Showing papers in "ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences in 2020"

Updates of `AW3D30' Alos Global Digital Surface Model with Other Open Access Datasets

Abstract: . In 2016 we first completed the global data processing of digital surface models (DSMs) by using the whole archives of stereo imageries derived from the Panchromatic Remote sensing Instrument for Stereo Mapping (PRISM) onboard the Advanced Land Observing Satellite (ALOS). The dataset was freely released to the public in 30 m grid spacing as the ‘ALOS World 3D - 30m (AW3D30)’, which was generated from its original version processed in 5 m or 2.5 m grid spacing. The dataset has been updated since then to improve the absolute/relative height accuracies with additional calibrations. However the most significant update that should be applied for improving the data usability is the filling of void areas, which correspond to approx. 10% of global coverage, mostly due to cloud covers. In this paper we introduce the updates of AW3D30 filling the voids with other open-access DSMs such as Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM), Advanced Spaceborne Thermal Emission and Reflection Radiometer Global DEM (ASTER GDEM), ArcticDEM, etc., through inter-comparisons among these datasets.

a Benchmark for Large-Scale Heritage Point Cloud Semantic Segmentation

Abstract: . The lack of benchmarking data for the semantic segmentation of digital heritage scenarios is hampering the development of automatic classification solutions in this field. Heritage 3D data feature complex structures and uncommon classes that prevent the simple deployment of available methods developed in other fields and for other types of data. The semantic classification of heritage 3D data would support the community in better understanding and analysing digital twins, facilitate restoration and conservation work, etc. In this paper, we present the first benchmark with millions of manually labelled 3D points belonging to heritage scenarios, realised to facilitate the development, training, testing and evaluation of machine and deep learning methods and algorithms in the heritage field. The proposed benchmark, available at http://archdataset.polito.it/, comprises datasets and classification results for better comparisons and insights into the strengths and weaknesses of different machine and deep learning approaches for heritage point cloud semantic segmentation, in addition to promoting a form of crowdsourcing to enrich the already annotated database.

Breizhcrops: a time series dataset for crop type mapping

Abstract: . We present BreizhCrops, a novel benchmark dataset for the supervised classification of field crops from satellite time series. We aggregated label data and Sentinel-2 top-of-atmosphere as well as bottom-of-atmosphere time series in the region of Brittany (Breizh in local language), north-east France. We compare seven recently proposed deep neural networks along with a Random Forest baseline. The dataset, model (re-)implementations and pre-trained model weights are available at the associated GitHub repository (https://github.com/dl4sits/breizhcrops) that has been designed with applicability for practitioners in mind. We plan to maintain the repository with additional data and welcome contributions of novel methods to build a state-of-the-art benchmark on methods for crop type mapping.

Semantic annotations on heritage models: 2D/3D approaches and future research challenges

Abstract: . Research in the field of Cultural Heritage is increasingly moving towards the creation of digital information systems, in which the geometric representation of an artifact is linked to some external information, through meaningful tags. The process of attributing additional and structured information to various elements in a given digital model is customarily identified with the term semantic annotation; the added contextual information is associated, for instance, to analysis and conservation terms. Starting from the existing literature, aim of this work is to discuss how semantic annotations are used, in digital architectural heritage models, to link the geometrical representation of an artefact with knowledge-related information. Most consolidated methods -such as traditional mapping on 2D media, are compared with more recent approaches making the most of 3D representation. Reference is made, in particular, to Heritage-BIM techniques and to collaborative reality-based platforms, such as Aioli (http://aioli.cloud). Potentialities and limits of the different solutions proposed in literature are critically discussed, also addressing future research challenges in Cultural Heritage application fields.

