Search

ABSTRACTAccurately predicting the geometric structure of a building's roof as a vectorized representation from a raster image is a challenging task in building reconstruction. In this paper, we propose an efficient and precise parsing method called Roof-Former, based on a vision Transformer. Our method involves three steps: (1) Image encoder and edge node initialization, (2) Image feature fusion with an enhanced segmentation refinement branch, and (3) Edge filtering and structural reasoning. Our method outperforms previous works on the vectorizing world building dataset and the Enschede dataset, with vertex and edge heat map F1-scores increasing from [Formula: see text], [Formula: see text] to [Formula: see text], [Formula: see text], and from [Formula: see text], [Formula: see text] to [Formula: see text], [Formula: see text], respectively. Furthermore, our method demonstrates superior performance compared to the current state-of-the-art based on qualitative evaluations, indicating its effectiveness in extracting global image information while maintaining the consistency and topological validity of the roof structure.

Abstract Mining has played an important role in the economies of South American countries. Although industrial mining prevails in most countries, the expansion of garimpo activity has increased substantially. Recently, Brazil exhibited two moments of garimpo dominance over industrial mining: 1989–1997 and 2019–2022. While industrial mining sites occupied ~ 360 km2 in 1985 but increased to 1800 km2 in 2022, a 5-fold increase, garimpo mining area increased by ~ 1200%, from ~ 218 km2 in 1985 to ~ 2627 km2 in 2022. More than 91% of this activity is concentrated in the Amazon. Where almost 40% of the sites are five years old or younger, this proportion increases to 62% within Indigenous lands (ILs). Regarding the legal aspect, at least 77% of the 2022 extraction sites showed explicit signs of illegality. Particular attention must be given to the Kayapo, Munduruku, and Yanomami ILs. Together, they concentrate over 90% of the garimpo across ILs.

Abstract Anaesthetics are used daily in human and veterinary medicine as well as in scientific research. Anaesthetics have an impact on cell homeostasis especially through modulation of protein post-translational modifications. O-GlcNAcylation, a ubiquitous post-translational modification, plays a role in many biological processes. The aims of this study were to evaluate whether (1) anaesthesia influences O-GlcNAcylation and (2) its stimulation affects physiological parameters. Male Wistar rats (n = 38) were anaesthetized with ketamine-xylazine or isoflurane. They randomly received either an intravenous injection of Ringer's lactate or NButGT (10mg/kg) in order to increase O-GlcNAcylation levels. One hour after induction of anaesthesia, haemodynamic parameters and plasmatic markers were evaluated. Heart, brain and lungs were harvested and O-GlcNAcylation levels and O-GlcNAc-related enzymes were evaluated by western blot. Cardiac and pulmonary O-GlcNAcylation levels and cardiac, cerebral and pulmonary O-GlcNAc associated enzyme expression were not impacted with anaesthesia. Compared with ketamine-xylazine, isoflurane had a lower impact on blood pressure, heart rate and glycaemia. Pharmacological stimulation of O-GlcNAcylation by NButGT did not affect the physiological parameters. This study offers unprecedented insights into the regulation of O-GlcNAcylation and O-GlcNAc related enzymes during anaesthesia. Pharmacological stimulation of O-GlcNAcylation over a 1-h period did not disrupt the physiological balance in healthy anaesthetized rats.

Building use information is important for urban planning, city digital twins, and informed policy formulation. Prior research has predominantly focused on mapping building use in broad categories, offering general insight into their actual use. Our study investigates the extraction of hierarchical building categories, encompassing both broad and detailed classifications while accounting for mixed-use. To achieve this, we explore the fusion of building function information from satellite images, digital surface models (DSM), street view images, and point of interest (POI) data. We propose a novel multi-label multimodal transformer-based feature fusion network, which is capable of simultaneously predicting four broad categories and 13 detailed categories. Experimental results demonstrate the efficacy of our method, as it maps most of the building use categories, with the weighted average F1 score for four broad categories and 13 detailed categories of 91% and 77%, respectively. Our experiments underscore the critical role of satellite images in building use classification, with the inclusion of DSM data and POI significantly enhancing the classification accuracy. By considering detailed use categories and accounting for mixed-use, our method provides more detailed insights into land use patterns, thereby contributing to urban planning and management.

