South Africa
South Africa

Time filter

Source Type

Schwegmann C.P.,University of Pretoria | Schwegmann C.P.,Meraka Institute | Kleynhans W.,University of Pretoria | Kleynhans W.,Meraka Institute | Salmon B.P.,University of Tasmania
IEEE Geoscience and Remote Sensing Letters | Year: 2017

The detection of ships at sea is a complex task made more so by adverse weather conditions, lack of night visibility, and large areas of concern. Synthetic aperture radar (SAR) imagery with large swaths can provide the needed coverage at a reduced resolution. The development of ship detection methods that can effectively detect ships despite the reduced image resolution is an important area of research. A novel ship detection method is introduced that makes use of a standard constant false alarm rate (FAR) prescreening step followed by a cascade classifier ship discriminator. Ships are identified using Haar-like features using adaptive boosting training on the classifier with an accuracy of 89.38% and FAR of 1.47 × 10-8 across a large swath Sentinel-1 and RADARSAT-2 newly created SAR data set. © 2004-2012 IEEE.

Luus F.P.S.,University of Pretoria | Van Den Bergh F.,Meraka Institute | Maharaj B.T.J.,University of Pretoria
IEEE Geoscience and Remote Sensing Letters | Year: 2014

Multitemporal land-use analysis is becoming increasingly important for the effective management of Earth resources. Despite that, consistent differences in the viewing and illumination geometry in satellite-borne imagery introduce some issues in the creation of land-use classification maps. The focus of this letter is settlement classification with high-resolution panchromatic acquisitions, using texture features to distinguish between settlement classes. The important multitemporal variance component of shadow is effectively removed before feature determination, which allows for minimum-supervision across-date classification. Shadow detection based on local adaptive thresholding is employed and experimentally shown to outperform existing fixed threshold shadow detectors in increasing settlement classification accuracy. Both same- and across-date settlement accuracies are significantly improved with shadow masking during feature calculation. A statistical study was performed and found to support the hypothesis that the increased accuracy is due to shadow masking specifically. © 2004-2012 IEEE.

Luus F.P.S.,University of Pretoria | Van Den Bergh F.,Meraka Institute | Maharaj B.T.J.,University of Pretoria
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing | Year: 2013

Settlement classifiers for multitemporal satellite image analysis have to overcome numerous difficulties related to across-date variances in viewing-and illumination geometry. Shadow anisotropy is a prominent contributing factor in classifier inaccuracy, so methods are introduced in this study to enable minimum-supervision classifier design that mitigate the effects of shadow profile differences. A segmentation-based shadow detector is proposed that utilizes a panchromatic segment merging algorithm with parameters that are robust against dynamic range variances seen in multitemporal imagery. The proposed shadow detector improves on the settlement classification accuracy achieved by fixed threshold detection paired with shadow removal in the presented case-study. The relationship between shadow detection accuracy and settlement classification accuracy is investigated, and it is shown that shadow removal produces greater settlement accuracy improvements for across-date experiments specifically. © 2013 IEEE.

Kleynhans W.,University of Pretoria | Kleynhans W.,Meraka Institute | Olivier J.C.,University of Pretoria | Olivier J.C.,Meraka Institute | And 5 more authors.
IEEE Geoscience and Remote Sensing Letters | Year: 2011

A method for detecting land cover change using NDVI time-series data derived from 500-m MODIS satellite data is proposed. The algorithm acts as a per-pixel change alarm and takes the NDVI time series of a 3 × 3 grid of MODIS pixels as the input. The NDVI time series for each of these pixels was modeled as a triply (mean, phase, and amplitude) modulated cosine function, and an extended Kalman filter was used to estimate the parameters of the modulated cosine function through time. A spatial comparison between the center pixel of the 3 × 3 grid and each of its neighboring pixel's mean and amplitude parameter sequence was done to calculate a change metric which yields a change or no-change decision after thresholding. Although the development of new settlements is the most prevalent form of land cover change in South Africa, it is rarely mapped, and known examples amount to a limited number of changed MODIS pixels. Therefore, simulated change data were generated and used for the preliminary optimization of the change detection method. After optimization, the method was evaluated on examples of known land cover change in the study area, and experimental results indicate an 89% change detection accuracy while a traditional annual NDVI differencing method could only achieve a 63% change detection accuracy. © 2010 IEEE.

Salmon B.P.,University of Pretoria | Olivier J.C.,University of Pretoria | Kleynhans W.,University of Pretoria | Wessels K.J.,Meraka Institute | And 2 more authors.
International Journal of Applied Earth Observation and Geoinformation | Year: 2011

This paper presents a novel land cover change detection method that employs a sliding window over hyper-temporal multi-spectral images acquired from the 7 bands of the MODerate-resolution Imaging Spectroradiometer (MODIS) land surface reflectance product. The method uses a Feedforward Multilayer Perceptron (MLP) for supervised change detection that operates on multi-spectral time series extracted with a sliding window from the dataset. The method was evaluated on both real and simulated land cover change examples. The simulated land cover change comprises of concatenated time series that are produced by blending actual time series of pixels from human settlements to those from adjacent areas covered by natural vegetation. The method employs an iteratively retrained MLP to capture all local patterns and to compensate for the time-varying climate change in the geographical area. The iteratively retrained MLP was compared to a classical batch mode trained MLP. Depending on the length of the temporal sliding window used, an overall change detection accuracy between 83% and 90% was achieved. It is shown that a sliding window of 6 months using all 7 bands of MODIS data is sufficient to detect land cover change reliably. Window sizes of 18 months and longer provide minor improvements to classification accuracy and change detection performance at the cost of longer time delays. © 2011 Elsevier B.V.

