With the increasing demand of autonomous systems, pixelwise semantic segmentation for visual scene understanding needs to be not only accurate but also efficient for potential real-time applications. In this paper, we propose Context Aggregation Network, a dual branch convolutional neural network, with significantly lower computational costs as compared to the state-of-the-art, while maintaining a

Tree-crown and height are primary tree measurements in forest inventory. Convolutional neural networks (CNNs) are a class of neural networks, which can be used in forest inventory; however, no prior studies have developed a CNN model to detect tree crown and height simultaneously. This study is the first-of-its-kind that explored training a mask region-based convolutional neural network (Mask R-CNN)

As remote sensing (RS) data obtained from different sensors become available largely and openly, multimodal data processing and analysis techniques have been garnering increasing interest in the RS and geoscience community. However, due to the gap between different modalities in terms of imaging sensors, resolutions, and contents, embedding their complementary information into a consistent, compact

Accurate estimations of daily mean land surface temperature (LST) are important for investigating the urban heat island effect, land-atmosphere energy exchanges, and global climate change. Moderate Resolution Imaging Spectroradiometer (MODIS) sensors can provide up to four instantaneous LSTs of a single day across the world. However, numerous studies, such as those on climate change and hydrology,

Accurate and high-resolution spatio-temporal information about crop phenology obtained from Synthetic Aperture Radar (SAR) data is an essential component for crop management and yield estimation at a local scale. Crop growth monitoring studies seldom exploit complete polarimetric information contained in dual-pol GRD SAR data. In this study, we propose three polarimetric descriptors: the pseudo scattering-type

Synthetic aperture radar (SAR) has great potential for timely monitoring of flood information as it penetrates the clouds during flood events. Moreover, the proliferation of SAR satellites with high spatial and temporal resolution provides a tremendous opportunity to understand the flood risk and its quick response. However, traditional algorithms to extract flood inundation using SAR often require

To derive shallow water bathymetry for coastal areas, a common approach is to deploy a scanning airborne bathymetric light detection and ranging (LiDAR) system or a shipborne echosounder for ground surveys. However, recent advancements in satellite remote sensing, including the Ice, Cloud and land Elevation Satellite-2 (ICESat-2) offer new tools for generating satellite derived bathymetry (SDB). The

A quarry failure along the slopes of the Wai Khar open-pit jade mine in Hpakant, Myanmar has led to the deaths of at least 172 jade miners on 2 July 2020. This paper conducts a systematic investigation of the incident by integrating data from multiple sensors, including high-resolution optical imagery, Sentinel-1 synthetic aperture radar (SAR) images, unmanned aerial system (UAS) footage, SRTM and

Semantic segmentation of 3D Light Detection and Ranging (LiDAR) indoor point clouds using deep learning has been an active topic in recent years. However, most deep neural networks on point clouds conduct multi-level feature fusion via a simple U-shape architecture, which lacks enough capacity on both classification and localization in the segmentation task. In this paper, we propose a Neural Architecture

The canopy bidirectional reflectance distribution function (BRDF) plays a pivotal role in estimating the biophysical parameters of plants, whereas soil background anisotropy creates challenges for their retrieval. Soil optical properties affect canopy anisotropic characteristics, especially in open-canopy areas. However, the remote sensing of background anisotropy is challenging due to the difficulties

Semantic segmentation is an essential part of deep learning. In recent years, with the development of remote sensing big data, semantic segmentation has been increasingly used in remote sensing. Deep convolutional neural networks (DCNNs) face the challenge of feature fusion: very-high-resolution remote sensing image multisource data fusion can increase the network’s learnable information, which is

Urban trees exhibit a wide range of ecosystem services that have long been unveiled and increasingly reported. The ability to map tree species and analyze tree health conditions would become vividly essential. Remote sensing techniques, especially hyperspectral imaging, are being evolved for species identification and vegetation monitoring from spectral reponse patterns. In this study, a hyperspectral

The thick cloud coverage phenomenon severely disturbs optical satellite observation missions (covering approximately 40–60% areas in the global scale). Therefore, the manner by which to eliminate thick cloud in remote sensing imagery is greatly significant and indispensable. In this study, we combine the deep spatio-temporal prior with low-rank tensor singular value decomposition (DP-LRTSVD) for thick

