Significance of AI-assisted techniques for epiphyte plant monitoring and identification from drone images.

Monitoring forest canopies is vital for ecological studies, particularly for assessing epiphytes in rain forest ecosystems. Traditional methods for studying epiphytes, such as climbing trees and building observation structures, are labor, cost intensive and risky. Unmanned Aerial Vehicles (UAVs) have emerged as a valuable tool in this domain, offering botanists a safer and more cost-effective means to collect data. This study leverages AI-assisted techniques to enhance the identification and mapping of epiphytes using UAV imagery. The primary objective of this research is to evaluate the effectiveness of AI-assisted methods compared to traditional approaches in segmenting/identifying epiphytes from UAV images collected in a reserve forest in Costa Rica. Specifically, the study investigates whether Deep Learning (DL) models can accurately identify epiphytes during complex backgrounds, even with a limited dataset of varying image quality. Systematically, this study compares three traditional image segmentation methods Auto Cluster, Watershed, and Level Set with two DL-based segmentation networks: the UNet and the Vision Transformer-based TransUNet. Results obtained from this study indicate that traditional methods struggle with the complexity of vegetation backgrounds and variability in target characteristics. Epiphyte identification results were quantitatively evaluated using the Jaccard score. Among traditional methods, Watershed scored 0.10, Auto Cluster 0.13, and Level Set failed to identify the target. In contrast, AI-assisted models performed better, with UNet scoring 0.60 and TransUNet 0.65. These results highlight the potential of DL approaches to improve the accuracy and efficiency of epiphyte identification and mapping, advancing ecological research and conservation.

A deep learning approach based on graphs to detect plantation lines.

Identifying plantation lines in aerial images of agricultural landscapes is re-quired for many automatic farming processes. Deep learning-based networks are among the most prominent methods to learn such patterns and extract this type of information from diverse imagery conditions. However, even state-of-the-art methods may stumble in complex plantation patterns. Here, we propose a deep learning approach based on graphs to detect plantation lines in UAV-based RGB imagery, presenting a challenging scenario containing spaced plants. The first module of our method extracts a feature map throughout the backbone, which consists of the initial layers of the VGG16. This feature map is used as an input to the Knowledge Estimation Module (KEM), organized in three concatenated branches for detecting 1) the plant positions, 2) the plantation lines, and 3) the displacement vectors between the plants. A graph modeling is applied considering each plant position on the image as vertices, and edges are formed between two vertices (i.e. plants). Finally, the edge is classified as pertaining to a certain plantation line based on three probabilities (higher than 0.5): i) in visual features obtained from the backbone; ii) a chance that the edge pixels belong to a line, from the KEM step; and iii) an alignment of the displacement vectors with the edge, also from the KEM step. Experiments were conducted initially in corn plantations with different growth stages and patterns with aerial RGB imagery to present the advantages of adopting each module. We assessed the generalization capability in the other two cultures (orange and eucalyptus) datasets. The proposed method was compared against state-of-the-art deep learning methods and achieved superior performance with a significant margin considering all three datasets. This approach is useful in extracting lines with spaced plantation patterns and could be implemented in scenarios where plantation gaps occur, generating lines with few-to-no interruptions.

Assessing methane emissions from paddy fields through environmental and UAV remote sensing variables.

Concerns about methane (CH4) emissions from rice, a staple sustaining over 3.5 billion people globally, are heightened due to its status as the second-largest contributor to greenhouse gases, driving climate change. Accurate quantification of CH4 emissions from rice fields is crucial for understanding gas concentrations. Leveraging technological advancements, we present a groundbreaking solution that integrates machine learning and remote sensing data, challenging traditional closed chamber methods. To achieve this, our methodology involves extensive data collection using drones equipped with a Micasense Altum camera and ground sensors, effectively reducing reliance on labor-intensive and costly field sampling. In this experimental project, our research delves into the intricate relationship between environmental variables, such as soil conditions and weather patterns, and CH4 emissions. We achieved remarkable results by utilizing unmanned aerial vehicles (UAV) and evaluating over 20 regression models, emphasizing an R2 value of 0.98 and 0.95 for the training and testing data, respectively. This outcome designates the random forest regressor as the most suitable model with superior predictive capabilities. Notably, phosphorus, GRVI median, and cumulative soil and water temperature emerged as the model's fittest variables for predicting these values. Our findings underscore an innovative, cost-effective, and efficient alternative for quantifying CH4 emissions, marking a significant advancement in the technology-driven approach to evaluating rice growth parameters and vegetation indices, providing valuable insights for advancing gas emissions studies in rice paddies.

Improving Optical Flow Sensor Using a Gimbal for Quadrotor Navigation in GPS-Denied Environment.

This paper proposes a new sensor using optical flow to stabilize a quadrotor when a GPS signal is not available. Normally, optical flow varies with the attitude of the aerial vehicle. This produces positive feedback on the attitude control that destabilizes the orientation of the vehicle. To avoid this, we propose a novel sensor using an optical flow camera with a 6DoF IMU (Inertial Measurement Unit) mounted on a two-axis anti-shake stabilizer mobile aerial gimbal. We also propose a robust algorithm based on Sliding Mode Control for stabilizing the optical flow sensor downwards independently of the aerial vehicle attitude. This method improves the estimation of the position and velocity of the quadrotor. We present experimental results to show the performance of the proposed sensor and algorithms.

Multispectral and thermal infrared data, visual scores for severity of common rust symptoms, and genotypic single nucleotide polymorphism data of three F2-derived biparental doubled-haploid maize populations.

Three F2-derived biparental doubled haploid (DH) maize populations were generated for genetic mapping of resistance to common rust. Each of the three populations has the same susceptible parent, but a different resistance donor parent. Population 1 and 3 consist of 320 lines each, population 2 consists of 260 lines. The DH lines were evaluated for their susceptibility to common rust in two years and with two replications in each year. For phenotyping, a visual score (VS) for susceptibility was assigned. Additionally, unmanned aerial vehicle (UAV) derived multispectral and thermal infrared data was recorded and combined in different vegetation indices ("remote sensing", RS). The DH lines were genotyped with the DarTseq method, to obtain data on single nucleotide polymorphisms (SNPs). After quality control, 9051 markers remained. Missing values were "imputed" by the empirical mean of the marker scores of the respective locus. We used the data for comparison of genome-wide association studies and genomic prediction when based on different phenotyping methods, that is either VS or RS data. The data may be interesting for reuse for instance for benchmarking genomic prediction models, for phytopathological studies addressing common rust, or for specifications of vegetation indices.

Monitoring of simulated clandestine graves of victims using UAVs, GPR, electrical tomography and conductivity over 4-8 years post-burial to aid forensic search investigators in Colombia, South America.

In Colombia there are estimated to be over 121,000 missing people and victims of forced disappearances. Forensic investigators therefore need assistance in determining optimal detection techniques for buried victims, to give victims' families closure and for the wider community to see that justice is being served. Previous research has created 12 controlled simulated clandestine graves of typical Colombian murder victim scenarios at 0.5 m - 1.2 m depths in savannah and rainforest sites in Colombia. The 0-3 years of geophysical monitoring results of were published, with this paper reporting on 4-8 years monitoring of both UAV drone results and geophysical data. The UAV results from the year 8 survey, published for first time from Colombia, showed that the simulated graves could still be located using NDVI and NIR multi-spectral data, but not using optical or other multi-spectral data. The 0-3 years of geophysical data found the simulated clandestine graves could be detected with electrical resistivity and GPR methods, with the 4-8 year surveys evidencing that they could still be detected using bulk ground conductivity surveys, GPR horizontal time slice datasets and 2D ERT profiles. Research implications suggest initial use of UAV remote sensing technology to pinpoint likely search areas, before subsequent ground reconnaissance, geophysical surveys and their interpretation, before intrusive investigation methods are employed for detecting missing and disappeared persons in Colombia.

Real-Time Person Detection in Wooded Areas Using Thermal Images from an Aerial Perspective.

Detecting people in images and videos captured from an aerial platform in wooded areas for search and rescue operations is a current problem. Detection is difficult due to the relatively small dimensions of the person captured by the sensor in relation to the environment. The environment can generate occlusion, complicating the timely detection of people. There are currently numerous RGB image datasets available that are used for person detection tasks in urban and wooded areas and consider the general characteristics of a person, like size, shape, and height, without considering the occlusion of the object of interest. The present research work focuses on developing a thermal image dataset, which considers the occlusion situation to develop CNN convolutional deep learning models to perform detection tasks in real-time from an aerial perspective using altitude control in a quadcopter prototype. Extended models are proposed considering the occlusion of the person, in conjunction with a thermal sensor, which allows for highlighting the desired characteristics of the occluded person.

Characterization of Rice Yield Based on Biomass and SPAD-Based Leaf Nitrogen for Large Genotype Plots.

