A Hybrid Image Classification Approach for the Systematic Analysis of Land Cover (lc) Changes in the Niger Delta Region

The landscape of the Niger Delta region of Nigeria is undergoing rapid changes as a result of natural and anthropogenic activities. This necessitates the development of a rapid, cost effective and efficient land cover (LC) classification technique to monitor the biophysical dynamics in the region. Due to the intricate land cover patterns prominent in the study area and the irregularly indistinguishable relationship between land cover and spectral signals, this paper introduces a combined use of unsupervised and supervised image classification for detecting LC classes. The technique utilizes the spectral recognition of the unsupervised classification in the performance mode and the selection of sampling sites from a principal component analyzed image of the supervised classification in the training mode. The unsupervised and supervised classification algorithms used are the generalized form of Heckbert quantization and Maximum Likelihood (ML) respectively. With the continuous conflict over the impact of oil activities in the area, this work provides an initial basis of monitoring LC change, which is an important factor to consider in the design of an environmental decision-making framework. Landsat TM and ETM+ images of 1987 and 2002 were used to test the hybrid classification technique. The overall result indicates the ability to separate more LC classes. Furthermore, the approach provides a means of improving on the deficiencies of the unsupervised and supervised classification methods.