This article presents the scientific outcomes of the 2023 Data Fusion Contest (DFC23) organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The contest consists of two tracks investigating the fusion of optical and synthetic aperture radar data for: 1) fine-grained roof type classification and 2) height estimation. During the development phase, 1000 people registered for the contest, while at the end 55 and 35 teams competed during the test phase in the two tracks, respectively. This article presents the methods and results obtained by the first and second-ranked teams of each track. In Track 1, both winning teams leveraged pretraining, modern network architectures, model ensembles, and measures to cope with the imbalanced class distribution. The solutions to Track 2 are more diverse and are characterized by modern multitask learning approaches. The data of this contest is openly available to the community for further research, development, and refinement of machine learning methods.

Satellite remote sensing images contain complex and diverse ground object information and the images exhibit spatial multi-scale characteristics, making the panoptic segmentation of satellite remote sensing images a highly challenging task. Due to the lack of large-scale annotated datasets for panoramic segmentation, existing methods still suffer from weak model generalization capabilities. To mitigate this issue, this paper leverages the advantages of the Segment Anything Model (SAM), which can segment any object in remote sensing images without requiring any annotations and proposes a high-resolution remote sensing image panoptic segmentation method called Remote Sensing Panoptic Segmentation SAM (RSPS-SAM). Firstly, to address the problem of global information loss caused by cropping large remote sensing images for training, a Batch Attention Pyramid was designed to extract multi-scale features from remote sensing images and capture long-range contextual information between cropped patches, thereby enhancing the semantic understanding of remote sensing images. Secondly, we constructed a Mask Decoder to address the limitation of SAM requiring manual input prompts and its inability to output category information. This decoder utilized mask-based attention for mask segmentation, enabling automatic prompt generation and category prediction of segmented objects. Finally, the effectiveness of the proposed method was validated on the high-resolution remote sensing image airport scene dataset RSAPS-ASD. The results demonstrate that the proposed method achieves segmentation and recognition of foreground instances and background regions in high-resolution remote sensing images without the need for prompt input, while providing smooth segmentation boundaries with a panoptic segmentation quality (PQ) of 57.2, outperforming current mainstream methods.

Spring frost is a risk for fruit tree production. In this study, a dynamic agrivoltaic system (AV) was tested as a solution to protect trees from frosts. The study was done in a nectarine AV in France in 2022 and 2023. The AV plot was paired with an adjacent control plot without panels. Air temperature nearby the trees was measured continuously with thermo-hygrometers each year. In 2022 and 2023 frost sensors to mimic organ temperature were also used. In 2023, bud temperatures were continuously measured during bloom. Frosts during bloom were observed in 2022 and 2023 but only the 2022 frost was associated with flower damage. Solar panels were positioned in horizontal position during the nights with frost. Night air temperature nearby the AV trees was warmer in comparison with control trees (increases between 0.27 and 0.47 °C). An increase between 0.25-1.29 °C was also observed for frost sensors and between 1.61-1.69 °C for the flower buds. Phenology was similar between control and AV trees. In 2002, 35% of control flowers were injured during frost while less than 10% were injured in the AV. We conclude that agrivoltaics can be used to protect flowers from frost.

