Influence of the Mosaicking Algorithm on Sentinel-1 Land Cover Classification Over Rough Terrain

Borlaf-Mena, Ignacio; Badea, Ovidiu; Tanase, Mihai A.

doi:10.1109/igarss47720.2021.9553648

Cited by 3 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, around 19% of the samples predicted as cropland are actually pasture and vice versa. This comes along with findings of other studies which report greater confusion between these classes for C-band pixel-based classifications (Orlikova and Horak, 2019;Borlaf-Mena et al, 2021;Samrat et al, 2021). Lastly, to analyze how much the input dataset really impacts the classification accuracy, we plotted Receiver Operator Characteristics (ROC) curves of both the pseudo-polarimetric data and the standard Sentinel-1 products for selected classes in Figure 15.…”

Section: Figure 13mentioning

confidence: 75%

Polarimetric information content of Sentinel-1 for land cover mapping: An experimental case study using quad-pol data synthesized from complementary repeat-pass acquisitions

Braun

Offermann²

2022

Front. Remote Sens.

View full text Add to dashboard Cite

This work presents a technique to merge two Sentinel-1 image products of complementary polarimetric information (HH/HV and VH/VV) to derive pseudo-polarimetric features, such as polarimetric covariance, but also model-based and eigenvalue-based decompositions and an unsupervised Wishart classification of scattering types. The images were acquired within a 6-day period over Southern Germany and have been processed to mimic an actual quad-pol product. This was analyzed statistically, visually and within several classification processes to get an understanding of how well such a dataset depicts scattering mechanisms and other polarimetric features as inputs for land use and land cover mapping. A systematic comparison with the original dual-polarization product showed an increase in information content and largely feasible polarimetric features. Yet, especially the average Alpha angle was found to be biased and too high for some of the compared surfaces. Despite these inaccuracies, the polarimetric features turned out to improve potential land cover mapping as compared with backscatter intensities and dual-polarization features of the input products alone. Among the most significant variables related to land use and cover reported by an independent dataset, Entropy, the co-polarization ratio and the C22 element of the covariance matrix generated the strongest impact on the class separability, although misclassifications between physically related classes remain. Yet, the findings are encouraging concerning further investigation of the polarimetric potential to combine repeat-pass acquisitions of Sentinel-1 for a better description of more specific types of land cover.

show abstract

Section: Figure 13mentioning

confidence: 75%

Polarimetric information content of Sentinel-1 for land cover mapping: An experimental case study using quad-pol data synthesized from complementary repeat-pass acquisitions

Braun

Offermann²

2022

Front. Remote Sens.

View full text Add to dashboard Cite

show abstract

Assessing the Utility of Sentinel-1 Coherence Time Series for Temperate and Tropical Forest Mapping

2021

View full text Add to dashboard Cite

This study tested the ability of Sentinel-1 C-band to separate forest from other common land use classes (i.e., urban, low vegetation and water) at two different sites. The first site is characterized by temperate forests and rough terrain while the second by tropical forest and near-flat terrain. We trained a support vector machine classifier using increasing feature sets starting from annual backscatter statistics (average, standard deviation) and adding long-term coherence (i.e., coherence estimate for two acquisitions with a large time difference), as well as short-term (six to twelve days) coherence statistics from annual time series. Classification accuracies using all feature sets was high (>92% overall accuracy). For temperate forests the overall accuracy improved by up to 5% when coherence features were added: long-term coherence reduced misclassification of forest as urban, whereas short-term coherence statistics reduced the misclassification of low vegetation as forest. Classification accuracy for tropical forests showed little differences across feature sets, as the annual backscatter statistics sufficed to separate forest from low vegetation, the other dominant land cover. Our results show the importance of coherence for forest classification over rough terrain, where forest omission error was reduced up to 11%.

show abstract

Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data

et al. 2023

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) image is an effective remote sensing data source for geographic surveys. However, accurate land cover mapping based on SAR image in areas of complex terrain has become a challenge due to serious geometric distortions and the inadequate separation ability of dual-polarization data. To address these issues, a new land cover mapping framework which is suitable for complex terrain is proposed based on Gaofen-3 data of ascending and descending orbits. Firstly, the geometric distortion area is determined according to the local incident angle, based on analysis of the SAR imaging mechanism, and the correct polarization information of the opposite track is used to compensate for the geometric distortion area, including layovers and shadows. Then, the dual orbital polarization characteristics (DOPC) and dual polarization radar vegetation index (DpRVI) of dual-pol SAR data are extracted, and the optimal feature combination is found by means of Jeffries–Matusita (J-M) distance analysis. Finally, the deep learning method 2D convolutional neural network (2D-CNN) is applied to classify the compensated images. The proposed method was applied to a mountainous region of the Danjiangkou ecological protection area in China. The accuracy and reliability of the method were experimentally compared using the uncompensated images and the images without DpRVI. Quantitative evaluation revealed that the proposed method achieved better performance in complex terrain areas, with an overall accuracy (OA) score of 0.93, and a Kappa coefficient score of 0.92. Compared with the uncompensated image, OA increased by 5% and Kappa increased by 6%. Compared with the images without DpRVI, OA increased by 4% and Kappa increased by 5%. In summary, the results demonstrate the importance of ascending and descending orbit data to compensate geometric distortion and reveal the effectiveness of optimal feature combination including DpRVI. Its simple and effective polarization information compensation capability can broaden the promising application prospects of SAR images.

show abstract

Influence of the Mosaicking Algorithm on Sentinel-1 Land Cover Classification Over Rough Terrain

Cited by 3 publications

References 12 publications

Polarimetric information content of Sentinel-1 for land cover mapping: An experimental case study using quad-pol data synthesized from complementary repeat-pass acquisitions

Polarimetric information content of Sentinel-1 for land cover mapping: An experimental case study using quad-pol data synthesized from complementary repeat-pass acquisitions

Assessing the Utility of Sentinel-1 Coherence Time Series for Temperate and Tropical Forest Mapping

Classification of Land Cover in Complex Terrain Using Gaofen-3 SAR Ascending and Descending Orbit Data

Contact Info

Product

Resources

About