Map Of Environment Research Articles

Deep indoor illumination estimation based on spherical gaussian representation with scene prior knowledge

High dynamic range illumination estimation from a single low dynamic range image is a critical task in the fields of computer vision, graphics and augmented reality. However, directly learning the full HDR environment map or parametric lighting information from a single image is extremely difficult and inaccurate. As a result, we propose a two-stage network approach for illumination estimation that integrates spherical gaussian (SG) representation with scene prior knowledge. In the first stage, a convolutional neural network is utilized to generate material and geometric information about the scene, which serves as prior knowledge for lighting prediction. In the second stage, we model indoor environment illumination using 128 SG functions with fixed center direction and bandwidth, allowing only the amplitude to vary. Subsequently, a Transformer-based lighting parameter regressor is employed to capture the complex relationship between the input images with scene prior information and its SG illumination. Additionally, we introduce a hybrid loss function, which combines a masked loss for high-frequency illumination with a rendering loss for improving the visual quality. By training and evaluating the lighting model on the created SG illumination dataset, the proposed method achieves competitive results in both quantitative metrics and visual quality, outperforming state-of-the-art methods.

Large-FoV 3D imaging of single-photon LiDAR at up to 12 km

Single-photon light detection and ranging (LiDAR) has emerged as a valuable technology for active imaging applications. The growing demand for wider applications has driven advancements in measurement range, imaging resolution, and field of view (FoV). Here, we present a high-resolution, large-FoV single-photon LiDAR system capable of panoramic imaging. The system employs continuous raster scanning with a single-photon detector array to achieve rapid measurements, while timing-based pixel segmentation ensures precise data organization. A histogram-folding-based data compression and reconstruction method was developed, resulting in a two-order-of-magnitude increase in processing speed during simulations while maintaining high image reconstruction quality. The experimental results demonstrated the system’s capacity for rapid, high-resolution, and large-FoV imaging, achieving a resolution of 7.2′′ across a 1.6∘×2.1∘ FoV (1052 × 803 pixels) for buildings up to 12 km, all captured and processed in just 10 min. This approach has great potential for use in environmental mapping and related fields.

O trabalho na Educação Ambiental Crítica

An environmental education (EE) system that does not analyze social and political issues cannot contribute to understanding the roots of problems involving the environment. The study of social relations and the production of life through work is fundamental to understanding the historical connection that human beings establish with nature and to pointing out ways to confront the environmental crisis - a symptom of a broader, civilizing crisis. More specifically in teacher training programs – essential subjects to the EE approach at school – it is important to not be fragmented and disconnected from the reality into which teachers and students are immersed. Therefore, analyzing and understanding the historical relationship between school, community, and their surrounding environment, especially regarding the concept of labor, is one of our bets for the training of critical and engaged teachers and citizens. In view of these concerns, we aim at describing and analyzing part of a teacher training program (initial and continuing) for members of a Pedagogical Residency Project, which occurred through the elaboration and carrying out of a participatory research study – an environmental mapping – with the community surrounding a local partnering school in Lavras-MG. Through this participatory research, content analysis, and the interviews with community members, we observed that the study of working relations, as well as other particularities of the local community, can bring elements of great relevance to the exercise of critical EE, especially in this context of teacher training.

Research on Path Planning of Agricultural UAV Based on Improved Deep Reinforcement Learning

Traditional manual or semi-mechanized pesticide spraying methods often suffer from issues such as redundant coverage and cumbersome operational steps, which fail to meet current pest and disease control requirements. Therefore, there is an urgent need to develop an efficient pest control technology system. This paper builds upon the Deep Q-Network algorithm by integrating the Bi-directional Long Short-Term Memory structure to propose the BL-DQN algorithm. Based on this, a path planning framework for pest and disease control using agricultural drones is designed. This framework comprises four modules: remote sensing image acquisition via the Google Earth platform, task area segmentation using a deep learning U-Net model, rasterized environmental map creation, and coverage path planning. The goal is to enhance the efficiency and safety of pesticide application by drones in complex agricultural environments. Through simulation experiments, the BL-DQN algorithm achieved a 41.68% improvement in coverage compared with the traditional DQN algorithm. The repeat coverage rate for BL-DQN was 5.56%, which is lower than the 9.78% achieved by the DQN algorithm and the 31.29% of the Depth-First Search (DFS) algorithm. Additionally, the number of steps required by BL-DQN was only 80.1% of that of the DFS algorithm. In terms of target point guidance, the BL-DQN algorithm also outperformed both DQN and DFS, demonstrating superior performance.

Landslide Susceptibility Mapping Based on Ensemble Learning in the Jiuzhaigou Region, Sichuan, China

Accurate landslide susceptibility mapping is vital for disaster forecasting and risk management. To address the problem of limited accuracy of individual classifiers and lack of model interpretability in machine learning-based models, a coupled multi-model framework for landslide susceptibility mapping is proposed. Using Jiuzhaigou County, Sichuan Province, as a case study, we developed an evaluation index system incorporating 14 factors. We employed three base models—logistic regression, support vector machine, and Gaussian Naive Bayes—assessed through four ensemble methods: Stacking, Voting, Bagging, and Boosting. The decision mechanisms of these models were explained via a SHAP (SHapley Additive exPlanations) analysis. Results demonstrate that integrating machine learning with ensemble learning and SHAP yields more reliable landslide susceptibility mapping and enhances model interpretability. This approach effectively addresses the challenges of unreliable landslide susceptibility mapping in complex environments.

Object detection and tracking for drones: A system design using dynamic visual SLAM

Abstract. Drones can play a quite crucial role in many walks of life today. Enhancing the visual perception ability of drones is crucial to their intelligence level. Among them, it is necessary to focus on strengthening the detection, tracking and mapping capabilities of drones for dynamic objects. However, the existing visual SLAM systems carried by drones do not perform well in dynamic environments. This project designs a monocular visual SLAM system specifically for drones, aiming to achieve efficient three-dimensional mapping and target tracking, surpassing the limitations of simple static mapping and positioning. Besides, this project constructs a drone dynamic SLAM system developed on the ORB-SLAM3 structure, uses drone images to detect, track and map object motion models, and reconstructs environmental maps to obtain motion parameters with real physical scales. This project strives to optimize the input pre-processing module, improve the validity of data and output environmental maps and raster maps. The outcomes demonstrate the system's strong accuracy and adaptability in dynamic installation procedures.

Natural and Human Impacts on Coastal Areas

Coasts are the most densely populated regions in the world and are vulnerable to different natural and human factors, e.g., sea-level rise, coastal accretion and erosion processes, the intensification of sea storms and hurricanes, the presence of marine litter, chronic pollution and beach oil spill accidents, etc. Although coastal zones have been affected by local anthropic activities for decades, their impacts on coastal ecosystems is often unclear. Several papers are presented in this Special Issue detailing the interactions between natural processes and human impacts in coastal ecosystems all around the world. A better understanding of such natural and human impacts is therefore of great relevance to confidently predict their negative effects on coastal areas and thus promote different conservation strategies. The implementation of adequate management measures will help coastal communities adapt to future scenarios in the short and long term and prevent damage due to different pollution types, e.g., beach oil spill accidents, through the establishment of Environmental Sensitivity Maps.

Enhancing environmental modeling and 3D point cloud construction for unmanned vehicles using laser SLAM and stereo vision with Convolutional Neural Networks

Abstract. This research presents an innovative SLAM algorithm that integrates Convolutional Neural Networks (CNNs) with LIDAR and stereo vision to significantly enhance the accuracy of environmental modeling and the construction of dense 3D point cloud maps in complex and dynamic surroundings. By processing pre-recorded video data and employing advanced image segmentation techniques, this study achieves a deep fusion of visual and geometric data, resulting in highly detailed and precise 3D representations of the environment. The experimental results demonstrate that this approach effectively detects and excludes dynamic objects, thereby significantly improving the overall quality, robustness, and reliability of the constructed maps. This work represents a substantial advancement in SLAM technology, particularly in its capability to model and capture intricate environmental details under varying conditions, making it a powerful tool for precise environmental mapping.

Improved snow property retrievals by solving for topography in the inversion of at-sensor radiance measurements

Abstract. Accurately modelling optical snow properties like snow albedo and specific surface area (SSA) are essential for monitoring the cryosphere in a changing climate and are parameters that inform hydrologic and climate models. These snow surface properties can be modelled from spaceborne imaging spectroscopy measurements but rely on digital elevation models (DEMs) of relatively coarse spatial scales (e.g. Copernicus at 30 m), which degrade accuracy due to errors in derived products such as slope and aspect. In addition, snow deposition and redistribution can change the apparent topography, and thereby static DEMs may not be considered coincident with the imaging spectroscopy dataset. Testing in three different snow climates (tundra, maritime, alpine), we established a new method that simultaneously solves snow, atmospheric, and terrain parameters, enabling a solution that is more unified across sensors and introduces fewer sources of uncertainty. We leveraged imaging spectroscopy data from Airborne Visible Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) and PRecursore IperSpettrale della Missione Applicativa (PRISMA) (collected within 1 h) to validate this method and showed a 25 % increase in performance for the radiance-based method over the static method when estimating SSA. This concept can be implemented in missions such as Surface Biology and Geology (SBG), the Environmental Mapping and Analysis Program (EnMap), and the Copernicus Hyperspectral Imaging Mission for the Environment (CHIME).

CGLight: An effective indoor illumination estimation method based on improved convmixer and GauGAN

Illumination consistency is a key factor for seamlessly integrating virtual objects with real scenes in augmented reality (AR) systems. High dynamic range (HDR) panoramic images are widely used to estimate scene lighting accurately. However, generating environment maps requires complex deep network architectures, which cannot operate on devices with limited memory space. To address this issue, this paper proposes CGLight, an effective illumination estimation method that predicts HDR panoramic environment maps from a single limited field-of-view (LFOV) image. We first design a CMAtten encoder to extract features from input images, which learns the spherical harmonic (SH) lighting representation with fewer model parameters. Guided by the lighting parameters, we train a generative adversarial network (GAN) to generate HDR environment maps. In addition, to enrich lighting details and reduce training time, we specifically introduce the color consistency loss and independent discriminator, considering the impact of color properties on the lighting estimation task while improving computational efficiency. Furthermore, the effectiveness of CGLight is verified by relighting virtual objects using the predicted environment maps, and the root mean square error and angular error are 0.0494 and 4.0607 in the gray diffuse sphere, respectively. Extensive experiments and analyses demonstrate that CGLight achieves a balance between indoor illumination estimation accuracy and resource efficiency, attaining higher accuracy with nearly 4 times fewer model parameters than the ViT-B16 model.

Inferring the dust emission at submillimeter and millimeter wavelengths using neural networks

Context. The Planck mission provided all-sky dust emission maps in the submillimeter (submm) to millimeter (mm) range at an angular resolution of 5′. In addition, some specific sources can be observed at long wavelengths and higher resolution using ground-based telescopes. These observations are limited to small scales and are sometimes not delivered to the community. These ground-based observations require extensive data processing before they become available for scientific analysis, and suffer from extended emission filtering. Aims. At present, we are still unable to fully understand the emissivity variations observed in different astrophysical environments at long (submm and mm) wavelengths. Several models have been developed to reproduce the diffuse Galactic medium, and each distinct environment requires an adjustment of the models. It is therefore challenging to estimate any dust emission in the submm-mm at a better resolution than the 5′ from Planck. In this analysis, based on supervised deep learning algorithms, we produced dust emission predictions in the two Planck bands centered at 850 µm (353 GHz) and 1.38 mm (217 GHz) at the Herschel resolution (37″). Prediction or forecasting is a frequently used term in machine learning or neural network research that refers to the output of an algorithm that has been trained on a given dataset and that is being used for modeling purposes. Methods. Herschel data of Galactic environments, ranging from 160 µm to 500 µm and smoothed to an angular resolution of 5′, were used to train the neural network. This training aimed to provide the most accurate model for reproducing Planck maps of dust emission at 850 µm and 1.38 mm. Then, using Herschel data only, the model was applied to predict dust emission maps at 37″. Results. The neural network is capable of reproducing dust emission maps of various Galactic environments with a difference of only a few percent at the Planck resolution. Remarkably, it also performs well for nearby extragalactic environments. This could indicate that large dust grains, probed by submm or mm observations, have similar properties in both our Galaxy and nearby galaxies, or at least that their spectral behaviors are comparable in Galactic and extragalactic environments. For the first time, we provide to the community dust emission prediction maps at 850 µm and 1.38 mm at the 37″ of several surveys: Hi-GAL, Gould Belt, Cold Cores, HERITAGE, Helga, HerM33es, KINGFISH, and Very Nearby Galaxies. The ratio of these two wavelength brightness bands reveals a derived emissivity spectral index statistically close to 1 for all the surveys, which favors the hypothesis of a flattened dust emission spectrum for wavelengths larger than 850 µm. Conclusions. Neural networks appear to be powerful algorithms that are highly efficient at learning from large datasets and achieving accurate reproductions with a deviation of only a few percent. However, to fully recover the input data during the training, it is essential to sample a sufficiently large range of datasets and physical conditions.

Enhancing aerial mapping with gamma radiation detection: a study in UAE

This work presents a comprehensive study on the development of a sophisticated gamma radiation detection system based on a drone-mounted gamma scintillation detector tailored for aerial mapping and radiation surveillance, aimed at generating an environmental radioactivity map within the United Arab Emirates (UAE). The project incorporates careful assembly and calibration techniques that utilize four high-resolution crystals (two CeBr3 and two Lanthanum Bromochloride crystals) to optimize detection sensitivity. Additionally, the study examines the effectiveness of a VETO system in improving the signal-to-noise ratio and reducing background. The detector system employs modern front-end and back-end electronics to digitize the signal at the outset of signal processing. The detector will be installed on a drone to facilitate thorough and effective surveys.

Analysis of trust and efficient take-over strategy with multi-sensor information fusion in conditionally automated driving

Abstract. In the recent development of Autonomous Vehicles (AVs), human-machine trust and take-over strategy are important research contents, which is related to whether the driving system can make the most of its performance and ensure driving safety. At the same time, the unique advantages of Multi-Sensor Information Fusion (MSIF) also make it more and more applied to the auxiliary driving system. At present, research on MSIF applications in automated driving mainly focuses on external environment perception and map construction. However, there is little research on the application of MSIF in vehicle Human-Machine Interaction (HMI). Therefore, this paper analyzes the application of MSIF in trust detection and take-over HMI, proposes the advantages of applying MSIF to the HMI of AVs, and points out that the HMI design of intelligent vehicles in the future can enhance the application of MSIF. Dynamic monitoring of human-machine trust and dynamic adjustment of HMI strategy of the intelligent driving system are realized to achieve a better effect and further guarantee driving safety.

Mapping Leaf Mass Per Area and Equivalent Water Thickness from PRISMA and EnMAP

With the continued advancement of spaceborne hyperspectral sensors, hyperspectral remote sensing is evolving as an increasingly pivotal tool for high-precision global monitoring applications. Novel image spectroscopy data, e.g., the PRecursore IperSpettrale della Missione Applicativa (PRISMA) and Environmental Mapping and Analysis Program (EnMAP), can rapidly and non-invasively capture subtle spectral information of terrestrial vegetation, facilitating the precise retrieval of the required vegetation parameters. As critical vegetation traits, Leaf Mass per Area (LMA) and Equivalent Water Thickness (EWT) hold significant importance for comprehending ecosystem functionality and the physiological status of plants. To address the demand for high-precision vegetation parameter datasets, a hybrid modeling approach was proposed in this study, integrating the radiative transfer model PROSAIL and neural network models to retrieve LMA and EWT from PRISMA and EnMAP images. To achieve this objective, canopy reflectance was simulated via PROSAIL, and the optimal band combinations for LMA and EWT were selected as inputs to train neural networks. The evaluation of the hybrid inversion models over field measurements showed that the RMSE values for the LMA and EWT were 4.11 mg·cm−2 and 9.08 mg·cm−2, respectively. The hybrid models were applied to PRISMA and EnMAP images, resulting in LMA and EWT maps displaying adequate spatial consistency, along with cross-validation results showing high accuracy (RMSELMA = 5.78 mg·cm−2, RMSEEWT = 6.84 mg·cm−2). The results demonstrated the hybrid inversion model’s universality and applicability, enabling the retrieval of vegetation parameters from image spectroscopy data and offering a valuable contribution to hyperspectral remote sensing for vegetation monitoring, though the availability of field measurement data remained a significant challenge.

Tightly coupled stereo vision-inertial odometry based on point and line feature

Abstract To improve the accuracy and robustness of visual simultaneous localization and mapping (SLAM) in low-texture environments, this paper proposes a robust and fast stereo vision inertial SLAM pose estimation method that combines point and line features with an inertial measurement unit (IMU). The method tightly couples visual point and line features with IMU constraints, forming a least-squares problem through the error of each constraint term for nonlinear optimization. To address the issues of over-segmentation and time consumption in traditional line segment detection (LSD) algorithms, an improved LSD algorithm is adopted to accelerate line feature extraction. This approach merges nearby line segments based on spatial geometric relationships and filters out invalid segments, improving the time efficiency of the algorithm. Finally, experiments conducted in low-texture environments demonstrate that our algorithm achieves high localization accuracy and robustness.

Chromatic covalent organic frameworks enabling in-vivo chemical tomography

Covalent organic frameworks designed as chromatic sensors offer opportunities to probe biological interfaces, particularly when combined with biocompatible matrices. Particularly compelling is the prospect of chemical tomography – or the 3D spatial mapping of chemical detail within the complex environment of living systems. Herein, we demonstrate a chromic Covalent Organic Framework (COF) integrated within silk fibroin (SF) microneedles that probe plant vasculature, sense the alkalization of vascular fluid as a biomarker for drought stress, and provide a 3D in-vivo mapping of chemical gradients using smartphone technology. A series of Schiff base COFs with tunable pKa ranging from 5.6 to 7.6 enable conical, optically transparent SF microneedles with COF coatings of 120 to 950 nm to probe vascular fluid and the surrounding tissues of tobacco and tomato plants. The conical design allows for 3D mapping of the chemical environment (such as pH) at standoff distances from the plant, enabling in-vivo chemical tomography. Chromatic COF sensors of this type will enable multidimensional chemical mapping of previously inaccessible and complex environments.

