An Optimal Approach for Land-Use / Land-Cover Mapping by Integration and Fusion of Multispectral Landsat OLI Images: Case Study in Baghdad, Iraq

Abstract Using solely an optical remotely sensed dataset to obtain an accurate thematic map of land use and land cover (LU/LC) is a serious challenge. The dataset fusion of multispectral and panchromatic images play a big role and provide an accurate estimation of LU/LC map simply because using a dataset from different spectrum portions with different spatial and spectral characteristics will improve image classification. For this study, the Landsat operational land imager multispectral and panchromatic images were adopted. This study aimed to investigate the effectiveness of using a panchromatic highly spatial resolution to refine the methodology for LU/LC mapping in Baghdad city, Iraq, by performing a comparison of classifications using different algorithms on multispectral and fused images. Different classification algorithms were employed to classify the data set; minimum distance (MD) and the maximum likelihood classifier (MLC). A suitable classification method was proposed to map LU/LC based on the outcome results. The result evaluation was conducted by applying a confusion matrix. An overall accuracy of a fused image using a principal component-based spectral sharpening algorithm and classified by the MLC classifier reveals the highest accurate results with an overall accuracy and kappa coefficient of 98.90% and 0.98, respectively. Results showed that the best methodology for LU/LC mapping of the study area is found from fusion of multispectral with panchromatic images via principal component-based spectral algorithm with MLC approach for classification.

Download Full-text

CLASSIFICATION OF SATELLITE FUSED DATA FOR LAND USE MAPPING IN DEVELOPMENT PLAN

PLANNING MALAYSIA JOURNAL ◽

10.21837/pmjournal.v9.i2.87 ◽

2011 ◽

Vol 9 (2) ◽

Author(s):

Norzailawati Mohd Noor ◽

Alias Abdullah ◽

Mazlan Hashim

Keyword(s):

Land Use ◽

Principal Component ◽

Kappa Statistic ◽

Development Plan ◽

Remotely Sensed Data ◽

Data Set ◽

Principal Component Transform ◽

Fused Image ◽

Fine Resolution

Land use mapping in development plan basically provides resources of information and important tool in decision making. In relation to this, fine resolution of recent satellite remotely sensed data have found wide applications in land use/land cover mapping. This study reports on work carried out for classification of fused image for land use mapping in detail scale for Local Plan. The LANDSATTM, SPOT Pan and IKONOS satellite were fused and examined using three data fusion techniques, namely Principal Component Transfonn (PCT), Wavelet Transform and Multiplicative fusing approach. The best fusion technique for three datasets was determined based on the assessment of class separabilities and visualizations evaluation of the selected subset of the fused datasets, respectively. Principal Component Transform has been found to be the best technique for fusing the three datasets, where the best fused data set was subjected to further classification for producing level of land use classes while level II and III pass on to nine classes of detail classification for local plan. The overall data classification accuracy of the best fused data set was 0.86 (kappa statistic). Final land use output from classified data was successfully generated in accordance to local plan land use mapping for development plan purposes.

Download Full-text

Maximum Fraction Images Derived from Year-Based Project for On-Board Autonomy-Vegetation (PROBA-V) Data for the Rapid Assessment of Land Use and Land Cover Areas in Mato Grosso State, Brazil

Land ◽

10.3390/land9050139 ◽

2020 ◽

Vol 9 (5) ◽

pp. 139 ◽

Cited By ~ 1

Author(s):

Henrique Luis Godinho Cassol ◽

Egidio Arai ◽

Edson Eyji Sano ◽

Andeise Cerqueira Dutra ◽

Tânia Beatriz Hoffmann ◽

...

Keyword(s):

Land Use ◽

Time Series ◽

Land Cover ◽

Confusion Matrix ◽

Google Earth ◽

Landsat 8 ◽

Validation Data ◽

Data Set ◽

Mato Grosso ◽

Fraction Images

This paper presents a new approach for rapidly assessing the extent of land use and land cover (LULC) areas in Mato Grosso state, Brazil. The novel idea is the use of an annual time series of fraction images derived from the linear spectral mixing model (LSMM) instead of original bands. The LSMM was applied to the Project for On-Board Autonomy-Vegetation (PROBA-V) 100-m data composites from 2015 (~73 scenes/year, cloud-free images, in theory), generating vegetation, soil, and shade fraction images. These fraction images highlight the LULC components inside the pixels. The other new idea is to reduce these time series to only six single bands representing the maximum and standard deviation values of these fraction images in an annual composite, reducing the volume of data to classify the main LULC classes. The whole image classification process was conducted in the Google Earth Engine platform using the pixel-based random forest algorithm. A set of 622 samples of each LULC class was collected by visual inspection of PROBA-V and Landsat-8 Operational Land Imager (OLI) images and divided into training and validation datasets. The performance of the method was evaluated by the overall accuracy and confusion matrix. The overall accuracy was 92.4%, with the lowest misclassification found for cropland and forestland (<9% error). The same validation data set showed 88% agreement with the LULC map made available by the Landsat-based MapBiomas project. This proposed method has the potential to be used operationally to accurately map the main LULC areas and to rapidly use the PROBA-V dataset at regional or national levels.

Download Full-text

CLASSIFICATION OF SATELLITE FUSED DATA FOR LAND USE MAPPING IN DEVELOPMENT PLAN

PLANNING MALAYSIA JOURNAL ◽

10.21837/pm.v9i2.87 ◽

2011 ◽

Vol 9 ◽

Author(s):

Noorzailawati Mohd Noor ◽

Alias Abdullah ◽

Mazlan Hashim

Keyword(s):

Land Use ◽

Principal Component ◽

Kappa Statistic ◽

Development Plan ◽

Remotely Sensed Data ◽

Data Set ◽

Principal Component Transform ◽

Fused Image ◽

Fine Resolution

Download Full-text

Land Use Land Cover map segmentation using Remote Sensing: A Case study of Ajoy river watershed, India

Journal of Intelligent Systems ◽

10.1515/jisys-2019-0155 ◽

2020 ◽

Vol 30 (1) ◽

pp. 273-286

Author(s):

Kalyan Mahata ◽

Rajib Das ◽

Subhasish Das ◽

Anasua Sarkar

Keyword(s):

Land Use ◽

Image Segmentation ◽

Cellular Automata ◽

Land Cover ◽

Satellite Imagery ◽

Current Model ◽

Discrete Dynamical System ◽

Land Use Land Cover ◽

Data Set ◽

Validity Indices

Abstract Image segmentation in land cover regions which are overlapping in satellite imagery, is one crucial challenge. To detect true belonging of one pixel becomes a challenging problem while classifying mixed pixels in overlapping regions. In current work, we propose one new approach for image segmentation using a hybrid algorithm of K-Means and Cellular Automata algorithms. This newly implemented unsupervised model can detect cluster groups using hybrid 2-Dimensional Cellular-Automata model based on K-Means segmentation approach. This approach detects different land use land cover areas in satellite imagery by existing K-Means algorithm. Since it is a discrete dynamical system, cellular automaton realizes uniform interconnecting cells containing states. In the second stage of current model, we experiment with a 2-dimensional cellular automata to rank allocations of pixels among different land-cover regions. The method is experimented on the watershed area of Ajoy river (India) and Salinas (California) data set with true class labels using two internal and four external validity indices. The segmented areas are then compared with existing FCM, DBSCAN and K-Means methods and verified with the ground truth. The statistical analysis results also show the superiority of the new method.

Download Full-text

LAND COVER CLASSIFICATION ALOS AVNIR DATA USING IKONOS AS REFERENCE

International Journal of Remote Sensing and Earth Sciences (IJReSES) ◽

10.30536/j.ijreses.2012.v9.a1822 ◽

2012 ◽

Vol 9 (1) ◽

Author(s):

Bambang Trisakti ◽

Dini Oktaviana Ambarwati

Keyword(s):

Land Cover ◽

Near Infrared ◽

Good Accuracy ◽

Confusion Matrix ◽

Principal Component ◽

Land Cover Classification ◽

Accuracy Evaluation ◽

Post Processing ◽

Classification Result ◽

Training Samples

Abstract. Advanced Land Observation Satellite (ALOS) is a Japanese satellite equipped with 3 sensors i.e., PRISM, AVNIR, and PALSAR. The Advanced Visible and Near Infrared Radiometer (AVNIR) provides multi spectral sensors ranging from Visible to Near Infrared to observe land and coastal zones. It has 10 meter spatial resolution, which can be used to map land cover with a scale of 1:25000. The purpose of this research was to determineclassification for land cover mapping using ALOS AVNIR data. Training samples were collected for 11 land cover classes from Bromo volcano by visually referring to very high resolution data of IKONOS panchromatic data. The training samples were divided into samples for classification input and samples for accuracy evaluation. Principal component analysis (PCA) was conducted for AVNIR data, and the generated PCA bands were classified using Maximum Likehood Enhanced Neighbor method. The classification result was filtered and re-classed into 8 classes. Misclassifications were evaluated and corrected in the post processing stage. The accuracy of classifications results, before and after post processing, were evaluated using confusion matrix method. The result showed that Maximum Likelihood Enhanced Neighbor classifier with post processing can produce land cover classification result of AVNIR data with good accuracy (total accuracy 94% and kappa statistic 0.92). ALOS AVNIR has been proven as a potential satellite data to map land cover in the study area with good accuracy.