Interaction between direct georeferencing, control point configuration and camera self-calibration for rtk-based uav photogrammetry

Abstract: . Unmanned Aerial Vehicles (UAV) are enjoying increasing popularity in the photogrammetric community. The Chinese supplier DJI is the market leader with about 70% of the global consumer UAV market. The Phantom model has been available for more than 10 years and its current version "RTK" is equipped with a 2-frequency GNSS receiver, as a basis for direct georeferencing of image flights, using RTK or PPK technologies. In the context of the paper, different case studies are investigated, which allow statements on the geometric accuracy of UAV image flights as well as on the self-calibration of the camera systems. In the first example, four DJI Phantom 4 RTK systems are examined, which were flown in a cross flight pattern configuration on the area of the UAV test field "Zeche Zollern" in Dortmund, Germany. The second example analyses the results of an open moorland area where the establishment of GCPs is extremely difficult and expensive, hence direct georeferencing offers a promising way to evaluate deformations, soil movements or mass calculations. In this example a DJI Matrice 210 v2 RTK drone has been used and the results of two different software packages (Agisoft Metashape and RealityCapture) are analysed. The third example presents a reference building that has been established by the Lower Saxony administration for geoinformation in order to evaluate UAV photogrammetry for cadastral purposes. Here again a DJI Phantom 4 RTK has been tested in a variety of flight configurations and a large number of high precision ground control and check points. The case studies show that the RTK option leads to sufficient results if at least 1 GCP is introduced. Flights without any GCPs lead to a significant height error in the order of up to 30 GSD.

Deep Convolutional Neural Networks for Weed Detection in Agricultural Crops Using Optical Aerial Images

Abstract: The presence of weeds in agricultural crops has been one of the problems of greatest interest in recent years as they consume natural resources and negatively affect the agricultural process. For this purpose, a model has been implemented to segment weed in aerial images. The proposed model relies on DeepLabv3 architecture trained upon patches extracted from high-resolution aerial imagery. The dataset employed consisted in 5 high-resolution images that describes a sugar beet agricultural field in Germany. SegNet and U-Net architectures were selected for comparison purposes. Our results demonstrate that balancing of data, together with a greater spatial context leads better results with DeepLabv3 achieving up to 0.89 and 0.81 in terms of AUC and F1-score, respectively.

Integrating expertises and ambitions for data-driven digital building permits – the eunet4dbp

Abstract: The digitalization of the process for building permit (involving the use of 3D information systems) is seen as a priority in a wide part of the world. Since it is a very multidisciplinary use case, involving a variety of stakeholders tackling complex issues and topics, some of them joined their efforts and skills in the European Network for Digital Building Permit. The initial activity of the network, after a review of on-going experiences, was a workshop to share knowledge about the topics involved and to identify the main ambitions of the network with respect to three pillars (i.e. Process - Rules and Requirements - Technology) and the related requirements. It was achieved through a collective brainstorming activity guided by digital tools, whose results were further analysed in a post-processing phase. Such results are presented in this paper and will be the base for planning the future network activity.

Ground truth generation and disparity estimation for optical satellite imagery

Abstract: . Several 3D reconstruction pipelines are being developed around the world for satellite imagery. Most of them implement their own versions of Semi-Global Matching, as an option for the matching step. However, deep learning based solutions already outperform every SGM derived algorithms on Kitti and Middlebury stereo datasets. But these deep learning based solutions need huge quantities of ground truths for training. This implies that the generation of ground truth stereo datasets, from satellite imagery and lidar, seems to be of great interest for the scientific community. It will aim at reducing the potential transfer learning difficulties, that could arise from a training done on datasets such as Middlebury or Kitti. In this work, we present a new ground truth generation pipeline. It produces stereo-rectified images and ground truth disparity maps, from satellite imagery and lidar. We also assess the rectification and the disparity accuracies of these outputs. We finally train a deep learning network on our preliminary ground truth dataset.

