Identifying annotations for adventure game generation from fiction text
- Authors: Berkland, Ross , Bangay, Shaun D
- Date: 2010
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433366 , vital:72965 , https://doi.org/10.1145/1899503.1899506
- Description: Recent advancements in Text-to-Scene research have lead to the devel-opment of systems which automatically extract key concepts from the text of a fiction book and generate computer animated movies depicting the sto-ry. Extracting such annotations from raw fiction text is a laborious process and so in this work we evaluate appropriate candidates to serve as the basis for the required annotations for generating interactive virtual worlds. We val-idate our choice by generating adventure games: interactive virtual worlds which create a stylized representation of the environment described in the text, populate it with characters related to the story and define game goals related to the plot of the fiction story. Our prototype produces a fully playa-ble game, making use of an existing open-source game engine. The pro-cess is evaluated using user tests in which participants are asked to meas-ure the accuracy with which the game represents the events, characters and goals described in the story. The response indicates that the chosen an-notation set is sufficient to define a game that is a plausibly acceptable rep-resentation of the text.
- Full Text:
- Date Issued: 2010
Minimum spanning trees for valley and ridge characterization in digital elevation maps
- Authors: Bangay, Shaun D , de Bruyn, David , Glass, Kevin R
- Date: 2010
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433247 , vital:72955 , https://doi.org/10.1145/1811158.1811171
- Description: Texture synthesis employs neighbourhood matching to generate appropriate new content. Terrain synthesis has the added constraint that new content must be geographically plausible. The profile recognition and polygon breaking algorithm (PPA) [Chang et al. 1998] provides a robust mechanism for characterizing terrain as systems of valley and ridge lines in digital elevation maps. We exploit this to create a terrain characterization metric that is robust, efficient to compute and is sensitive to terrain properties.
- Full Text:
- Date Issued: 2010
A method for automatically creating 3d animated scenes from annotated fiction text
- Authors: Glass, Kevin R , Bangay, Shaun D
- Date: 2009
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/432699 , vital:72893 , https://www.iadisportal.org/ijcsis/papers/2009110208.pdf
- Description: This paper describes a strategy for automatically converting fiction text into 3D animations. It assumes the existence of fiction text annotated with avatar, object, setting, transition and relation annotations, and presents a transformation process that converts annotated text into quantified constraint systems, the solutions to which are used in the population of 3D environments. Constraint solutions are valid over temporal intervals, ensuring that consistent dynamic behaviour is produced. A substantial level of automation is achieved, while providing opportunities for creative manual intervention in animation process. The process is demonstrated using annotated examples drawn from popular fiction text that are converted into animation sequences, confirming that the desired results can be achieved with only high-level human direction.
- Full Text:
- Date Issued: 2009
Simulating crowd phenomena in african markets
- Authors: Tasse, Flora P , Glass, Kevin R , Bangay, Shaun D
- Date: 2009
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433285 , vital:72959 , https://doi.org/10.1145/1503454.1503463
- Description: Crowd simulation is an important feature in the computer graphics field. Typical implementations simulate battle scenes, emergency situations, safety issues or add content to virtual environments. The problem stated in this paper falls in the last category. We present a crowd simulation behavioural model which allows us to simulate identified phenomena in popular local African markets such as narrow street flows and crowd formation around street performances. We propose a three-tier architecture model enable to produce intentions, perform path planning and control movement. We demonstrate that this approach produces the desired behaviour associated with crowds in an African market, which includes navigation, flow formation and circle creation.
- Full Text:
- Date Issued: 2009
Automating the creation of 3D animation from annotated fiction text
- Authors: Glass, Kevin R , Bangay, Shaun D
- Date: 2008
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/432639 , vital:72889 , https://www.iadisportal.org/digital-library/automating-the-creation-of-3d-animation-from-annotated-fiction-text
- Description: This paper describes a strategy for automatically converting fiction text into 3D animations. It assumes the existence of fiction text annotated with avatar, object, setting, transition and relation annotations, and presents a transformation process that converts annotated text into quantified constraint systems, the solutions to which are used in the population of 3D environments. Constraint solutions are valid over temporal intervals, ensuring that consistent dynamic behaviour is produced. A substantial level of automation is achieved, while providing opportunities for creative manual intervention in animation process. The process is demonstrated using annotated examples drawn from popular fiction text that are converted into animation sequences, confirming that the desired results can be achieved with only high-level human direction.
