Unmanned Aerial Vehicle Images Research Articles

Speeding up UAV-based crop variability assessment through a data fusion approach using spatial interpolation for site-specific management

Innovations in precision agriculture enhance complex tasks, reduce environmental impact, and increase food production and cost efficiency. One of the main challenges is ensuring rapid information availability for autonomous vehicles and standardizing processes across platforms to maximize interoperability. The lack of drone technology standardisation, communication barriers, high costs, and post-processing requirements sometimes hinder their widespread use in agriculture. This research introduces a standardized data fusion framework for creating real-time spatial variability maps using images from different Unmanned Aerial Vehicles (UAVs) for Site-Specific Crop Management (SSM). Two spatial interpolation methods were used (Inverse Distance Weight, IDW, and Triangulated Irregular Networks, TIN), selected for their computational efficiency and input flexibility. The proposed framework can use different UAV image sources and offers versatility, speed, and efficiency, consuming up to 98 % less time, energy, and computing requirements than standard photogrammetry techniques, providing rapid field information, allowing edge computing incorporation into the UAV data acquisition phase. Experiments conducted in Spain, Serbia, and Finland in 2022 under the H2020 FlexiGroBots project demonstrated a strong correlation between results from this method and those from standard photogrammetry techniques (up to r = 0.93). In addition, the correlation with Sentinel 2 satellite images was as strong as that obtained with photogrammetry-based orthomosaics (up to r = 0.8). The proposed approach could support irrigation leak detection, soil parameter estimation, weed management, and satellite integration for agriculture.

Triangulated Irregular Network based Seamline Determination for Fast Image Stitching of Multiple UAV Images

Abstract. To maintain the efficiency of UAV (unmanned aerial vehicle) remote sensing, rapid image stitching is essential to make multiple UAV images into a seamless mosaic image. Relief displacement introduces variations in object appearance for each image, causing mismatch errors at mosaic seamlines. Traditional approaches involve orthorectifying images using DSMs (digital surface models). While these approaches allow for accurate image stitching, they do not cope with the advantages of UAVs due to their time consumption. In contrast, fast image stitching techniques that do not use orthorectification are well suited for UAV image processing. Related researches have attempted to optimize seamlines to eliminate the errors caused by relief displacement without the use of DSMs. We propose to utilize a TIN (triangular irregular network) of tiepoints to effectively eliminate errors caused by relief displacement while maintaining the fast speed of image stitching. In this study, a TIN is constructed based image tiepoints whose ground coordinates have been obtained through bundle adjustment. The edges of the TIN are used to generate seamlines for image stitching, and the facets of the TIN are used to select minimal images for image stitching and to optimize seamlines. Image stitching results of our proposed method had small error of 1–2 pixels and the processing time of less than 10 minutes for 97 UAV images. This study showed that the proposed method could stitch multiple images while maintaining stable quality using only geometric clues of a TIN of tiepoints.

Comparison of urban physical environments and thermal properties extracted from unmanned aerial vehicle images and ENVI-met model simulations

Identifying the thermal properties of urban areas and integrating these properties into spatial planning is essential for sustainable development. Continuous and efficient improvements of urban thermal environments require novel studies, which are limited to date. This study addresses this gap by presenting a comparison of the physical environments and thermal properties of an urban area (Changwon National University, Gyeongsangnam-do, South Korea) based on unmanned aerial vehicle (UAV) images and ENVI-met model simulations. We predicted the thermal environment of the study area using UAV images and explored the potential application of UAVs in spatial planning. The comparison revealed that the coefficient of determination (R2) between mean radiant temperature (Tmrt) values simulated by the ENVI-met model and predicted from UAV images was 0.168–0.320. Significant differences were observed in shaded areas and vegetated regions with tall trees, where UAVs encountered difficulties in collecting accurate information due to obstructed visibility. The discrepancies between the simulated and predicted Tmrt values highlight the limitations of UAVs in capturing data in shaded and densely vegetated areas, as well as disparities in the physical environments determined by the two methods. Despite these limitations, UAVs can be valuable tools for urban and environmental planning. Future advancements addressing these limitations may enable UAVs to efficiently diagnose urban thermal environments and guide improvement efforts.

