Assessment of Multi-Temporal Image Fusion  for Remote Sensing Application

Yuhendra,; Sumantyo, Joshapat Tetuko Sri

doi:10.18517/ijaseit.7.3.1676

Cited by 4 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evaluating the mosaic product were performed with both of direct measurement on each method and comparing the mosaic results to a reference image. Visual assessment involve subjective factors and personal preference that can influence the results of the evaluation [20] Direct measurements performed with visual assessment, horizontal and vertical profile analysis. The horizontal and vertical profile are better than visual assessment to illustrate and compare the similarities and differences between morphometric [21].…”

Section: Accuracy Assessmentmentioning

confidence: 99%

An Analysis of Black Fill Artefacts Noise Removal on GRD Products Sentinel-1 Data

Dyatmika¹,

Sambodo²,

Arief³

2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) is an active remote sensing satellite which is able to acquire cloud free images in all weather conditions. It is also capable of night time operation. Sentinel-1 data is one of SAR data which is good for monitoring natural resources in area with high cloud cover throughout the year. Processing the data until mosaic product needs good methods and right procedure. An highlight processes to remove noise through border of GRD data scene necessary to do because the processing chain from raw data into L1 GRD (Ground Range Detected) products were leading to artefacts at the near and far range image borders. The artefacts were not visible at a glance in the raw data but, observable clearly after performing mosaic a sets of data. Some methods to fix the problem are available to use such as common noise removal methods. This paper analysed methods to do noise removal i.e. using a tool in ESA's provided Sentinel-1 software (Sentinel Application Platform -SNAP) and proposed noise removal method using simple thresholding and segmentation process. The mosaic products results from both method shown good results visually but the detailed histogram shown that the S-1 Remove GRD Border Noise results still have a very low value pixels in the black-fill area while the Random Noise Removal removed all of the noise. PSNR of raw data mosaic, GRD Border Noise and Random Noise Removal results sequentially 8.5, 18.6 and 19.7 dB indicated that Random Noise Removal get the highest similarity to reference data.

show abstract

Section: Accuracy Assessmentmentioning

confidence: 99%

An Analysis of Black Fill Artefacts Noise Removal on GRD Products Sentinel-1 Data

Dyatmika¹,

Sambodo²,

Arief³

2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…The Kappa coefficient is based on the consistency of the assessment by considering all aspects. There are several accuracy assessment percentages that can be calculated, including accuracy (omission error), user accuracy (commission error) and overall accuracy obtained from the error matrix or confusion matrix (Yuhendra, 2017;Baumann et al, 2012;Bargiel, 2017). Through matrix error (confusion matrix), user accuracy, the producer's accuracy, overall accuracy, the Kappa coefficient (Kappa coefficient) can be obtained mathematically in the following ways.…”

Section: Accuracy Assessmentmentioning

confidence: 99%

“…Satellite data and high-resolution imagery (Landsat, Sentinel, Spot, QuickBird) help to overcome certain limitations of RS by improving processes like image sharpening, classification of land, detection of changes and object identification. Recently, high-resolution RS data are considered indispensable for monitoring essential aspects of the Earth's surfaces (Li et al, 2011;Yuhendra, 2017;Yuhendra et al, 2012). For the highresolution image, an optical image from Sentinel-2 is used along with the SAR image from Sentinel 1A.…”

Section: Introductionmentioning

confidence: 99%

“…Due to the limitations of optical SAR image processing, scientists are increasing efforts to refine and improve remote sensing (Segl et al, 2015;Wang et al, 2016;Fernández-Manso et al, 2016;Immitzer et al, 2016;Novelli et al, 2016;Storey et al, 2016;Van der Werff and Van der Meer, 2016). In image fusion applications, the fusion of sensor data can help RS perform better at classifying land, detecting changes, identifying objects, segmenting images, updating maps and monitoring hazards (Li et al, 2011;Yuhendra, 2017;Yuhendra et al, 2012). This research examines multitemporal Sentinel-1 (SAR) and Sentinel-2 (Optical) satellite data, for land cover mapping and classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Temporal Sentinel-2 Images for Classification Accuracy