- Full Text:
- Date Issued: 2008
Designing a framework for animal identification
- Authors: Krijer, Hans , Foster, Gregory G , Bangay, Shaun D
- Date: 2008
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/432726 , vital:72895 , https://www.cs.ru.ac.za/research/g99k3906/hans.pdf
- Description: The conventional methods of animal identification can be replaced with a semi-automatic image analysis tool, which distinguishes individuals based on their unique markings. A flexible framework for the analysis must encompass a combination of relevant features with interchangeable animal-specific modules. Developing a Java-ImageJ plug-in alleviates routine functionality, but enforces some degree of conformity. Zebra photographs are used as the initial data under consideration. De-interlacing, adaptive thresholding, smoothing and sharpening are identified as beneficial pre-processing steps. Binarisation and sequential thinning are discussed as essential processing stages. Pattern extraction and matching is based on vectors relative to a manually defined region of interest. Provision for enhancing the system to allow fully automatic processing must be made.
- Full Text:
- Date Issued: 2008
Evaluating and improving morpho-syntactic classification over multiple corpora using pre-trained, off-the-shelf, parts-of-speech tagging tools reviewed article
- Authors: Glass, Kevin R , Bangay, Shaun D
- Date: 2008
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433427 , vital:72969 , https://hdl.handle.net/10520/EJC28053
- Description: This paper evaluates six commonly available parts-of-speech tagging tools over corpora other than those upon which they were originally trained. In particular this investigation measures the performance of the selected tools over varying styles and genres of text without retraining, under the assumption that domain specific training data is not always available. An investigation is performed to determine whether improved results can be achieved by combining the set of tagging tools into ensembles that use voting schemes to determine the best tag for each word. It is found that while accuracy drops due to non-domain specific training, and tag-mapping between corpora, accuracy remains very high, with the support vector machine-based tagger, and the decision tree-based tagger performing best over different corpora. It is also found that an ensemble containing a support vector machine-based tagger, a probabilistic tagger, a decision-tree based tagger and a rule-based tagger produces the largest increase in accuracy and the largest reduction in error across different corpora, using the Precision-Recall voting scheme.
- Full Text:
- Date Issued: 2008
Flock inspired area coverage using wireless boid-like sensor agents
- Authors: Chibaya, Colin , Bangay, Shaun D
- Date: 2008
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433440 , vital:72970 , 10.1109/UKSIM.2008.102
- Description: Simulated flocking is achievable using three boid rules [13]. We propose an area coverage model inspired by Reynolds’ flocking algorithm, investigating strategies for achieving quality coverage using flocking rules. Our agents are identical and autonomous, using only local sensory information for indirect communication. Upon deployment, agents are in the default separation mode. The cohesion rule would then guarantee that agents remain within the swarm, covering spaces with explored neighbour spaces. Four experiments are conducted to evaluate our model in terms of coverage quality achieved. We firstly investigate agents’ separation speed before the speed with which isolated agents re-organizes is investigated. The third experiment compares coverage quality achieved using our model with coverage quality achieved using random guessing. Finally, we investigate fault tolerance in the event of agents’ failures. Our model exhibits good separation and cohesion speed, achieving high quality coverage. Additionally, the model is fault tolerant and adaptive to agents’ failures.