Building archaeology documentation and analysis through open source hbim solutions via nurbs modelling

Abstract: . The implementation of historical information within BIM (Building Information Modelling) platforms has experienced great development processes during last years, generating excellent studies based on Historic Building Information Modelling (Murphy et al., 2009; 2013). The HBIM developing growth is certainly explained due to advantages concerning the documentation step as well as monitoring operations for Cultural Heritage assets. In this sense, information concerning historical architectures can be extracted directly from walls and masonries and it is related to stratigraphic information derived from archaeological analysis: this kind of analysis is fundamental in order to comprehend the evolution of the construction site through the identification of layers due to modifications and actions (Parenti R., 2000). The inclusion of stratigraphic analysis inside a HBIM workflow could be an innovative point as far as the management and monitoring is concerned. This kind of documentation, that was not designed to be included inside a common BIM platform, could be collected coupled with digital metric information derived from metric surveys even if it is still considered an ongoing research field, especially since Cultural Heritage assets have no BIM standard classification. For this reason, the main goal of this research is to adapt the possibilities of open source solutions concerning BIM methodologies to building archaeology documentation and analysis exploring unconventional strategies and also overcoming 3D modelling limitations of BIM software with free form modeler based on NURBS algorithm (Oreni et al., 2014), developing a particular scan-to-BIM process that, owing to the used opens source solutions and algorithm, can be renamed scan-to-openBIM via NURBS.

Virtual tours and informational models for improving territorial attractiveness and the smart management of architectural heritage: the 3d-imp-act project

Abstract: . The promotion and dissemination of architectural heritage for cultural enhancement and touristic enjoyment are increasingly focused on innovative ICTs, including 3D Geographic Information Systems, photorealistic models and scenes, and VR/AR immersive digital environments, which enable the interaction of visitors with a variety of informational contents, both educational and specialist. Within the above-mentioned framework, this paper will firstly outline the general objectives of the project “3D-IMP-ACT”, which has been funded under the international cooperation programme IPA CBC Interreg Italy-Albania-Montenegro. In this research, some ICT tools are tested and validated to create “virtual networks” of international ancient architectures and sites, based on the identification of “physical networks” of common historic, environmental and technical characteristics and infrastructural connections, in order to address coordinated strategies and transversal policies for development and management. Then, the paper will describe and discuss some results from the design and implementation of the project WebGIS system, which integrates virtual tours of 360° panoramas, 3D models from photomodelling of pictures taken by drones, multimedia contents, and 2D/3D historic evolution schemes within a single platform, where the users are supported in recognizing and exploring the tangible and intangible correspondences among the project pilot-cases. In conclusion, some remarks will be proposed on the potential benefits of the platform as an expert system which supports the technical assessment and control of architectural heritage toward maintenance, refurbishment and conservation.

Virtual Reality to Support Technical Knowledge in Cultural Heritage. The Case Study of Cryptoporticus in the Archaeological Site of Egnatia (italy)

Abstract: . Digitalization and interactivity of reality in Augmented and Virtual Environments represent the synergic union between current technology potentialities and smartness of users in going beyond the traditional perception of real environment. As it is well-known, touristic bodies already taken advantages of Virtual Environments as cultural and touristic promotion of historic and archaeological sites. However, the analysis of potentialities in supporting technical community and professionals are still underway. Starting from the survey of instruments and protocols in previous experiences, the work presents a methodological flow aimed to create a virtual environment using 360° images – Virtual Tour – where the first phase of technical knowledge in historic sites can be resumed. In detail, a double level of knowledge can be reached: firstly, a virtual environment containing information about the actual state of conservation, then an upgraded one with historic and technical information (e.g. reports, images, surveys, etc.) added in an interactive as well intuitive way. The protocol has been applied to the undergrounded Cryptoporticus of Egnatia, an archaeological site in Apulia Region (Italy).

Introducing automatic satellite image processing into land cover mapping by photo-interpretation of airborne data

Abstract: . A series of five land cover maps, widely known as COS (Carta de Uso e Ocupacao do Solo), have been produced since 1990 for mainland Portugal. Previous to 2015, all maps were produced through photo-interpretation of orthophotos. Land cover and land use changes were detected through comparison of previous and recent orthophotos, which were used for map updating, thereby producing a new map. The remaining areas of no change were preserved across the maps for consistency. Despite the value of the maps produced, the method is very time-consuming and limited to the single-date reference of the orthophotos. From 2015 onwards, a new approach was adopted for map production. Photo-interpretation of orthophoto maps is still the basis of mapping, but assisted by products derived from satellite data. The goals are three-fold: (i) cut time production, (ii) increase map accuracy, and (iii) further detail the nomenclature. The last map published (COS 2015) benefited from change detection and classification analyses of Landsat data, namely for guiding the photo-interpretation in forest, shrublands, and mapping annual agriculture. Time production and map error have been reduced comparing to previous maps. The new 2018 map, currently in production, further explores this approach. Landsat 8 time series of 2015–2018 are used for change detection in vegetation based on NDVI differencing, thresholding and clustering. Sentinel-2 time series of 2017–2018 are used to classify Autumn/Winter crops and Spring/Summer crops based on NDVI temporal profiles and classification rules. Benefits and pitfalls of the new mapping approach are presented and discussed.