High-temperature anomalies (HTAs) of the earth's surface, such as fires, volcanic activities, and industrial heat sources, have a profound impact on Earth's system. Sentinel-2 Multispectral Instrument (MSI) provides spatially-specific information for precisely measuring the location and extent of HTAs at a fine scale. However, detecting HTAs from MSI images remains challenging because the emitted radiance

Deep learning methods have achieved the state-of-the-art performance of object detection and tracking in natural images, such as keypoint-based detectors and appearance/motion-based trackers. However, for small and blurry moving vehicles in satellite videos, keypoint-based detectors cause the missed detection of keypoints and incorrect keypoint matching. In terms of multi-object tracking, it is difficult

Indoor map is a fundamental element of indoor location-based services (ILBS). However, traditional indoor mapping techniques are labor-intensive and time-consuming. The advancement of smartphones offers great opportunities for crowdsourcing-based indoor mapping, which is one of the most promising applications due to its low cost and flexibility. Over the last decade, many crowdsourcing-based indoor

Automatic change detection from remotely sensed imagery is extremely important for many applications, including land use mapping. In recent years, a growing number of researchers have applied capable deep-learning methods to the research on change detection. The majority of deep learning-based change detection methods currently perform pixel-by-pixel classification at the original image scale, but

Aerial scene recognition is a fundamental visual task and has attracted an increasing research interest in the last few years. Most of current researches mainly deploy efforts to categorize an aerial image into one scene-level label, while in real-world scenarios, there often exist multiple scenes in a single image. Therefore, in this paper, we propose to take a step forward to a more practical and

Change detection in remote sensing images aims to accurately determine any significant land surface changes based on acquired multi-temporal image data, being a pivotal task of remote sensing image processing. Over the past few years, owing to its powerful learning and expression ability, deep learning has been widely applied in the general field of image processing and has demonstrated remarkable

Vectorized reconstruction from indoor point cloud has attracted increasing attention in recent years due to its high regularity and low memory consumption. Compared with aerial mapping of outdoor urban environments, indoor point cloud generated by LiDAR scanning or image-based 3D reconstruction usually contain more clutter and missing areas, which greatly increase the difficulty of vectorized reconstruction

The extensive amount of Earth observation satellite images available brings opportunities and challenges for land mapping in global and regional scales. These large datasets have motivated the use of satellite image time series analysis coupled with machine learning techniques to produce land use and cover class maps. To be successful, these methods need good quality training samples, which are the

Land use as contained in geospatial databases constitutes an essential input for different applications such as urban management, regional planning and environmental monitoring. In this paper, a hierarchical deep learning framework is proposed to verify the land use information. For this purpose, a two-step strategy is applied. First, given high-resolution aerial images, the land cover information

Semantic labeling is an essential but challenging task when interpreting point clouds of 3D scenes. As a core step for scene interpretation, semantic labeling is the task of annotating every point in the point cloud with a label of semantic meaning, which plays a significant role in plenty of point cloud related applications. For airborne laser scanning (ALS) point clouds, precise annotations can considerably

The glacier environment in the Namcha Barwa–Gyala Peri (NBGP) massif is regarded as one of the most sensitive areas to climate change, yet the change estimates remain inadequate due to the limited knowledge of the complex debris-covered glacier environment and the lack of available remote sensing data caused by continuously cloudy weather. To examine the changes of the complex glacial environment,

Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing methods simply stack different point attributes/modalities (e.g. coordinates, intensity, depth, etc.) as image channels to increase information capacity, but ignore

A recent development in Interferometric Synthetic Aperture Radar (InSAR) technology is integrating multiple SAR satellite data to dynamically extract ground features. This paper addresses two relevant challenges: identification of common ground targets from different SAR datasets in space, and concatenation of time series when dealing with temporal dynamics. To address the first challenge, we describe

Semantic segmentation in 3D point-clouds plays an essential role in various applications, such as autonomous driving, robot control, and mapping. In general, a segmentation model trained on one source domain suffers a severe decline in performance when applied to a different target domain due to the cross-domain discrepancy. Various Unsupervised Domain Adaptation (UDA) approaches have been proposed

