Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geograp... more Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geographic information systems applications. The modules of the aforementioned image processing software are based on conventional multi-class classifiers/algorithms such as maximum likelihood classifier. These conventional multi-class classifiers/algorithms are usually written in programming languages such as C, C++, and python. The objective of this research is to experiment the use of a binary classifier/algorithm for multi-class remote sensing task, implemented in MATLAB. MATLAB is a programming language just like C, C++, and python. In this research, the support vector machine binary classifier/algorithm based on a one-against-one approach implemented in MATLAB is applied to remote sensing multi-class problem. Both simulated and empirical satellite remote sensing data are used to train and test a one-against-one support vector machine classifier. For the purpose of validating the experimen...
Data assimilation allows merging of different sources of data to estimate possible states of a sy... more Data assimilation allows merging of different sources of data to estimate possible states of a system as it evolves in time. This therefore supports the idea of combining classical observations with Global Positioning System (GPS) observations to improve the integrity of first order geodetic controls in Nigeria. Given that these geodetic controls, which were established using traditional techniques and whose algorithms are still in use, the task of optimizing the coordinate values of these monuments to improve efficiency and accuracy in conventional geodetic operations around Nigeria is still a challenge. This study introduces the Extended Kalman Filter (EKF) technique for the modeling of these observations and their uncertainties in addition to exogenous noise, which is handled by an approximate set-valued state estimator. The proposed EKF provides a feasible linearization process in merging classical and GPS data collection modes as shown in our study. For each discrete time in th...
The management of land and resources has seen many and varied approaches and systems. Land regist... more The management of land and resources has seen many and varied approaches and systems. Land registration and cadastre has been some of the approaches and systems, and a digital cadastre map is the main component of this system. Fundamental to this study was the design and implementation of a digital cadastre to generate digital plans and related attribute information. This also facilitates efficient land management, spatial planning and the issuance of land titles in order to promote security of land tenure, reduce land disputes so as to enhance revenue generation. The study location was the New Yenagoa City, Tourism Island, Bayelsa State, Nigeria. The approach adopted involved acquiring geometric data through ground surveying method, and the non-geometric (attribute) data were acquired through social survey. The database of the layout was designed using the vector data modelling, while the graphical display of the spatial data was performed using AutoCAD 2016 and ArcGIS 10.1. Spatia...
Nowadays, there are efforts around the globe to coordinate all mapping activities using the earth... more Nowadays, there are efforts around the globe to coordinate all mapping activities using the earth-centred WGS 84. Therefore the need to transform Nigerian coordinates hitherto based on the Nigerian non-earth centred Minna Datum to the global WGS 84. This research presents a 3D coordinate transformation between the local Minna Datum and the global WGS 84 datum in Nigeria using total least squares. The Bursa-Wolf and Molodensky-Badekas similarity/conformal transformation models are used for the experiment. One hundred and ten points are selected, of which sixty points are used to compute the values of the unknown parameters while the remaining fifty points are used to compute the accuracy of the model. The experiment shows that total least squares yields better result than the least squares; and also that the Molodensky-Badekas model results are better than those of the Bursa-Wolf model.
The Niger delta region of Nigeria has undergone severe Eco-environmental changes. This alteration... more The Niger delta region of Nigeria has undergone severe Eco-environmental changes. This alteration has caused unquantifiable eco-environmental changes to natural land cover, hence, the need for an assessment of the past, present and future Land use/land cover dynamics of the region. Multi-temporal Landsat satellite images of 1986, 2002 & 2016 and IDRISI based Land Change Modeler were used for this study. Spatio-temporal analysis of LULC change between 1986 and 2016 showed that all the Land use/land cover classes were considerably altered from their initial state. The forest recorded a depletion of 29.09% of its extent. Mangrove and vegetation also had losses of 1.85% and 2.17% respectively. But high and low density built up recorded gains up to 20% through conversions of forested and arable vegetated lands to settlements. The projected result indicated almost similar trend of LULC changes as witness from 1986-2016. It showed that high and low density built will further increase by 17...
Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geograp... more Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geographic information systems applications. The modules of the aforementioned image processing software are based on conventional multi-class classifiers/algorithms such as maximum likelihood classifier. These conventional multi-class classifiers/algorithms are usually written in programming languages such as C, C++, and python. The objective of this research is to experiment the use of the parametric Gaussian mixture model multi-class classifier/algorithm for multi-class remote sensing task, implemented in MATLAB. MATLAB is a programming language just like C, C++, and python. In this research, a computer program implemented in MATLAB is used to experiment the Gaussian mixture model algorithm. Using the supervised classification technique, both simulated and empirical satellite remote sensing data are used to train and test the Gaussian mixture model algorithm. For the purpose of validating th...
The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in ... more The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in remote sensing is the ability to develop classifiers that can substantially discern the different classes inherent in natural and man-made targets. Emphasis has shifted from the use of conventional classifiers to modern non-parametric classifiers such as the Artificial Neural Network (ANN) and Support Vector Machine (SVM), and most recently the hybrid Deep Neural Network (DNN) which is a fusion of Deep Learning (DL) and ANN. This research therefore presents the novel application of Deep Support Vector Machine (DSVM), which is a fusion of DL and SVM to PolSAR image classification. Two PolSAR images of Flevoland region in the Netherlands and Winnipeg in Canada are used as test beds for the experiment. The Lee filter is used to filter the images to suppress the speckle noise in the images. The Pauli decomposition is applied to decompose the images into , , polarimetric channels. Then, the G...
Despite the classical least squares being the de-facto technique for adjusting Surveying networks... more Despite the classical least squares being the de-facto technique for adjusting Surveying networks, this research explores the application of total least squares to solving a linear surveying network problem. The linear surveying network used for the experiment is a three-loop levelling network. The augmented matrix of the design matrix and observation vector is first computed. Thereafter the singular value decomposition of the augmented matrix of the design matrix and the vector of unknown parameters are obtained. The residuals from the total least squares when compared with those from the classical least squares, are relatively better.
Currently the Unmanned Aerial Vehicle (UAV) have become an alternative for different engineering ... more Currently the Unmanned Aerial Vehicle (UAV) have become an alternative for different engineering applications, especially in surveying. One of these applications is in route surveys, but there are questions about its accuracy and efficiency. The purpose of this research was to evaluate how the UAV photogrammetry technology can compete or replace the traditional ground surveying methods of data acquisition for route survey through data obtained with total station. In order to answer the questions of accuracy, data from the same test location were obtained. A comparison was conducted between the two datasets to evaluate the accuracy of the UAV technique and the classical method, compared to a referenced dataset. This referenced data consisted of twenty-three (23) Ground Control Points (GCPs) established with a dual frequency GNSS receiver, and evenly distributed along the 1.1km route. In other to maintain consistency in both methods of data acquisition, the same GCPs used as markers d...
This research explores the implementation of a loosely coupled logistic regression model and geog... more This research explores the implementation of a loosely coupled logistic regression model and geographic information systems in modelling and predicting future urban expansion of Lagos from historical remote sensing data (Landsat TM images of Lagos acquired on 1984, 2000 and 2005). ArcGIS and MATLAB software are used for the modelling. The three Landsat images are classified using the k-means unsupervised algorithm in MATLAB. Ten salient explanatory land use variables are extracted for the calibration of the model. The model is calibrated by running a simulation for period 1984 to 2000. The computed logistic coefficients of the 10 explanatory variables show that all the 10 explanatory variables are significant at 95% confidence level based on a two-tailed test, since all the 10 variables yields p-values <0.05. The simulated map in 2000 is compared with the reference data in 2000; and evaluated using the Kappa statistic. The computed Kappa statistic is 0.7640; which implies a subst...
Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geograp... more Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geographic information systems applications. The modules of the aforementioned image processing software are based on conventional multi-class classifiers/algorithms such as maximum likelihood classifier. These conventional multi-class classifiers/algorithms are usually written in programming languages such as C, C++, and python. The objective of this research is to experiment the use of a binary classifier/algorithm for multi-class remote sensing task, implemented in MATLAB. MATLAB is a programming language just like C, C++, and python. In this research, the support vector machine binary classifier/algorithm based on a one-against-one approach implemented in MATLAB is applied to remote sensing multi-class problem. Both simulated and empirical satellite remote sensing data are used to train and test a one-against-one support vector machine classifier. For the purpose of validating the experimen...
Data assimilation allows merging of different sources of data to estimate possible states of a sy... more Data assimilation allows merging of different sources of data to estimate possible states of a system as it evolves in time. This therefore supports the idea of combining classical observations with Global Positioning System (GPS) observations to improve the integrity of first order geodetic controls in Nigeria. Given that these geodetic controls, which were established using traditional techniques and whose algorithms are still in use, the task of optimizing the coordinate values of these monuments to improve efficiency and accuracy in conventional geodetic operations around Nigeria is still a challenge. This study introduces the Extended Kalman Filter (EKF) technique for the modeling of these observations and their uncertainties in addition to exogenous noise, which is handled by an approximate set-valued state estimator. The proposed EKF provides a feasible linearization process in merging classical and GPS data collection modes as shown in our study. For each discrete time in th...
The management of land and resources has seen many and varied approaches and systems. Land regist... more The management of land and resources has seen many and varied approaches and systems. Land registration and cadastre has been some of the approaches and systems, and a digital cadastre map is the main component of this system. Fundamental to this study was the design and implementation of a digital cadastre to generate digital plans and related attribute information. This also facilitates efficient land management, spatial planning and the issuance of land titles in order to promote security of land tenure, reduce land disputes so as to enhance revenue generation. The study location was the New Yenagoa City, Tourism Island, Bayelsa State, Nigeria. The approach adopted involved acquiring geometric data through ground surveying method, and the non-geometric (attribute) data were acquired through social survey. The database of the layout was designed using the vector data modelling, while the graphical display of the spatial data was performed using AutoCAD 2016 and ArcGIS 10.1. Spatia...
Nowadays, there are efforts around the globe to coordinate all mapping activities using the earth... more Nowadays, there are efforts around the globe to coordinate all mapping activities using the earth-centred WGS 84. Therefore the need to transform Nigerian coordinates hitherto based on the Nigerian non-earth centred Minna Datum to the global WGS 84. This research presents a 3D coordinate transformation between the local Minna Datum and the global WGS 84 datum in Nigeria using total least squares. The Bursa-Wolf and Molodensky-Badekas similarity/conformal transformation models are used for the experiment. One hundred and ten points are selected, of which sixty points are used to compute the values of the unknown parameters while the remaining fifty points are used to compute the accuracy of the model. The experiment shows that total least squares yields better result than the least squares; and also that the Molodensky-Badekas model results are better than those of the Bursa-Wolf model.
The Niger delta region of Nigeria has undergone severe Eco-environmental changes. This alteration... more The Niger delta region of Nigeria has undergone severe Eco-environmental changes. This alteration has caused unquantifiable eco-environmental changes to natural land cover, hence, the need for an assessment of the past, present and future Land use/land cover dynamics of the region. Multi-temporal Landsat satellite images of 1986, 2002 & 2016 and IDRISI based Land Change Modeler were used for this study. Spatio-temporal analysis of LULC change between 1986 and 2016 showed that all the Land use/land cover classes were considerably altered from their initial state. The forest recorded a depletion of 29.09% of its extent. Mangrove and vegetation also had losses of 1.85% and 2.17% respectively. But high and low density built up recorded gains up to 20% through conversions of forested and arable vegetated lands to settlements. The projected result indicated almost similar trend of LULC changes as witness from 1986-2016. It showed that high and low density built will further increase by 17...
Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geograp... more Software like ILWIS and GRASS GIS can be employed for remote sensing image processing and geographic information systems applications. The modules of the aforementioned image processing software are based on conventional multi-class classifiers/algorithms such as maximum likelihood classifier. These conventional multi-class classifiers/algorithms are usually written in programming languages such as C, C++, and python. The objective of this research is to experiment the use of the parametric Gaussian mixture model multi-class classifier/algorithm for multi-class remote sensing task, implemented in MATLAB. MATLAB is a programming language just like C, C++, and python. In this research, a computer program implemented in MATLAB is used to experiment the Gaussian mixture model algorithm. Using the supervised classification technique, both simulated and empirical satellite remote sensing data are used to train and test the Gaussian mixture model algorithm. For the purpose of validating th...
The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in ... more The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in remote sensing is the ability to develop classifiers that can substantially discern the different classes inherent in natural and man-made targets. Emphasis has shifted from the use of conventional classifiers to modern non-parametric classifiers such as the Artificial Neural Network (ANN) and Support Vector Machine (SVM), and most recently the hybrid Deep Neural Network (DNN) which is a fusion of Deep Learning (DL) and ANN. This research therefore presents the novel application of Deep Support Vector Machine (DSVM), which is a fusion of DL and SVM to PolSAR image classification. Two PolSAR images of Flevoland region in the Netherlands and Winnipeg in Canada are used as test beds for the experiment. The Lee filter is used to filter the images to suppress the speckle noise in the images. The Pauli decomposition is applied to decompose the images into , , polarimetric channels. Then, the G...
Despite the classical least squares being the de-facto technique for adjusting Surveying networks... more Despite the classical least squares being the de-facto technique for adjusting Surveying networks, this research explores the application of total least squares to solving a linear surveying network problem. The linear surveying network used for the experiment is a three-loop levelling network. The augmented matrix of the design matrix and observation vector is first computed. Thereafter the singular value decomposition of the augmented matrix of the design matrix and the vector of unknown parameters are obtained. The residuals from the total least squares when compared with those from the classical least squares, are relatively better.
Currently the Unmanned Aerial Vehicle (UAV) have become an alternative for different engineering ... more Currently the Unmanned Aerial Vehicle (UAV) have become an alternative for different engineering applications, especially in surveying. One of these applications is in route surveys, but there are questions about its accuracy and efficiency. The purpose of this research was to evaluate how the UAV photogrammetry technology can compete or replace the traditional ground surveying methods of data acquisition for route survey through data obtained with total station. In order to answer the questions of accuracy, data from the same test location were obtained. A comparison was conducted between the two datasets to evaluate the accuracy of the UAV technique and the classical method, compared to a referenced dataset. This referenced data consisted of twenty-three (23) Ground Control Points (GCPs) established with a dual frequency GNSS receiver, and evenly distributed along the 1.1km route. In other to maintain consistency in both methods of data acquisition, the same GCPs used as markers d...
This research explores the implementation of a loosely coupled logistic regression model and geog... more This research explores the implementation of a loosely coupled logistic regression model and geographic information systems in modelling and predicting future urban expansion of Lagos from historical remote sensing data (Landsat TM images of Lagos acquired on 1984, 2000 and 2005). ArcGIS and MATLAB software are used for the modelling. The three Landsat images are classified using the k-means unsupervised algorithm in MATLAB. Ten salient explanatory land use variables are extracted for the calibration of the model. The model is calibrated by running a simulation for period 1984 to 2000. The computed logistic coefficients of the 10 explanatory variables show that all the 10 explanatory variables are significant at 95% confidence level based on a two-tailed test, since all the 10 variables yields p-values <0.05. The simulated map in 2000 is compared with the reference data in 2000; and evaluated using the Kappa statistic. The computed Kappa statistic is 0.7640; which implies a subst...
Uploads
Papers by ANIEKAN EYOH