The use of Unmanned Aerial Vehicle (UAV) images for biomass and nitrogen estimation offers multiple opportunities for improving rice yields. UAV images provide detailed, high-resolution visual information about vegetation properties, enabling the identification of phenotypic characteristics for selecting the best varieties, improving yield predictions, and supporting ecosystem monitoring and conservation efforts. In this study, an analysis of biomass and nitrogen is conducted on 59 rice plots selected at random from a more extensive trial comprising 400 rice genotypes. A UAV acquires multispectral reflectance channels across a rice field of subplots containing different genotypes. Based on the ground-truth data, yields are characterized for the 59 plots and correlated with the Vegetation Indices (VIs) calculated from the photogrammetric mapping. The VIs are weighted by the segmentation of the plants from the soil and used as a feature matrix to estimate, via machine learning models, the biomass and nitrogen of the selected rice genotypes. The genotype IR 93346 presented the highest yield with a biomass gain of 10,252.78 kg/ha and an average daily biomass gain above 49.92 g/day. The VIs with the highest correlations with the ground-truth variables were NDVI and SAVI for wet biomass, GNDVI and NDVI for dry biomass, GNDVI and SAVI for height, and NDVI and ARVI for nitrogen. The machine learning model that performed best in estimating the variables of the 59 plots was the Gaussian Process Regression (GPR) model with a correlation factor of 0.98 for wet biomass, 0.99 for dry biomass, and 1 for nitrogen. The results presented demonstrate that it is possible to characterize the yields of rice plots containing different genotypes through ground-truth data and VIs.

Combining exposed tree roots and UAV imagery to quantify land denudation in central Mexico.

Approximately 42 % of Mexico is affected by soil denudation resulting from moderate to severe sheet erosion and gullying processes. At Huasca de Ocampo (central Mexico), soil degradation has been linked to intense land use dating back to pre-Hispanic times as well as to unfavorable geological, geomorphic, and climatic conditions. Here, we quantify erosion rates with high precision at annual to multi-decadal timescales by combining, for the first time, dendrogeomorphic reconstructions and UAV-based remote sensing. To assess rates of sheet erosion and gullying processes over the longer-term erosion rates (10-60 yrs), we assessed the age and first exposure of 159 roots to determine sheet erosion rates and gullying processes. At shorter timescales (<3 yrs), we employed an Unmanned Aerial Vehicle (UAV) to develop digital surface models (DSMs) for February 2020 and September 2022. Exposed roots provided evidence of sheet erosion ranging between 2.8 and 43.6 mm yr-1 and channel widening ranging between 11 and 270 mm yr-1, with highest erosion rates found along gully slopes. The UAV-based approach pointed to intense gully headcut retreat with rates between 164.8 and 870.4 mm yr-1; within gullies, channel widening rates ranged between 88.7 and 213.6 mm yr-1 and gully incision rates were between 11.8 and 109.8 mm yr-1. The two approaches yielded very comparable results regarding gully erosion and channel widening; this underlines the potential of using exposed roots to quantifying soil degradation processes retrospectively and considerably beyond the period covered by UAV imagery.

IoT Off-Grid, Data Collection from a Machine Learning Classification Using UAV.

IoT encompasses various objects, technologies, communication standards, sensors, actuators in powered environments, and networked communication. The concept adopted here, IoT off-grid, considers an environment without commercial electricity and commercial internet. Managing various utilities with IoT and collecting the relevant information from this environment is the purpose of this project. It uses machine learning to select relevant data. These data are collected safely using a drone that travels through the off-grid stations. A systematic literature mapping is presented, identifying the state of the art. The result is a software architecture proposal with configurations in the drone and off-grid stations that contemplate data collection from the IoT off-grid environment. The results are also presented with different selection algorithms used in machine learning and final execution in the prototype.

UAV-Based Smart Educational Mechatronics System Using a MoCap Laboratory and Hardware-in-the-Loop.

Within Industry 4.0, drones appear as intelligent devices that have brought a new range of innovative applications to the industrial sector. The required knowledge and skills to manage and appropriate these technological devices are not being developed in most universities. This paper presents an unmanned aerial vehicle (UAV)-based smart educational mechatronics system that makes use of a motion capture (MoCap) laboratory and hardware-in-the-loop (HIL) to teach UAV knowledge and skills, within the Educational Mechatronics Conceptual Framework (EMCF). The macro-process learning construction of the EMCF includes concrete, graphic, and abstract levels. The system comprises a DJI Phantom 4, a MoCap laboratory giving the drone location, a Simulink drone model, and an embedded system for performing the HIL simulation. The smart educational mechatronics system strengthens the assimilation of the UAV waypoint navigation concept and the capacity for drone flight since it permits the validation of the physical drone model and testing of the trajectory tracking control. Moreover, it opens up a new range of possibilities in terms of knowledge construction through best practices, activities, and tasks, enriching the university courses.

System Identification and Nonlinear Model Predictive Control with Collision Avoidance Applied in Hexacopters UAVs.

Accurate trajectory tracking is a critical property of unmanned aerial vehicles (UAVs) due to system nonlinearities, under-actuated properties and constraints. Specifically, the use of unmanned rotorcrafts with accuracy trajectory tracking controllers in dynamic environments has the potential to improve the fields of environment monitoring, safety, search and rescue, border surveillance, geology and mining, agriculture industry, and traffic control. Monitoring operations in dynamic environments produce significant complications with respect to accuracy and obstacles in the surrounding environment and, in many cases, it is difficult to perform even with state-of-the-art controllers. This work presents a nonlinear model predictive control (NMPC) with collision avoidance for hexacopters' trajectory tracking in dynamic environments, as well as shows a comparative study between the accuracies of the Euler-Lagrange formulation and the dynamic mode decomposition (DMD) models in order to find the precise representation of the system dynamics. The proposed controller includes limits on the maneuverability velocities, system dynamics, obstacles and the tracking error in the optimization control problem (OCP). In order to show the good performance of this control proposal, computational simulations and real experiments were carried out using a six rotary-wind unmanned aerial vehicle (hexacopter-DJI MATRICE 600). The experimental results prove the good performance of the predictive scheme and its ability to regenerate the optimal control policy. Simulation results expand the proposed controller in simulating highly dynamic environments that showing the scalability of the controller.

Smart Multi-Sensor System for Remote Air Quality Monitoring Using Unmanned Aerial Vehicle and LoRaWAN.

Deaths caused by respiratory and cardiovascular diseases have increased by 10%. Every year, exposure to high levels of air pollution is the cause of 7 million premature deaths and the loss of healthy years of life. Air pollution is generally caused by the presence of CO, NO2, NH3, SO2, particulate matter PM10 and PM2.5, mainly emitted by economic activities in large metropolitan areas. The problem increases considerably in the absence of national regulations and the design, installation, and maintenance of an expensive air quality monitoring network. A smart multi-sensor system to monitor air quality is proposed in this work. The system uses an unmanned aerial vehicle and LoRa communication as an alternative for remote and in-situ atmospheric measurements. The instrumentation was integrated modularly as a node sensor to measure the concentration of carbon monoxide (CO), nitrogen dioxide (NO2), ammonia (NH3), sulfur dioxide (SO2), and suspended particulate mass PM10 and PM2.5. The optimal design of the multi-sensor system has been developed under the following constraints: A low weight, compact design, and low power consumption. The integration of the multi-sensor device, UAV, and LoRa communications as a single system adds aeeded flexibility to currently fixed monitoring stations.

Fuzzy Gain-Scheduling PID for UAV Position and Altitude Controllers.

Unmanned aerial vehicle (UAV) applications have evolved to a wide range of fields in the last decade. One of the main challenges in autonomous tasks is the UAV stability during maneuvers. Thus, attitude and position control play a crucial role in stabilizing the vehicle in the desired orientation and path. Many control techniques have been developed for this. However, proportional integral derivative (PID) controllers are often used due their structure and efficiency. Despite PID's good performance, different requirements may be present at different mission stages. The main contribution of this research work is the development of a novel strategy based on a fuzzy-gain scheduling mechanism to adjust the PID controller to stabilize both position and altitude. This control strategy must be effective, simple, and robust to uncertainties and external disturbances. The Robot Operating System (ROS) integrates the proposed system and the flight control unit. The obtained results showed that the proposed approach was successfully applied to the trajectory tracking and revealed a good performance compared to conventional PID and in the presence of noises. In the tests, the position controller was only affected when the altitude error was higher, with an error of 2% lower.

Analysis of a Fast Control Allocation approach for nonlinear over-actuated systems.

Autonomous Robots with multiple directional thrusters are normally over-actuated systems that require nonlinear control allocation methods to map the forces that drive the robot's dynamics and act as virtual control variables to the actuators. This process demands computational efforts that, sometimes, are not available in small robotic platforms. The present paper introduces a new control allocation approach with fast convergence, high accuracy, and dealing with complex nonlinear problems, especially in embedded systems. The adopted approach divides the desired nonlinear system into coupled linear problems. For that purpose, the Real Actions (RAs) and Virtual Control Variables (VCVs) are broke in two or more sets each. While the RA subsets are designed to linearize the system according to different input subspaces, the VCV is designed to be partially coupled to overlap the output subspaces. This approach generates smaller linear systems with fast and robust convergence used sequentially to solve nonlinear allocation problems. This methodology is assessed in mathematical tutorial cases and over-actuated UAV simulations.

Closing Connectivity Gap: An Overview of Mobile Coverage Solutions for Not-Spots in Rural Zones.

Access to broadband communications in different parts of the world has become a priority for some governments and regulatory authorities around the world in recent years. Building new digital roads and pursuing a connected society includes looking for easier access to the internet. In general, not all areas where people congregate are fully covered, especially in rural zones, thus restricting access to data communications and inducing inequality. In the present review article, we have comprehensively surveyed the use of three platforms to deliver broadband services to such remote and low-income areas, and they are proposed as follows: unmanned aerial vehicles (UAV), altitude platforms (AP), and low-Earth orbit (LEO) satellites. These novel strategies support the connected and accessible world hypothesis. Hence, UAVs are considered a noteworthy solution since their efficient maneuverability can solve rural coverage issues or not-spots.

Flight Planning Optimization of Multiple UAVs for Internet of Things.

This article presents an approach to autonomous flight planning of Unmanned Aerial Vehicles (UAVs)-Drones as data collectors to the Internet of Things (IoT). We have proposed a model for only one aircraft, as well as for multiple ones. A clustering technique that extends the scope of the number of IoT devices (e.g., sensors) visited by UAVs is also addressed. The flight plan generated from the model focuses on preventing breakdowns due to a lack of battery charge to maximize the number of nodes visited. In addition to the drone autonomous flight planning, a data storage limitation aspect is also considered. We have presented the energy consumption of drones based on the aerodynamic characteristics of the type of aircraft. Simulations show the algorithm's behavior in generating routes, and the model is evaluated using a reliability metric.

Communication Interface Manager for Improving Performance of Heterogeneous UAV Networks.

Exchanging messages with stable connections in missions composed of multiple unmanned aerial vehicles (UAV) remains a challenge. The variations in UAV distances from each other, considering their individual trajectories, and the medium dynamic factors are important points to be addressed.In this context, to increase the stability of UAV-to-UAV (U2U) communication with link quality, this paper presents an interface manager (IM) that is capable of improving communication in multi-UAV networks.Given a predefined set of available individual wireless interfaces, the proposed IM dynamically defines the best interface for sending messages based on on-flight conditions sensed and calculated dynamically from the wireless medium. Different simulation scenarios are generated using a complex and realistic experimental setup composed of traditional simulators such as NS-3, Gazebo, and GzUAV. IEEE 802.11n 2.4 GHz and 802.11p 5 GHz interfaces are used for the IM selection. The IM performance is evaluated in terms of metrics from the medium-access-control (MAC) and physical layers, which aim to improve and maintain the connectivity between the UAVs during the mission, and from the application layer, which targets the reliability in the delivery of messages. The obtained results show that compared with the cases where a single interface is used, the proposed IM is able to increase the network throughput and presents the best proportion of transmitted and received packets, reception power (-60 dBm to -75 dBm), and loss (-80 dB to -85 dB), resulting in a more efficient and stable network connections.

The use of an unoccupied aerial vehicle to survey shark species over sand and rocky-reef habitats in a marine protected area.

Cabo Pulmo National Park was established in 1995 and has since seen a large increase in fish biomass. An unoccupied aerial vehicle (UAV) was used to survey shallow coastal habitat in which lemon sharks (Negaprion brevirostris), bull sharks (Carcharhinus leucas) and Pacific nurse sharks (Ginglymostoma unami) were recorded. Sharks were more common in the afternoon, potentially using warmer shallow areas to behaviourally thermoregulate. This study highlights UAV surveying to be a viable tool for species identification, a limitation of previous terrestrial surveys conducted in the area.

A Framework for Coverage Path Planning Optimization Based on Point Cloud for Structural Inspection.

Different practical applications have emerged in the last few years, requiring periodic and detailed inspections to verify possible structural changes. Inspections using Unmanned Aerial Vehicles (UAVs) should minimize flight time due to battery time restrictions and identify the terrain's topographic features. In this sense, Coverage Path Planning (CPP) aims at finding the best path to coverage of a determined area respecting the operation's restrictions. Photometric information from the terrain is used to create routes or even refine paths already created. Therefore, this research's main contribution is developing a methodology that uses a metaheuristic algorithm based on point cloud data to inspect slope and dams structures. The technique was applied in a simulated and real scenario to verify its effectiveness. The results showed an increasing 3D reconstructions' quality observing optimizing photometric and mission time criteria.