Unmanned Aerial Vehicle Platform 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.

Real-time and Intelligent Moving Targets Tracking based on UAV Remote Sensing Video Camera and Brain-like Computing Chips

Abstract. Moving target tracking technology based on Unmanned Aerial Vehicles (UAV) is widely used in many fields such as automatic inspection and emergency response. The existing moving target tracking methods usually have the problems of large computation and low tracking efficiency. Limited by the computing power of the UAV platform, real-time tracking and analysis of multiple targets based on the video data collected by UAV platform is a difficult task. In this paper, we proposed a novel Target Specific Filtering Tracking with Memory (TSFMTrack) method designed for UAV-based real-time tracking tasks, which involves a Tracklet Filtering Module (TFM) for capturing object appearance features and a Tracklet Matching Module (TMM) for bounding box association in each frame. By experimental comparison with other State-Of-The-Art (SOTA) methods on popular MOT and UAV tracking datasets, the TSFMTrack have shown obvious advantages in accuracy, computational efficiency and reliability. Furthermore, we deployed the TSFMTrack on the brain-inspired chip Lynchip KA200, the experimental results have shown that the TSFMTrack is effective on edge computational platform and suitable for UAV real-time tracking tasks.

Light-weight Fusion Network for UAV Visible-light and Infrared Images based on Real-time Brain-like Intelligent Computing

Abstract. Multiple sensors equipped on the Unmanned Aerial Vehicle (UAV) enables the acquisition of multi-modal and multi-source remote sensing data. UAV remote sensing usually faces with real-time or near-real-time tasks in complex and highly dynamic environments, such as disaster monitoring, traffic management, border patrol and so on. Under these conditions, the image fusion algorithm needs to be high efficiency, precision and reliability. In this paper, we proposed an intelligent real-time fusion network for UAV multi-source remote sensing data based on AI brain-like chips, and deployed the algorithm on the UAV platform to achieve online high-efficiency computing. Firstly, we have developed a novel image fusion algorithm named SFNet for infrared and visible image fusion based on ShuffleNetv2. Then, we use ZCA and l1-norm to process the remodeled deep feature. The weight maps are generated by bi-cubic interpolation and soft-max operation. Finally, the fused image is reconstructed by weighted-average operation. The proposed SFNet is deployed on the Lynxi KA200 brain computing chip, and a comprehensive inference test is carried out with UAV remote sensing data. Several State-Of-The-Art (SOTA) data fusion algorithms are deployed on the same chip for experimental comparison. The proposed SFNet is proved to have faster inference speed and better feature extraction results on brain-like chips. It is more suitable for real-time UAV remote sensing image fusion tasks.

Surface topography modelling and ice flow velocity mapping of Dalk Glacier, East Antarctica: application of UAV remote sensing

Abstract. The Antarctic Ice Sheet is the largest potential contributor to global sea level rise due to global climate warming, making it important to monitor changes in the marginal outlet glacier dynamics and surface topography. The unmanned aerial vehicle (UAV), a new platform, has been proven to be a useful tool in glaciological applications because it can collect data in a variety of ways and has a high spatial and temporal resolution compared to traditional ground-based measurements and remote sensing from space. In this study, we used the combined UAV platform composed of the DJI Mavic 3 Enterprise (M3E) and M300 (L1) versions to perform high-accuracy on-site investigations of Dalk Glacier, a typical outlet glacier near the Zhongshan Station in East Antarctica. During the 39th Chinese Antarctic Expedition (CHINARE) in 2022–2023, UAV surveys with multiple sensors were performed. The M3E optical camera makes it possible to reconstruct high-resolution ortho-mosaic and digital elevation models (DEMs) of Dalk Glacier with high accuracy based on photogrammetric principles, helping us to extract the features of glacier surface topography, while dense point clouds derived from the L1 LiDAR camera are used to validate and improve the three-dimensional accuracy. To further monitor the dynamics and stability of Dalk Glacier, we generate ice flow velocity maps using ortho-mosaics for the years 2019, 2020, and 2023. The spatiotemporal changes in ice flow velocities were further compared with the products derived from satellite remote sensing data.