Background: Dietary intake and metabolism variations are associated with molecular changes and more particularly in the transcriptome. O-GlcNAcylation is a post-translational modification added and removed respectively by OGT and OGA. The UDP-GlcNAc, the substrate of OGT, is produced by UAP1 and UAP1L1. O-GlcNAcylation is qualified as a metabolic sensor and is involved in the modulation of gene expression. We wanted to unveil if O-GlcNAcylation is linking metabolic transition to transcriptomic changes and to highlight modifications of O-GlcNAcylation during the postnatal cardiac development. Methods: Hearts were harvested from rats at birth (D0), before (D12) and after suckling to weaning transition with normal (D28) or delayed weaning diet from D12 to D28 (D28F). O-GlcNAcylation levels and proteins expression were evaluated by Western blot. Cardiac transcriptomes were evaluated via 3′SRP analysis. Results: Cardiac O-GlcNAcylation levels and nucleocytoplasmic OGT (ncOGT) were decreased at D28 while full length OGA (OGA) was increased. O-GlcNAcylation levels did not changed with delayed weaning diet while ncOGT and OGA were respectively increased and decreased. Uapl1 was the only O-GlcNAcylation-related gene identified as differentially expressed throughout postnatal development. Conclusion: Macronutrients switch promotes changes in the transcriptome landscape that are independent from O-GlcNAcylation levels. UAP1 and UAP1L1 are not the main regulator element of O-GlcNAcylation throughout postnatal development.

With global warming and the increase of heatwaves frequencies, it has become urgent to protect crops. Agrivoltaic systems tackle this issue by shading plants with photovoltaic panels to lower the temperature of canopies. However, a permanent shading would lead to an important loss of carbon for plants. For this reason, dynamic agrivoltaic systems (AVD) emerged with panels which could be steered in real time according to the needs of plants. Shading at the right time is not that easy with the risk to either miss a hot event and cause serious and irreversible injuries to the plants or shade too often, and impact carbon production. In this paper we present first an experiment with measurements of leaf temperature at different positions of grapevine canopy for two summer days in 2020 and 2021. Then, the energy balance sub-model part of a crop model that simulate plant growth for fruit trees and vines grown in heterogeneous AVD environments is presented. Finally, after having evaluated the coherence of the model with experimental results, the relevance of a mechanistic model to steer solar panels and protect plants from heat is illustrated through several examples. The heterogeneity of temperature within the canopy observed in the field experiments related with different variables such as air and ground temperature, leaf orientation and self-shading was correctly reproduced by the model. This work indicated that canopy temperature could be more integrative than a unique threshold of air temperature to take decisions on panel orientation to protect plants from heat stress.

Delineating and modelling building roof plane structures is an active research direction in urban-related studies, as understanding roof structure provides essential information for generating highly detailed 3D building models. Traditional deep-learning models have been the main focus of most recent research endeavors aiming to extract pixel-based building roof plane areas from remote-sensing imagery. However, significant challenges arise, such as delineating complex roof boundaries and invisible boundaries. Additionally, challenges during the post-processing phase, where pixel-based building roof plane maps are vectorized, often result in polygons with irregular shapes. In order to address this issue, this study explores a state-of-the-art method for planar graph reconstruction applied to building roof plane extraction. We propose a framework for reconstructing regularized building roof plane structures using aerial imagery and cadastral information. Our framework employs a holistic edge classification architecture based on an attention-based neural network to detect corners and edges between them from aerial imagery. Our experiments focused on three distinct study areas characterized by different roof structure topologies: the Stadsveld–‘t Zwering neighborhood and Oude Markt area, located in Enschede, The Netherlands, and the Lozenets district in Sofia, Bulgaria. The outcomes of our experiments revealed that a model trained with a combined dataset of two different study areas demonstrated a superior performance, capable of delineating edges obscured by shadows or canopy. Our experiment in the Oude Markt area resulted in building roof plane delineation with an F-score value of 0.43 when the model trained on the combined dataset was used. In comparison, the model trained only on the Stadsveld–‘t Zwering dataset achieved an F-score value of 0.37, and the model trained only on the Lozenets dataset achieved an F-score value of 0.32. The results from the developed approach are promising and can be used for 3D city modelling in different urban settings.

El trabajo de Martín Castro se instala en un problema transitado por la bibliografía desde una perspectiva nueva que involucra los lenguajes políticos, los usos de ciertos términos, en este caso oligarquía, sus derivas y transformaciones para dar cuenta de la composición de las dirigencias políticas en el tránsito del siglo XIX al XX y del “orden conservador” a la emergencia de la democracia de masas.

