A review on deep learning in UAV remote sensing Osco, Lucas Prado; Marcato Junior, José; Marques Ramos, Ana Paula ...
International journal of applied earth observation and geoinformation,
October 2021, 2021-10-00, 2021-10-01, Letnik:
102
Journal Article
Recenzirano
Odprti dostop
•Combining deep learning and UAV-based data is an emerging trend in remote sensing.•Most articles published rely on CNN-based methods.•Future perspectives in UAV-based data processing still have much ...to cover.
Deep Neural Networks (DNNs) learn representation from data with an impressive capability, and brought important breakthroughs for processing images, time-series, natural language, audio, video, and many others. In the remote sensing field, surveys and literature revisions specifically involving DNNs algorithms’ applications have been conducted in an attempt to summarize the amount of information produced in its subfields. Recently, Unmanned Aerial Vehicle (UAV)-based applications have dominated aerial sensing research. However, a literature revision that combines both “deep learning” and “UAV remote sensing” thematics has not yet been conducted. The motivation for our work was to present a comprehensive review of the fundamentals of Deep Learning (DL) applied in UAV-based imagery. We focused mainly on describing the classification and regression techniques used in recent applications with UAV-acquired data. For that, a total of 232 papers published in international scientific journal databases was examined. We gathered the published materials and evaluated their characteristics regarding the application, sensor, and technique used. We discuss how DL presents promising results and has the potential for processing tasks associated with UAV-based image data. Lastly, we project future perspectives, commentating on prominent DL paths to be explored in the UAV remote sensing field. This revision consisting of an approach to introduce, commentate, and summarize the state-of-the-art in UAV-based image applications with DNNs algorithms in diverse subfields of remote sensing, grouping it in the environmental, urban, and agricultural contexts.
As a fundamental and important task in remote sensing, remote sensing image scene understanding (RSISU) has attracted tremendous research interest in recent years. RSISU includes the following ...sub-tasks: remote sensing image scene classification, remote sensing image scene retrieval, and scene-driven remote sensing image object detection. Although these sub-tasks have different goals, they share some communal hints. Hence, this paper tries to discuss them as a whole. Similar to other domains (e.g., speech recognition and natural image recognition), deep learning has also become the state-of-the-art technique in RSISU. To facilitate the sustainable progress of RSISU, this paper presents a comprehensive review of deep-learning-based RSISU methods, and points out some future research directions and potential applications of RSISU.
The current superresolution (SR) methods based on deep learning have shown remarkable comparative advantages but remain unsatisfactory in recovering the high-frequency edge details of the images in ...noise-contaminated imaging conditions, e.g., remote sensing satellite imaging. In this paper, we propose a generative adversarial network (GAN)-based edge-enhancement network (EEGAN) for robust satellite image SR reconstruction along with the adversarial learning strategy that is insensitive to noise. In particular, EEGAN consists of two main subnetworks: an ultradense subnetwork (UDSN) and an edge-enhancement subnetwork (EESN). In UDSN, a group of 2-D dense blocks is assembled for feature extraction and to obtain an intermediate high-resolution result that looks sharp but is eroded with artifacts and noises as previous GAN-based methods do. Then, EESN is constructed to extract and enhance the image contours by purifying the noise-contaminated components with mask processing. The recovered intermediate image and enhanced edges can be combined to generate the result that enjoys high credibility and clear contents. Extensive experiments on Kaggle Open Source Data set , Jilin-1 video satellite images, and Digitalglobe show superior reconstruction performance compared to the state-of-the-art SR approaches.
One of the challenging tasks in modern aquatic remote sensing is the retrieval of near-surface concentrations of Total Suspended Solids (TSS). This study aims to present a Statistical, inherent ...Optical property (IOP) -based, and muLti-conditional Inversion proceDure (SOLID) for enhanced retrievals of satellite-derived TSS under a wide range of in-water bio-optical conditions in rivers, lakes, estuaries, and coastal waters. In this study, using a large in situ database (N > 3500), the SOLID model is devised using a three-step procedure: (a) water-type classification of the input remote sensing reflectance (Rrs), (b) retrieval of particulate backscattering (bbp) in the red or near-infrared (NIR) regions using semi-analytical, machine-learning, and empirical models, and (c) estimation of TSS from bbp via water-type-specific empirical models. Using an independent subset of our in situ data (N = 2729) with TSS ranging from 0.1 to 2626.8 g/m3, the SOLID model is thoroughly examined and compared against several state-of-the-art algorithms (Miller and McKee, 2004; Nechad et al., 2010; Novoa et al., 2017; Ondrusek et al., 2012; Petus et al., 2010). We show that SOLID outperforms all the other models to varying degrees, i.e.,from 10 to >100%, depending on the statistical attributes (e.g., global versus water-type-specific metrics). For demonstration purposes, the model is implemented for images acquired by the MultiSpectral Imager aboard Sentinel-2A/B over the Chesapeake Bay, San-Francisco-Bay-Delta Estuary, Lake Okeechobee, and Lake Taihu. To enable generating consistent, multimission TSS products, its performance is further extended to, and evaluated for, other missions, such as the Ocean and Land Color Instrument (OLCI), Moderate Resolution Imaging Spectroradiometer (MODIS), Visible Infrared Imaging Radiometer Suite (VIIRS), and Operational Land Imager (OLI). Sensitivity analyses on uncertainties induced by the atmospheric correction indicate that 10% uncertainty in Rrs leads to <20% uncertainty in TSS retrievals from SOLID. While this study suggests that SOLID has a potential for producing TSS products in global coastal and inland waters, our statistical analysis certainly verifies that there is still a need for improving retrievals across a wide spectrum of particle loads.
•Model (SOLID) is developed for estimating TSS in coastal/inland waters.•Validated with a wide range of trophic/turbidity conditions•Performance is thoroughly gauged against five other models.•Model produces stable performance in optically complex aquatic ecosystems.•Performance is assessed for several satellite missions.
Due to the urgent demand for remote sensing big data analysis, large-scale remote sensing image retrieval (LSRSIR) attracts increasing attention from researchers. Generally, LSRSIR can be divided ...into two categories as follows: uni-source LSRSIR (US-LSRSIR) and cross-source LSRSIR (CS-LSRSIR). More specifically, US-LSRSIR means the inquiry remote sensing image and images in the searching data set come from the same remote sensing data source, whereas CS-LSRSIR is designed to retrieve remote sensing images with a similar content to the inquiry remote sensing image that are from a different remote sensing data source. In the literature, US-LSRSIR has been widely exploited, but CS-LSRSIR is rarely discussed. In practical situations, remote sensing images from different kinds of remote sensing data sources are continually increasing, so there is a great motivation to exploit CS-LSRSIR. Therefore, this paper focuses on CS-LSRSIR. To cope with CS-LSRSIR, this paper proposes source-invariant deep hashing convolutional neural networks (SIDHCNNs), which can be optimized in an end-to-end manner using a series of well-designed optimization constraints. To quantitatively evaluate the proposed SIDHCNNs, we construct a dual-source remote sensing image data set that contains eight typical land-cover categories and 10 000 dual samples in each category. Extensive experiments show that the proposed SIDHCNNs can yield substantial improvements over several baselines involving the most recent techniques.
Central to the looming paradigm shift toward data-intensive science, machine-learning techniques are becoming increasingly important. In particular, deep learning has proven to be both a major ...breakthrough and an extremely powerful tool in many fields. Shall we embrace deep learning as the key to everything? Or should we resist a black-box solution? These are controversial issues within the remote-sensing community. In this article, we analyze the challenges of using deep learning for remote-sensing data analysis, review recent advances, and provide resources we hope will make deep learning in remote sensing seem ridiculously simple. More importantly, we encourage remote-sensing scientists to bring their expertise into deep learning and use it as an implicit general model to tackle unprecedented, large-scale, influential challenges, such as climate change and urbanization.