- Full Text:
- Date Issued: 2008
Optimisation of Bacillus thuringiensis var. israelensis (Vectobac®) applications for the blackfly control programme on the Orange River, South Africa
- Authors: Rivers-Moore, Nick A , Bangay, Shaun D , Palmer, R W
- Date: 2008
- Language: English
- Type: Article
- Identifier: vital:7090 , http://hdl.handle.net/10962/d1012421
- Description: The Orange River, South Africa's largest river, is a critical water resource for the country. In spite of the clear economic benefits of regulating river flows through a series of impoundments, one of the significant undesirable ecological consequences of this regulation has been the regular outbreaks of the pest blackfly species Simulium chutteri and S. damnosum s.l. (Diptera: Simuliidae). The current control programme, carried out by the South African National Department of Agriculture, uses regular applications, by helicopter, of the target-specific bacterial larvicide Bacillus thuringiensis var. israelensis. While cost-benefit analyses show significant benefits to the control programme, benefits could potentially be further increased through applying smaller volumes of larvicide in an optimised manner, which incorporates upstream residual amounts of pesticide through downstream carry. Using an optimisation technique applied in the West African Onchocerciasis Control Programme, to a 136 km stretch of the Orange River which includes 31 blackfly breeding sites, we demonstrate that 28.5% less larvicide could be used to potentially achieve the same control of blackfly. This translates into potential annual savings of between R540 000 and R1 800 000. A comparison of larvicide volumes estimated using traditional vs. optimised approaches at different discharges, illustrates that the savings on optimisation decline linearly with increasing flow volumes. Larvicide applications at the lowest discharge considered (40 m3·s-1) showed the greatest benefits from optimisations, with benefits remaining but decreasing to a theoretical 30% up to median flows of 100 m3·s-1. Given that almost 70% of flows in July are less than 100 m3·s-1, we suggest that an optimised approach is appropriate for the Orange River Blackfly Control Programme, particularly for flow volumes of less than 100 m3·s-1. We recommend that trials be undertaken over two reaches of the Orange River, one using the traditional approach, and another using the optimised approach, to test the efficacy of using optimised volumes of B.t.i.
- Full Text:
- Date Issued: 2008
The relationship between emergence of the shortest path and information value using ant-like agents
- Authors: Chibaya, Colin , Bangay, Shaun D
- Date: 2008
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433318 , vital:72961 , https://doi.org/10.1145/1456659.1456663
- Description: Ant-like agents forage between two points. These agents' probabilistic movements are based on the use of two pheromones; one marking trails towards the goal and another marking trails back to the starting point. Path selection decisions are influenced by the relative levels of attractive and repulsive pheromone in each agent's local environment. Our work in [5] evaluates three pheromone perception strategies, investigating path formation speed, quality, directionality, robustness and adaptability under different parameter settings(degree of randomness, pheromone evaporation rate and pheromone diffusion rate).
- Full Text:
- Date Issued: 2008
A naive salience-based method for speaker identification in fiction books
- Authors: Glass, Kevin R , Bangay, Shaun D
- Date: 2007
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/432627 , vital:72888 , https://pubmed.ncbi.nlm.nih.gov/10350927/
- Description: This paper presents a salience-based technique for the annotation of directly quoted speech from fiction text. In particular, this paper determines to what extent a naïve (without the use of complex machine learning or knowledge-based techniques) scoring technique can be used for the identification of the speaker of speech quotes. The presented technique makes use of a scoring technique, similar to that commonly found in knowledge-poor anaphora resolution research, as well as a set of hand-coded rules for the final identification of the speaker of each quote in the text. Speaker identification is shown to be achieved using three tasks: the identification of a speech-verb associated with a quote with a recall of 94.41%; the identification of the actor associated with a quote with a recall of 88.22%; and the selection of a speaker with an accuracy of 79.40%.
- Full Text:
- Date Issued: 2007
A probabilistic movement model for shortest path formation in virtual ant-like agents
- Authors: Chibaya, Colin , Bangay, Shaun D
- Date: 2007
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433125 , vital:72945 , https://doi.org/10.1145/1292491.1292493
- Description: We propose a probabilistic movement model for controlling ant-like agents foraging between two points. Such agents are all identical, simple, autonomous and can only communicate indirectly through the environment. These agents secrete two types of pheromone, one to mark trails towards the goal and another to mark trails back to the starting point. Three pheromone perception strategies are proposed (Strategy A, B and C). Agents that use strategy A perceive the desirability of a neighbouring location as the difference between levels of attractive and repulsive pheromone in that location. With strategy B, agents perceive the desirability of a location as the quotient of levels of attractive and repulsive pheromone. Agents using strategy C determine the product of the levels of attractive pheromone with the complement of levels of repulsive pheromone. We conduct experiments to confirm directionality as emergent property of trails formed by agents that use each strategy. In addition, we compare path formation speed and the quality of the formed path under changes in the environment. We also investigate each strategy's robustness in environments that contain obstacles. Finally, we investigate how adaptive each strategy is when obstacles are eventually removed from the scene and find that the best strategy of these three is strategy A. Such a strategy provides useful guidelines to researchers in further applications of swarm intelligence metaphors for complex problem solving.