Development of a UAV-borne sorbent tube sampler and its application on the vertical profile measurement of volatile organic compounds

Vertical detection of volatile organic compounds (VOCs) is essential to expend our understanding of the distribution characteristics of VOCs and improve the predictive ability of existing air quality models. In this work, we report the development of a sorbent tube sampler based on an unmanned aerial vehicle (UAV) platform. Vertical profile measurement of VOCs with a vertical resolution of 25 m was achieved. The sampler consists of five lightweight VOC sorbent tubes and a 5-way solenoid valve, making it available for collecting five atmospheric VOC samples in a single flight with a time response of less than 30 min. The sampler weighed ∼ 1.45 kg and had dimensions of 240 mm × 220 mm × 100 mm with small penetration loss (< 10%) under 4-liter sampling conditions (flow rate of 200 mL/min). Commercialized SUMMA canisters were used as experimental controls to investigate the possible loss of self-made sampler for target compounds in the same sampling process. Comparison experiment on the ground showed that the concentration differences for all VOC species were lower than 0.14 μg/m3, proving the good reliability for VOCs measurements using sorbent tube sampler. The UAV platform also incorporated online instruments for meteorological parameters and O3 measurement. The sampler was successfully applied to characterize the vertical profiles of VOCs up to 100 m in October 2023 in the Huaihe River Basin of China. The UAV platform and the sorbent tube sampler demonstrate good performance and will be a valuable and reliable tool for vertical VOCs measurement.

Analysis of Unmanned Aerial Vehicle Communication Performance with Optic Sensor Integration

This paper presents a novel algorithmic framework to enhance unmanned aerial vehicle (UAV) communication performance through the adaptive integration of optical sensor data. The framework features a dynamic sensor integration algorithm (DSIA) that optimizes sensor bitrates based on real-time bandwidth availability and mission-driven priorities. An adaptive compression scheme works alongside the DSIA to maintain high data fidelity and resolution at lower bitrates. Together, these algorithms provide an efficient and scalable solution for managing high-volume UAV sensor data under varying conditions. The efficiency gains are demonstrated through simulations highlighting the framework's ability to reduce packet loss and latency while maximizing image quality for a given communication bandwidth constraint. The scalable architecture ensures robustness across diverse UAV platforms, sensor types, and operational scenarios. Simulation results validate up to a 75% reduction in latency and a 45% improvement in image resolution compared to conventional fixed bitrate approaches. By optimizing sensor data relevancy and transmission fidelity, this framework enables more effective UAV communication and enhances mission performance.

Unmanned aerial vehicles (UAVs)-based crop lodging susceptibility and seed yield assessment during different growth stages of rapeseed (Brassica napus)

Lodging is a great challenge in rapeseed production that significantly affects seed yield and quality. Prediction of lodging susceptibility and seed yield through unmanned aerial vehicles (UAVs)-based framework offers remarkable prospects for higher applicability in agriculture. This study aims to explore the possibility of using a UAV-based framework for predicting the stem and root lodging susceptibility (represented by safety factor, SFs and SFr respectively) and seed yield at different growth stages of rapeseed. The Red-Green-Blue (RGB) and multispectral (MS) images were captured during various growth stages by UAV platforms to calculate 16 vegetation indices (VIs). Furthermore, the relationships of these VIs with lodging susceptibility and seed yield were also established using multiple linear regression (MLR) and four machine learning methods (including random forest machine (RFR), support vector machine, artificial neural network, and K-nearest neighbors). The results revealed that MS-VIs provided a good estimation of seed yield, and stem and root lodging susceptibilities. Among the 16 VIs analyzed, MS-VI SR85 emerged as the best predictor for both seed yield and lodging susceptibility, as is evident by its highest importance scores. Furthermore, when RGB-VIs were coupled with MS-VIs, the R2 values for estimating seed yield, stem lodging and root lodging resistance were enhanced by 150%, 69.6% and 106%, respectively, in comparison with RGB-VIs. Similarly, the RFR provided a more accurate machine learning method for predicting seed yield and lodging susceptibility compared to the other three models. Stem elongation stage was the optimum growth stage for the estimation of seed yield, and stem and root lodging susceptibilities due to its maximum prediction accuracy, as is suggested by the highest R2 values. It can be inferred that a UAV-based framework in combination with RFR could serve as a high-throughput technique for large-scale prediction of lodging susceptibility and seed yield, as early as at stem elongation stage and thus provides an opportunity for timely agronomic intervention.

Enhanced Lightweight YOLOX for Small Object Wildfire Detection in UAV Imagery.

