Scene Recognition for Complicated UAV Images Based on Land Surface Classification of Superpixel

Variations in climatic pattern due to boundary layer processes at the topoclimatic scale are critical for ecosystems and human activity, including agriculture, fruit harvesting, and animal husbandry. Here, a new method for topoclimate mapping based on land surface temperature (LST) computed from the brightness temperature of Landsat ETM+ thermal bands (band6) is presented. The study was conducted in a coastal lowland area with glacial landforms (Wolin Island). The method presented is universal for various areas, and is based on freely available remote sensing data. The topoclimatic typology obtained was compared to the classical one based on meteorological data. It was proven to show a good sensitivity to changes in topoclimatic conditions (demonstrated by changes in LST distribution) even in flat, agricultural areas with only small variations in topography. The technique will hopefully prove to be a convenient and relatively fast tool that can improve the topoclimatic classification of other regions. It could be applied by local authorities and farmer associations for optimizing agricultural production.

Download Full-text

Terrain-Based Shadow Correction Method for Assessing Supraglacial Features on the Greenland Ice Sheet

Frontiers in Remote Sensing ◽

10.3389/frsen.2021.690474 ◽

2021 ◽

Vol 2 ◽

Author(s):

Sasha. Z. Leidman ◽

Åsa K. Rennermalm ◽

Richard G. Lathrop ◽

Matthew. G. Cooper

Keyword(s):

Land Surface ◽

Greenland Ice Sheet ◽

Correction Method ◽

Correction Coefficient ◽

Digital Elevation ◽

Aerial Vehicle ◽

Sediment Cover ◽

Elevation Model ◽

Uav Images ◽

Gis Software

The presence of shadows in remotely sensed images can reduce the accuracy of land surface classifications. Commonly used methods for removing shadows often use multi-spectral image analysis techniques that perform poorly for dark objects, complex geometric models, or shaded relief methods that do not account for shadows cast on adjacent terrain. Here we present a new method of removing topographic shadows using readily available GIS software. The method corrects for cast shadows, reduces the amount of over-correction, and can be performed on imagery of any spectral resolution. We demonstrate this method using imagery collected with an uncrewed aerial vehicle (UAV) over a supraglacial stream catchment in southwest Greenland. The structure-from-motion digital elevation model showed highly variable topography resulting in substantial shadowing and variable reflectance values for similar surface types. The distribution of bare ice, sediment, and water within the catchment was determined using a supervised classification scheme applied to the corrected and original UAV images. The correction resulted in an insignificant change in overall classification accuracy, however, visual inspection showed that the corrected classification more closely followed the expected distribution of classes indicating that shadow correction can aid in identification of glaciological features hidden within shadowed regions. Shadow correction also caused a substantial decrease in the areal coverage of dark sediment. Sediment cover was highly dependent on the degree of shadow correction (k coefficient), yet, for a correction coefficient optimized to maximize shadow brightness without over-exposing illuminated surfaces, terrain correction resulted in a 49% decrease in the area covered by sediment and a 29% increase in the area covered by water. Shadow correction therefore reduces the overestimation of the dark surface coverage due to shadowing and is a useful tool for investigating supraglacial processes and land cover change over a wide variety of complex terrain.

Download Full-text

Using UAV Multispectral Images for Classification of Forest Burn Severity—A Case Study of the 2019 Gangneung Forest Fire

Forests ◽

10.3390/f10111025 ◽

2019 ◽

Vol 10 (11) ◽

pp. 1025 ◽

Cited By ~ 8

Author(s):

Jung-il Shin ◽

Won-woo Seo ◽

Taejung Kim ◽

Joowon Park ◽

Choong-shik Woo

Keyword(s):

Forest Fire ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Accurate Method ◽

Burn Severity ◽

Spectral Angle Mapper ◽

Before And After ◽

Uav Images ◽

Uav Image

Unmanned aerial vehicle (UAV)-based remote sensing has limitations in acquiring images before a forest fire, although burn severity can be analyzed by comparing images before and after a fire. Determining the burned surface area is a challenging class in the analysis of burn area severity because it looks unburned in images from aircraft or satellites. This study analyzes the availability of multispectral UAV images that can be used to classify burn severity, including the burned surface class. RedEdge multispectral UAV image was acquired after a forest fire, which was then processed into a mosaic reflectance image. Hundreds of samples were collected for each burn severity class, and they were used as training and validation samples for classification. Maximum likelihood (MLH), spectral angle mapper (SAM), and thresholding of a normalized difference vegetation index (NDVI) were used as classifiers. In the results, all classifiers showed high overall accuracy. The classifiers also showed high accuracy for classification of the burned surface, even though there was some confusion among spectrally similar classes, unburned pine, and unburned deciduous. Therefore, multispectral UAV images can be used to analyze burn severity after a forest fire. Additionally, NDVI thresholding can also be an easy and accurate method, although thresholds should be generalized in the future.

Download Full-text

A theory of prior streams as a casual factor of soil occurrence in the riverine plain of South-Eastern Australia

Australian Journal of Agricultural Research ◽

10.1071/ar9500231 ◽

1950 ◽

Vol 1 (3) ◽

pp. 231 ◽

Cited By ~ 62

Author(s):

BW Butler

Keyword(s):

Land Surface ◽

Alluvial Fan ◽

South Eastern ◽

South Wales ◽

Local Soil ◽

Murray River ◽

Eastern Australia ◽

Soil Surveys ◽

South Eastern Australia

A new theory is submitted on the origin of the soil formations in the alluvial plains region of southern New South Wales and Victoria embracing the Murray River and tributaries which has been given the name of the Riverine Plain of South-Eastern Australia. The Riverine Plain is delineated and the climate and physiography of the environment are briefly described. The theory postulates the occurrence of a system of prior streams independent of the present stream pattern; from the activity of this system the present soils and land surface were derived. The formations are discussed in terms of sedimentary array, salinity, and degree of leaching. Figures illustrate the ideal sediment pattern of a prior stream formation, a typical alluvial fan, and a simplified map of the region showing prior and present stream systems. A classification of the named soils from local soil surveys is given in the form of 15 sequences of general catenary relationship. The influence of halomorphism in soil development is discussed with the deduction that solonetzous and solodous soils occur generally throughout the region. The age of prior stream activity is set at late Pleistocene to early Recent.

