Low-altitude Unmanned Aerial Vehicle Research Articles

Combining spectrum, thermal, and texture features using machine learning algorithms for wheat nitrogen nutrient index estimation and model transferability analysis

The nitrogen nutrition index (NNI) has been extensively applied for the diagnosis of crop nitrogen status, providing insights into efficient nitrogen utilization and plant growth. In this study, we utilized a low-altitude unmanned aerial vehicle (UAV) platform, equipped with multispectral (MS), red–green–blue (RGB), and thermal infrared (TIR) cameras, to comprehensively capture wheat spectral information. The analysis of the relationship between NNI and relative yield revealed an initially linear relationship, which saturated for high NNI values. To enhance accuracy and minimize complexity, we employed a random forest (RF) – recursive feature elimination (RFE) method to select features as inputs for four machine learning (ML) models: back propagation neural network (BPNN), extreme learning machine (ELM), support vector regression (SVR), and Gaussian process regression (GPR). After feature selection, the prediction accuracies of single-sensor models were ranked as: MS > RGB > TIR. The R2 values for the four ML models were in the range of 0.54–0.75. Among multi-sensor combinations, the GPR with MS + RGB + TIR input features achieved the best results with R2 = 0.89 and RPD = 2.52. Further, the dataset was partitioned into six subsets based on location and cultivar variety to evaluate model transferability. The results showed that the transferability largely suffered during the bivariate conditions of different varieties at different locations; the transferability of the model was average improved by 11 % when GPR was combined with transfer component analysis (TCA). The accuracy and transferability of the NNI estimation models significantly improved, offering valuable guidance and methodological support for diagnosing the nitrogen nutrient status of wheat.

AFENet: Attention-guided feature enhancement network and a benchmark for low-altitude UAV sewage outfall detection

Inspecting sewage outfall into rivers is significant to the precise management of the ecological environment because they are the last gate for pollutants to enter the river. Unmanned Aerial Vehicles (UAVs) have the characteristics of maneuverability and high-resolution images and have been used as an important means to inspect sewage outfalls. UAVs are widely used in daily sewage outfall inspections, but relying on manual interpretation lacks the corresponding low-altitude sewage outfall images dataset. Meanwhile, because of the sparse spatial distribution of sewage outfalls, problems like less labeled sample data, complex background types, and weak objects are also prominent. In order to promote the inspection of sewage outfalls, this paper proposes a low-attitude sewage outfall object detection dataset, namely UAV-SOD, and an attention-guided feature enhancement network, namely AFENet. The UAV-SOD dataset features high resolution, complex backgrounds, and diverse objects. Some of the outfall objects are limited by multi-scale, single-colored, and weak feature responses, leading to low detection accuracy. To localize these objects effectively, AFENet first uses the global context block (GCB) to jointly explore valuable global and local information, and then the region of interest (RoI) attention module (RAM) is used to explore the relationships between RoI features. Experimental results show that the proposed method improves detection performance on the proposed UAV-SOD dataset than representative state-of-the-art two-stage object detection methods.

Detection of Military Targets on Ground and Sea by UAVs with Low-Altitude Oblique Perspective

Small-scale low-altitude unmanned aerial vehicles (UAVs) equipped with perception capability for military targets will become increasingly essential for strategic reconnaissance and stationary patrols in the future. To respond to challenges such as complex terrain and weather variations, as well as the deception and camouflage of military targets, this paper proposes a hybrid detection model that combines Convolutional Neural Network (CNN) and Transformer architecture in a decoupled manner. The proposed detector consists of the C-branch and the T-branch. In the C-branch, Multi-gradient Path Network (MgpNet) is introduced, inspired by the multi-gradient flow strategy, excelling in capturing the local feature information of an image. In the T-branch, RPFormer, a Region–Pixel two-stage attention mechanism, is proposed to aggregate the global feature information of the whole image. A feature fusion strategy is proposed to merge the feature layers of the two branches, further improving the detection accuracy. Furthermore, to better simulate real UAVs’ reconnaissance environments, we construct a dataset of military targets in complex environments captured from an oblique perspective to evaluate the proposed detector. In ablation experiments, different fusion methods are validated, and the results demonstrate the effectiveness of the proposed fusion strategy. In comparative experiments, the proposed detector outperforms most advanced general detectors.