Satellite remote sensing images contain complex and diverse ground object information and the images exhibit spatial multi-scale characteristics, making the panoptic segmentation of satellite remote sensing images a highly challenging task. Due to the lack of large-scale annotated datasets for panoramic segmentation, existing methods still suffer from weak model generalization capabilities. To mitigate this issue, this paper leverages the advantages of the Segment Anything Model (SAM), which can segment any object in remote sensing images without requiring any annotations and proposes a high-resolution remote sensing image panoptic segmentation method called Remote Sensing Panoptic Segmentation SAM (RSPS-SAM). Firstly, to address the problem of global information loss caused by cropping large remote sensing images for training, a Batch Attention Pyramid was designed to extract multi-scale features from remote sensing images and capture long-range contextual information between cropped patches, thereby enhancing the semantic understanding of remote sensing images. Secondly, we constructed a Mask Decoder to address the limitation of SAM requiring manual input prompts and its inability to output category information. This decoder utilized mask-based attention for mask segmentation, enabling automatic prompt generation and category prediction of segmented objects. Finally, the effectiveness of the proposed method was validated on the high-resolution remote sensing image airport scene dataset RSAPS-ASD. The results demonstrate that the proposed method achieves segmentation and recognition of foreground instances and background regions in high-resolution remote sensing images without the need for prompt input, while providing smooth segmentation boundaries with a panoptic segmentation quality (PQ) of 57.2, outperforming current mainstream methods. [ABSTRACT FROM AUTHOR]

Deep learning-based semantic segmentation models for building delineation face the challenge of producing precise and regular building outlines. Recently, a building delineation method based on frame field learning was proposed by Girard et al. (2020) to extract regular building footprints as vector polygons directly from aerial RGB images. A fully convolution network (FCN) is trained to learn simultaneously the building mask, contours, and frame field followed by a polygonization method. With the direction information of the building contours stored in the frame field, the polygonization algorithm produces regular outlines accurately detecting edges and corners. This paper investigated the contribution of elevation data from the normalized digital surface model (nDSM) to extract accurate and regular building polygons. The 3D information provided by the nDSM overcomes the aerial images’ limitations and contributes to distinguishing the buildings from the background more accurately. Experiments conducted in Enschede, the Netherlands, demonstrate that the nDSM improves building outlines’ accuracy, resulting in better-aligned building polygons and prevents false positives. The investigated deep learning approach (fusing RGB + nDSM) results in a mean intersection over union (IOU) of 0.70 in the urban area. The baseline method (using RGB only) results in an IOU of 0.58 in the same area. A qualitative analysis of the results shows that the investigated model predicts more precise and regular polygons for large and complex structures.

Abstract Aims Diastolic dysfunction is common in cardiovascular diseases, particularly in the case of heart failure with preserved ejection fraction. The challenge is to develop adequate animal models to envision human therapies in the future. It has been hypothesized that this diastolic dysfunction is linked to alterations in the nitric oxide (•NO) pathway. To investigate this issue further, we investigated the cardiac functions of a transgenic rat model (Tgβ3) that overexpresses the human β3‐adrenoceptor (hβ3‐AR) in the endothelium with the underlying rationale that the •NO pathway should be stimulated in the endothelium. Methods and results Transgenic rats (Tgβ3) that express hβ3‐AR under the control of intercellular adhesion molecule 2 promoter were developed for a specific expression in endothelial cells. Transcriptomic analyses were performed on left ventricular tissue from 45‐week‐old rats. Among all altered genes, we focus on •NO synthase expression and endothelial function with arterial reactivity and evaluation of •NO and O2•− production. Cardiac function was characterized by echocardiography, invasive haemodynamic studies, and working heart studies. Transcriptome analyses illustrate that several key genes are regulated by the hβ3‐AR overexpression. Overexpression of hβ3‐AR leads to a reduction of Nos3 mRNA expression (−72%; P

