Department Publications

Human activity recognition finds many applications in areas such as surveillance, and sports. Such a system classifies a spatio-temporal feature descriptor of a human figure in a video, based on training examples. However many classifiers face the constraints of the long training time, and the large size of the feature vector. Our method, due to the use of an Support Vector Machine (SVM) classifier, on an existing spatio-temporal feature descriptor resolves these problems in human activity recognition. Comparison of our system with existing classifiers using two standard datasets shows that our system is much superior in terms of the computational time, and either it surpasses or is on par with the existing recognition rates. It performs on par or marginally inferior to existing systems, when the number of training examples are a few due to the imbalance, although consistently better in terms of computation time.

Packet Classification is the enabling function for many Internet functions like QoS and Security. In this paper we propose a Classification engine architecture which exploits parallelism to increase throughput. The architecture also make use of the Temporal locality observed in Internet traffic positively by employing Popular Rule Caching mechanism to increase the classification throughput. We also introduce Rule Splitting mechanism to increase the accuracy of the rule caching mechanism. Simulation results revealed that the architecture is capable of achieving a throughput of more than 200Gbps when lowest amount of temporal locality is present for worst case packet size of 40 bytes.

In planetary rover missions, there exist severe communication constraints, which make it difficult to control rovers from a long distance (eg from the Earth). Therefore, there is a need to address the important issue of onboard local autonomy to allow deployed rovers to make their own decisions, which contributes to increased scientific return. To achieve this, robot algorithms should be constantly improved and innovative hardware mechanisms should be sought. In this context, simulators play a major role as they can help researchers develop novel technologies even without having access to expensive hardware components. In this paper, the authors present ongoing work on the planetary rover simulation environment that have been developed for testing and validating autonomous navigation of a planetary exploration rover using opensource tools. The simulation system has been developed using Gazebo, an open source 3D multi-robot simulation framework and ROS. The developed simulator provides an essential tool for visualization of the rover functionality for many state-of-art algorithms.

This paper introduces techniques for designing and implementing remotely controllable outdoor robots with the ability to localize itself while traversing in hazardous environments. The robot platform designed is a semi-autonomous tiller modified as required by the application. Localization based on wireless sensor network which has been a research interest of is addressed here with the use of Zigbee protocol. A Kalman filter was applied for the initial gathering of training data. For the improvement of the accuracy of position estimation, a fuzzy inference system is introduced. An extended Kalman filter is applied at the end in order to fuse the encoder data with the filtered RSS data. Results prove that a metric accuracy varying from 2m to 10m is achievable depending on the location of the robot with respect to the sensor nodes.

The outage probability of a recently proposed relay network with multiple antennas at the relay is analyzed. The relay uses maximal ratio combining to combine the received signals, while it uses maximal ratio transmission for the transmission. It is assumed that the reception at the relay and the destination are corrupted by multiple co-channel interfering signals. Closed-form outage probability expressions are derived when the relay is operated in the amplify-and-forward mode with fixed gain. Both cases of equal power and unequal power interferers are considered.

Feature descriptors have enabled feature matching under varying imaging conditions, while mostly being backed by experimental evidence. In addition to imposing some restrictions in imaging conditions needed to ensure matching, extending the existing descriptors is not straightforward due to the lack of sound mathematical bases. In this work, by using a surface bending versus shape histogram based on the principal curvatures, we are able to produce a descriptor which is not sensitive to the errors in dominant orientation assignment. Experimental evaluations show that our descriptor outperforms existing descriptors in the areas of viewpoint, rotation, scale, zoom, lighting and compression changes, with the exception of resilience to blur. Further, we apply this descriptor for accuracy demanding applications such as homography estimation and pose estimation. The experimental results show significant improvements in estimated homography and pose in terms of residual error and Sampson distance respectively.

The outage probability of a multiuser amplify-and-forward relaying protocol is investigated. The practical case where there are co-channel interference signals present at the network is considered for the analysis. Exact expressions and closed-form lower bounds are derived for the outage probability. Three network configurations are analyzed based on the presence of co-channel interference in the system.

Sustainable retrofit of community buildings is a timely and strategic approach to reduce the community buildings’ greenhouse gas emission contribution. The objective of the project entitled Sustainable renewal/retrofit of public buildings is to deliver reliable and strategic plans for sustainable renewal of community buildings. This paper reports the work carried out in the first phase of the post-evaluation stage of the Sustainable renewal/retrofit of public buildings project. The pilot trial version of the dual purpose sensor network is discussed here. The first version of ZigBee (IEEE 802.15) based wireless sensor network is developed to measure the Indoor Environment Quality of the building which is capable of performing post-retrofit validation for the project.