Yuhendra¹,

Yulianti²

2019

Journal of Computer Science

View full text Add to dashboard Cite

The term 'multi-temporal' refers to data recorded by sensors scanning the same scene at different dates and times. In this research, Sentinel-2A images were selected for the analyses. Sentinel-2 is a very new program of the European Space Agency (ESA) designed for fine spatial resolution global monitoring. Land Cover-Land Use (LCLU) classification tasks can take advantage of the fusion of radar and optical remote sensing data, generally leading to increased mapping accuracy. Here we propose a methodological approach to fuse information from the new European Space Agency Sentinel-1 and Sentinel-2 imagery for accurate land cover mapping of a portion of the South Solok region, West Sumatra. Data pre-processing used the European Space Agency's Sentinel Application Platform and the SEN2COR toolboxes. The two main objectives of this study are to evaluate the potential use and synergetic effects of ESA Sentinel-1A C-band SAR and Sentinel-2A Optical data for classification and mapping of LCLU. First, the pre-processing chain supported by sensor-specific toolboxes developed by ESA represents a reliable and fast approach for the preparation of ready-to-process imagery. Second, an investigation to derive a methodological framework to integrate Sentinel-1 and Sentinel-2 imagery for land cover mapping by integrating radar and optical imagery has been set up and tested. The results of object-based classification produced higher accuracy than pixel-based classifications if the same type of classifier is used. The classifier algorithms using k-Nearest Neighbors (k-NN) function performed slightly better, with an overall accuracy of 91.30%.

show abstract

“…Being located near volcanoes provides high enthalpy values in terms of the geothermal energy potential. The geothermal resource refers to the amount of geothermal heat that can be generated if specific technological and economic conditions are met [3]. The Indonesian government stated at the 2000 World Geothermal congress that there were 276 locations that could be used for geothermal energy production.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Landsat 8 TIRS data capability for the preliminary study of geothermal energy resources in West Sumatra

Yuhendra¹,

Sumantyo²

2020

TELKOMNIKA

View full text Add to dashboard Cite

West Sumatra is one of has big geothermal energy resources potential. Remote sensing technology can have a role in geothermal exploration activity to measure the distribution of land surface temperatures (LST) and predict the geothermal potential area. Main study to obtain the assessment of Landsat 8 TIRS (Landsat`s Thermal Infrared Sensor) data capability for geothermal energy resources estimation. Mono-window algorithms were used to generate the LST maps. Data set was combined with a digital elevation model (DEM) to identify the potential geothermal energy based on the variation in surface temperature. The result that were derived from LST map of West Sumatra shows that ranged from -8.6 C 0 to 32.59 C 0 and the different temperatures are represented by a graduated pink to brown shading. A calculated result clearly identifies the hot areas in the dataset, which are brown in colour images. Lima Puluh Kota, Tanah Datar, Solok, and South Solok areas showed the high-temperature value (Brown) in the range of 28.1 C 0 to 32.59 C 0 color in images which means that they possess high potential for generating thermal energy. In contrast, the temperatures were lower (Pink) in the north-eastern areas and the range distribution was from -8.5 C 0 to 5 C 0 .

show abstract

Assessment of Multi-Temporal Image Fusion for Remote Sensing Application

Cited by 4 publications

References 19 publications

An Analysis of Black Fill Artefacts Noise Removal on GRD Products Sentinel-1 Data

An Analysis of Black Fill Artefacts Noise Removal on GRD Products Sentinel-1 Data

Multi-Temporal Sentinel-2 Images for Classification Accuracy

Assessment of Landsat 8 TIRS data capability for the preliminary study of geothermal energy resources in West Sumatra

Contact Info

Product

Resources

About