Deep learning methods based on Fully convolution networks (FCNs) have shown an impressive progress in building outline delineation from very high resolution (VHR) remote sensing (RS) imagery. Common issues still exist in extracting precise building shapes and outlines, often resulting in irregular edges and over smoothed corners. In this paper, we use PolyMapper, a recently introduced deep-learning framework that is able to predict object outlines in a vector representation directly. We have introduced two main modifications to this baseline method. First, we introduce EffcientNet as backbone feature encoder to our network, which uses compound coefficient to scale up all dimensions of depth/width/resolution uniformly, to improve the processing speed with fewer parameters. Second, we integrate a boundary refinement block (BRB) to strengthen the boundary feature learning and to further improve the accuracy of corner prediction. The results demonstrate that the end-to-end learnable model is capable of delineating polygons of building outlines that closely approximate the structure of reference labels. Experiments on the crowdAI building instance segmentation datasets show that our model outperforms PolyMapper in all COCO metrics, for instance showing a 0.13 higher mean Average Precision (AP) value and a 0.60 higher mean Average Recall value. Also qualitative results show that our method segments building instances of various shapes more accurately.

Updated information on urban land use allows city planners and decision makers to conduct large scale monitoring of urban areas for sustainable urban growth. Remote sensing data and classification methods offer an efficient and reliable way to update such land use maps. Features extracted from land cover maps are helpful on performing a land use classification task. Such prior information can be embedded in the design of a deep learning based land use classifier by applying a multitask learning setup—simultaneously solving a land use and a land cover classification task. In this study, we explore a fully convolutional multitask network to classify urban land use from very high resolution (VHR) imagery. We experimented with three different setups of the fully convolutional network and compared it against a baseline random forest classifier. The first setup is a standard network only predicting the land use class of each pixel in the image. The second setup is a multitask network that concatenates the land use and land cover class labels in the same output layer of the network while the other setup accept as an input the land cover predictions, predicted by a subpart of the network, concatenated to the original input image patches. The two deep multitask networks outperforms the other two classifiers by at least 30% in average F1-score.

The application of UAV-based aerial imagery has advanced exponentially in the past two decades. This can be attributed to UAV operational flexibility, ultra-high spatial resolution, inexpensiveness, and UAV-based sensors enhancement. Nonetheless, the application of multitemporal series of multispectral UAV imagery still suffers significant misregistration errors, and therefore becoming a concern for applications such as precision agriculture. Direct image georeferencing and co-registration is commonly done using ground control points; this is usually costly and time consuming. This research proposes a novel approach for automatic co-registration of multitemporal UAV imagery using intensity-based keypoints. The Speeded Up Robust Features (SURF), Binary Robust Invariant Scalable Keypoints (BRISK), Maximally Stable Extremal Regions (MSER) and KAZE algorithms, were tested and parameters optimized. Image matching performance of these algorithms informed the decision to pursue further experiments with only SURF and KAZE. Optimally parametrized SURF and KAZE algorithms obtained co-registration accuracies of 0.1 and 0.3 pixels for intra-epoch and inter-epoch images respectively. To obtain better intra-epoch co-registration accuracy, collective band processing is advised whereas one-to-one matching strategy is recommended for inter-epoch co-registration. The results were tested using a maize crop monitoring case and the; comparison of spectral response of vegetation between the UAV sensors, Parrot Sequoia and Micro MCA was performed. Due to the missing incidence sensor, spectral and radiometric calibration of Micro MCA imagery is observed to be key in achieving optimal response. Also, the cameras have different specifications and thus differ in the quality of their respective photogrammetric outputs.