The application of the convolutional neural network has shown to greatly improve the accuracy of building extraction from remote sensing imagery. In this paper, we created and made open a ...high-quality multisource data set for building detection, evaluated the accuracy obtained in most recent studies on the data set, demonstrated the use of our data set, and proposed a Siamese fully convolutional network model that obtained better segmentation accuracy. The building data set that we created contains not only aerial images but also satellite images covering 1000 km 2 with both raster labels and vector maps. The accuracy of applying the same methodology to our aerial data set outperformed several other open building data sets. On the aerial data set, we gave a thorough evaluation and comparison of most recent deep learning-based methods, and proposed a Siamese U-Net with shared weights in two branches, and original images and their down-sampled counterparts as inputs, which significantly improves the segmentation accuracy, especially for large buildings. For multisource building extraction, the generalization ability is further evaluated and extended by applying a radiometric augmentation strategy to transfer pretrained models on the aerial data set to the satellite data set. The designed experiments indicate our data set is accurate and can serve multiple purposes including building instance segmentation and change detection; our result shows the Siamese U-Net outperforms current building extraction methods and could provide valuable reference.
Cross-modal hashing plays a pivotal role in large-scale remote sensing (RS) ship image retrieval. RS ship images often exhibit similar overall appearance with subtle differences. Existing hashing ...methods typically employ feature non-interaction strategies to generate common hash codes, which may not effectively capture the correlations between cross-modal ship images to reduce inter-modality discrepancies. To address this issue, we propose a novel cross-modal hashing approach based on Feature Semi-Interaction and Semantic Ranking (FSISR) for RS ship image retrieval. Our FSISR approach not only captures intricate correlations between different ship image modalities, but also enables the construction of hash tables for large-scale retrieval. FSISR comprises a feature semi-interaction module and a semantic ranking objective function. The semi-interaction module utilizes clustering centers from one modality to learn the correlations between two modalities and generate robust shared representations. The objective function optimizes these representations in a common Hamming space, consisting of a shared semantic alignment loss and a margin-free ranking loss. The alignment loss employs a shared semantic layer to preserve label-level similarity, while the ranking loss incorporates hard examples to establish a margin-free loss that captures similarity ranking relationships. We evaluate the performance of our method on benchmark datasets and demonstrate its effectiveness for cross-modal RS ship image retrieval. https://github.com/sunyuxi/FSISR.
The Global Precipitation Measurement (GPM) Integrated Multi-satellite Retrievals for GPM (IMERG) products provide quasi-global (60° N–60° S) precipitation estimates, beginning March 2014, from the ...combined use of passive microwave (PMW) and infrared (IR) satellites comprising the GPM constellation. The IMERG products are available in the form of near-real-time data, i.e., IMERG Early and Late, and in the form of post-real-time research data, i.e., IMERG Final, after monthly rain gauge analysis is received and taken into account. In this study, IMERG version 3 Early, Late, and Final (IMERG-E,IMERG-L, and IMERG-F) half-hourly rainfall estimates are compared with gauge-based gridded rainfall data from the WegenerNet Feldbach region (WEGN) high-density climate station network in southeastern Austria. The comparison is conducted over two IMERG 0.1° × 0.1° grid cells, entirely covered by 40 and 39 WEGN stations each, using data from the extended summer season (April–October) for the first two years of the GPM mission. The entire data are divided into two rainfall intensity ranges (low and high) and two seasons (warm and hot), and we evaluate the performance of IMERG, using both statistical and graphical methods. Results show that IMERG-F rainfall estimates are in the best overall agreement with the WEGN data, followed by IMERG-L and IMERG-E estimates, particularly for the hot season. We also illustrate, through rainfall event cases, how insufficient PMW sources and errors in motion vectors can lead to wide discrepancies in the IMERG estimates. Finally, by applying the method of Villarini and Krajewski (2007), we find that IMERG-F half-hourly rainfall estimates can be regarded as a 25 min gauge accumulation, with an offset of +40 min relative to its nominal time.