Target detection technology based on unmanned aerial vehicle (UAV)-derived aerial imagery has been widely applied in the field of forest fire patrol and rescue. However, due to the specificity of UAV platforms, there are still significant issues to be resolved such as severe omission, low detection accuracy, and poor early warning effectiveness. In light of these issues, this paper proposes an improved YOLOX network for the rapid detection of forest fires in images captured by UAVs. Firstly, to enhance the network's feature-extraction capability in complex fire environments, a multi-level-feature-extraction structure, CSP-ML, is designed to improve the algorithm's detection accuracy for small-target fire areas. Additionally, a CBAM attention mechanism is embedded in the neck network to reduce interference caused by background noise and irrelevant information. Secondly, an adaptive-feature-extraction module is introduced in the YOLOX network's feature fusion part to prevent the loss of important feature information during the fusion process, thus enhancing the network's feature-learning capability. Lastly, the CIoU loss function is used to replace the original loss function, to address issues such as excessive optimization of negative samples and poor gradient-descent direction, thereby strengthening the network's effective recognition of positive samples. Experimental results show that the improved YOLOX network has better detection performance, with mAP@50 and mAP@50_95 increasing by 6.4% and 2.17%, respectively, compared to the traditional YOLOX network. In multi-target flame and small-target flame scenarios, the improved YOLO model achieved a mAP of 96.3%, outperforming deep learning algorithms such as FasterRCNN, SSD, and YOLOv5 by 33.5%, 7.7%, and 7%, respectively. It has a lower omission rate and higher detection accuracy, and it is capable of handling small-target detection tasks in complex fire environments. This can provide support for UAV patrol and rescue applications from a high-altitude perspective.

Drone‐based imaging sensors, techniques, and applications in plant phenotyping for crop breeding: A comprehensive review

AbstractOver the last decade, the use of unmanned aerial vehicles (UAVs) for plant phenotyping and field crop monitoring has significantly evolved and expanded. These technologies have been particularly valuable for monitoring crop growth and health and for managing abiotic and biotic stresses such as drought, fertilization deficiencies, disease, and bioaggressors. This paper provides a comprehensive review of the progress in UAV‐based plant phenotyping, with a focus on the current use and application of drone technology to gain information on plant growth, development, adaptation, and yield. We reviewed over 200 research articles and discuss the best tools and methodologies for different research purposes, the challenges that need to be overcome, and the major research gaps that remain. First, the review offers a critical focus on elucidating the distinct characteristics of UAV platforms, highlighting the diverse sensor technologies employed and shedding light on the nuances of UAV data acquisition and processing methodologies. Second, it presents a comprehensive analysis of the multiple applications of UAVs in field phenotyping, underscoring the transformative potential of integrating machine learning techniques for plant analysis. Third, it delves into the realm of machine learning applications for plant phenotyping, emphasizing its role in enhancing data analysis and interpretation. Furthermore, the paper extensively examines the open issues and research challenges within the domain, addressing the complexities and limitations faced during data acquisition, processing, and interpretation. Finally, it outlines the future trends and emerging technologies in the field of UAV‐based plant phenotyping, paving the way for innovative advancements and methodologies.

Weed Management Using UAV and Remote Sensing in Malaysia Paddy Field: A Review

Controlling weed infestation is pivotal to achieving the maximum yield in paddy fields. At a time of exponential human population growth and depleting arable land mass, finding the solution to this problem is crucial. For a long time, herbicides have been the most favoured approach for weed control due to their efficacy and ease of application. However, adverse effects on the environment due to the excessive use of herbicides have prompted more cautious and effective herbicide usage. Many weed species tend to dominate the field, and the weed thrived in patches, rendering conventional broad herbicide spraying futile. Site-specific weed management (SSWM) consists of two strategies: weed mapping and selective herbicide application. Since its introduction into the agriculture sector, unmanned aerial vehicles (UAV) have become the platform of choice for carrying both the remote sensing system for weed mapping and the selective application of herbicide. Red-Green-Blue (RGB), multispectral and hyperspectral sensors on UAVs enable highly accurate weed mapping. In Malaysia, adopting this technology is highly possible, given the nature of government-administrated rice cultivation. This review provides insight into the weed management practice using remote sensing techniques on UAV platforms with potential applications in Malaysia's paddy field. It also discusses the recent works on weed mapping with imaging remote sensing on a UAV platform.

