The development of a system for monitoring trend in range condition in the arid shrublands of Western Australia.

Holm, AM; Burnside, DG; Mitchell, A A

doi:10.1071/rj9870014

Cited by 78 publications

(36 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…• Normalised Difference Vegetation Index (NDVI) The Normalised Difference Vegetation Index (NDVI) is a numerical indicator to evaluate whether the target being observed contains live green vegetation Holm AM (1987).…”

Section: Feature Extractionmentioning

confidence: 99%

Pixel-Based Land Cover Classification by Fusing Hyperspectral And Lidar Data

Jahan

Awrangjeb

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Land cover classification has many applications like forest management, urban planning, land use change identification and environment change analysis. The passive sensing of hyperspectral systems can be effective in describing the phenomenology of the observed area over hundreds of (narrow) spectral bands. On the other hand, the active sensing of LiDAR (Light Detection and Ranging) systems can be exploited for characterising topographical information of the area. As a result, the joint use of hyperspectral and LiDAR data provides a source of complementary information, which can greatly assist in the classification of complex classes. In this study, we fuse hyperspectral and LiDAR data for land cover classification. We do a pixel-wise classification on a disjoint set of training and testing samples for five different classes. We propose a new feature combination by fusing features from both hyperspectral and LiDAR, which achieves competent classification accuracy with low feature dimension, while the existing method requires high dimensional feature vector to achieve similar classification result. Also, for the reduction of the dimension of the feature vector, Principal Component Analysis (PCA) is used as it captures the variance of the samples with a limited number of Principal Components (PCs). We tested our classification method using PCA applied on hyperspectral bands only and combined hyperspectral and LiDAR features. Classification with support vector machine (SVM) and decision tree shows that our feature combination achieves better classification accuracy compared to the existing feature combination, while keeping the similar number of PCs. The experimental results also show that decision tree performs better than SVM and requires less execution time.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Pixel-Based Land Cover Classification by Fusing Hyperspectral And Lidar Data

Jahan

Awrangjeb

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Impervious surfaces on the other hand reflect fairly equally in both the red and infrared portion of the electromagnetic spectrum (Holme et al, 1987). Hence impervious surfaces had values closer to one while grassland and woodland hand values closer to 10.…”

Section: 3mentioning

confidence: 87%

Built-Up Area and Land Cover Extraction Using High Resolution Pleiades Satellite Imagery for Midrand, in Gauteng Province, South Africa

Fundisi

Musakwa

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract:Urban areas, particularly in developing countries face immense challenges such as climate change, poverty, lack of resources poor land use management systems, and week environmental management practices. Mitigating against these challenges is often hampered by lack of data on urban expansion, urban footprint and land cover. To support the recently adopted new urban agenda 2030 there is need for the provision of information to support decision making in the urban areas. Earth observation has been identified as a tool to foster sustainable urban planning and smarter cities as recognized by the new urban agenda, because it is a solution to unavailability of data. Accordingly, this study uses high resolution EO data Pleiades satellite imagery to map and document land cover for the rapidly expanding area of Midrand in Johannesburg, South Africa. An unsupervised land cover classification of the Pleiades satellite imagery was carried out using ENVI software, whereas NDVI was derived using ArcGIS software. The land cover had an accuracy of 85% that is highly adequate to document the land cover in Midrand. The results are useful because it provides a highly accurate land cover and NDVI datasets at localised spatial scale that can be used to support land use management strategies within Midrand and the City of Johannesburg South Africa.

show abstract

“…For unhealthy or sparse vegetation, much of the visible light is reflected while less of the near-infrared light is reflected. Bare soils on the other hand reflect moderately in both the red and infrared portions of the electromagnetic spectrum [28,29]. The study focused on the satellite bands that are most sensitive to vegetation information (near-infrared and red) in order to derive the NDVI information for the study area.…”

Section: Lst Estimation and Ndvi Extractionmentioning

confidence: 99%

Multi-Temporal Change Detection at a Limestone Mining and Cement Production Facility in Central Nigeria

Ujoh¹

2014

AJEP

View full text Add to dashboard Cite

Limestone mining and cement production at Yandev, Nigeria commenced in 1980 without an environmental impact assessment (EIA) to ascertain the extent of impact these activities could bring to bear on the physical and living conditions of the host environment. This study was carried out to assess the impact that mining of limestone and production of cement has inflicted on the quality and density of vegetation within the study area about 32 years since production commenced. Multi-temporal satellite imageries of the study area (Landsat for 1976(Landsat for , 1986(Landsat for , 1996 and Nigeriasat-1 for 2006), ILWIS Academia 3.3 and SPSS Version 15 were used for data analyses. Landuse and landcover (LULC) change detection; land surface temperature (LST) extraction; and normalized differentials of vegetation index (NDVI) estimation were carried out. The paired t-test was used for landcover data analysis. The study discovered first, that LULC changes occurred with built-up area increasing from 0. (1976, 1986 and 1996) while NDVI signifies decline in quality and health status of vegetation cover over the study period (1986, 1996 and 2006). The study concludes that there is rapid decline in density and quality of vegetation cover within the study area. Ameliorative measures are recommended to include reforestation and improvement in limestone mining methods/techniques amongst others.

show abstract

The development of a system for monitoring trend in range condition in the arid shrublands of Western Australia.

Cited by 78 publications

References 8 publications

Pixel-Based Land Cover Classification by Fusing Hyperspectral And Lidar Data

Pixel-Based Land Cover Classification by Fusing Hyperspectral And Lidar Data

Built-Up Area and Land Cover Extraction Using High Resolution Pleiades Satellite Imagery for Midrand, in Gauteng Province, South Africa

Multi-Temporal Change Detection at a Limestone Mining and Cement Production Facility in Central Nigeria

Contact Info

Product

Resources

About