3D reconstruction of spherical images based on incremental structure from motion

ABSTRACT 3D reconstruction plays an increasingly important role in modern photogrammetric systems. Conventional satellite or aerial-based remote sensing (RS) platforms can provide the necessary data sources for the 3D reconstruction of large-scale landforms and cities. Even with low-altitude UAVs (Unmanned Aerial Vehicles), 3D reconstruction in complicated situations, such as urban canyons and indoor scenes, is challenging due to the frequent tracking failures of camera frames and high data collection costs. Recently, spherical images have been extensively exploited due to the capability of recording surrounding environments using one camera exposure. Classical 3D reconstruction pipelines, however, cannot be used for spherical images. Besides, there exist few software packages for the 3D reconstruction of spherical images. Based on the imaging geometry of spherical cameras, this study investigates the algorithms for relative orientation using spherical correspondences, absolute orientation using 3D correspondences between the scene and spherical points, as well as cost functions for BA (bundle adjustment) optimization. Besides, an incremental SfM (Structure from Motion) workflow has been proposed for spherical images by using the above-mentioned algorithms. The proposed solution is finally verified by using three spherical datasets captured by both consumer-grade and professional spherical cameras. The results demonstrate that the proposed SfM workflow can achieve the successful 3D reconstruction of complex scenes and provide useful clues for the implementation in open-source software packages. The source code would be publicly available.

Unmanned aerial vehicle-assisted wideband cognitive radio network based on DDQN-SAC

Cognitive radio (CR) systems have emerged as effective tools for improving spectrum efficiency and meeting the growing demands of communication. This study focuses on a flexible CR system based on opportunistic spectrum access technology, which enables secondary networks to efficiently utilize unoccupied spectrum resources for information transmission by actively sensing the spectrum utilization of primary networks. Specifically, we introduce unmanned aerial vehicles (UAV) technology into the CR system to further enhance its flexibility and adaptability, which enables the transmission efficiency of low-altitude UAV networks. In this CR system, UAVs are employed for more flexible spectrum management. The objective of this research is to maximize the average achievable rate of SUs by jointly optimizing the trajectories of secondary UAV, the trajectories of primary UAV, the beamforming of secondary UAV, subchannel allocation and sensing time. To achieve this goal, we employ deep reinforcement learning (DRL) algorithms to optimize these variables. Compared to traditional optimization algorithms, DRL algorithms not only have lower computational complexity but also achieve faster convergence. To address the mixed-action space problem, we propose a Dueling DQN-Soft Actor Critic algorithm. Simulation results demonstrate that the proposed approach in this paper significantly enhances the performance of the CR system compared to traditional baseline schemes. This is manifested in higher spectrum efficiency and data transmission rates, while minimizing interference with the primary network. This innovative research combines drone technology and DRL algorithms, bringing new opportunities and challenges to the future development of cognitive communication systems.

Privacy-Preserving Location Authentication for Low-altitude UAVs: A Blockchain-based Approach

Efficient and trusted regulation of unmanned aerial vehicles (UAVs) is an essential but challenging issue in the future era of Internet of Low-altitude Intelligence, due to the difficulties in UAVs' identity recognition and location matching, potential for falsified information reporting, etc. To address this challenging issue, in this paper, we propose a blockchain-based UAV location authentication scheme, which employs a distance bounding protocol to establish a location proof, ensuring the authenticity of UAV positions. To preserve the privacy of UAVs, anonymous certificates and zero-knowledge proof are used. The security of the proposed scheme is analyzed. Experiments demonstrate the efficiency and feasibility of the proposed scheme.