Automated pavement marking integrity assessment using a UAV platform – a test case of public parking

ABSTRACT Intact pavement markings organize the utilization of the pavement surface area, increase the road capacity, and improve traffic safety. However, deterioration occurring over the service life will lead to traffic safety hazards. A detailed inspection is regarded as the central tenet of pavement marking management. Conventional manual assessment approaches are time-consuming, qualitative, and argued to be subjective. Thus, cost reduction, quantitative analysis, and automatization have been the focus of research. Unmanned Aerial Vehicle (UAV) platform has been studied wildly in civil tasks due to its low cost and high maneuverability. A UAV-based platform was developed in this research to address the inefficiency, access limitations, and image processing of existing road marking inspection systems. In this research, the resolution of the image is 5472 × 3080 pixels and is captured with a fixed focal length of 8.8 mm. Given intensity differences between pixels of paintings and asphalt backgrounds, the pixels belonging to painting regions are classified using the K-mean clustering algorithm. After detecting all parking lines from images, the Otsu method was employed to determine the threshold of 0.9 as the quantitative indicator of painting quality. The UAV-based platform exhibits expected performance in assessing the pavement markings in a parking area. Future research will explore the deployment in city-scale applications.

Utilizing unmanned aerial vehicle technology for environmental monitoring: Future trends, methods, and applications

AbstractThis paper provides an overview of the application of Unmanned Aerial Vehicles (UAVs) in environmental monitoring, with a focus on air pollution surveillance. Initially, the paper highlights the significance of UAV technology for real‐time air quality monitoring in developing countries and explores the characteristics of fixed‐wing and multirotor UAVs in monitoring air pollutants. It then delves into methods of measuring air pollutants using UAV platforms, including the three‐dimensional distribution of pollutants around roadsides, green belts, and street‐facing communities. The advantages of UAV measurements, such as lower costs, greater flexibility, and the ability to monitor in three dimensions, are emphasized. Finally, the paper discusses future trends in the field of environmental monitoring using UAVs, including technological advancements, evolving regulatory policies, and integration with other technologies like Artificial Intelligence, big data analytics, and 5G communication. These developments suggest an increasingly significant role for UAVs in environmental monitoring, enhancing efficiency, reducing costs, and contributing to public participation and environmental awareness. However, due to the delays in publication and review processes, the most recent studies may not have been included in the literature review, leading to a scenario where the review might not reflect the latest research trends.

MRG-T: Mask-Relation-Guided Transformer for Remote Vision-Based Pedestrian Attribute Recognition in Aerial Imagery

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), utilizing UAV platforms for visual surveillance has become very attractive, and a key part of this is remote vision-based pedestrian attribute recognition. Pedestrian Attribute Recognition (PAR) is dedicated to predicting multiple attribute labels of a single pedestrian image extracted from surveillance videos and aerial imagery, which presents significant challenges in the computer vision community due to factors such as poor imaging quality and substantial pose variations. Despite recent studies demonstrating impressive advancements in utilizing complicated architectures and exploring relations, most of them may fail to fully and systematically consider the inter-region, inter-attribute, and region-attribute mapping relations simultaneously and be stuck in the dilemma of information redundancy, leading to the degradation of recognition accuracy. To address the issues, we construct a novel Mask-Relation-Guided Transformer (MRG-T) framework that consists of three relation modeling modules to fully exploit spatial and semantic relations in the model learning process. Specifically, we first propose a Masked Region Relation Module (MRRM) to focus on precise spatial attention regions to extract more robust features with masked random patch training. To explore the semantic association of attributes, we further present a Masked Attribute Relation Module (MARM) to extract intrinsic and semantic inter-attribute relations with an attribute label masking strategy. Based on the cross-attention mechanism, we finally design a Region and Attribute Mapping Module (RAMM) to learn the cross-modal alignment between spatial regions and semantic attributes. We conduct comprehensive experiments on three public benchmarks such as PETA, PA-100K, and RAPv1, and conduct inference on a large-scale airborne person dataset named PRAI-1581. The extensive experimental results demonstrate the superior performance of our method compared to state-of-the-art approaches and validate the effectiveness of mask-relation-guided modeling in the remote vision-based PAR task.