Download Full-text

Mineral Classification of Land Surface Using Multispectral LWIR and Hyperspectral SWIR Remote-Sensing Data. A Case Study over the Sokolov Lignite Open-Pit Mines, the Czech Republic

Remote Sensing ◽

10.3390/rs6087005 ◽

2014 ◽

Vol 6 (8) ◽

pp. 7005-7025 ◽

Cited By ~ 24

Author(s):

Gila Notesco ◽

Veronika Kopačková ◽

Petr Rojík ◽

Guy Schwartz ◽

Ido Livne ◽

...

Keyword(s):

Remote Sensing ◽

Czech Republic ◽

Land Surface ◽

Remote Sensing Data ◽

Open Pit ◽

Open Pit Mines ◽

The Czech Republic ◽

Sensing Data

Download Full-text

A Continental-Scale Classification of Rainfall Seasonality Regimes in Africa Based on Gridded Precipitation and Land Surface Temperature Products

Journal of Applied Meteorology and Climatology ◽

10.1175/jamc-d-11-024.1 ◽

2011 ◽

Vol 50 (12) ◽

pp. 2504-2513 ◽

Cited By ~ 50

Author(s):

Stefanie M. Herrmann ◽

Karen I. Mohr

Keyword(s):

Surface Temperature ◽

Land Surface Temperature ◽

Land Surface ◽

Driving Forces ◽

Spatial Scales ◽

Wet Season ◽

Continental Scale ◽

Rainfall Seasonality ◽

The Stability

AbstractA classification of rainfall seasonality regimes in Africa was derived from gridded rainfall and land surface temperature products. By adapting a method that goes back to Walter and Lieth’s approach of presenting climatic diagrams, relationships between estimated rainfall and temperature were used to determine the presence and pattern of humid, arid, and dry months. The temporal sequence of humid, arid, and dry months defined nonseasonal as well as single-, dual-, and multiple-wet-season regimes with one or more rainfall peaks per wet season. The use of gridded products resulted in a detailed, spatially continuous classification for the entire African continent at two different spatial resolutions, which compared well to local-scale studies based on station data. With its focus on rainfall patterns at fine spatial scales, this classification is complementary to coarser and more genetic classifications based on atmospheric driving forces. An analysis of the stability of the resulting seasonality regimes shows areas of relatively high year-to-year stability in the single-wet-season regimes and areas of lower year-to-year stability in the dual- and multiple-wet-season regimes as well as in transition zones.

Download Full-text

EXTRACTION OF COASTLINES WITH FUZZY APPROACH USING SENTINEL-1 SAR IMAGE

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

10.5194/isprs-archives-xli-b7-747-2016 ◽

2016 ◽

Vol XLI-B7 ◽

pp. 747-751

Author(s):

N. Demir ◽

M. Kaynarca ◽

S. Oy

Keyword(s):

Standard Deviation ◽

Optical Sensors ◽

Land Surface ◽

Airborne Lidar ◽

Surface Model ◽

Lidar Data ◽

Sar Image ◽

Fuzzy Approach ◽

The Mean

Coastlines are important features for water resources, sea products, energy resources etc. Coastlines are changed dynamically, thus automated methods are necessary for analysing and detecting the changes along the coastlines. In this study, Sentinel-1 C band SAR image has been used to extract the coastline with fuzzy logic approach. The used SAR image has VH polarisation and 10x10m. spatial resolution, covers 57 sqkm area from the south-east of Puerto-Rico. Additionally, radiometric calibration is applied to reduce atmospheric and orbit error, and speckle filter is used to reduce the noise. Then the image is terrain-corrected using SRTM digital surface model. Classification of SAR image is a challenging task since SAR and optical sensors have very different properties. Even between different bands of the SAR sensors, the images look very different. So, the classification of SAR image is difficult with the traditional unsupervised methods. In this study, a fuzzy approach has been applied to distinguish the coastal pixels than the land surface pixels. The standard deviation and the mean, median values are calculated to use as parameters in fuzzy approach. The Mean-standard-deviation (MS) Large membership function is used because the large amounts of land and ocean pixels dominate the SAR image with large mean and standard deviation values. The pixel values are multiplied with 1000 to easify the calculations. The mean is calculated as 23 and the standard deviation is calculated as 12 for the whole image. The multiplier parameters are selected as a: 0.58, b: 0.05 to maximize the land surface membership. The result is evaluated using airborne LIDAR data, only for the areas where LIDAR dataset is available and secondly manually digitized coastline. The laser points which are below 0,5 m are classified as the ocean points. The 3D alpha-shapes algorithm is used to detect the coastline points from LIDAR data. Minimum distances are calculated between the LIDAR points of coastline with the extracted coastline. The statistics of the distances are calculated as following; the mean is 5.82m, standard deviation is 5.83m and the median value is 4.08 m. Secondly, the extracted coastline is also evaluated with manually created lines on SAR image. Both lines are converted to dense points with 1 m interval. Then the closest distances are calculated between the points from extracted coastline and manually created coastline. The mean is 5.23m, standard deviation is 4.52m. and the median value is 4.13m for the calculated distances. The evaluation values are within the accuracy of used SAR data for both quality assessment approaches.

Download Full-text