The Study of Various Regression Models Establishment to Identify Farmland Soil Moisture Content at Different Depths Using Unmanned Aerial Vehicle Multispectral Data: A Case in North China Plain

Soil moisture content is one of the most important soil indices for agriculture production. With the increasing food requirement and limited irrigation water sources, it is of great significance to accurately and quickly measure the soil moisture content for precision irrigation, especially in deficient agricultural areas, such as North China Plain. To achieve this goal, more attention was paid to the application of unmanned aerial vehicle multispectral reflectance technology. However, it was urgent to enhance the regression models between spectral data and soil realistic moisture content, and there were limited studies about the regression research on deep soil layers. Thus, the farmland of winter wheat–summer maize double cropping at Yongnian District, Hebei, North China, was selected as the study area. A six-band multispectral camera mounted on a low-altitude unmanned aerial vehicle (UAV) was used to obtain the field spectral reflectance with bands from 470~810 nm, and meanwhile, soil moisture content at different depths (10, 20, 30, 40, 50, and 60 cm) was measured after maize sowing. Unary linear regression (ULR), multivariate linear regression (MLR), ridge regression (RR), and an artificial neural network (ANN) were employed to establish regression models. The results demonstrated that the sensitive bands of spectral reflectance were 690 nm, 470 nm, and 810 nm. Those models all established significant regression at the depths of 0–20 cm and 40–60 cm, particularly at 10, 50, and 60 cm soil layers. However, for a depth of 20–40 cm, the prediction accuracy was generally lower. Among MLR, RR, and BP models, the MLR exhibited the highest identification accuracy, which was most recommended for the application. The findings of this study provide technical guidance and effective regression for the multispectral reflectance on the farmland of North China Plain, especially for deep soil layer moisture prediction.

A 3D-2DCNN-CA approach for enhanced classification of hickory tree species using UAV-based hyperspectral imaging

Hickory trees possess substantial economic, nutritional, and ecological value, and they play a pivotal role in both human societies and natural ecosystems. To maximize benefits, many bases have adopted a composite planting strategy. Effective and timely monitoring of hickory forest species information is crucial for precise management and conservation. In this study, a low-altitude unmanned aerial vehicle (UAV) was employed to capture RGB and hyperspectral data from the canopy of two hickory bases. A hybrid convolutional neural network structure was then utilized to classify different tree species and congeneric hickory species. By introducing a channel attention module to refine the features of hyperspectral images, classification stability was enhanced. The experimental results demonstrate that hyperspectral images yield superior classification performance in hickory species identification compared to RGB images, particularly in classifying highly homogeneous tree species. The 3D-2DCNN-CA proposed in this paper demonstrated the best performance in classifying hickory species compared to other classification methods. In the classification of different tree species, the accuracy for a single hickory reached 99.38%, and in the classification of the same hickory species, it achieved an accuracy of 93.97%. Furthermore, this method also achieved significant classification results at the single-tree scale. These results indicate that the method can realize fine-scale monitoring of hickory forests and provide substantial support for forest land management and expert guidance on planting distribution.

A review of perception sensors, techniques, and hardware architectures for autonomous low-altitude UAVs in non-cooperative local obstacle avoidance

Unmanned Aerial Vehicles (UAVs) can detect and communicate with cooperative obstacles through established protocols. However, non-cooperative obstacles pose a significant threat to UAVs during low-flight operations. These obstacles include static obstacles like buildings, trees, or communication towers and dynamic objects like other UAVs. The application of autonomous UAVs in low-altitude surveillance has motivated research into non-cooperative local obstacle avoidance. This paper provides an overview of such solutions that have been proposed within the last decade. Unlike most literature that limits obstacle avoidance to algorithms, this work provides an in-depth review of obstacle avoidance components, namely the perception sensor, techniques, and hardware architecture of the obstacle avoidance system. This review categorizes the non-cooperative obstacle avoidance techniques into four groups: gap-based methods, geometric methods, repulsive force-based methods, and Artificial Intelligence (AI) based methods. This paper provides a comprehensive resource for researchers working on collision-free surveillance by autonomous UAVs at low altitudes.