UAV Photogrammetric Surveys for Tree Height Estimation

In the context of precision agriculture (PA), geomatic surveys exploiting UAV (unmanned aerial vehicle) platforms allow the dimensional characterization of trees. This paper focuses on the use of low-cost UAV photogrammetry to estimate tree height, as part of a project for the phytoremediation of contaminated soils. Two study areas with different characteristics in terms of mean tree height (5 m; 0.7 m) are chosen to test the procedure even in a challenging context. Three campaigns are performed in an olive grove (Area 1) at different flying altitudes (30 m, 40 m, and 50 m), and one UAV flight is available for Area 2 (42 m of altitude), where three species are present: oleander, lentisk, and poplar. The workflow involves the elaboration of the UAV point clouds through the SfM (structure from motion) approach, digital surface models (DSMs), vegetation filtering, and a GIS-based analysis to obtain canopy height models (CHMs) for height extraction based on a local maxima approach. UAV-derived heights are compared with in-field measurements, and promising results are obtained for Area 1, confirming the applicability of the procedure for tree height extraction, while the application in Area 2 (shorter tree seedlings) is more problematic.

A Comprehensive Review of UAV-Assisted FSO Relay Systems

The evolving requirements of next-generation mobile communications networks can be met by leveraging vertically deployed Unmanned Aerial Vehicle (UAV) platforms integrated with Free Space Optical communications (FSO). This integration offers a flexible and scalable architecture capable of delivering high-rate communication without requiring licenses while aligning with the multi-gigabit paradigm. In recent times, the increasing availability of commercial aerial platforms has facilitated experimental demonstrations of UAV-enabled FSO systems, which play a crucial role in proposed backhaul networks and point-to-point communications by overcoming Line-of-Sight (LOS) challenges. These systems can be rapidly deployed to meet sudden demand scenarios. This document provides a comprehensive review of relevant field demonstrations of UAV-enabled FSO relay systems, with a particular focus on commercially available, free-flying platforms that are driving advancements in this domain. It categorizes the different platforms by considering the operational altitudes of these systems and their payload actuation capacity, which determines their adaptability to variables. The analysis aims to distill the design considerations that lead to optimal performance regarding communications throughput and other relevant metrics. Moreover, it also attempts to highlight areas where design choices have fallen short, indicating gaps in current research efforts toward the widespread adoption of UAV-enabled FSO relay systems. Finally, this work endeavors to outline effective design considerations, guidelines, and recommendations to bridge these identified gaps. It serves as a valuable reference guide for researchers involved in developing UAV-enabled FSO relay systems, enabling them to make informed decisions and pave the way for the successful implementation of such systems.

A Deep Learning Approach for Surface Crack Classification and Segmentation in Unmanned Aerial Vehicle Assisted Infrastructure Inspections.

Surface crack detection is an integral part of infrastructure health surveys. This work presents a transformative shift towards rapid and reliable data collection capabilities, dramatically reducing the time spent on inspecting infrastructures. Two unmanned aerial vehicles (UAVs) were deployed, enabling the capturing of images simultaneously for efficient coverage of the structure. The suggested drone hardware is especially suitable for the inspection of infrastructure with confined spaces that UAVs with a broader footprint are incapable of accessing due to a lack of safe access or positioning data. The collected image data were analyzed using a binary classification convolutional neural network (CNN), effectively filtering out images containing cracks. A comparison of state-of-the-art CNN architectures against a novel CNN layout "CrackClassCNN" was investigated to obtain the optimal layout for classification. A Segment Anything Model (SAM) was employed to segment defect areas, and its performance was benchmarked against manually annotated images. The suggested "CrackClassCNN" achieved an accuracy rate of 95.02%, and the SAM segmentation process yielded a mean Intersection over Union (IoU) score of 0.778 and an F1 score of 0.735. It was concluded that the selected UAV platform, the communication network, and the suggested processing techniques were highly effective in surface crack detection.