The short-term electricity demand forecasting has become one of the major research area in power system engineering. By combining the smart metering to the short-term demand forecasting techniques, new features can be added to save on demand and electricity bill. This paper illustrates the methodology used to forecast electricity demand over short period of time which can be used with smart meters. Polynomial fitting with interpolation is used to forecast the demand by taking the apparent power sample points from smart meters. The outcome of this work will be beneficial to the residential or industrial electricity consumers to control the demand side loads. It will help the industrial consumers to save on maximum demand charge with the introduction of warning message or residential consumers to reduce their electricity bill by cutting down non-essential loads in peak hours.

Developing autonomous mobile robots that can coexist with human in populated environments is still considered a big challenge. To address this problem the authors propose a novel scheme to assist mobile robots by providing localization information externally. This scheme combines the autonomous navigation and target tracking research fields to arrive at a structured assistance system for autonomous mobile robots. In the proposed scheme, the environment is sensed using a laser range finder and a camera based sensor unit. Using the Rao-Blackwellized particle filter technique, the robots that need assistance are continuously tracked. In contrast with conventional laser range finder based tracking systems, the placement of the sensor is changed to a level above average human height and the mobile robots are modified by attaching a cylindrical pole. The experiments showed the validity of the proposed …

Opportunistic beamforming (OBF) is a well-known communication technique that utilizes partial channel state information (CSI) to obtain multiuser diversity gains in the downlink. We focus on the structure of the optimal homogenous threshold feedback policy that maximizes the ergodic downlink sum-rate for OBF under a peak feedback load constraint, which we model by using a multi-packet reception model for the uplink. We solve the resulting quasi-convex optimization problem by obtaining a formula for the sum-rate maximizing feedback probability. While providing insights on the implications of our results in practical systems, we also illustrate the tradeoff between feedback and rate by obtaining the Pareto optimal boundary between feasible and infeasible feedback-rate pairs.

A novel single-integral representation for the bivariate Rician distribution was presented in a recent letter in this Transactions (ibid., vol. 59, no. 11. pp. 2951-2954, Nov. 2011). The expression given for the bivariate Rician probability density function (PDF) [1, eq. (12a)] contains a typographical error. The correct expression for the bivariate Rician PDF is presented here.

A satellite elephant collar is a device mounted on an elephant's neck to track its position and movements. This information is essential for conservation and management of this highly endangered species. Currently available units are proprietary designs by few manufacturers and no literature can be found about their internal operation. This lack of published information hampers the evolution and development of future collaring systems with increased features and functionalities for research, conservation and management. Critical issues for improvement include live time of the collar, which is related to power consumption and operational modes of the unites, and remote programmability allowing for changes in data acquisition during deployment. Most commercially available collars lack the ability to change data acquisition schedules remotely over the air, and therefore data acquisition is un-optimized, which is …

In this thesis, multidimensional signal processing techniques to mitigate disturbances in synthetic aperture systems such as radio telescopes are investigated. Here, two computationally efficient three-dimensional (3D) spatio-temporal (ST) finite impulse response (FIR) cone filter bank structures are proposed. Furthermore, a strategy is proposed to design 3D ST FIR frustum filter banks, having double-frustum-shaped passbands oriented along the temporal axis, derived from appropriate 3D ST FIR cone filter banks. Both types of cone and frustum filter banks are almost alias free and provide near-perfect reconstruction. In the proposed cone and frustum filter banks, both temporal and spatial filtering operations can be carried out at a significantly lower rate compared to previously reported 3D ST FIR cone filter banks implying lower power consumption. Furthermore, the proposed cone and frustum filter banks require a significantly lower computational complexity than previously reported 3D ST FIR cone and frustum filter banks. Importantly, this is achieved without deteriorating the improvement in signal-to-interference-plus-noise ratio. A theoretical analysis of brightness distribution (BD) errors caused by parameter perturbations and mismatches among the transfer functions of receivers employed in synthetic aperture systems is presented. First, the BD errors caused by perturbations in the transfer functions of low noise amplifiers (LNAs) and anti-aliasing filters (AAFs) are considered, and the characteristics of the additive BD error and its effects on synthesized BDs are thoroughly analyzed. Second, the conditions that should be satisfied by the transfer …

Motion Blur due to the relative motion between the camera and object can seriously degrade image quality. We present an FPGA based motion blur detection and correction algorithm which is implemented on top of a configurable soft-processor based architecture. The system consists of two main modules. The blur detection module identifies the blur length and angle, and the restoration module uses regularized inverse filtering to remove the motion blur. The Processing algorithms are implemented as separate cores on the FPGA fabric where the soft processor core is only used for managing system configuration. The system can achieve a frame rate of 15fps for a 720p HD video stream.

