Development of classification system for LULC using remote sensing and GIS

Alshari, Eman A.; Gawali, Bharti W.

doi:10.1016/j.gltp.2021.01.002

Cited by 91 publications

(26 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These signatures are the spectral reflectance range for a specific element and were further used to assign the LULC class to each pixel (Nguyen et al 2020). There are various classification techniques which give excellent accuracies such as Random Forests (RF), Support Vector Machine (SVM) and Maximum Likelihood Classifier (MLC) (Alshari and Gawali 2021). Among these techniques, MLC is the most commonly used classification technique for various remote sensing applications (Allam et al 2019;Chughtai et al 2021).…”

Section: Input Layer Preparationmentioning

confidence: 99%

Urban modelling and forecasting of landuse using SLEUTH model

Kumar

Agrawal

2022

Int. J. Environ. Sci. Technol.

View full text Add to dashboard Cite

The present study performs landcover modelling using the SLEUTH model. The urban land use changing factors are calibrated to predict the Land Use Land Cover (LULC) for a densely populated and developing smart city, Prayagraj, India. This research aims to use the SLEUTH model for simulating the future urban growth with the help of historical LULC (1990LULC ( -2020, road network and elevation data. The influence of road gravity and slope resistant coefficients is very significant in this study's outcome. The built-up area of the region increased from 40.22 km 2 (5.10% of total area) in 1990 to 85.89 km 2 (10.89%) in 2020. According to prediction results, in the next 20 years, the built-up growth rate would be 1.9% and approximated built-up area would be 118.66 km 2 (14.98%) in the year 2040. The quality of the result has been quantified in terms of best fit value of Optimal SLEUTH Metric (OSM) and validated against the existing LULC. The study utilises a spatially explicit urban growth model with 30 m resolution remote sensing data and provides future landuse of Prayagraj city.

show abstract

Section: Input Layer Preparationmentioning

confidence: 99%

Urban modelling and forecasting of landuse using SLEUTH model

Kumar

Agrawal

2022

Int. J. Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Early researches in remote sensing semantic segmentation often leveraged and developed the digital features, among which some works [17], [20], [21] rely on the physical properties of land-covers and some other works [36], [37] capture the local spatial information. Subsequently, many deep structures [38], [39], [40], [41], whose fully connected layers are removed, have been borrowed in semantic segmentation models not only for remote sensing images but also for natural images [42], [43], [44].…”

Section: A Semantic Segmentationmentioning

confidence: 99%

“…Blue circles indicate the feature maps and orange circles indicate the hidden variables. drawn increasing attentions in the remote sensing community [15], [16], [17].…”

Section: Introductionmentioning

confidence: 99%

“…For implementing semantic segmentation, the methods to transfer the spectral signals into digital features first came into researchers' views, and classical classifiers in machine learning [18], [19] could be applied to predict pixel-wise landcover categories [17], [20], [21], where elaborate computation procedures could be exploited to obtain features corresponding to diverse land-cover distributions. Nevertheless, with predefined man-made calculations, hand-crafted features are hard to represent numberless different land-cover distributions in real-world environments, which has encouraged following researches to focus on improving the flexibility and representation capabilities of features through learnable deep structures [3], [22], [23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images

Yang,

Tong,

Xia

et al. 2021

Preprint

View full text Add to dashboard Cite

Targeting at depicting land covers with pixel-wise semantic categories, semantic segmentation in remote sensing images needs to portray diverse distributions over vast geographical locations, which is difficult to be achieved by the homogeneous pixel-wise forward paths in the architectures of existing deep models. Although several algorithms have been designed to select pixel-wise adaptive forward paths for natural image analysis, it still lacks theoretical supports on how to obtain optimal selections. In this paper, we provide mathematical analyses in terms of the parameter optimization, which guides us to design a method called Hidden Path Selection Network (HPS-Net). With the help of hidden variables derived from an extra mini-branch, HPS-Net is able to tackle the inherent problem about inaccessible global optimums by adjusting the direct relationships between feature maps and pixel-wise path selections in existing algorithms, which we call hidden path selection. For the better training and evaluation, we further refine and expand the 5-class Gaofen Image Dataset (GID-5) to a new one with 15 land-cover categories, i.e., GID-15. The experimental results on both GID-5 and GID-15 demonstrate that the proposed modules can stably improve the performance of different deep structures, which validates the proposed mathematical analyses.

show abstract

“…This study compared the number of buildings by satellite imagery and by census. Land Change Modeler (LCM) has been widely implemented to predict the land use/cover change [5]- [7]. This method needs a land use/cover classification based on satellite imageries that will be used as well in the current study for finding percentage of vegetation in Ciamis and Pangandaran District, West Java, Indonesia, as the study area.…”

Section: Introductionmentioning

confidence: 99%

Untitled

2022

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Diminishing of green areas (vegetation, park, forest, etc.) influences the climate change and the quality of life in an area. Indonesia has large are, hence, it is difficult to find the number of vegetation and without the computer-based calculation accurately. Also, nowadays, the remote sensing technology has been widely used to capture the large region using satellite sensor, e.g., Landsat, Sentinel, Ikonos, etc. from websites that give free access like United States Geological Survey (USGS). Many vertical applications can be used to calculate percentage of vegetation, e.g., IDRISI, Dyna-Clue, eCognition, etc., but in this study, a Matlab-based calculation was used. This programming language will convert a data into a mat-file that can be integrated in a single datastore, hence the program will execute the data efficiently. In a datastore, many regions can be calculated simultaneously using the big data facility in Matlab. The study shows the calculation using a special data format (mat-file) has good accuracy and fast although in this study multispectral data were used before conversion into normalized difference vegetation index (NDVI).

show abstract

Development of classification system for LULC using remote sensing and GIS

Cited by 91 publications

References 24 publications

Urban modelling and forecasting of landuse using SLEUTH model

Urban modelling and forecasting of landuse using SLEUTH model

Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images

Untitled

Contact Info

Product

Resources

About