Butgereit L.,Meraka Institute | Coetzee L.,Meraka Institute | Smith A.C.,Meraka Institute
Proceedings - 2011 6th International Conference on Pervasive Computing and Applications, ICPCA 2011 | Year: 2011

The Internet of Things is the paradigm of connecting physical objects (things) with digital intelligence to the Internet. People have been connecting to the Internet for decades. It is only recently that things have been able to connect to the Internet. There are many examples of things posting their status on Twitter and allowing uni-directional access. TurnMeOn is an example of allowing bi-directional access between people and things using Internet protocols. Users can query the status of a light bulb. In addition, users can turn a light bulb on and off. © 2011 IEEE.

Butgereit L.,Meraka Institute
Proceedings - 2011 6th International Conference on Pervasive Computing and Applications, ICPCA 2011 | Year: 2011

South Africa is a semi-arid country and water resources need to be monitored. The Internet of Things is the phenomenon of more and more things (as opposed to people and services) becoming connected to the Internet. This paper describes a project where four major South African dams are connected to Twitter and Facebook (and other social media such as MXit and Google Chat) in a mechanism which would be easy to replicate for additional dams or rivers. Data is supplied by the South African Department of Water Affairs. Beachcomber (a Mobicents based JEE application) routes the data to appropriate service building blocks and resource adaptors to ensure that the information is widely disseminated. © 2011 IEEE.

Featherstone C.,Meraka Institute | Van Der Poel E.,University of South Africa
ACM International Conference Proceeding Series | Year: 2015

This paper is to describes a method for interposing computer generated melody with tone linked to unique entities within the text of a novel. Background: A recent study describing a piece of software called "TransProse" has already shown that sentiment in the text of a novel can be used to automatically generate simple piano music that reflects the same sentiment as the novel. This study wished to establish a method whereby, if after aligning the text with the melody, the sentiment in the words surrounding particular characters as they occurred within the novel could produce another melody line, for each character, that could reflect the individual characters' tone and distinguish the melodies ascribed to each character from each other. Method: The sentiment in the text of the novel is extracted by looking up the words in a database that groups the words into emotional groups called "Ekman categories". Simplistic relations between aspects of music such as pitch and tempo are chosen based on the two categories that contained the most words. These chosen attributes are then used to generate the first two melody lines. The paragraphs within which the named entities referring to characters are found is manually determined and the top "Ekman category" of the named entities is obtained through simplistic methods of extraction. Each bar of the melody is aligned with individual paragraphs of text and an additional melody line is generated for each character. Results: Adjusting the fitness function of the Genetic algorithm (GA) that was used was not sufficient to link the tone of the characters to the melody. Assigning each character their own short melodic phrase and varying the phrase appropriately achieved the desired outcome but requires additional work to harmonise better with the first two melody lines. © 2015 ACM.

Featherstone C.,Meraka Institute
2013 IST-Africa Conference and Exhibition, IST-Africa 2013 | Year: 2013

Being able to identify and predict crime trends or track criminal movement would help anyone interested in preventing criminal activity or being able to assess where crime enforcement is needed, particularly in crimes where constant policing is impossible, such as cable theft. Many neighbourhoods in South Africa have formed voluntary community policing groups, who keep in touch using SMS and two way radios. Some have adopted websites and even Twitter as a means of being more easily in touch quickly and transparently. The influential groups recognising the value and using Twitter include, Crime Line (@CrimeLineZA) and the South African Police Service (@SAPoliceService). This paper argues that existing technologies can make communication more useful in terms of data gathering, prediction and spotting broader patterns. An assessment is done to determine if South African people are already using Twitter to report crime and to find out what information they are sharing, with the goal of estabishing whether it could be useful as a source of information for the prevention of crime. © 2013 The Authors.

Featherstone C.,Meraka Institute
IEEE International Conference on Adaptive Science and Technology, ICAST | Year: 2013

Could Social Media, and in particular, microblogs such as Twitter, play a part in helping to track criminal movement? The aim of this paper is to narrow the focus of this broader problem of using social media to crowdsource information to assist in the fight against crime, to the specific problem of identifying the description of vehicles in microblog text. As this problem has many aspects, especially in terms of data gathering and identification, an initial search is performed on preset keywords and the resulting database is tagged. The tags are then analysed to determine which features are the most common. Topic models are then run on the data to determine if any useful keyword can be found for further searches and initial statistics are recorded as a baseline for further processing. Our primary concern is establishing the common content of the relevant Tweets. The result could be used both for help with data collection as well as with feature selection when learning classification algorithms for data mining. © 2013 IEEE.

Loading Meraka Institute collaborators
Loading Meraka Institute collaborators