MDPI - Publisher of Open Access Journals

18 pages, 11514 KiB

Open AccessArticle

Remote-Sensing Cross-Domain Scene Classification: A Dataset and Benchmark

by Kang Liu, Jian Yang and Shengyang Li

Remote Sens. 2022, 14(18), 4635; https://doi.org/10.3390/rs14184635 - 16 Sep 2022

Cited by 8 | Viewed by 3425

Domain adaptation for classification has achieved significant progress in natural images but not in remote-sensing images due to huge differences in data-imaging mechanisms between different modalities and inconsistencies in class labels among existing datasets. More importantly, the lack of cross-domain benchmark datasets has become a major obstacle to the development of scene classification in multimodal remote-sensing images. In this paper, we present a cross-domain dataset of multimodal remote-sensing scene classification (MRSSC). The proposed MRSSC dataset contains 26,710 images of 7 typical scene categories with 4 distinct domains that are collected from Tiangong-2, a Chinese manned spacecraft. Based on this dataset, we evaluate several representative domain adaptation algorithms on three cross-domain tasks to build baselines for future research. The results demonstrate that the domain adaptation algorithm can reduce the differences in data distribution between different domains and improve the accuracy of the three tasks to varying degrees. Furthermore, MRSSC also achieved fairly results in three applications: cross-domain data annotation, weakly supervised object detection and data retrieval. This dataset is believed to stimulate innovative research ideas and methods in remote-sensing cross-domain scene classification and remote-sensing intelligent interpretation. Full article

► Show Figures

Figure 1

94 pages, 38060 KiB

Open AccessEditor’s ChoiceArticle

Recognition of Sedimentary Rock Occurrences in Satellite and Aerial Images of Other Worlds—Insights from Mars

by Kenneth S. Edgett and Ranjan Sarkar

Remote Sens. 2021, 13(21), 4296; https://doi.org/10.3390/rs13214296 - 26 Oct 2021

Cited by 18 | Viewed by 13442

Abstract

Sedimentary rocks provide records of past surface and subsurface processes and environments. The first step in the study of the sedimentary rock record of another world is to learn to recognize their occurrences in images from instruments aboard orbiting, flyby, or aerial platforms. For two decades, Mars has been known to have sedimentary rocks; however, planet-wide identification is incomplete. Global coverage at 0.25–6 m/pixel, and observations from the Curiosity rover in Gale crater, expand the ability to recognize Martian sedimentary rocks. No longer limited to cases that are light-toned, lightly cratered, and stratified—or mimic original depositional setting (e.g., lithified deltas)—Martian sedimentary rocks include dark-toned examples, as well as rocks that are erosion-resistant enough to retain small craters as well as do lava flows. Breakdown of conglomerates, breccias, and even some mudstones, can produce a pebbly regolith that imparts a “smooth” appearance in satellite and aerial images. Context is important; sedimentary rocks remain challenging to distinguish from primary igneous rocks in some cases. Detection of ultramafic, mafic, or andesitic compositions do not dictate that a rock is igneous, and clast genesis should be considered separately from the depositional record. Mars likely has much more sedimentary rock than previously recognized. Full article

(This article belongs to the Special Issue Mars Remote Sensing)

► Show Figures

Figure 1

16 pages, 5423 KiB

Open AccessArticle

Estimation of Noise in the In Situ Hyperspectral Data Acquired by Chang’E-4 and Its Effects on Spectral Analysis of Regolith

by Honglei Lin, Yangting Lin, Yong Wei, Rui Xu, Yang Liu, Yazhou Yang, Sen Hu, Wei Yang and Zhiping He

Remote Sens. 2020, 12(10), 1603; https://doi.org/10.3390/rs12101603 - 18 May 2020

Cited by 7 | Viewed by 3837

Abstract

The Chang’E-4 (CE-4) spacecraft landed successfully on the far side of the Moon on 3 January 2019, and the rover Yutu-2 has explored the lunar surface since then. The visible and near-infrared imaging spectrometer (VNIS) onboard the rover has acquired numerous spectra, providing unprecedented insight into the composition of the lunar surface. However, the noise in these spectral data and its effects on spectral interpretation are not yet assessed. Here we analyzed repeated measurements over the same area at the lunar surface to estimate the signal–noise ratio (SNR) of the VNIS spectra. Using the results, we assessed the effects of noise on the estimation of band centers, band depths, FeO content, optical maturity (OMAT), mineral abundances, and submicroscopic metallic iron (SMFe). The data observed at solar altitudes <20° exhibit low SNR (25 dB), whereas the data acquired at 20°–35° exhibit higher SNR (35–37 dB). We found differences in band centers due to noise to be ~6.2 and up to 28.6 nm for 1 and 2 μm absorption, respectively. We also found that mineral abundances derived using the Hapke model are affected by noise, with maximum standard deviations of 6.3%, 2.4%, and 7.0% for plagioclase, pyroxene, and olivine, respectively. Our results suggest that noise has significant impacts on the CE-4 spectra, which should be considered in the spectral analysis and geologic interpretation of lunar exploration data. Full article

(This article belongs to the Special Issue Lunar Remote Sensing and Applications)

► Show Figures

Graphical abstract

Search Results (3)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (3)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI