-turn guidance systems. A field trial of our prototype uncovers great potential for this type of implicit navigation and is received positively by our participants. We discuss the technical implementation of our prototype, detailed findings from quantitative and subjective evaluation data gathered during the field trial and highlight possible strands for further research and development.

Feature-Based Indoor Navigation Using Augmented Reality

We present a prototype for indoor navigation using Augmented Reality that uses interior features to determine the users location and provide navigation instructions. We test our prototype in a simulated physical shopping mall environment and find that AR-based navigation can provide usability advantages in indoor locations, particularly where targets are located on different floors. We conclude by recommending further work in presenting interior navigation instructions using AR.

Extended fast compressive tracking with weighted multi-frame template matching for fast motion tracking

State of the art tracking algorithm significantly extended.Multi-frame template matching greatly improves tracking accuracy.Tracking of fast moving targets and motion blur improved.Real-time operation in excess of 120 frames per secondAlgorithm performs strongly against state of the art. The work presented in this letter extends upon state of the art visual object tracking algorithms, the Real-time Compressive Tracker and the Fast Compressive Tracker, increasing the overall tracking accuracy at a minimal computational cost and reduction in frame rate. A template matching processing stage is incorporated in order to increase the robustness of the algorithm while maintaining a frame rate well within the requirements for real time operation. We utilise a weighted multi-frame similarity metric, template matching a bank of the top classifier outputs against the ground truth bounding box and a recently stored target bounding box to select the appropriate target location in the following frame. Unlike the original algorithm, the proposed method utilises more of the available data to make more informed tracking decisions than purely using the highest classifier output. Multiple similarity metrics have been employed in the template matching stage to compare their performance on a range of commonly used publicly available image sequences. The extended algorithm clearly demonstrated an increase in the overall performance while maintaining a high frame-rate.

me-Commerce: An Infrastructure for Personal Predictive Mobile Commerce

Given mobile phone penetration statistics and current mobile phone technical specifications, it is apparent that in developed countries, the majority of citizens carry not just mobile phones, but true mobile computing devices. These devices are still primarily used for telephony, although information access is slowly emerging as a popular service on these devices. Despite the availability of network connectivity and device characteristics that make Information Access possible, this is currently generally confined to accessing the WWW. While useful, this method is not the best way of providing information access to mobile devices. This paper discusses current research in the use of mobile services and proceeds by presenting a background on an infrastructure for a focused information access application for mobile commerce. Through this background, we discuss the need for embedding multi-dimensional context awareness into the design of applications that provide dedicated, targeted and personalised information access to users, and describe the dimensional vectors necessary for the acquisition of contextual information. Further to this, the paper highlights the challenges that must be overcome in obtaining contextual information on a mobile computing scenario, as required by the design we propose.

An implementation focused approach to teaching image processing and machine vision - from theory to beagleboard

The explosion of multimedia applications within embedded devices has ensured that Image Processing and Machine Vision has now become a mainstream subject within most Computer Science and Electronic Engineering curricula. Yet often there exists a disconnection between the rapid prototyping tools that are taught within the laboratory to demonstrate concepts and those that are used for actual deployment in a stand-alone product. This calls for an approach whereby students are exposed to multiple levels of abstraction, in order to align the skill sets of our students with the requirements and expectations of industry. This paper describes the development of a senior level undergraduate course that introduces machine vision and image processing algorithms and implementation topics within the larger context of embedded computing. The key focus is that the student appreciates the theoretical concepts but is also capable of implementing them on embedded processors for prototyping or production.

Selective Sampling Importance Resampling Particle Filter Tracking With Multibag Subspace Restoration.

The focus of this paper is a novel object tracking algorithm which combines an incrementally updated subspace-based appearance model, reconstruction error likelihood function and a two stage selective sampling importance resampling particle filter with motion estimation through autoregressive filtering techniques. The primary contribution of this paper is the use of multiple bags of subspaces with which we aim to tackle the issue of appearance model update. The use of a multibag approach allows our algorithm to revert to a previously successful appearance model in the event that the primary model fails. The aim of this is to eliminate tracker drift by undoing updates to the model that lead to error accumulation and to redetect targets after periods of occlusion by removing the subspace updates carried out during the period of occlusion. We compare our algorithm with several state-of-the-art methods and test on a range of challenging, publicly available image sequences. Our findings indicate a significant robustness to drift and occlusion as a result of our multibag approach and results show that our algorithm competes well with current state-of-the-art algorithms.

Using an Optical Proximity Sensor to Measure Foot Clearance During Gait: Agreement With Motion Analysis

Foot clearance is an important measurement variable in understanding trip falls. Current methods for measuring foot clearance are limited by their inability to capture multiple steps and confinement to a laboratory. Given that variation in this parameter is considered a factor in trip falling, its measurement in the field over multiple steps would be valuable. The development of an optical proximity sensor (OPS) has created the opportunity to collect this type of data. This study aimed to test the validity of an OPS through comparison with a motion capture system. Twenty subjects aged 33(+/−10) years, with a height of 174(+/−6) cm and a weight of 75(+/−12) kg, walked at three self selected velocities (preferred, slow, and fast). The OPS was mounted on the shoe of each subject. The motion of the shoe was recorded with a motion analysis system which tracked three markers attached to the shoe and outer casing of the OPS. Both systems were sampled at 50 Hz. The lowest point of the foot during the swing phase was recorded from each system and compared using intraclass correlation coefficients (ICCs). There was excellent agreement between the two systems. ICCs of 0.925 (all speeds), 0.931 (preferred), 0.966 (slow), and 0.889 (fast) were recorded. These results represent a strong agreement between the two systems in measuring the lowest point during swing. The OPS could thus be used instead of a camera system to record foot clearance, opening up opportunities for data collection over long periods of time, in natural settings. These results should be interpreted in context of the young healthy sample.

An extended Real-Time Compressive Tracking Method using weighted multi-frame Cosine Similarity Metric

This paper presents an extended algorithm for Real-time Compressive Tracking using Cosine Similarity Metric for object tracking. The method utilises a weighted multi-frame cosine similarity metric with the ground truth bounding box and a recently computed target bounding box. In comparison to the original algorithm it is capable of handling fast motion with a greater degree of accuracy. The proposed algorithm has been benchmarked on a desktop computer and subsequently implemented on a Texas Instruments ARM based DM3730 Beagleboard-xM. The proposed algorithm demonstrates a significant performance increase in fast motion video sequences. In addition, the low computational complexity of the algorithm makes it well suited for embedded applications.

Service Broker Based on Cloud Service Description Language

This paper proposes a cloud service broker that aims to deliver semantic cloud services - with orchestration of most feasible specifications - while composing unified solution from various providers. The Service Broker is designed based on Cloud Service Description Language (CSDL), specifically with OASIS Topology and Orchestration Specification for Cloud Applications (TOSCA).