Lankan agricultural community. The objective of this paper is to identify the methods and implementations that can be applied to the agricultural sector of Sri Lanka. While composing the framework with identified implementations the cost, scientific and technological knowledge of the farmers were taken into consideration.

It is known that every working day millions of drivers are looking for a place to park and most of the urban traffic occur due to the drivers loitering in search of parking spaces. We wished to offer a simple solution to this problem by implementing a car park navigating system using ultrasonic sensors. RS-485 protocol, a mobile application and Bluetooth communication. The system indicates whether the car park is full or not and provide a simple navigation to the driver to the vacant spot.

Real Time Location Estimation systems (RTLS) developed for outdoor environments have shown significant errors due to changes in atmospheric conditions, multipath propagation and inherent signal strength variations. In this paper, we present an improved Wi-Fi based RTLS solution for the outdoors that reduces the above impacts. In addition this paper presents the development of a portable device for implementing the above RTLS solution. The research makes use of Euclidean, standard deviation based and probabilistic algorithms. Data smoothening is done to reduce the multipath propagation issues. The different algorithm combinations are compared via their error cumulative distribution functions.

The paper presents a video transmission technique for surveillance systems deployed over wireless networks. In order to be integrated into modern wireless and IP based networks, video surveillance systems should possess the ability to deal with variable network quality. The developed technique allows the system to adaptively compensate for unpredictable changes in the network. A statistical method is used to predict parameters related to network quality, and accordingly vary the frame rate of the video stream transmitted.

In this work we focus on the problem of detecting vehicles that come to a stop, in a video of approximately 15 frames per second. The videos are retrieved by surveillance cameras fixed as shown in Fig. 1 which are located few meters from the ground.

Increasing use of CCTV for city and building surveillance has given rise to an environment where an object (a person) might traverse through the field of vi>vv of many cameras. In this paper we explore the problem of tracking multiple objects in a multi camera environment, which is a highly addressed area in computer vision. Our research involves real time tracking of objects while they are moving in a multi camera environment with non-overlapping field of v/ewjr and detecting them when they re-uppear in the same or another camera in the same system. Previous methods of using offline trained classifiers with huge databases are time consuming and have the drawback of incapability of detecting arbitrarily selected objects. We address this issue by online training with the initial sample given and is based on the TLD (Tracking, Learning, Detection) framework. We extend the idea to formulate our methodology to …

In computer vision crass-correlation is a standard approach for local feature matching in feature tracking applications. For this Normalized cross-correlation (NCC) is implemented on spatial domain, because it does not have a simple and efficient frequency domain expression. Therefore in applications which demand real-time processing, a dedicated hardware implementation of NCC is essential to meet the computational cost in spatial domain. In this paper we present a Field Programmable Gate Array (FPGA) implementation of NCC based on the multi-port memory controller together with Fast Normalize Cross-correlation. Practical experimentation shows that our system can achieve frame rates closer to 100 for a search window size of 100x100 and template size of 15x15, with only using two dual-port memories.

The growth of the Sri Lankan healthcare sector is a necessity at this stage due to an increasingly ageing community and a significant increase in non-communicable diseases. Despite many regulations that given the sector, it continues to be inundated with many problems in relation to delivery of healthcare services./ Although the state is a prominent player in the industry, private sector healthcare facilities provide curative out patitent care to 60% of the population in the country. The World Health Organisation strategic agenda, Strategic Framework for Health Development in Sri Lanka as well as the Health Master Plan had highlighted the necessity of Information Systems for improved service delivery in the sector./ The existing Information Systems with it's administrative and financial bias has failed to add value in the interaction between the healthcare worker and the patient. The study investigates the possible …

Augmented Reality (AR) is one of the emerging technologies being used for enhancing user experience in many applications. Specific devices for various tasks are been replaced by Smart Phones making them a unique platform to implement all functionalities in one device. In this paper we present a real-time AR framework for mobile devices that takes into consideration key technical challenges such as limited processing power and battery life. The framework is having four separate modules, Marker Detection, Identification, Camera pose calculation and Embedding visual information. A 2D pattern called a marker is used to uniquely identify the objects. The marker in the camera view is detected and tracked so that information contained in the marker is exploited. Tracked four corners of the marker are used to calculate the 6 DOF of camera position, which is further processed to place 3D graphics on the real scene …