Remote Sensing Image Processing Techniques Research Articles

A 2D/3D multimodal data simulation approach with applications on urban semantic segmentation, building extraction and change detection

Advances in remote sensing image processing techniques have further increased the demand for annotated datasets. However, preparing annotated multi-temporal 2D/3D multimodal data is especially challenging, both for the increased costs of the annotation step and the lack of multimodal acquisitions available on the same area. We introduce the Simulated Multimodal Aerial Remote Sensing (SMARS) dataset, a synthetic dataset aimed at the tasks of urban semantic segmentation, change detection, and building extraction, along with a description of the pipeline to generate them and the parameters required to set our rendering. Samples in the form of orthorectified photos, digital surface models and ground truth for all the tasks are provided. Unlike existing datasets, orthorectified images and digital surface models are derived from synthetic images using photogrammetry, yielding more realistic simulations of the data. The increased size of SMARS, compared to available datasets of this kind, facilitates both traditional and deep learning algorithms. Reported experiments from state-of-the-art algorithms on SMARS scenes yield satisfactory results, in line with our expectations. Both benefits of the SMARS datasets and constraints imposed by its use are discussed. Specifically, building detection on the SMARS-real Potsdam cross-domain test demonstrates the quality and the advantages of proposed synthetic data generation workflow. SMARS is published as an ISPRS benchmark dataset and can be downloaded from https://www2.isprs.org/commissions/comm1/wg8/benchmark_smars/.

Editorial for the Special Issue “New Advances on Sub-Pixel Processing: Unmixing and Mapping Methods”

Innovative remote sensing image processing techniques have been progressively studied due to the increasing availability of remote sensing images, powerful techniques of data analysis, and computational power [...]

Interaction between sediment transport rate and tectonic activity: the case of Kızılırmak Basin on the tectonically active NAFZ, Turkey

The degree of interaction between sediment transport rate and tectonic activity is a major issue that draws the attention of researchers. Because of the complexity in the modeling process of uplift and subsidence rate, it is quite difficult to determine the rate of interaction between erosion and tectonic activity. In this study, the sediment transport rate of Kizilirmak Basin, which is located on the tectonically active North Anatolian Fault Zone (NAFZ), was investigated to determine the effect of tectonic activity on sediment transport rate. The sediment transport rate of the basin was evaluated by using the drainage channel width, the topographic wetness index (TWI), and the revised universal soil equation (RUSLE) model. The Aster Global Digital Elevation Model (GDEM), Landsat 8 Operational Land Imager (OLI) scenes, a 1:800,000 scale soil map, and 30 years of rainfall records at 41 stations were used for the analysis. The drainage channel width, the TWI, and derivation and grid-based integration of the RUSLE parameters were performed by using GIS (terrain analysis, spatial data analysis) and remote sensing image processing techniques. The relationship among the derived parameters and tectonic activity was evaluated by Getis–Ord $$ {G}_i^{\ast } $$ statistics. The results show that at the 99 and 95% confidence intervals, statistically significant cold spot values of the channel widths, hot spot values of the mean annual soil loss values, and cold spots of the TWI values are more intensely clustered around fault lines. These clustering areas not only indicate the areas where the rate of sediment transport is high, but also the areas where the tectonic activity of the NAFZ is more vigorous.

Slope failure susceptibility zonation using integrated remote sensing and GIS techniques: A case study over Jhingurdah open pit coal mine, Singrauli coalfield, India

The susceptibility of slopes in open pit coal mines to various modes of failure (i.e., plane, wedge, circular and toppling failure) could be envisaged by virtue of processing and analysis of pertinent satellite data. The aim of the present study was to integrate thematic maps generated using remote sensing image processing techniques, in order to finally produce slope failure hazard zonation maps in and around Singrauli coalfield, India. The various failure-inducing factors, variables and parameters can be extracted from different satellite data and imageries. The data acquired by different sensors such as TM, ETM+, etc., of LANDSAT series and CARTOSAT of ISRO Bhuvan was used in this study. All these data were subsequently used to create different thematic maps such as slope map, lithological map, land use/land cover map, principal component analysis map, digital elevation model (DEM), etc. An advanced analysis for extraction of lineament attributes was also undertaken.

Harbor Water Area Extraction From Pan-Sharpened Remotely Sensed Images Based on the Definition Circle Model

Harbor water area extraction is a key step in nearshore environment pollution surveillance using remote sensing image processing techniques. This letter proposes the definition circle (DC) model of color gradient to describe color fluctuations in harbor water surface areas based on pan-sharpened remote sensing images. The DC model includes two steps: center setting and radius tuning. In the center setting process, labeled training set pixels are selected in the red, green, and blue color space. Then, center setting is completed in the hue, saturation, and intensity color space using the perceptron model. In the radius tuning process, positive and negative sample pixels are used to tune the radius value. After these two steps, the DC model can describe the color gradient of a water surface area and provide accurate harbor water area extraction. A series of experiments shows that the proposed DC model is robust and performs better than other extraction methods based on pan-sharpened remote sensing images.