Research Progress of High-Speed Data Transmission Technology for Lightweight and Small-Sized Unmanned Aerial Vehicle Platforms

With the continuous development of science and technology, UAV technology has been widely used in various fields. As an essential part, light and small UAV platforms have the advantages of being small, lightweight, and easy to operate and thus have been widely used in aerial photography, monitoring, rescue, and other fields. However, the traditional data transmission method can no longer meet the demand for the data transmission speed and stability of small and light UAV platforms. Wireless optical communication has the advantages of being high-speed and license-free, as well as having a large bandwidth strong anti-interference ability, and good confidentiality. Therefore, this paper aims to study high-speed data transmission technology for light and small UAV platforms to improve their transmission speed and stability. In this paper, the characteristics and advantages of UAV airborne laser communication are first elaborated to illustrate the advancements and importance of data transmission technology based on light and small UAV platforms. Then, the composition of a UAV airborne laser communication system is clarified to illustrate the feasibility of conducting airborne laser communication research. Then, the current domestic and international research status of people on light and small UAV airborne laser communication high-speed data transmission systems is reviewed, and its key technical features are analyzed. Finally, the prospects for its application and development trend are investigated.

An open-source method for producing reliable water temperature maps for ecological applications using non-radiometric sensors

The number of thermal sensors mounted on Unmanned Aerial Vehicles (UAVs) has increased considerably in recent years, with several of those currently available on the market being very attractive due to their low cost and ease of use. UAV platforms coupled with non-radiometric thermal sensors tend to be least expensive, but few studies have evaluated the reliability of data they produce or developed workflows to improve data accuracy. Here we present a complete method for obtaining accurate and precise water temperature data from non-radiometric sensors, including bias correction, calibration, image stitching and wetted area extraction. We illustrate the utility of the method through its application to the assessment of thermal conditions in two tropical river reaches. The whole procedure is implemented in the R language, and we provide a tutorial and customizable functions. Validation tests indicate that our method produces water temperature estimates that are comparable to those from more expensive sensors (mean absolute error <0.5 °C) and so can be used to answer ecological questions with great confidence. The method dramatically increases the accessibility of thermal imaging in ecology by providing accurate data that is cost-effective and not computationally intensive, and for calibration and validation relies on only small and lightweight equipment that can transported and used in remote locations.

Advancements of UAV and Deep Learning Technologies for Weed Management in Farmland

With the continuous growth of the global population and the increasing demand for crop yield, enhancing crop productivity has emerged as a crucial research objective on a global scale. Weeds, being one of the primary abiotic factors impacting crop yield, contribute to approximately 13.2% of annual food loss. In recent years, Unmanned Aerial Vehicle (UAV) technology has developed rapidly and its maturity has led to widespread utilization in improving crop productivity and reducing management costs. Concurrently, deep learning technology has become a prominent tool in image recognition. Convolutional Neural Networks (CNNs) has achieved remarkable outcomes in various domains, including agriculture, such as weed detection, pest identification, plant/fruit counting, maturity grading, etc. This study provides an overview of the development of UAV platforms, the classification of UAV platforms and their advantages and disadvantages, as well as the types and characteristics of data collected by common vision sensors used in agriculture, and discusses the application of deep learning technology in weed detection. The manuscript presents current advancements in UAV technology and CNNs in weed management tasks while emphasizing the existing limitations and future trends in its development process to assist researchers working on applying deep learning techniques to weed management.

Deep Learning Based Object Detection with Unmanned Aerial Vehicle Equipped with Embedded System

This study aims to introduce an Unmanned Aerial Vehicle (UAV) platform capable of performing real-time object detection and classification tasks using computer vision techniques in the field of artificial intelligence. Previous scientific research reveals the utilization of two different methods for object detection and classification via UAVs. One of these methods involves transmitting the acquired UAV images to a ground control center for processing, whereafter the processed data is relayed back to the UAV. The other approach entails transferring images over the internet to a cloud system, where image processing is conducted, and the resultant data is subsequently sent back to the UAV. This allows the UAV to autonomously perform predefined tasks. Enabling the UAV with autonomous decision-making capabilities and the ability to perform object detection and classification from recorded images requires an embedded artificial intelligence module. The ability of the UAV to utilize image processing technologies through embedded systems significantly enhances its object detection and classification capabilities, providing it with a significant advantage. This enables the UAV to be used more effectively and reliably in various tasks. In the proposed approach, image processing was achieved by mounting a Raspberry Pi 4 and camera on the UAV. Additionally, a Raspberry Pi-compatible 4G/LTE modem kit was used to provide remote intervention capability, and the Coral Edge TPU auxiliary processor was used to increase object detection speed. The TensorFlow Library and the SSD MobilNetV2 convolutional neural network model were used for image processing. During test flights, accuracy values of approximately 96.3% for car detection and 96.2% for human detection were achieved.