Lightweight Low-Altitude UAV Object Detection Based on Improved YOLOv5s

Abstract In the context of rapid developments in drone technology, the significance of recognizing and detecting low-altitude unmanned aerial vehicles (UAVs) has grown. Although conventional algorithmic enhancements have increased the detection rate of low-altitude UAV targets, they tend to neglect the intricate nature and computational demands of the algorithms. This paper introduces ATD-YOLO, an enhanced target detection model based on the YOLOv5s architecture, aimed at tackling this issue. Firstly, a realistic low-altitude UAV dataset is fashioned by amalgamating various publicly available datasets. Secondly, a C3F module grounded in FasterNet, incorporating Partial Convolution (PConv), is introduced to decrease model parameters while upholding detection accuracy. Furthermore, the backbone network incorporates an Efficient Multi-Scale Attention (EMA) module to extract essential image information while filtering out irrelevant details, facilitating adaptive feature fusion. Additionally, the universal upsampling operator CARAFE (Content-aware reassembly of features) is utilized instead of nearest-neighbor upsampling. This enhancement boosts the performance of the feature pyramid network by expanding the receptive field for data feature fusion. Lastly, the Slim-Neck network is introduced to fine-tune the feature fusion network, thereby reducing the model’s floating-point calculations and parameters. Experimental findings demonstrate that the improved ATD-YOLO model achieves an accuracy of 92.8%, with a 31.4% decrease in parameters and a 28.7% decrease in floating-point calculations compared to the original model. The detection speed reaches 75.37 frames per second (FPS). These experiments affirm that the proposed enhancement method meets the deployment requirements for low computational power while maintaining high precision.

Measurement-based fading characteristics analysis and modeling of UAV to vehicles channel

With the rapid development of unmanned aerial vehicle (UAV) and autonomous driving technology, wireless communication between UAV and vehicles has become one of the hotspots in the research of intelligent transportation systems (ITS). Particularly, link-level UAV-based communication requires correlation characteristics of propagation channel. In the current channel measurement, the transmitter or receiver of the ground is fixed, which ignores the high dynamics of the vehicle and the complexity of the environment in the ITS scene. Therefore, it is necessary to conduct a dynamic channel measurement and analysis for UAV. In this paper, we carry out an UAV-to-Vehicle (U2V) measurement campaign in S- and C-band for multiple scenarios of low-altitude UAV and mobile vehicles propagation and provide a comprehensive investigation of channel fading characteristics. Based on the measurement data, the statistics of large-scale fading (path loss, shadow fading and its autocorrelation) and small-scale fading (amplitude distribution) for several typical measurement scenarios are extracted first, which are compared with other air-to-ground (A2G) and standard terrestrial propagation scenarios to analyze the U2V propagation characteristics in various scenarios. A comprehensive analysis and comparative study of all considered channel parameters extracted is then performed to reflect the physical laws behind the measurements. The analysis results reveal that the Log-distance model outperforms the considered typical models in terms of predicting the path loss, and the proposed autocorrelation model shows better performance than traditional models. The quantitative results are essential for modeling and realizing reliable communications in U2V wireless systems and analyzing the performance for UAV-enabled ITS.

Dual-Channel Semi-Supervised Adversarial Network for Building Segmentation from UAV-Captured Images

Accurate building extraction holds paramount importance in various applications such as urbanization rate calculations, urban planning, and resource allocation. In response to the escalating demand for precise low-altitude unmanned aerial vehicle (UAV) building segmentation in intricate scenarios, this study introduces a semi-supervised methodology to alleviate the labor-intensive process of procuring pixel-level annotations. Within the framework of adversarial networks, we employ a dual-channel parallel generator strategy that amalgamates the morphology-driven optical flow estimation channel with an enhanced multilayer sensing Deeplabv3+ module. This approach aims to comprehensively capture both the morphological attributes and textural intricacies of buildings while mitigating the dependency on annotated data. To further enhance the network’s capability to discern building features, we introduce an adaptive attention mechanism via a feature fusion module. Additionally, we implement a composite loss function to augment the model’s sensitivity to building structures. Across two distinct low-altitude UAV datasets within the domain of UAV-based building segmentation, our proposed method achieves average mean pixel intersection-over-union (mIoU) ratios of 82.69% and 79.37%, respectively, with unlabeled data constituting 70% of the overall dataset. These outcomes signify noteworthy advancements compared with contemporaneous networks, underscoring the robustness of our approach in tackling intricate building segmentation challenges in the domain of UAV-based architectural analysis.