Estimating future temporal patterns of Surface Urban Heat Islands (SUHIs) on multiple time scales is an ongoing research endeavor. Among these time scales, estimation of next-day SUHIs is of special significance to urban residents, yet we currently lack a simple but efficient approach for making such estimations. In the present study, we propose a statistical strategy for estimating next-day nighttime

Field-scale crop monitoring is essential for agricultural management and policy making for food security and sustainability. Automating crop classification process while elaborating a workflow is a key step for reliable and precise crop mapping. This study aims to develop an approach for crop classification in the state of Rio Grande do Sul, Brazil, following the specific goals of i) evaluating spatial

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global encoder network (LGENet) for semantic segmentation of ALS point clouds. Adapting the KPConv network, we first extract features by both 2D and 3D point convolutions

Image compression usually includes two important operations: compression and decompression. The compression process includes the operation of discarding information, while the decompression process is to retrieve the lost information. In order to make the decompressed image more similar to the original image, the classic compression methods generally adopt the process of approximately reversible compression

Very high-resolution satellite images (VHRSIs) with improved spatial resolution provide unprecedented opportunities to explore the geometric and semantic information of the world. Accordingly, to compensate for the bias of exterior orientation parameters, bundle adjustment of VHRSIs is required. Owing to the sparse points, the bundle adjustment of a few VHRSIs omits high-frequency errors and attitude

Video object detection is a fundamental research task for scene understanding. Compared with object detection in images, object detection in videos has been less researched due to shortage of labelled video datasets. As frames in a video clip are highly correlated, a larger quantity of video labels are needed to have good data variation, which are not always available as the labels are much more expensive

Common aquatic remote sensing algorithms estimate the trophic state (TS) of inland and nearshore waters through the inversion of remote sensing reflectance (Rrs (λ)) into chlorophyll-a (chla) concentration. In this study we present a novel method that directly inverts Rrs (λ) into TS without prior chla retrieval. To successfully cope with the optical diversity of inland and nearshore waters the proposed

Timely and reliable information about irrigated croplands is important for crop water stress analysis and studies of water, energy, and food security. This study mapped irrigated and non-irrigated corn at 30 m resolution for the state of Nebraska using a two-step multi-temporal image classification of MODIS and Landsat Analysis Ready Data (ARD). Starting from the drought year of 2012, when there was

The automatic semantic segmentation of the huge amount of acquired remote sensing data has become an important task in the last decade. Images and Point Clouds (PCs) are fundamental data representations, particularly in urban mapping applications. Textured 3D meshes integrate both data representations geometrically by wiring the PC and texturing the surface elements with available imagery. We present

Indoor semantic segmentation is a long-standing vision task that has been recently advanced by convolutional neural networks (CNNs), but this task remains challenging by high occlusion and large scale variation of indoor scenes. Existing CNN-based methods mainly focus on using auxiliary depth data to enrich features extracted from RGB images, hence, they pay less attention to exploiting multi-scale

Photogrammetry is increasingly being used to characterize rock slope hazards in mountainous environments. With growth in the amount of point cloud data being collected, there is a need for algorithmic and rapid point cloud interpretation methods to prepare the data for engineering analysis. However, there is a lack of semantic segmentation literature focused on geological datasets and the potential

Forest managers demand reliable and cost-efficient methodologies to implement forest resilience concepts in post-fire decision-making at different spatio-temporal scales. In this paper, we developed a generalizable remote sensing-based tool to measure disturbance impact and engineering resilience at short-term in forest ecosystems affected by wildland fires. The case study was a mixed-severity wildfire

Unmanned Aerial Vehicles (UAVs) have become an essential photogrammetric measurement as they are affordable, easily accessible and versatile. Aerial images captured from UAVs have applications in small and large scale texture mapping, 3D modelling, object detection tasks, Digital Terrain Model (DTM) and Digital Surface Model (DSM) generation etc. Photogrammetric techniques are routinely used for 3D

The reconstruction of level-of-detail 2 (LOD-2) buildings has drawn considerable attention over the past two decades. Since completely automatic reconstruction approaches still face many difficulties in industry solutions, efficient and robust interactive modeling tools are of huge demand. This paper proposes an interactive LOD-2 modeling approach that can generate boundary-precise and topology-correct

