Comparative Analysis of Change Detection Techniques In Landuse / Landcover Mapping of Oyo Town, Oyo State, Nigeria

Abstract

Landcover is the natural surface of the earth undisturbed by human activities. It represents vegetation, natural or man-made features and every other visible evidence of land use. Landuse on the other hand refers to the use of land by humans while Change detection is the process of identifying differences in the state of an object or phenomenon by observing it in different times. This study is aimed at comparative analysis of change detection techniques in landuse/ landcover mapping of Oyo town with the objectives of comparing and evaluating the results of different change detection techniques as well as production of Landuse/ Landcover map of the study area for the period of 1990 and 2016. Landsat images of 1990, 2003 and 2016 covering the study area (Path 191, Row 54 & 55) were collected from the archives of United States Geological Survey (USGS) agency and image processing and analysis were done using ERDAS Imagine 2015 and ArcGIS 10.5. The results of the study were achieved through image pre-processing, image enhancement, image band combination, change detection through pre-classification (image differencing, image ratioing, Principal Component Analysis) and Post-Classification Comparison (PCC) methods, and results analysed. The result of accuracy assessment in this research shows that a PCA produces a better result of 91.67% while PCC delivered accuracy that ranges between 83.33% and 87.5%. However, PCC gives a better result on the change detection in the study area as it affords more analysis on the study area based on the thematic classes generated for each landuse and landcover of the study area. This study hereby recommends Post-Classification Comparison (PCC) and Principal Component Analysis (PCA) for change detection in the study area. Further research on change detection in the study area should be carried out using Object-Based Image Analysis (OBIA) using high resolution images because this research is hinge on pixel based classification of medium resolution images.

Psychosocial factors as predictors of aggressive behaviors among primary school learners

“…Aggressive behavior has been a perturbing issue for stakeholders due to the frightening increase in violent crimes and other social vices in Nigerian society and schools, leading to high dropout rates and learners' poor academic outcomes (Saheed, 2019; Ojuope & Ekundayo, 2020). The frequency at which teenagers engage in aggressive behaviors poses a threat to societal tranquility and peaceful coexistence.…”

On the Use of Sentinel-2 NDVI Time Series and Google Earth Engine to Detect Land-Use/Land-Cover Changes in Fire-Affected Areas

“…(i) Techniques focused on comparing two (or multiple) dates comparison can be split into approaches based on a post-classification comparison (PCC) and procedures based on a direct comparison, generally known as comparative pre-classification [37][38][39][40][41]. (ii) Multi-temporal analysis methods can be split into: (i) temporal segmentation algorithms, such as CCDC (continuous change detection and classification), VERDeT (vegetation regeneration and disturbance estimates through time), and LandTrend [41][42][43][44][45][46][47][48]; and (ii) trend analysis [49][50][51][52][53][54][55][56] to detect land-use/land-cover changes by analyzing the pixelin-time signal [47,[57][58][59][60].…”