Identification and Classification of Degradation-Indicator Grass Species in a Desertified Steppe Based on HSI-UAV

The emergence and number of grassland degradation-indicator grass species are important in evaluating the extent of grassland degradation. Plant populations in desertified steppe are distributed randomly and at low density. Specifically, degradation-indicator grass species mainly exist as individuals, making spectrum-based identification difficult. Here, a low-altitude unmanned aerial vehicle (UAV) hyperspectral remote-sensing system was constructed to identify the typical degradation-indicator grass species of a desertified steppe in China. The ASI index (Artemisia frigida Willd. and Stipa breviflora Grisb. index) and classification rules were proposed and applied. We implemented a comprehensive application of amplified differences in spectral characteristics between vegetation communities and assigned plant senescence reflectance-index bands, using the characteristics of the plant populations under observation and UAV hyperspectral remote-sensing data, to solve the problems resulting from high similarity while identifying ground objects. Our results lay a solid foundation for monitoring and evaluating desertified steppe degradation-indicator grass species based on remote sensing.

Review on the development of multi- and hyperspectral remote sensing technology for exploration of copper–gold deposits

Most Copper (Cu) and Gold (Au) deposits are accompanied by hydrothermal alteration, generally related to ore-forming hydrothermal fluids. Multispectral and hyper-spectral Remote Sensing (RS) technology is essential for Cu-Au mineral prospecting. This paper provides an overview of RS data and the research situation and development tendencies of RS exploration technologies related to Cu-Au deposits. Initially, RS geologists applied the Band Ratio (BR) and Principal Component Analysis (PCA) to extract hydroxyl and iron anomalies from Landsat RS data to characterize the hydrothermal alterations associated with Cu-Au deposits. In the era of advanced spaceborne thermal emission and reflection radiometry (ASTER), clay minerals, sulfate minerals, carbonate minerals, silica minerals, and iron minerals can be identified because of three Visible and near-infrared bands (VNIR), six shortwave infrared bands (SWIR), and five Thermal Infrared bands (TIR). Alteration of mineral assemblages can be carried out to map alteration zones, which are essential for calibrating Cu-Au alteration zones, such as the typical alteration zoning characteristics of Porphyry Copper Deposits (PCD). Because of its high spectral resolution, Satellite hyperspectral RS can quantitatively map surface alteration minerals to indicate the exploration of Cu-Au deposits. RS geologists have extensively researched matching libraries and field spectra for Alteration Mineral Mapping (AMM). However, subpixel mineral information caused by low spatial resolution and atmospheric factors has an unavoidable influence on satellite hyperspectral RS AMM, and it is essential to use low-altitude unmanned aerial vehicle (UAV) hyperspectral RS. UAV hyperspectral AMM combined with geochemistry and geophysics is a means of prospecting and exploring Cu-Au deposits.

An Operational Capacity Assessment Method for an Urban Low-Altitude Unmanned Aerial Vehicle Logistics Route Network

The Federal Aviation Administration introduced the concept of urban air mobility (UAM), a new three-dimensional transport system that operates with a fusion of manned/unmanned aerial vehicles on an urban or intercity scale. The rapid development of UAM has brought innovation and dynamism to many industries, especially in the field of logistics. Various types of unmanned aerial vehicles (UAVs) for use in transport logistics are being designed and produced. UAV logistics refers to the use of UAVs, usually carrying goods and parcels, to achieve route planning, identify risk perception, facilitate parcel delivery, and carry out other functions. This research provides a method for assessing the operational capacity of a UAV logistics route network. The concept of “logistics UAV route network operation capacity” is defined, and a bi-objective optimization model for assessing the route network’s operating capacity is developed. The first objective is to maximize the number of UAV logistics delivery plans that can be executed in a fixed operation time. The second objective is to minimize the total operational impedance value in a fixed operation time. To solve the bi-objective optimization model, the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) is utilized. A UAV logistics route network with 62 nodes is developed to assess the rationale and validity of the proposed concept. The experiments show that with an increase in operation time, the route network’s optimal operational capacity gradually increases, the convergence speed of the algorithm slows down, and the optimization magnitude gradually reduces. Two key parameters—operational safety interval and flight speed—are further analyzed in the experiments. According to the experiments, as the safety interval increases, the route network’s average operational capacity steadily diminishes, as does its sensitivity to the safety interval. The average operational capacity steadily rose with the rise in flight speed, especially when the UAV logistics flight speed was between 10 m/s and 10.5 m/s. In that range, the operational capacity of the route network was substantially impacted by the flight speed.

Low-Altitude UAV Air-to-Ground Multilink Channel Modeling and Analysis at 2.4 and 5.9 GHz

Due to low cost and high operability, unmanned aerial vehicle(UAV) becomes a key component in future intelligent transportation system(ITS) for various use cases. Air-to-ground(A2G) communication is a fundamental technology for integration of UAV in the ITS, where accurate analysis and modeling of UAV A2G wireless channel are of great importance for communication algorithm development. In this paper, we present a comprehensive analysis and modeling of low altitude UAV A2G channel at 2.4 and 5.9 GHz based on multi-link channel measurement campaign. Based on the measured data, the value of path loss as a function of the elevation angle and distance is proposed. Further, the shadow fading(SF) is analyzed for different frequency bands and the spatial correlation is evaluated. Particularly, it is found that the influence of UAV altitude on shadowing is significant and should be considered when developing A2G communication system.

A Real-Time Path Planning Method for Urban Low-Altitude Logistics UAVs.

To solve the problem of poor real-time performance in path planning algorithms for unmanned aerial vehicles (UAVs) in low-altitude urban logistics, a path planning method combining modified Beetle Antennae Search (BAS) with the Simulated Annealing (SA) algorithm is proposed. Firstly, based on the requirements of task execution and constraints of UAV flight, a fitness function for real-time search of waypoints is designed while ensuring the safety and obstacle avoidance of the UAV. Then, to improve the search accuracy and real-time performance, determining the initial search direction in the BAS algorithm is improved, while the search step size and antennae sensing length are updated in real-time according to the distance between the UAV and the obstacle. Finally, the SA algorithm is combined with the BAS algorithm to update the waypoints, expanding the search range of each waypoint, avoiding the process of updating the waypoints from becoming trapped in the local optimal waypoints. Meanwhile, the effectiveness of the next waypoint is evaluated based on the Metropolis criterion. This paper generates a virtual urban logistics distribution environment based on the density and distribution of urban buildings, and compares the performance of algorithms in obstacle-sparse, obstacle-moderate, and obstacle-dense environments. The simulation results demonstrate that the improved method in this paper has a more significant capacity for environmental adaptation. In terms of the path length, waypoints, safety obstacle avoidance, and smoothness, the planned path outperforms the original BAS method. It satisfies the needs of real-time path planning for UAVs involved in urban low-altitude logistics.

Research on Public Air Route Network Planning of Urban Low-Altitude Logistics Unmanned Aerial Vehicles