Winter wheat is one of the most important staple crops in the world. Accurate and timely information on the spatial distribution and temporal change of winter wheat is critical for food security and environmental sustainability. Multi-temporal images and time series data of medium resolution are widely used in winter wheat mapping. However, relatively long revisit times and image noise often result

Remote sensing methods which produce point clouds, such as terrestrial laser scanning (TLS), terrestrial photogrammetry (TP), and small unmanned aerial systems (sUAS) have become an integral component of geotechnical monitoring programs. Applications such as rock-slope monitoring benefit from multi-platform datasets to be acquired in two or more different epochs. Accurate registration of these datasets

Crowd-sourced geographic information has great potential in scientific and public domains, and is recently under consideration by geospatial professionals as an alternative to traditional spatial data collection. The success, however, implies a need to build long-term reliance on the crowd-sourcing projects, and poses growing concern over the quality of the constantly evolving data. In general, we

Functional zones are the basic units of cities and the mapping work is fundamental to urban management, investigation, and research. The existing urban functional zone (UFZ) mapping methods usually utilize visual features from high spatial resolution optical images, and focus on two-dimensional image features, such as texture and landscape. However, UFZ is a comprehensive concept including geographical

Road extraction is to automatically label the pixels of roads in satellite imagery with specific semantic categories based on the extraction of the topographical meaningful features. For governments, timely and accurate road mapping is crucial to plan infrastructure development and mobilize relief around the world. Recent advances in deep learning have shown their dominance on road extraction from

Abandoned houses (AH) are focal points in urban communities by threatening local security, destroying housing markets, and burdening government finance in the U.S. legacy cities. In particular, individual-level AH detection provides essential information for fine-resolution urban studies, government decision-makers, and private sector practitioners. However, three primary conventional data sources

The Near Surface Concentrations (NSC) of O3, CO, and NO2 are crucial worldwide indicators of air quality. However, current frameworks devised for the estimation of the NSC of O3, CO, and NO2 have defects, such as coarse spatial resolution and large missing coverage. To address this issue, this study aims to estimate the daily (~13:30 local time) full-coverage NSC of O3, CO, and NO2 at a high spatial

Individual tree extraction from urban mobile laser scanning (MLS) point clouds is important for many urban applications. Recently, deep learning-based semantic segmentation of urban MLS point clouds has achieved significant progress, which makes it possible to segment tree point clouds. However, tree segments often are spatially overlapping with varying shapes and incompleteness caused by occlusion

Road detection from very high-resolution (VHR) remote sensing imagery is of great importance in a broad array of applications. However, the most advanced deep learning based methods often produce fragmented road segments, due to the complex backgrounds of the images, such as the occlusions and shadows caused by trees and buildings, or the surrounding objects with similar textures. In this research

Land Surface Temperature (LST) is a fundamental state variable for land surface processes, long available from satellite observations in the thermal infrared. Here we make an assessment of LST products derived from the Spinning Enhanced Visible and Infrared Imager (SEVIRI) on-board the geostationary satellite Meteosat Second Generation (MSG), and from the Advanced Very High Resolution Radiometer (AVHRR)

Change detection plays a crucial role in observing earth surface transition and has been widely investigated using deep learning methods. However, the current deep learning methods for pixel-wise change detection still suffer from limited accuracy, mainly due to their insufficient feature extraction and context aggregation. To address this limitation, we propose a novel Cross Layer convolutional neural

This paper introduces five new density and accuracy metrics for aerial point clouds that address the complexity and objectives of modern, dense laser scans of urban scenes. The five metrics describe (1) vertical surface density (points per area on vertical surfaces); (2) vertical density as a function of horizontal density; (3) vertical surface accuracy; and a decomposition of error into (4) within-pass

Plant diversity safeguards wetland ecosystem functions, stability, and resilience, but is threatened by habitat loss and degradation. Remote sensing could support the cost-effective management of biodiversity by providing consistent and frequent data at large scales. While identifying individual species from remote sensing datasets with low spatial and spectral resolution is challenging, studies can

Accurate crop type mapping provides numerous benefits for a deeper understanding of food systems and yield prediction. Ever-increasing big data, easy access to high-resolution imagery, and cloud-based analytics platforms like Google Earth Engine have drastically improved the ability for scientists to advance data-driven agriculture with improved algorithms for crop type mapping using remote sensing