scholarly journals Gudalur Spectral Target Detection (GST-D): A New Benchmark Dataset and Engineered Material Target Detection in Multi-Platform Remote Sensing Data

2020 ◽  
Vol 12 (13) ◽  
pp. 2145 ◽  
Author(s):  
Sudhanshu Shekhar Jha ◽  
Rama Rao Nidamanuri
Keyword(s):  
Remote Sensing ◽  
Target Detection ◽  
Satellite Imagery ◽  
Hyperspectral Imagery ◽  
Remote Sensing Data ◽  
Benchmark Dataset ◽  
Remote Sensing Imagery ◽  
Sensing Data ◽  
Detection Algorithms ◽  
Reference Target

Target detection in remote sensing imagery, mapping of sparsely distributed materials, has vital applications in defense security and surveillance, mineral exploration, agriculture, environmental monitoring, etc. The detection probability and the quality of retrievals are functions of various parameters of the sensor, platform, target–background dynamics, targets’ spectral contrast, and atmospheric influence. Generally, target detection in remote sensing imagery has been approached using various statistical detection algorithms with an assumption of linearity in the image formation process. Knowledge on the image acquisition geometry, and spectral features and their stability across different imaging platforms is vital for designing a spectral target detection system. We carried out an integrated target detection experiment for the detection of various artificial target materials. As part of this work, we acquired a benchmark multi-platform hyperspectral and multispectral remote sensing dataset named as ‘Gudalur Spectral Target Detection (GST-D)’ dataset. Positioning artificial targets on different surface backgrounds, we acquired remote sensing data by terrestrial, airborne, and space-borne sensors on 20th March 2018. Various statistical and subspace detection algorithms were applied on the benchmark dataset for the detection of targets, considering the different sources of reference target spectra, background, and the spectral continuity across the platforms. We validated the detection results using the receiver operation curve (ROC) for different cases of detection algorithms and imaging platforms. Results indicate, for some combinations of algorithms and imaging platforms, consistent detection of specific material targets with a detection rate of about 80% at a false alarm rate between 10−2 to 10−3. Target detection in satellite imagery using reference target spectra from airborne hyperspectral imagery match closely with the satellite imagery derived reference spectra. The ground-based in-situ reference spectra offer a quantifiable detection in airborne or satellite imagery. However, ground-based hyperspectral imagery has also provided an equivalent target detection in the airborne and satellite imagery paving the way for rapid acquisition of reference target spectra. The benchmark dataset generated in this work is a valuable resourcefor addressing intriguing questions in target detection using hyperspectral imagery from a realistic landscape perspective.

scholarly journals An Unsupervised Algorithm for Change Detection in Hyperspectral Remote Sensing Data Using Synthetically Fused Images and Derivative Spectral Profiles

2017 ◽  
Vol 2017 ◽  
pp. 1-14 ◽  
Author(s):  
Youkyung Han ◽  
Anjin Chang ◽  
Seokkeun Choi ◽  
Honglyun Park ◽  
Jaewan Choi
Keyword(s):  
Remote Sensing ◽  
Change Detection ◽  
Hyperspectral Imagery ◽  
Remote Sensing Data ◽  
Hyperspectral Remote Sensing ◽  
Hyperspectral Images ◽  
Sensing Data ◽  
Detection Algorithms ◽  
Change Detection Algorithms ◽  
Spectral Profiles

Multitemporal hyperspectral remote sensing data have the potential to detect altered areas on the earth’s surface. However, dissimilar radiometric and geometric properties between the multitemporal data due to the acquisition time or position of the sensors should be resolved to enable hyperspectral imagery for detecting changes in natural and human-impacted areas. In addition, data noise in the hyperspectral imagery spectrum decreases the change-detection accuracy when general change-detection algorithms are applied to hyperspectral images. To address these problems, we present an unsupervised change-detection algorithm based on statistical analyses of spectral profiles; the profiles are generated from a synthetic image fusion method for multitemporal hyperspectral images. This method aims to minimize the noise between the spectra corresponding to the locations of identical positions by increasing the change-detection rate and decreasing the false-alarm rate without reducing the dimensionality of the original hyperspectral data. Using a quantitative comparison of an actual dataset acquired by airborne hyperspectral sensors, we demonstrate that the proposed method provides superb change-detection results relative to the state-of-the-art unsupervised change-detection algorithms.

scholarly journals Monitoring of specially protected natural territories of forest-steppe landscapes of the Stavropol upland by means of remote sensing data

2021 ◽  
Vol 27 (1) ◽  
pp. 364-376
Author(s):  
Tigran Shahbazyan
Keyword(s):  
Remote Sensing ◽  
Satellite Imagery ◽  
Satellite Images ◽  
Remote Sensing Data ◽  
Anthropogenic Factors ◽  
Forest Steppe ◽  
Landsat 8 ◽  
Sensing Data ◽  
Ndvi Index ◽  
The Impact