As urban populations continue to grow and road traffic congestion worsens, traditional ground logistics has become less efficient. This has led to longer logistics times and increased costs. Therefore, unmanned aerial vehicle (UAV) logistics has become increasingly popular. However, free-planned routes cannot meet the safety and efficiency requirements of urban airspace mobility. To address this issue, a public air route network for low-altitude logistics UAVs needs to be established in urban areas. This paper proposes a public route network planning method based on the obstacle-based Voronoi diagram and A* algorithm, as follows: Firstly, construct a city airspace grid model in which the characteristics of the airspace are mapped onto the grid map. Introduce an obstacle clustering algorithm based on DBSCAN to generate representative obstacle points as the Voronoi seed nodes. Utilize the Voronoi diagram to establish the initial route network. Then, conduct an improved path planning by employing the A* algorithm for obstacle avoidance in route edges that pass through obstacles. To ensure the safe operation of drones, set constraints on the route safety interval. This process will generate a low-altitude public air route network for urban areas. After considering the flight costs of logistics UAVs at different altitudes, the height for the route network layout is determined. Finally, the route network evaluation indicators are established. The simulation results demonstrate that compared with the city road network planning method and the central radial network planning method, the total route length is shortened by 7.1% and 9%, respectively, the airspace coverage is increased by 9.8% and 35%, respectively, the average network degree is reduced by 52.6% and 212%, respectively, and the average flight time is reduced by 19.4s and 3.7s, respectively. In addition, by solving the network model using the Dijkstra algorithm, when the energy cost and risk cost weights are 0.6 and 0.4, respectively, and the safety interval is taken as 15 m, the total path cost value of the planned trajectory is minimized.

Assessing narrow brown leaf spot severity and fungicide efficacy in rice using low altitude UAV imaging

The utilization of unmanned aerial vehicle (UAV)-based imaging systems offers precise detection of plant diseases and aids in decision-making regarding fungicide applications to optimize disease control. This study employed a twin-lens multispectral camera mounted on a low-altitude UAV to capture imagery data from rice field plots that were treated with different fungicides. The objectives of this study were to assess the severity of narrow brown leaf spot (NBLS) caused by Cercospora janseana and to evaluate the efficacy of fungicide control. Eighteen color features and vegetation indices were extracted from RGB images, while nine color features and vegetation indices were extracted from multispectral images. Through correlation analysis, four spectral features, namely Lab-a, ExGR, VDVI, and g, were found to exhibit high correlations with disease severity. Specifically, RGB imagery had greater correlation coefficients (exceeding 0.95) for both ExGR and Lab-a features compared to multispectral imagery. A multifeature inversion modeling approach was employed, using support vector regression with the top four spectral features to predict NBLS severity. The results indicated R2 values were above 0.93 for all support vector regressions. Furthermore, the efficacies of ten different fungicide treatments were evaluated, with UAV imaging consistently aligning with ground truth rating data in terms of efficacy ranking. These results demonstrate the potential of UAV imagery for use as a valuable tool for NBLS detection and assessing fungicide efficacy, offering significant benefits in the management of NBLS, which is a globally important disease in rice.

Optimal trajectory planning of a small UAV using solar energy and wind energy

Due to size limitations and the working environment near the ground, small low-altitude unmanned aerial vehicles (UAVs) cannot carry large-area solar cells and energy storage devices. Solar energy alone has only a limited effect on the improvement of their endurance. To solve this problem, this study proposes the combination of solar energy technology and dynamic soaring technology to improve the endurance of small UAVs. Then, the optimal energy acquisition strategy based on the combination of solar energy and dynamic soaring technology is analyzed in terms of energy. The motion equations and energy acquisition and consumption models of a small solar UAV based on horizontal wind shear are established. Moreover, an optimal trajectory planning problem with the maximum charging power of rechargeable batteries as the optimization objective is proposed. The optimal trajectory is solved based on the hp adaptive pseudo-spectral method, and the optimal trajectory combining the two technologies is simulated and compared with the constant-altitude constant-velocity (CACV) trajectory of the UAV using only solar technology. The simulation results show that under the flight background of tmission = 6:00 (summer sunrise) and β = 0.125 s−1 (wind gradient of the wind shear), the optimized O-type trajectory decreased the energy consumption power by 39.86% and increased the solar energy acquisition power by 86.34% compared to the CACV trajectory. Consequently, the small UAV stores more energy in the rechargeable batteries to improve the endurance performance. Compared to the environment where the sun is located on the leeward side of the wind shear, the environment where the sun is located on the windward side of the wind shear can enable the UAV to acquire more energy through the optimized O-type trajectory.