- Full Text:
- Date Issued: 2007
Animated feather coats using field lines
- Authors: Bangay, Shaun D
- Date: 2007
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433338 , vital:72963 , https://doi.org/10.1145/1294685.1294713
- Description: The tedious task of manually placing feathers on computer animated ob-jects involves aligning feathers, ensuring that they do not insect each other or penetrate the surface, deforming every feather to match the local surface features, and ensuring that the feather coat is consistent when the underly-ing object is animated. We present a technique for generating a feather coat over an object. Feather orientation is specified quickly and easily, feathers are deformed while ensuring collision prevention, and the coat can be ani-mated. We create a vector field in the space surrounding the body object and deform feathers to align with the field lines. The non-intersection proper-ty of the field lines ensures that feather intersections are avoided. We pro-vide a formulation of a suitable vector field and demonstrate that it is capa-ble of producing realistic feather coats. The process can easily be integrated into the work-flow of standard modelling and animation processes. We show examples of feather coat creation on a range of objects, proving that field line based placement of feather coats provides the desired functionality for feather modelling and animation.
- Full Text:
- Date Issued: 2007
Constraint-based conversion of fiction text to a time-based graphical representation
- Authors: Glass, Kevin R , Bangay, Shaun D
- Date: 2007
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433141 , vital:72946 , https://doi.org/10.1145/1292491.1292494
- Description: This paper presents a method for converting unrestricted fiction text into a time-based graphical form. Key concepts extracted from the text are used to formulate constraints describing the interaction of entities in a scene. The solution of these constraints over their respective time intervals provides the trajectories for these entities in a graphical representation.
- Full Text:
- Date Issued: 2007
Mechanisms for multimodality: taking fiction to another dimension
- Authors: Glass, Kevin R , Bangay, Shaun D , Alcock, Bruce
- Date: 2007
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433226 , vital:72953 , https://doi.org/10.1145/1294685.1294708
- Description: We present methods for automatically constructing representations of fiction books in a range of modalities: audibly, graphically and as 3D virtual environments. The correspondence between the sequential ordering of events against the order of events presented in the text is used to correctly resolve the dynamic interactions for each representation. Synthesised audio created from the fiction text is used to calibrate the base time-line against which the other forms of media are correctly aligned. The audio stream is based on speech synthesis using the text of the book, and is enhanced using distinct voices for the different characters in a book. Sound effects are included automatically. The graphical representation represents the text (as subtitles), identifies active characters and provides visual feedback of the content of the story. Dynamic virtual environments conform to the constraints implied by the story, and are used as a source of further visual content. These representations are all aligned to a common time-line, and combined using sequencing facilities to provide a multimodal version of the original text.
- Full Text:
- Date Issued: 2007
Zebra fingerprints: towards a computer-aided identification system for individual zebra
- Authors: Foster, Gregory G , Krijer, Hans , Bangay, Shaun D
- Date: 2007
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433482 , vital:72973 , https://doi.org/10.1145/1108590.1108616
- Description: The article presents a study which investigates the development of a computer-aided system for individual zebra identification based on the lateral side stripe pattern. The model proposed for individual animal identification is based on a combination of image processing and fingerprint identification technology. About 20 minutes of zebra footage was filmed at the Amakhala Game Reserve in South Africa. The study indicates that there is sufficient variation in lateral stripe patterns to differentiate individual animals.