One of the major challenges in precision viticulture in Europe is the detection and mapping of flavescence dorée (FD) grapevine disease to monitor and contain its spread. The lack of effective cures and the need for sustainable preventive measures are nowadays crucial issues. Insecticides and the plants uprooting are commonly employed to withhold disease infection, even if these solutions imply serious economic consequences and a strong environmental impact. The development of a rapid strategy to identify the disease is required to cover large portions of the crop and thus to limit damages in a time-effective way. This paper investigates the use of Unmanned Aerial Vehicles (UAVs), a cost-effective approach to early detection of diseased areas. We address this task with an object detection deep network, Faster R-CNN, instead of a traditional pixel-wise classifier. This work tests Faster R-CNN performance on this specific application through a comparative analysis with a pixel-wise classification algorithm (Random Forest). To take advantage of the full image resolution, the experimental analysis is performed using the original UAV imagery acquired in real conditions (instead of the derived orthomosaic). The first result of this paper is the definition of a new dataset for FD disease identification by UAV original imagery at the canopy scale. Moreover, we demonstrate the feasibility of applying Faster-R-CNN as a quasi-real-time alternative solution to semantic segmentation. The trained Faster-R-CNN achieved an average precision of 82% on the test set.

La crisis de 1930 trajo incertidumbre, abrió un escenario de tanteos en todos los niveles y redefinió las reglas de juego entre sectores productivos y entre éstos y el estado. El problema en el cual se inscribe este texto es dar cuenta de esas transformaciones a través del seguimiento de la reforma del código de comercio (ley 11729), la ley de organización del personal bancario (12637) y los proyectos relativos al salario y el seguro social para recuperar la posición de los industriales desde las intervenciones públicas de las corporaciones que se arrogaban su representación, fundamentalmente memoriales y solicitadas presentadas al parlamento para incidir sobre el contenido de las iniciativas en debate o, simplemente, para evitarlas. Esto no supone asumir identidad entre un universo –el de las asociaciones- y otro –el de los empresarios-, sino avanzar sobre las posibilidades abiertas en esta etapa del desarrollo del tema. Por otra parte, seguir el itinerario de proyectos efectivamente sancionados o abandonados en alguna de las comisiones nos permite recuperar la dinámica parlamentaria, las alternativas de la tarea de legislar, el modo en que la prensa se involucra en el proceso y las estrategias que las corporaciones asumen cuando perciben que sus intereses están amenazados.

Airborne photogrammetry and airborne laser scanning are two commonly used technologies used for topographical data acquisition at the city level. Change detection between airborne laser scanning data and photogrammetric data is challenging since the two point clouds show different characteristics. After comparing the two types of point clouds, this paper proposes a feed-forward Convolutional Neural Network (CNN) to detect building changes between them. The motivation from an application point of view is that the multimodal point clouds might be available for different epochs. Our method contains three steps: First, the point clouds and orthoimages are converted to raster images. Second, square patches are cropped from raster images and then fed into CNN for change detection. Finally, the original change map is post-processed with a simple connected component analysis. Experimental results show that the patch-based recall rate reaches 0.8146 and the precision rate reaches 0.7632. Object-based evaluation shows that 74 out of 86 building changes are correctly detected.

In very high resolution (VHR) remote sensing (RS) classification tasks, conventional pixel-based contextual information extraction methods such as morphological profiles (MPs), extended MPs (EMPs) and MPs with partial reconstruction (MPPR) with limited numbers, sizes and shapes of structural elements (SEs) cannot perfectly match all sizes and shapes of the objects in an image. To overcome such limitation, we introduce novel spatial feature extractors, namely, the superpixel-guided morphological profiles (SPMPs), where the superpixels are used as SEs in opening by reconstruction and closing by reconstruction operations. Moreover, to avoid possible side effects from unusual maximum and minimum values within superpixels, the mean pixel value of superpixels is adopted (SPMPsM). Additionally, new decision forest based on penalizing the attributes in previous trees, the ForestPA is introduced and evaluated through a comparative investigation on three VHR multi-/hyperspectral RS image classification tasks. Support vector machine and benchmark ensemble classifiers, including bagging, AdaBoost, MultiBoost, ExtraTrees, Random Forest and Rotation Forest, are adopted. The experimental results confirm the effectiveness and superior performances of the proposed SPMPs and SPMPsM relative to those of the MPs and MPPR. Moreover, ForestPA outperforms only bagging and is not suitable for learning from large numbers of samples with high dimensionality from the computational efficiency and classification accuracy perspective.

