Filters
Availability
Publication Year
Resource Type
Faculty
School/Institute
Publication Search Results
Sort
Results per page
1 - 10 of 37
-
-
-
-
-
(2007)ThesisMost current DFVPLs support flow control to facilitate experiments and complex problems. However, current approaches in DFVPLs still remain inefficient. We show that inadequacies in existing visual programming languages may be magnified in applications involving image analysis. These include a lack of efficient communication mechanisms and strong dependency on human involvement to customise properties. For instance, properties in one computational component can not be shared for other components. Moreover, conditional expressions used in control components hold data values that are unrelated with those computational components. Furthermore, since image processing libraries usua.lly only explicitly support pipeline processing, as exemplified by the widely used Insight Toolkit for Medical Image Segmentation and Registration (ITK), a looping algorithm would be difficult to implement without a feedback mechanism supported by the visual language itself. We propose a data-flow visual programming language that encompasses several novel control constructs and parameterised computational units. These components are facilitated by a novel hybrid data-flow model. We also present several conceptual models and design alternatives for control constructs. Several mechanisms and techniques are provided to enhance data propagation for these components. We demonstrate, in an environment that utilises ITK as the underlying processing engine, that the inadequacies in existing DFVPLs can be satisfactorily addressed through the visual components proposed in this thesis.
-
-
-
-
(2008)ThesisThe effectiveness of location aware applications is dependent on the accuracy of the supporting positioning system. This work evaluates the accuracy of an indoors 802.11 positioning system based on signal strength fingerprinting. The system relies on an empirical survey of signal strength prior to positioning. During this survey, signal strength recordings are made at a set of positions across the environment. These recordings are used as training data for the system during positioning. In this thesis, two surveying methods, five positioning algorithms, and two spatial output averaging methods are trialled. Accuracy is determined by empirical testing in two separate environments: a 100m square domestic house and the 1,333m square third floor of the University of New South Wales Computer Science and Engineering building. In the two environments, the lowest mean distance errors are 1.25m and 2.86m respectively.
-
(2008)ThesisObject tracking is an active research topic in computer vision and has appli- cation in several areas, such as event detection and robotics. Vehicle tracking is used in Intelligent Transport System (ITS) and surveillance systems. Its re- liability is critical to the overall performance of these systems. Feature-based methods that are used to represent distinctive content in visual frames are one approach to vehicle tracking. Existing feature-based tracking systems can only track vehicles under ideal conditions. They have difficulties when used under a variety of conditions, for example, during both the day and night. They are highly dependent on stable local features that can be tracked for a long time period. These local features are easily lost because of their local property and image noise caused by factors such as, headlight reflections and sun glare. This thesis presents a new approach, addressing the reliability issues mentioned above, tracking whole feature groups composed of feature points extracted with the Scale Invariant Feature Transform (SIFT) algorithm. A feature group in- cludes several features that share a similar property over a time period and can be tracked to the next frame by tracking individual feature points inside it. It is lost only when all of the features in it are lost in the next frame. We cre- ate these feature groups by clustering individual feature points using distance, velocity and acceleration information between two consecutive frames. These feature groups are then hierarchically clustered by their inter-group distance, velocity and acceleration information. Experimental results show that the pro- posed vehicle tracking system can track vehicles with the average accuracy of over 95%, even when the vehicles have complex motions in noisy scenes. It gen- erally works well even in difficult environments, such as for rainy days, windy days, and at night. We are surprised to find that our tracking system locates and tracks motor bikes and pedestrians. This could open up wider opportunities and further investigation and experiments are required to confirm the tracking performance for these objects. Further work is also required to track more com- plex motions, such as rotation and articulated objects with different motions on different parts.