Browsing by Author "Fourie, Christoff"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A one-class object-based system for sparse geographic feature identification
    (Stellenbosch : University of Stellenbosch, 2011-03) Fourie, Christoff; Van Niekerk, Adriaan; Mucina, L.; University of Stellenbosch. Faculty of Arts and Social Sciences. Dept. of Geography and Environmental Studies.
    ENGLISH ABSTRACT: The automation of information extraction from earth observation imagery has become a field of active research. This is mainly due to the high volumes of remotely sensed data that remain unused and the possible benefits that the extracted information can provide to a wide range of interest groups. In this work an earth observation image processing system is presented and profiled that attempts to streamline the information extraction process, without degradation of the quality of the extracted information, for geographic object anomaly detection. The proposed system, implemented as a software application, combines recent research in automating image segment generation and automatically finding statistical classifier parameters and attribute subsets using evolutionary inspired search algorithms. Exploratory research was conducted on the use of an edge metric as a fitness function to an evolutionary search heuristic to automate the generation of image segments for a region merging segmentation algorithm having six control parameters. The edge metric for such an application is compared with an area based metric. The use of attribute subset selection in conjunction with a free parameter tuner for a one class support vector machine (SVM) classifier, operating on high dimensional object based data, was also investigated. For common earth observation anomaly detection problems using typical segment attributes, such a combined free parameter tuning and attribute subset selection system provided superior statistically significant results compared to a free parameter tuning only process. In some extreme cases, due to the stochastic nature of the search algorithm employed, the free parameter only strategy provided slightly better results. The developed system was used in a case study to map a single class of interest on a 22.5 x 22.5km subset of a SPOT 5 image and is compared with a multiclass classification strategy. The developed system generated slightly better classification accuracies than the multiclass classifier and only required samples from the class of interest.
  • Thumbnail Image
    Item
    Semi-automated segment generation for geographic novelty detection using edge and area metrics
    (CONSAS Conference, 2012) Fourie, Christoff; Van Niekerk, Adriaan; Mucina, Ladislav
    An approach to generating accurate image segments for land-cover mapping applications is to model the process as an optimisation problem. Area-based empirical discrepancy metrics are used to evaluate instances of generated segments in the search process. An edge metric, called the pixel correspondence metric (PCM), is evaluated in this approach as a fitness function for segmentation algorithm free-parameter tuning. The edge metric is able to converge to user-provided reference segments in an earth observation mapping problem when adequate training data are available. Two common metaheuristic search functions were tested, namely particle swarm optimisation (PSO) and differential evolution (DE). The edge metric is compared with an area-based metric, regarding classification results of the land-cover elements of interests for an arbitrary problem. The results show the potential of using edge metrics, as opposed to area metrics, for evaluating segments in an optimisation-based segmentation algorithm parameter-tuning approach.