Contemporary land administration (LA) systems incorporate the concepts of cadastre and land registration. Conceptually, LA is part of a global land management paradigm incorporating LA functions such as land value, land tenure, land development, and land use. The implementation of land-related policies integrated with well-maintained spatial information reflects the aim set by the United Nations to deliver tenure security for all (Sustainable Development Goal target 1.4, amongst many others). Innovative methods for data acquisition, processing, and maintaining spatial information are needed in response to the global challenges of urbanization and complex urban infrastructure. Current technological developments in remote sensing and geo-spatial information science provide enormous opportunities in this respect. Over the past decade, the increasing usage of unmanned aerial vehicles (UAVs), satellite and airborne-based acquisitions, as well as active remote sensing sensors such as LiDAR, resulted in high spatial, spectral, radiometric, and temporal resolution data. Moreover, significant progress has also been achieved in automatic image orientation, surface reconstruction, scene analysis, change detection, classification, and automatic feature extraction with the help of artificial intelligence, spatial statistics, and machine learning. These technology developments, applied to LA, are now being actively demonstrated, piloted, and scaled. This Special Issue hosts papers focusing on the usage and integration of emerging remote sensing techniques and their potential contribution to the LA domain.

In complex classification tasks, such as the classification of heterogeneous vegetation covers, the high similarity between classes can confuse the classification algorithm when assigning the correct class labels to unlabelled samples. To overcome this problem, this study aimed to develop a classification method by integrating graph-based semi-supervised learning (SSL) and an expert system (ES). The proposed method was applied to vegetation cover classification in a wetland in the Netherlands using Sentinel-2 and RapidEye imagery. Our method consisted of three main steps: object-based image analysis (OBIA), integration of SSL and an ES (SSLES), and finally, random forest classification. The generated image objects and the related features were used to construct the graph in SSL. Then, an independently developed and trained ES was used in the labelling stage of SSL to reduce the uncertainty of the process, before the final classification. Different spectral band combinations of Sentinel-2 were then considered to improve the vegetation classification. Our results show that integrating SSL and an ES can result in significantly higher classification accuracy (83.6%) compared to a supervised classifier (64.9%), SSL alone (71.8%), and ES alone (69.5%). Moreover, utilisation of all Sentinel-2 red-edge spectral band combinations yielded the highest classification accuracy (overall accuracy of 83.6% with SSLES) compared to the inclusion of other band combinations. The results of this study indicate that the utilisation of an ES in the labelling process of SSL improves the reliability of the process and provides robust performance for the classification of vegetation cover.

BackgroundRecent studies suggest that computerized puzzle games are enjoyable, easy to play, and engage attentional, visuospatial, and executive functions. They may help mediate impairments seen in cognitive decline in addition to being an assessment tool. Eye tracking provides a quantitative and qualitative analysis of gaze, which is highly useful in understanding visual search behavior. ObjectiveThe goal of the research was to test the feasibility of eye tracking during a puzzle game and develop adjunct markers for cognitive performance using eye-tracking metrics. MethodsA desktop version of the Match-3 puzzle game with 15 difficulty levels was developed using Unity 3D (Unity Technologies). The goal of the Match-3 puzzle was to find configurations (target patterns) that could be turned into a row of 3 identical game objects (tiles) by swapping 2 adjacent tiles. Difficulty levels were created by manipulating the puzzle board size (all combinations of width and height from 4 to 8) and the number of unique tiles on the puzzle board (from 4 to 8). Each level consisted of 4 boards (ie, target patterns to match) with one target pattern each. In this study, the desktop version was presented on a laptop computer setup with eye tracking. Healthy older subjects were recruited to play a full set of 15 puzzle levels. A paper-pencil–based assessment battery was administered prior to the Match-3 game. The gaze behavior of all participants was recorded during the game. Correlation analyses were performed on eye-tracking data correcting for age to examine if gaze behavior pertains to target patterns and distractor patterns and changes with puzzle board size (set size). Additionally, correlations between cognitive performance and eye movement metrics were calculated. ResultsA total of 13 healthy older subjects (mean age 70.67 [SD 4.75] years; range 63 to 80 years) participated in this study. In total, 3 training and 12 test levels were played by the participants. Eye tracking recorded 672 fixations in total, 525 fixations on distractor patterns and 99 fixations on target patterns. Significant correlations were found between executive functions (Trail Making Test B) and number of fixations on distractor patterns (P=.01) and average fixations (P=.005). ConclusionsOverall, this study shows that eye tracking in puzzle games can act as a supplemental source of data for cognitive performance. The relationship between a paper-pencil test for executive functions and fixations confirms that both are related to the same cognitive processes. Therefore, eye movement metrics might be used as an adjunct marker for cognitive abilities like executive functions. However, further research is needed to evaluate the potential of the various eye movement metrics in combination with puzzle games as visual search and attentional marker.