- Full Text:
- Date Issued: 2007
Duplicating road patterns in south african informal settlements using procedural techniques
- Authors: Glass, Kevin R , Morkel, Chantelle , Bangay, Shaun D
- Date: 2006
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/432875 , vital:72909 , https://doi.org/10.1145/1108590.1108616
- Description: The formation of informal settlements in and around urban complexes has largely been ignored in the context of procedural city modeling. However, many cities in South Africa and globally can attest to the presence of such settlements. This paper analyses the phenomenon of informal settlements from a procedural modeling perspective. Aerial photography from two South African urban complexes, namely Johannesburg and Cape Town is used as a basis for the extraction of various features that distinguish different types of settlements. In particular, the road patterns which have formed within such settlements are analysed, and various procedural techniques proposed (including Voronoi diagrams, subdivision and L-systems) to replicate the identified features. A qualitative assessment of the procedural techniques is provided, and the most suitable combination of techniques identified for unstructured and structured settlements. In particular it is found that a combination of Voronoi diagrams and subdivision provides the closest match to unstructured informal settlements. A combination of L-systems, Voronoi diagrams and subdivision is found to produce the closest pattern to a structured informal settlement.
- Full Text:
- Date Issued: 2006
Graph matching with subdivision surfaces for texture synthesis on surfaces
- Authors: Bangay, Shaun D , Morkel, Chantelle
- Date: 2006
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433351 , vital:72964 , https://doi.org/10.1145/1108590.1108601
- Description: Existing texture synthesis-from example strategies for polygon meshes typically make use of three components: a multi-resolution mesh hierarchy that allows the overall nature of the pattern to be reproduced before filling in detail; a matching strategy that extends the synthesized texture using the best fit from a texture sample; and a transfer mechanism that copies the selected portion of the texture sample to the target surface. We introduce novel alternatives for each of these components. Use of √2-subdivision surfaces provides the mesh hierarchy and allows fine control over the surface complexity. Adaptive subdivision is used to create an even vertex distribution over the surface. Use of the graph defined by a surface region for matching, rather than a regular texture neighbourhood, provides for flexible control over the scale of the texture and allows simultaneous matching against multiple levels of an image pyramid created from the texture sample. We use graph cuts for texture transfer, adapting this scheme to the context of surface synthesis. The resulting surface textures are realistic, tolerant of local mesh detail and are comparable to results produced by texture neighbourhood sampling approaches.
- Full Text:
- Date Issued: 2006
Hierarchical rule generalisation for speaker identification in fiction books
- Authors: Glass, Kevin R , Bangay, Shaun D
- Date: 2006
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433174 , vital:72949 , https://doi.org/10.1145/1216262.1216266
- Description: This paper presents a hierarchical pattern matching and generalisation technique which is applied to the problem of locating the correct speaker of quoted speech found in fiction books. Patterns from a training set are generalised to create a small number of rules, which can be used to identify items of interest within the text. The pattern matching technique is applied to finding the Speech-Verb, Actor and Speaker of quotes found in fiction books. The technique performs well over the training data, resulting in rule-sets many times smaller than the training set, but providing very high accuracy. While the rule-set generalised from one book is less effective when applied to different books than an approach based on hand coded heuristics, performance is comparable when testing on data closely related to the training set.
- Full Text:
- Date Issued: 2006
Implementing the GrabCut segmentation technique as a plugin for the GIMP
- Authors: Marsh, Matthew , Bangay, Shaun D , Lobb, Adele
- Date: 2006
- Subjects: To be catalogued
- Language: English
- Type: text , article
- Identifier: http://hdl.handle.net/10962/433207 , vital:72951 , https://doi.org/10.1145/1108590.1108618
- Description: Image segmentation requires a segmentation tool that is fast and easy to use. The GIMP has built in segmentation tools, but under some circumstances these tools perform badly. "GrabCut" is an innovative segmentation technique that uses both region and boundary information in order to perform segmentation. Several variations on the "GrabCut" algorithm have been implemented as a plugin for the GIMP. The results obtained using "GrabCut" are comparable, and often better than the results of all the other built in segmentation tools.
- Full Text:
- Date Issued: 2006