Download Full-text

Land Use/Land Cover Changes Monitoring and Analysis of Dubai Emirate, UAE Using Multi-Temporal Remote Sensing Data

10.29007/jvz3 ◽

2018 ◽

Cited By ~ 2

Author(s):

Mohamed Mostafa Mohamed ◽

Samy Elmahdy

Keyword(s):

Land Use ◽

Land Cover ◽

Accuracy Assessment ◽

Low Cost ◽

Confusion Matrix ◽

Land Development ◽

Remote Sensing Data ◽

Land Use Land Cover ◽

Spectral Angle Mapper ◽

Fast Pace

Dubai is a rapidly urbanizing emirate with land development succeeding at a fast pace. The present study aims to develop a low-cost classifier based on the spectral angle mapper (SAM) and image difference (ID) algorithms. The proposed approach was developed in order to improve Land use/ Land cover (LULC) classification maps for the purpose of monitoring and analysing LULC change during the period from 2000 to 2015 for the Emirate of Dubai. The approach starts by collecting 320 training samples from high resolution images such as QuickBird with a spatial resolution of 60 cm followed by applying a 3×3 spatial convulsion filter, majority/ minority analysis, sieving classes and clump map of the produced LULC maps. After that, the accuracy of the maps were assigned using confusion matrix. The accuracy assessment demonstrated that the targeted 2000, 2005,2010 and 2015 LULC maps have 88.125%, 89.069%, 90.122% and 96.096% accuracy, respectively. The results exhibited that the built-up areas increased by 233.72 km2 (5.81%) from 2000 to 2005 and keeps to increase even up and till the present time. The results also showed that the changes in the periods 2000-2005 and 2010-2015 confirmed that net vegetation area loses were more obvious from 2005 to 2005 than from 2010 to 2015, reducing from 47.618 km2 to 40,820 km2, respectively. This study is of great help to urban planners and decision makers.

Download Full-text

The Use of Spot-HRV Data for the Mapping of the Land Cover (applied upon East-Mono, Central Togo)

Afrika Focus ◽

10.21825/af.v7i1.6123 ◽

1991 ◽

Vol 7 (1) ◽

Author(s):

Beata Maria De Vliegher

Keyword(s):

Remote Sensing ◽

Land Use ◽

Land Cover ◽

Image Interpretation ◽

Remote Sensing Data ◽

Image Data ◽

Visual Image ◽

Data Set ◽

Land Cover Map ◽

Colour Composite

The mapping of the land use in a tropical wet and dry area (East-Mono, Central Togo) is made using remote sensing data, recorded by the satellite SPOT. The negative, multispectral image data set has been transferred into positives by photographical means and afterwards enhanced using the diazo technique. The combination of the different diazo coloured images resulted in a false colour composite, being the basic document for the visual image interpretation. The image analysis, based upon differences in colour and texture, resulted in a photomorphic unit map. The use of a decision tree including the various image characteristics allowed the conversion of the photomorphic unit map into a land cover map. For this, six main land cover types could be differentiated resulting in 16 different classes of the final map. KEY WORDS :Remote sensing, SPOT, Multispectral view, Visual image interpre- tation, Mapping, Vegetation, Land use, Togo.

Download Full-text

A COMPARATIVE ASSESSMENT OF EFFICACY OF SUPER RESOLVED AIRBORNE HYPERSPECTRAL OUTPUTS IN URBAN MATERIAL AND LAND COVER INFORMATION EXTRACTION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-5-653-2018 ◽

2018 ◽

Vol XLII-5 ◽

pp. 653-658 ◽

Cited By ~ 1

Author(s):

K. Mishra ◽

A. Siddiqui ◽

V. Kumar

Keyword(s):