Cost-benefit Analysis of Rail Tunnel Inspection for Photogrammetry and Laser Scanning

Abstract: . The civil engineering and construction sector, including the railway industry, is seeking innovative approaches to reduce costs on repetitive and labour-intensive tasks and avoid the use of highly qualified staff for simple manual duties. Such tasks can include the visual inspection of tunnels, where the process is still dominated by manual operations. Our work compares Close Range Photogrammetry (CRP) and Terrestrial Laser Scanning (TLS), both performed with low-end sensors to reflect the industry’s tendency towards easy to use and easy to maintain hardware. It also analyses the benefits of substituting conventional visual inspections of tunnels with automated survey approaches and computer vision techniques. The project’s outcomes suggest that photogrammetry is a valid alternative to laser scanning for visual inspection of concrete segmentally lined tunnels: from the geometric point of view it provides global accuracy at comparable level to laser scanning, in addition it halves the time to generate the 3D model and provides the user with photo-realistic outputs. It is generally more versatile and it is easier to inspect, visualise and navigate the data. The authors argue that the results presented here will push tunnel inspection in the direction of automated approaches with direct benefits on surveying costs as well as Health & Safety (H&S). Utilising available technology supports risk-based asset management and thus ensures safe and operational performance of a railway for passengers to use.

Icesat-2 altimetry as geodetic control

Abstract: . Digital elevation models (DEMs) are of fundamental importance for a large variety of scientific and commercial applications. Many geoscience studies require the most precise and current information about the Earth’s topography. Independent quality assessments of these DEMs are crucial to their appropriate use in land process studies, as inputs to models, and for detection of topographic change. The Ice, Cloud and land Elevation Satellite (ICESat) provided globally-distributed elevation data of high accuracy that demonstrated to be well-suited for evaluating continental DEMs after appropriate editing (Carabajal and Harding, 2005; Carabajal and Harding, 2006; Carabajal et al., 2010 and 2011; Carabajal and Boy, 2016). ICESat-2, launched on September 15th, 2018, provides an opportunity to develop a dataset suitable for Geodetic Ground Control. With increased coverage, ICESat-2/ATLAS features 6 laser beams with 532 nm wavelength, using photon counting technologies. With a nearly polar orbit, altimetry from ICESat-2 is available for latitudes reaching up to 88 degrees, on a 91-day repeat orbit with monthly sub-cycles. ICESat-2’s footprint size is ∼17 m, at 10 kHz pulse repetition frequency, or 0.75 m along track. Its pointing control is 45 m, with a pointing knowledge of 6.5 m, and a single photon precision of 800 ps. Sophisticated data processing techniques on the ground, optimized by surface type, produce high quality estimates of topography. We illustrate the use of ICESat-2 altimetry to assess DEM’s accuracy using ATL08 release 002 elevations (Land and Vegetation) products (Neuenschwander and Pitts, 2019), showing comparable results to those using ICESat-derived Geodetic Ground Control.

MAPPING WITHOUT DYNAMIC: ROBUST LiDAR-SLAM FOR UGV MOBILE MAPPING IN DYNAMIC ENVIRONMENTS

Abstract: . Detection And Tracking of Moving Objects (DATMO) is essential and necessary for mobile mapping system to generate clean and accurate point clouds maps since dynamic targets in real-world scenarios will deteriorate the performance of whole system. In this research, a robust LiDAR-SLAM system is presented incorporated with a real-time dynamic objects removal module to improve the accuracy of 6 DOF pose estimation and precision of maps. The key idea of the proposed method is to efficiently cluster the sparse point clouds of moving objects and then track them independently so as to relieve their influence on the odometry and mapping results. In the back-end, in order to further refine the point clouds maps, a valid probabilistic map fusion method is performed based on the free-space theory. We have evaluated our system on the dataset collected from daily crowded environments full of moving objects, providing competitive results with the state-of-the-art system both on the pose estimation and point cloud mapping.

Modeling of emergency evacuation in building fire

Abstract: . One of the main problems of rescue workers in confrontation of fired complex buildings is the lack of sufficient information about the building indoor environment and their emergency exit ways. Building information modeling (BIM) is a database for building a 3D model of building information to create a 3D building geometry network model. This paper has implemented some GIS and BIM integration analyses to determine the shortest and safest paths to people under fire risk and simulate their movement in the building. Plasco building was a multi-story shop in Tehran which has been fired in 2017 and destroyed. This paper attempts to simulate the firefighting and rescue operations in Plasco Building using an integration of BIM and GIS. There is no detailed information about the building and the fire incident, therefore the developed BIM and corresponding geometric network might differ slightly. The shortest and safest paths to the exit door or windows where the fire ladders are located are computed and analyzed. As a result of 15 scenarios developed in this paper, it was found that at 87% of the cases, the safest paths for the emergency exit of the people at risk were longer than the shortest paths. This study has evaluated different scenarios for the shortest and safest paths using Dijkstra algorithm considering different origins and destination points in the 3D indoor environment to assist the rescue operations.

A study of smart campus environment and its security attacks

Abstract: . The smart campus is a sustainable and well-connected environment that aims to improve experience, efficiency and education. It uses a variety of interconnected components, smart applications and networked technologies to facilitate communication, make more efficient use of resources, improve performance, security and quality of campus services. However, as with many other smart environments, the smart campus is vulnerable to many security issues and threats that make it face many security-related challenges that limit its development. In our paper, we intend to provide an overview of smart campuses by highlighting the main applications and technologies used in this environment, presenting several vulnerabilities and susceptible attacks that affect data and information security in the smart campus. Moreover, we discuss the major challenges of smart campus and we conclude by overviewing some current security solutions to deal with campus security issues.

Deep learning for remote sensing image classification for agriculture applications

Abstract: . This research examines the ability of deep learning methods for remote sensing image classification for agriculture applications. U-net and convolutional neural networks are fine-tuned, utilized and tested for crop/weed classification. The dataset for this study includes 60 top-down images of an organic carrots field, which was collected by an autonomous vehicle and labeled by experts. FCN-8s model achieved 75.1% accuracy on detecting weeds compared to 66.72% of U-net using 60 training images. However, the U-net model performed better on detecting crops which is 60.48% compared to 47.86% of FCN-8s.

Dbscan optimization for improving marine trajectory clustering and anomaly detection

Abstract: . Today maritime transportation represents 90% of international trade volume and there are more than 50,000 vessels sailing the ocean every day. Therefore, reducing maritime transportation security risks by systematically modelling and surveillance should be of high priority in the maritime domain. By statistics, majority of maritime accidents are caused by human error due to fatigue or misjudgment. Auto-vessels equipped with autonomous and semi-autonomous systems can reduce the reliance on human’s intervention, thus make maritime navigation safer. This paper presents a clustering method for route planning and trajectory anomalies detection, which are the essential part of auto-vessel system design and development. In this paper, we present the development of an enhanced density-based spatial clustering (DBSCAN) method that can be applied on historical or real-time Automatic Identification System (AIS) data, so that vessel routes can be modelled, and the trajectories’ anomalies can be detected. The proposed methodology is based on developing an optimized trajectory clustering approach in two stages. Firstly, to increase the attribute dimension of the vessel’s positioning data, therefore other characteristics such as velocity and direction are considered in the clustering process along with geospatial information. Secondly, the DBSCAN clustering model has been enhanced by introducing the Mahalanobis Distance metric considering the correlations of the position cluster points aiming to make the identification process more accurate as well as reducing the computational cost.

Determination of optimal location for setting up cell phone tower in city environment using lidar data

Abstract: . Cell phones have become an inherent part of human life and have grown rapidly in the last decade. In India, there are nearly 120 crore cell phone users which require setting up of cell phone tower at an appropriate location to transmit the signals. A signal strength that is measured in (dBm) keeps on varying from one location to another. Over the decades, there has been a great deal of concern about placing a cell phone tower to manage adequate signal strength for an area. During transmission, the signals get affected by the position of building, ground and the distances the signals need to travel before reaching any receiver or user location. Existing researches focus on the requirement of a suitable number of cell phone towers for a big area in a GIS environment. Depending on the building and other infrastructure present in an area an optimal location can be determined for setting up the cell phone tower. However, the detailed 3D data is required for it. In this paper, a LiDAR-based technique is attempted. Using the point cloud data of the RGIPT campus, features like building, ground, obstruction points, etc are extracted. To determine the transmission paths for the signal, building/object boundary(es), etc. coming in the path(s) between the cell phone tower and the receiver location are determined. Once the detailed paths for the signal transmission i.e, direct path, or path after diffraction (around the buildings), and/or reflection (from the wall and ground) are determined, terrain parameters (distance, path difference, attenuation, etc) are ascertained. These are then used to model and determine the relative signal strength for any receiver location. The position of cell phone tower is then tested for optimal XY, and Z position to ascertain the best location for setting up the cell phone tower. The method is verified against various path determination algorithms. A centroid and viewshed based approach is adopted here. The technique is generic, novel and essentially work with LiDAR point data without needing DEM and can be applied for any terrain condition.

Deep learning applied to water segmentation

Abstract: . The use of deep learning (DL) with convolutional neural networks (CNN) to monitor surface water can be a valuable supplement to costly and labour-intense standard gauging stations. This paper presents the application of a recent CNN semantic segmentation method (SegNet) to automatically segment river water in imagery acquired by RGB sensors. This approach can be used as a new supporting tool because there are only a few studies using DL techniques to monitor water resources. The study area is a medium-scale river (Wesenitz) located in the East of Germany. The captured images reflect different periods of the day over a period of approximately 50 days, allowing for the analysis of the river in different environmental conditions and situations. In the experiments, we evaluated the input image resolutions of 256 × 256 and 512 × 512 pixels to assess their influence on the performance of river segmentation. The performance of the CNN was measured with the pixel accuracy and IoU metrics revealing an accuracy of 98% and 97%, respectively, for both resolutions, indicating that our approach is efficient to segment water in RGB imagery.

Uav block georeferencing and control by on-board gnss data

Abstract: . Unmanned Aerial Vehicles (UAV) are established platforms for photogrammetric surveys in remote areas. They are lightweight, easy to operate and can allow access to remote sites otherwise difficult (or impossible) to be surveyed with other techniques. Very good accuracy can be obtained also with low-cost UAV platforms as far as a reliable ground control is provided. However, placing ground control points (GCP) in these contexts is time consuming and requires accessibility that, in some cases, can be troublesome. RTK-capable UAV platforms are now available at reasonable costs and can overcome most of these problems, requiring just few (or none at all) GCP and still obtaining accurate results. The paper will present a set of experiments performed in cooperation with ARPA VdA (the Environmental Protection Agency of Valle d’Aosta region, Italy) on a test site in the Italian Alps using a Dji Phantom 4 RTK platform. Its goals are: a) compare accuracies obtainable with different calibration procedures (pre- or on-the-job/self-calibration); b) evaluate the accuracy improvements using different number of GCP when the site allows for it; and c) compare alternative positioning modes for camera projection centres determination, (Network RTK, RTK, Post Processing Kinematic and Single Point Positioning).

Visualising Detailed Citygml and Ade at the Building Scale

Abstract: . There is an increasing activity in developing workflows and implementations to convert BIM data into CityGML. However, there are still not many platforms that are suitable to view and interact with the detailed information stored as a result of such conversions, especially if an Application Domain Extension (ADE) is involved to support additional information. We investigated the ease of use and features supported by visualisation software and tools with CityGML and ADE support, and propose an approach to develop a tool that combines useful features using a set of generic rules that can extract CityGML ADE attributes. The work, while generic, is geared towards detailed architectural datasets sourced from BIM. We implemented the approach in a web-based viewer supporting the visualisation of CityGML datasets enriched with ADE features.

Brazildam: A Benchmark Dataset For Tailings Dam Detection

Abstract: In this work we present BrazilDAM, a novel public dataset based on Sentinel-2 and Landsat-8 satellite images covering all tailings dams cataloged by the Brazilian National Mining Agency (ANM). The dataset was built using georeferenced images from 769 dams, recorded between 2016 and 2019. The time series were processed in order to produce cloud free images. The dams contain mining waste from different ore categories and have highly varying shapes, areas and volumes, making BrazilDAM particularly interesting and challenging to be used in machine learning benchmarks. The original catalog contains, besides the dam coordinates, information about: the main ore, constructive method, risk category, and associated potential damage. To evaluate BrazilDAM’s predictive potential we performed classification essays using state-of-the-art deep Convolutional Neural Network (CNNs). In the experiments, we achieved an average classification accuracy of 94.11% in tailing dam binary classification task. In addition, others four setups of experiments were made using the complementary information from the original catalog, exhaustively exploiting the capacity of the proposed dataset.

Identifying epiphytes in drones photos with a conditional generative adversarial network (c-gan)

Abstract: . Unmanned Aerial Vehicle (UAV) missions often collect large volumes of imagery data. However, not all images will have useful information, or be of sufficient quality. Manually sorting these images and selecting useful data are both time consuming and prone to interpreter bias. Deep neural network algorithms are capable of processing large image datasets and can be trained to identify specific targets. Generative Adversarial Networks (GANs) consist of two competing networks, Generator and Discriminator that can analyze, capture, and copy the variations within a given dataset. In this study, we selected a variant of GAN called Conditional-GAN that incorporates an additional label parameter, for identifying epiphytes in photos acquired by a UAV in forests within Costa Rica. We trained the network with 70%, 80%, and 90% of 119 photos containing the target epiphyte, Werauhia kupperiana (Bromeliaceae) and validated the algorithm’s performance using a validation data that were not used for training. The accuracy of the output was measured using structural similarity index measure (SSIM) index and histogram correlation (HC) coefficient. Results obtained in this study indicated that the output images generated by C-GAN were similar (average SSIM = 0.89–0.91 and average HC 0.97–0.99) to the analyst annotated images. However, C-GAN had difficulty to identify when the target plant was away from the camera, was not well lit, or covered by other plants. Results obtained in this study demonstrate the potential of C-GAN to reduce the time spent by botanists to identity epiphytes in images acquired by UAVs.

Are measured ground control points still required in uav based large scale mapping? assessing the positional accuracy of an rtk multi-rotor platform

Abstract: . The estimate of External Orientation (E.O.) parameters for a block of images is a crucial step in the photogrammetric pipeline and the most demanding in terms of required time and human effort, both during the fieldwork and post-processing phases. Different researchers developed strategies to minimize the impact of this phase. Despite the achievement of good results, it was not possible until now to completely cancel the effect of this step. However, the efforts of the researchers in these years have also been devoted to the implementation of direct photogrammetry strategies, in order to almost completely automate the E.O. of the photogrammetric block. These new approaches were made possible also thanks to the latest developments of commercial UAVs, especially in terms of the installed GPS/GNSS (Global Positioning System/Global Navigation Satellite System) hardware. The aim of this manuscript is to evaluate the different perspectives and issues connected with the deployment of a UAV (Unmanned Aerial Vehicle) equipped with a multi-frequency GPS/GNSS receiver. Starting from the considerations mentioned above and leveraging previous works based on a fixed-wing platform, the focus of this contribution is the assessment of the real performances of an RTK multi-rotor platform addressing several questions. Is it possible to generate added-value products with centimetre 3D accuracies without measuring any ground control point? Which are the operational requirements to be taken into account in the planning phase? Are consolidated UAV mapping operational workflows already available to enable a robust direct georeferencing approach?