Beam Orbital Parameter Prediction Based on the Deployment of Cascaded Neural Networks at Edge Intelligence Acceleration Nodes

During the beam current calibration process, accurate guidance of the beam current to the metal target is a challenging issue for proton accelerators. To address this challenge, we propose the use of beam orbital parameters combined with reinforcement learning algorithms to achieve automatic beam calibration. This study introduces a system architecture that employs edge intelligent acceleration nodes based on deep learning acceleration techniques. We designed a system to predict BPM parameters using a cascaded backpropagation neural network (CBPNN) that is informed by the physical structure. This system serves as an environmental map for reinforcement learning, aiding beam current correction. The CBPNN was implemented on the acceleration node to hasten the forward inference process, leveraging sparsification, quantization algorithms, and pipelining techniques. Our experimental results demonstrated that the simulated inference speed reached 28 μs with FPGA hardware as the edge acceleration node, achieving forward inference speeds 35.66 and 12.66 times faster than those of the CPU and GPU. The energy efficiency ratio was 10.582 MOPS/W, which was 989 and 410 times that of the CPU and GPU, respectively. This confirms the designed architecture’s energy efficiency and low latency attributes.

Efficient Environment Map Rendering Based on Decomposition

AbstractThis paper presents an efficient environment map sampling algorithm designed to render high‐quality, low‐noise images with only a few light samples, making it ideal for real‐time applications. We observe that bright pixels in the environment map produce high‐frequency shading effects, such as sharp shadows and shading, while the rest influence the overall tone of the scene. Building on this insight, our approach differs from existing techniques by categorizing the pixels in an environment map into emissive and non‐emissive regions and developing specialized algorithms tailored to the distinct properties of each region. By decomposing the environment lighting, we ensure that light sources are deposited on bright pixels, leading to more accurate shadows and specular highlights. Additionally, this strategy allows us to exploit the smoothness in the low‐frequency component by rendering a smaller image with more lights, thereby enhancing shading accuracy. Extensive experiments demonstrate that our method significantly reduces shadow artefacts and image noise compared to previous techniques, while also achieving lower numerical errors across a range of illumination types, particularly under limited sample conditions.

Modified ICP based Framework for 3D Localization and Mapping in GNSS-denied Environments using LiDAR

Abstract. Lidar odometry and mapping has emerged as fundamental technology in various fields, including accurate positioning and mapping, autonomous vehicles, robotics, and environmental monitoring. The ability to create accurate maps and calculate trajectories is essential for localization and navigation in complex environments, particularly in scenarios where GNSS signal are unavailable. In this context, we propose a novel method for simultaneous localization and mapping (SLAM) specifically designed for GNSS-denied environments and without the need for high-accuracy ranging or inertial measurement units (IMUs). Our approach aims to address the challenges posed by GNSS-denied environments and the cost constraints associated with using multiple sensors. By using only lidar sensors, specifically the Velodyne VLP 16 sensor, we offer a cost-effective solution. Our method utilizes a modified version of the Iterative Closest Point (ICP) algorithm to handle consecutive lidar scans seamlessly. In addition to our method, we conducted thorough accuracy assessments on the created map. The reason behind extensive accuracy evaluation is to ensure the quality of registration. By comparing alignment between the features of different frames within the map and determining the error between the registered features and the original, we gain a more comprehensive understanding of registration quality.

Efficient Multi-floor Indoor Mapping with A Versatile Rotating LiDAR System

Abstract. Light Detection And Ranging (LiDAR) technology has provided an impactful way to capture 3D environmental map. However, consistent mapping in sensing-degenerated and perceptually-limited scenes (e.g. multi-story buildings) or under high dynamic sensor motion (e.g. rotating platform) remains a significant challenge. To this end, an efficient multi-floor indoor mapping system is proposed in this paper utilizing a versatile rotating LiDAR platform. In the front end, measurements from motor, IMU and LiDAR are tightly integrated to track the fast motion state of system, based on iterative Error State Kalman Filter (ESKF). Then linear and planar features are extracted from the point cloud map voxelized with adaptive resolutions. A sliding-window-based batch optimization is performed to simultaneously optimize the states of local frames with reference to the map consistency. In the experiments, we investigated the influence of rotating speed on the mapping performance as well as the superiority of rotating mechanism when compared to standard LiDAR setup. Moreover, comparative studies with one of the SOTA work, FAST-LIO2, have shown the competitive mapping results in multi-floor indoor environments.