Land use/land cover in view of earth observation: data sources, input dimensions, and classifiers—a review of the state of the art
read more
Citations
Remote Sensing And Image Interpretation
Recent Applications of Landsat 8/OLI and Sentinel-2/MSI for Land Use and Land Cover Mapping: A Systematic Review
Development of classification system for LULC using remote sensing and GIS
Hyperspectral remote sensing in precision agriculture: present status, challenges, and future trends
References
Random Forests
High-Resolution Global Maps of 21st-Century Forest Cover Change
A land use and land cover classification system for use with remote sensor data
Object based image analysis for remote sensing
Change detection techniques
Related Papers (5)
Production of the Japan 30-m Land Cover Map of 2013–2015 Using a Random Forests-Based Feature Optimization Approach
Frequently Asked Questions (18)
Q2. What are the techniques used in the above study?
The techniques used in 389 above study include image object segmentation and rule based techniques which harness the spectral 390 and spatial attributes of the LiDAR datasets.
Q3. What is the motivation behind the synergy between different datasets?
The motivation behind the synergy of different datasets is to harness the different 119 properties such as spatial, spectral, topographic, texture for improving the accuracy of land cover 120 mapping and temporal for improving the change dynamics.
Q4. What is the significance of a spectral imaging system for LULC?
To overcome the low spectral and spatial resolution, hyperspectral imaging systems have been 260 developed that can detect subtle changes in the spectral ranges, and thus discriminate between 261 vegetation types, crops and other features during LULC classification (Pandey et al. 2018).
Q5. What are the techniques used to improve the accuracy of LULC mapping?
Other techniques such as Principal Component Analysis (PCA), Spectral 560 Mixture Analysis (SMA), Minimum Noise Fraction transformation (MNF), Linear Spectral Unmixing 561 (LSU) Matched filtering techniques (Braswell et al., 2003), have been also applied to reduce the data 562 dimensionality especially of big datasets (either space-borne or air-borne hyperspectral images) for 563 LULC mapping.
Q6. What is the main reason for the use of advanced remote sensing imageries?
With 194 the recent advancement in the space-borne missions, advanced remote sensing imageries with higher 195 spatial resolution are used that achieve higher accuracies nowadays.
Q7. What are the advantages of LiDAR integration for LULC mapping?
Data fusion 425 enhances the information and the composite images are visually more interpretable and better for 426 being used for LULC mapping and achieve higher accuracy than individual data.
Q8. What is the simplest way to detect change in a dynamic urban environment?
Unsupervised change detection in VHR remote 987 sensing imagery–an object-based clustering approach in a dynamic urban environment.
Q9. What did Bartels and Wei (2006) do?
Bartels and Wei (2006) performed LiDAR based maximum 386 likelihood classifications fused with co-registered spectral bands achieving accurate results.
Q10. How did Breiman (2001) 375 use an unsupervised classification algorithm for mapping purposes?
In order to 374 exploit the properties of individual data such as texture, backscattering amplitudes, Breiman (2001) 375 employed an unsupervised classification algorithm for mapping purposes.
Q11. What are the requirements for the downscaling process?
multi-sensors and multi-source 400 remotely sensed images require downscaling process to match the spatial resolution between the all 401 employed images.
Q12. What is the way to generate a meaningful crisp image?
the use of advanced fuzzy approach helps to generate 550 meaningful crisp image objects using segmentation techniques (Kindu et al. 2013).
Q13. What is the cost of using hyperspectral images for mapping?
the use 284 of hyperspectral images has overcome the inability of multispectral images to differentiate the 285 different types within same features (crop types, plant types), and therefore, hyperspectral images 286 have been in use for mapping and change analysis though it is expensive in case of airborne images.
Q14. How many times did Adar et al. 255 (2014) use multispectral and?
Adar et al. 255 (2014) utilised multispectral and hyperspectral images (HyMap) acquired at two or more different 256 times to detect spatial, spectral and temporal changes.
Q15. What is the simplest way to reduce landscape heterogeneity?
Reducing landscape heterogeneity for improved land 939 use and land cover (LULC) classification across the large and complex Ethiopian highlands.
Q16. What is the way to improve the accuracy of the classification of urban areas?
Improved classification accuracy based on the output-level fusion of high-resolution 951 satellite images and airborne LiDAR data in urban area.
Q17. What is the implementation of different remote sensing data according to the user needs and requirements?
The implementation of different remotely sensed data is according 129 to the users' needs and the requirement for large area coverage, high spatial resolution, spectral 130 resolution, temporal resolution or combination of one or more together.
Q18. How many LULC change patterns and dynamic changes have been presented with conventional methods?
114LULC change patterns and dynamic changes have been presented with conventional methods, 115 individual remote sensing data, multi-sensor, multi-source, multi-sensor-temporal data are widely 116 used for assessment and evaluation of LULC change and patterns of the landscape (Figure 2).