Determination of Kula basalts (geosite) in Turkey using remote sensing techniques

Kula Region (Manisa, Turkey), with its 80 volcanic cones, lava flows, basalt plateaus and basalt columns, fairy chimney formations in canyons carved by the Gediz River, shelter cities hidden in volcanic lava, footprint fossils belonging to the first humans, and geological uniqueness, has a great importance in terms of geotourism potential as it is being a natural heritage in the Aegean region of Anatolia. In this study, some remote sensing image processing techniques such as band combination, band rationing, and principal component analyses were used to depict the cultural and natural geosite known as Kula basalts in Turkey. Satellite images utilized here in this study were Landsat band images (band 1 to band 7). Principal component analyses (PCA) were performed on the first ratio group with 5/4, 5/1, and 3/7 bands and then on the second ratio group with 3/1, 4/5, and 3/2 bands. As a conclusion and outcome of this PCA, it was found that red, green, and blue (RGB) composite with PC1 and PC3 gray-level images from the first ratio group and PC2 gray-level image from the second group showed up the basalt areas better than those from other techniques studied in this research. After unsupervised classification of this final composite of PCA, it is computed that the basalt rocks in Kula cover an area of 36,774 ha totally.

Environmental hazards and distribution of radioactive black sand along the Rosetta coastal zone in Egypt using airborne spectrometric and remote sensing data

High-resolution airborne gamma ray spectrometry, conducted in 2003, was used to estimate radioactive elements spatial abundance along the Rosetta coastal zone area. It was noticed that both Uranium and Thorium are concentrated in the black sand deposits along the beach. In contrary, Potassium was observed in high level abundance at the cultivated Nile Delta lands due to the accumulated usage of fertilizers. Exposure Rate (ER), Absorbed Dose Rate (ADR) and Annual Effective Dose Rate (AEDR) were calculated to evaluate the radiation background influence in human. Results indicated that the human body in the study sites is subjected to radiation hazards exceeds the accepted limit for long duration exposure. In addition, the areas covered by the highest concentration of Uranium and Thorium show the highest level of radiogenic heat production. Detection the environmental hazards of the radioactive black sands in the study site encouraged this research to monitor the spatial and temporal distribution of these sediments. The Landsat Thematic Mapper images acquired in 1990, 2003 and 2013 were analyzed using remote sensing image processing techniques. Image enhancements, classification and changes detection indicated a positive significant relationship between the patterns of coastline changes and distribution of the radioactive black sand in the study sites. The radioactive black sands are usually concentrated in the eroded areas. Therefore, in 1990 high concentration of the radioactive black sands were observed along the eastern and western flanks of the Rosetta promontory. Distribution of these sediments decreased due to the construction of the protective sea walls. Most of the radioactive black sands are transported toward the east in Abu Khashaba bay under the effect of the longshore currents and toward the west in Alexandria and Abu Quir bay under the action of the seasonal reverse currents.

Remote sensing-based analysis of the planform changes in the Upper Amazon River over the period 1986–2006

An analysis of the planform changes of the Colombian reach of the Amazon River was carried out over a period of 19.9 years. Remote sensing image processing techniques were applied to Landsat images acquired in 1986, 1994, 2001 and, 2006. These images were selected based on minimal daily water level variations, while providing the widest temporal span. Plan view river changes and geomorphologic characteristics were examined to identify which channel pattern classification best represents this large tropical river system. Discharge was also analyzed to determine whether changes in the river's plan view are a direct response to variations in discharge. The system had a depositional tendency between 1986 and 2006, with a period where erosion was more intense than deposition between 1994 and 2001. Percent change in the plan view area of the system (1.4% yr−1) and the maximum migration rates (125 m yr−1) suggest that this reach of the Amazon is less active than reaches upstream and the downstream reach between the confluences of the Jutaí and Japurá Rivers. Variations in discharge appear to be responsible for deposition and erosion dynamics observed after this remote sensing analysis in the Colombian reach of the Amazon River. Characteristics including multiple channels with vegetated islands developed from within-channel deposition, meandering planform, lateral activity of channel margins, and the absence of islands with saucer-like morphology suggest a multichannel, meandering pattern for this reach of the Amazon, that corresponds to a laterally active anabranching river.