The article considers the methodology of monitoring specially protected natural areas using remote sensing data. The research materials are satellite images of the Landsat 5 and Landsat 8 satellites, obtained from the resource of the US Geological Survey. The key areas of the study were 3 specially protected areas located within the boundaries of the forest-steppe landscapes of the Stavropol upland, the reserves «Alexandrovskiy», «Russkiy Les», «Strizhament». The space survey materials were selected for the period 1991–2020, and the data from the summer seasons were used. The NDVI index is chosen as the method of processing the spectral channels of satellite imagery. To integrate long-term satellite imagery into a single raster image, the method of variance of the variation series for the NDVI index was used. The article describes an algorithm for processing satellite images, which allows us to identify the features of the dynamics of the vegetation state of the studied territory for the period 1991–2020. The bitmap image constructed by means of the variance of the NDVI index was classified by the quantile method, to translate numerical values into classes with qualitative characteristics. There were 4 classes of the territory according to the degree of dynamism of the vegetation state: “stable”, “slightly variable”, “moderately variable”, “highly variable”. The paper highlights the factors of landscape transformation, including natural and anthropogenic ones. In the course of the study, the determining influence of anthropogenic factors of transformation was noted. The greatest impact is on the reserve «Alexandrovskiy», the least on the reserve «Russkiy Les», in the reserve «Strizhament» the impact is expressed locally. The paper identifies the leading anthropogenic factors of vegetation transformation, based on their influence on vegetation.

scholarly journals Analytical review of remote sensing data sources suitable for mapping of land resource in Chernivtsi region

2013 ◽  
pp. 331-338
Author(s):  
J. Smirnov
Keyword(s):  
Remote Sensing ◽  
Key Words ◽  
Spatial Resolution ◽  
Satellite Imagery ◽  
Remote Sensing Data ◽  
Data Sources ◽  
Land Resource ◽  
Land Resources ◽  
Sensing Data ◽  
Analytical Review

In the article described the sources of remote sensing data and analyzed their suitability for involvement in the process Chernivtsi region land resources mapping. Taken into account space surveying systems of different spatial resolution and aerial photographic surveys. As a result, have been identified the best sources of data that can be used in the Chernivtsi region land resources mapping. Key words: land resources, remote sensing, satellite imagery, mapping of land resources, sources of remote sensing data.

Floating marine litter detection algorithms and techniques using optical remote sensing data: A review

2021 ◽  
Vol 170 ◽  
pp. 112675
Author(s):  
Konstantinos Topouzelis ◽  
Dimitris Papageorgiou ◽  
Giuseppe Suaria ◽  
Stefano Aliani
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Optical Remote Sensing ◽  
Marine Litter ◽  
Sensing Data ◽  
Detection Algorithms

scholarly journals Deep-learning-based information mining from ocean remote-sensing imagery

2020 ◽  
Vol 7 (10) ◽  
pp. 1584-1605 ◽  
Author(s):  
Xiaofeng Li ◽  
Bin Liu ◽  
Gang Zheng ◽  
Yibin Ren ◽  
Shuangshang Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Remote Sensing Data ◽  
Information Mining ◽  
Remote Sensing Imagery ◽  
Sensing Data ◽  
Sensing Applications ◽  
Data Archives ◽  
Ocean Remote Sensing ◽  
Learning Frameworks

Abstract With the continuous development of space and sensor technologies during the last 40 years, ocean remote sensing has entered into the big-data era with typical five-V (volume, variety, value, velocity and veracity) characteristics. Ocean remote-sensing data archives reach several tens of petabytes and massive satellite data are acquired worldwide daily. To precisely, efficiently and intelligently mine the useful information submerged in such ocean remote-sensing data sets is a big challenge. Deep learning—a powerful technology recently emerging in the machine-learning field—has demonstrated its more significant superiority over traditional physical- or statistical-based algorithms for image-information extraction in many industrial-field applications and starts to draw interest in ocean remote-sensing applications. In this review paper, we first systematically reviewed two deep-learning frameworks that carry out ocean remote-sensing-image classifications and then presented eight typical applications in ocean internal-wave/eddy/oil-spill/coastal-inundation/sea-ice/green-algae/ship/coral-reef mapping from different types of ocean remote-sensing imagery to show how effective these deep-learning frameworks are. Researchers can also readily modify these existing frameworks for information mining of other kinds of remote-sensing imagery.

scholarly journals A new look at the Butic Canal, Egypt

2021 ◽  
Vol 70 (1) ◽  
pp. 29-38
Author(s):  
Robert Schiestl
Keyword(s):  
Remote Sensing ◽  
Roman Empire ◽  
Digital Elevation Model ◽  
Satellite Imagery ◽  
Nile Delta ◽  
Remote Sensing Data ◽  
Historical Sources ◽  
Sensing Data ◽  
Digital Elevation ◽  
Elevation Model

Abstract. The Butic Canal – a Roman period transversal route across the northern Nile Delta – was the longest artificial watercourse in the Nile Delta, yet it remains very poorly understood. To date, the canal has not yet been verified by archeological excavations. The route of the eastern section of the canal has been indirectly identified based on a linear elevated feature most likely representing earth from the excavation of the canal. This study combines the analysis of historical sources and remote sensing data, such as satellite imagery and the TanDEM-X digital elevation model, in order to discuss its date of construction, route, and functions. Based on the data of the digital elevation model, new constructional features are visible in the eastern delta providing the first detailed route of a Roman-era artificial watercourse in Egypt. It is suggested that the canal's construction is placed in the context of imperial investments in the infrastructure of the eastern part of the Roman empire.

Sign in / Sign up

Export Citation Format

Share Document