Land Cover ◽

Spatial Resolution ◽

Urban Areas ◽

Near Infrared ◽

Infrared Imaging ◽

Spatial Information ◽

Confusion Matrix ◽

Spectral Characteristics ◽

Support Vector ◽

Spectral Angle Mapper

Abstract. Urban areas despite being heterogeneous in nature are characterized as mixed pixels in medium to coarse resolution imagery which renders their mapping as highly inaccurate. A detailed classification of urban areas therefore needs both high spatial and spectral resolution marking the essentiality of different satellite data. Hyperspectral sensors with more than 200 contiguous bands over a narrow bandwidth of 1&ndash;10nm can distinguish identical land use classes. However, such sensors possess low spatial resolution. As the exchange of rich spectral and spatial information is difficult at hardware level resolution enhancement techniques like super resolution (SR) hold the key. SR preserves the spectral characteristics and enables feature visualization at a higher spatial scale. Two SR algorithms: Anchored Neighbourhood Regression (ANR) and Sparse Regression and Natural Prior (SRP) have been executed on an airborne hyperspectral scene of Advanced Visible/Near Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) for the mixed environment centred on Kankaria Lake in the city of Ahmedabad thereby bringing down the spatial resolution from 8.1m to 4.05m. The generated super resolved outputs have been then used to map ten urban material and land cover classes identified in the study area using supervised Spectral Angle Mapper (SAM) and Support Vector Machine (SVM) classification methods. Visual comparison and accuracy assessment on the basis of confusion matrix and Pearson’s Kappa coefficient revealed that SRP super-resolved output classified using radial basis function (RBF) kernel based SVM is the best outcome thereby highlighting the superiority of SR over simple scaling up and resampling approaches.

Download Full-text

Land use and land cover changes in the Lower Neretva Region from 1990 to 2020

Hrvatski geografski glasnik/Croatian Geographical Bulletin ◽

10.21861/hgg.2021.83.02.01 ◽

2021 ◽

Vol 83 (2) ◽

pp. 7-31

Author(s):

Josip Šetka ◽

◽

Petra Radeljak Kaufmann ◽

Luka Valožić ◽

◽

...

Keyword(s):

Land Use ◽

Land Cover ◽

Agricultural Land ◽

Confusion Matrix ◽

Hybrid Approach ◽

Land Cover Changes ◽

Landsat 8 ◽

Economic Changes ◽

Sparse Vegetation ◽

Landsat 7

Changes in land use and land cover are the result of complex interactions between humans and their environment. This study examines land use and land cover changes in the Lower Neretva Region between 1990 and 2020. Political and economic changes in the early 1990s resulted in changes in the landscape, both directly and indirectly. Multispectral image processing was used to create thematic maps of land use and land cover for 1990, 2005, and 2020. Satellite images from Landsat 5, Landsat 7 and Landsat 8 were the main source of data. Land use and land cover structure was assessed using a hybrid approach, combining unsupervised and manual (visual) classification methods. An assessment of classification accuracy was carried out using a confusion matrix and kappa coefficient. According to the results of the study, the percentage of built-up areas increased by almost 33%. Agricultural land and forests and grasslands also increased, while the proportion of swamps and sparse vegetation areas decreased.

Download Full-text

A COMPARISON OF OBJECT-BASED AND PIXEL-BASED APPROACHES FOR LAND USE/LAND COVER CLASSIFICATION USING LAPAN-A2 MICROSATELLITE DATA

International Journal of Remote Sensing and Earth Sciences (IJReSES) ◽

10.30536/j.ijreses.2017.v14.a2680 ◽

2017 ◽

Vol 14 (1) ◽

pp. 27 ◽

Cited By ~ 1

Author(s):

Jalu Tejo Nugroho ◽

. Zylshal ◽

Nurwita Mustika Sari ◽

Dony Kushardono

Keyword(s):

Land Use ◽

Land Cover ◽

Confusion Matrix ◽

Digital Camera ◽

Land Use Land Cover ◽

Central Java ◽

Object Based ◽

Accuracy Result ◽

Blurring Effect

In recent years, small satellite industry has been a rapid trend and become important especially when associated with operational cost, technology adaptation and the missions. One mission of LAPAN-A2, the 2nd generation of microsatellite that developed by Indonesian National Institute of Aeronautics and Space (LAPAN), is Earth observation using digital camera that provides imagery with 3.5 m spatial resolution. The aim of this research is to compare between object-based and pixel-based classification of land use/land cover (LU/LC) in order to determine the appropriate classification method in LAPAN-A2 dataprocessing (case study Semarang, Central Java).The LU/LC were classified into eleven classes, as follows: sea, river, fish pond, tree, grass, road, building 1, building 2, building 3, building 4 and rice field. The accuracy of classification outputs were assessed using confusion matrix. The object-based and pixel-based classification methods result for overall accuracy are 31.63% and 61.61%, respectively. According to accuracy result, it was thought that blurring effect on LAPAN-A2 data may be the main cause ofaccuracy decrease. Furthermore, the result is suggested to use pixel-based classification to be applied inLAPAN-A2 data processing.

Download Full-text