In-situ slum upgrading projects include infrastructural improvements such as new roads, which are perceived to improve the quality of life for the residents and encourage structural improvements at a household level. Although these physical changes are easily visible in satellite imagery, it is more difficult to track incremental improvements undertaken by the residents – which are perhaps more closely linked to the socio-economic development of the households themselves. The improved detail provided by imagery obtained from Unmanned Aerial Vehicles (UAVs) has the potential to monitor these more subtle changes in a settlement. This paper provides a framework which takes advantage of high-resolution imagery and a detailed elevation model from UAVs to detect changes in informal settlements. The proposed framework leverages expert knowledge to provide training labels for deep learning and thus avoids the cost of manual labelling. The semantic classification is then used to interpret a change mask and identify: new buildings, the creation of open spaces, and incremental roof upgrading in an informal settlement. The methodology is demonstrated on UAV imagery of an informal settlement in Kigali, Rwanda, successfully identifying changes between 2015 and 2017 with an Overall Accuracy of 95 % and correctly interpreting changes with an Overall Accuracy of 91 %. Results reveal that almost half the buildings in the settlement show visible changes in the roofing material, and 61 % of these changed less than 1m². This demonstrates the incremental nature of housing improvements in the settlement.

Debilidad, ineficacia, ineficiencia, abandono de sus funciones de control e inercia legislativa, constituyeron las principales críticas al parlamento a lo largo de su historia. El objetivo de este texto es confrontar las impugnaciones que se acumularon en torno a la eficacia del Congreso entre 1932 y 1943 y ponerlas en diálogo con el modo en que la Cámara de Diputados se hizo cargo de ellas a través de las propuestas abortadas y sancionadas para regular su funcionamiento interno; respuestas parciales y fragmentarias al problema nunca resuelto de la representación.

Snow is an important feature on our planet, and measuring its extent has advantages in climate studies. Snow mapping through satellite remote sensing is often affected by cloud cover. This issue can be resolved by using short wave infrared (SWIR) sensors. In order to obtain an effective cloud mask, our study aims to use SWIR data of a ResourceSat-2 satellite. We employ Convolutional Neural Networks (CNN) to discriminate similar pixels of clouds and snow. The technique is expected to give a high accuracy compared to traditional methods such as thresholding. The cloud mask thus produced can also be used for creating the metadata for Indian Remote Sensing products.

Deep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs). In state-of-the-art techniques, this conversion is slow because each point is converted into a separate image. This approach leads to highly redundant computation during conversion and classification. The goal of this study is to design a more efficient data conversion and ground classification. This goal is achieved by first converting the whole point cloud into a single image. The classification is then performed by a Fully Convolutional Network (FCN), a modified version of CNN designed for pixel-wise image classification. The proposed method is significantly faster than state-of-the-art techniques. On the ISPRS Filter Test dataset, it is 78 times faster for conversion and 16 times faster for classification. Our experimental analysis on the same dataset shows that the proposed method results in 5.22 % of total error, 4.10 % of type I error, and 15.07 % of type II error. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher). The method was also tested on a very high point density LIDAR point clouds resulting in 4.02 % of total error, 2.15 % of type I error and 6.14 % of type II error.