Mitigating image residuals systematic patterns in underwater photogrammetry

Abstract: . Systematic errors may result from the adoption of an incomplete functional model that is not able to properly incorporate all the effects involved in the image formation process. These errors very likely appear as systematic residual patterns in image observations and produce deformations of the photogrammetric model in object space. The Brown/Beyer model of self-calibration is often adopted in underwater photogrammetry, although it does not take into account the refraction introduced by the passage of the optical ray through different media, i.e. air and water. This reduces the potential accuracy of photogrammetry underwater. In this work, we investigate through simulations the depth-dependent systematic errors introduced by unmodelled refraction effects when both flat and dome ports are used. The importance of camera geometry to reduce the deformation in the object space is analyzed and mitigation measures to reduce the systematic patterns in image observations are investigated. It is shown how, for flat ports, the use of a stochastic approach, consisting in radial weighting of image observations, improves the accuracy in object space up to 50%. Iterative look-up table corrections are instead adopted to reduce the evident systematic residual patterns in the case of dome ports.

Internet of things for smart healthcare: a review on a potential iot based system and technologies to control covid-19 pandemic

Abstract: . Healthcare is an important part of life. Sadly, the spread of Covid-19 has strained the majority of health systems and the demand for resources from hospital kits to doctors and nurses have become extremely high. However, the significant advancement in the computing sector have led to the emergence of Internet of Things (IoT) which has now become one of the most powerful information and communication technologies due to its capability to connects object such as medical kits, monitoring cameras, home appliances and so on… Capitalizing on the efficiency of data retrieval from smart objects in the health sector, it is clear that a solution is necessary and required to improve the health sector in the era of Covid-19 pandemic while continuing to provide a high-quality care to patients. In this paper, a real-time covid-19 monitoring system is introduced in a form of an IoT based bracelet that measures body temperature and blood oxygen level, which are essential factors for determining the patient’s condition and whether he needs a quick intervention to enter ICU room. The bracelet also has a GPS tracker to determine the patient’s commitment to quarantine and social distancing. Based on the study conducted with more than 50 medical stuff, the IoT based bracelet was identified as a promising tool that can help control the spread of the covid-19 virus, by providing a modern access to medical healthcare services anywhere and anytime which is useful for the patient and hospital management stuff.

An End-To-End Framework For Low-Resolution Remote Sensing Semantic Segmentation

Abstract: High-resolution images for remote sensing applications are often not affordable or accessible, especially when in need of a wide temporal span of recordings. Given the easy access to low-resolution (LR) images from satellites, many remote sensing works rely on this type of data. The problem is that LR images are not appropriate for semantic segmentation, due to the need for high-quality data for accurate pixel prediction for this task. In this paper, we propose an end-to-end framework that unites a super-resolution and a semantic segmentation module in order to produce accurate thematic maps from LR inputs. It allows the semantic segmentation network to conduct the reconstruction process, modifying the input image with helpful textures. We evaluate the framework with three remote sensing datasets. The results show that the framework is capable of achieving a semantic segmentation performance close to native high-resolution data, while also surpassing the performance of a network trained with LR inputs.

Accuracy Assessment and Calibration of Low-Cost Autonomous LIDAR Sensors

Abstract: . A number of low-cost, small form factor, high resolution lidar sensors have recently been commercialized in an effort to fill the growing needs for lidar sensors on autonomous vehicles. These lidar sensors often report performance as range precision and angular accuracy, which are insufficient to characterize the overall quality of the point clouds returned by these sensors. Herein, a detailed geometric accuracy analysis of two representative autonomous sensors, the Ouster OSI-64 and the Livox Mid-40, is presented. The scanners were analyzed through a rigorous least squares adjustment of data from the two sensors using planar surface constraints. The analysis attempts to elucidate the overall point cloud accuracy and presence of systematic errors for the sensors over medium (