Integration of field measurements with unmanned aerial vehicle to predict forest inventory metrics at tree and stand scales in natural pure Crimean pine forests

ABSTRACT Inventorying forest ecosystems is an essential part of forest management planning. However, it is quite costly and time-consuming, particularly for larger areas. Recently, significant developments have been made in unmanned aerial vehicle (UAV) technology to improve the cost and time efficiency in forest inventory. Therefore, UAV images have become one of the inventory tools that produces data with high spatial resolution in determining forest resources. This study aims to investigate the contribution of UAV data to forest inventory in a case study area with a total of 30 sample plots located in pure and natural Crimean pine (Pinus nigra J.F. Arnold ssp. pallasiana (Lamb.) Holmboe) stands in the Black Sea backward region of Türkiye. Total tree height (h) and stem volume (v) were recorded at individual tree level (n = 367), and the number of trees (N), mean height (hmean), top height (htop), stand basal area (BA) and stand volume (V) were calculated at sample plot level (n = 30) from both the field and UAV-based data. Pearson’s correlation coefficients (r) for h and v were 0.96 and 0.72, respectively, the highest correlation at the sample plot level was observed for the hmean - htop (r = 0.96), while the lowest correlation was found for BA (r = 0.54). The suitability of the observation and prediction values was assessed using a t-test at both individual tree and sample plot levels. According to the t-test results, the observation and prediction values for h, v, hmean, htop, BA and V metrics were found to be compatible (p > 0.05), but not for N (p < 0.05). Overall results indicated that UAV technology has a potential to be used in forest inventory and can contribute to the determination of individual tree and stand metrics. Thereby, it saves cost and time in forest inventory studies and helps monitoring the dynamic structure of the forest ecosystem with an effective approach in forest inventory.

3D Modeling of rural environments from multiscale aerial imagery

Given the increasing attention to environmental preservation and sustainable development, the digitization of rural landscapes stands out as a pivotal strategy for effective environmental management and sustainability, land use planning, and preservation of cultural heritage. This work proposes a novel methodology for generating 3D models of rural landscapes by integrating multiscale data sources. Although Unmanned Aerial Vehicles (UAV) simplify the acquisition of multi-source data, their coverage is typically restricted to small landscapes due to their limited range and flight time. On the other hand, although the use of aerial images provides a broader view of the terrain, it is important to note that the low resolution of these images interferes with the task of accurate 3D modeling. Given these challenges, we propose a methodology that combines UAV data and high-resolution aerial imagery provided by the Spanish National Orthophoto Program (PNOA). This multi-source data integration is crucial to generating detailed and accurate 3D models of rural environments. The proposed methodology involves three steps: (1) semantic segmentation of aerial images identifying features such as vegetation, ground, and human-made structures, (2) estimation of the Digital Elevation Model (DEM), and (3) 3D modeling of rural environments using the point clouds generated from UAV images. The conducted experiments demonstrate the effectiveness of our approach identifying and representing previously mentioned features. Thus, this work presents advances in 3D representation techniques for real scenarios, contributing to the coordination of land utilization and environmental sustainability in rural landscapes.

Development of a trash classification system to map potential Aedes aegypti breeding grounds using unmanned aerial vehicle imaging

Aedes aegypti mosquitos are the primary vector for dengue, chikungunya, and Zika viruses and tend to breed in small containers of water, with a propensity to breed in small piles of trash and abandoned tires. This study piloted the use of aerial imaging to map and classify potential Ae. aegypti breeding sites with a specific focus on trash, including discarded tires. Aerial images of coastal and inland sites in Kenya were obtained using an unmanned aerial vehicle. Aerial images were reviewed for identification of trash and suspected trash mimics, followed by extensive community walk-throughs to identify trash types and mimics by description and ground photography. An expert panel reviewed aerial images and ground photos to develop a classification scheme and evaluate the advantages and disadvantages of aerial imaging versus walk-through trash mapping. A trash classification scheme was created based on trash density, surface area, potential for frequent disturbance, and overall likelihood of being a productive Ae. aegypti breeding site. Aerial imaging offers a novel strategy to characterize, map, and quantify trash at risk of promoting Ae. aegypti proliferation, generating opportunities for further research on trash associations with disease and trash interventions.

Rapid monitoring of the spatial distribution of soil organic matter using unmanned aerial vehicle imaging spectroscopy

ABSTRACT An existing technique for quickly obtaining the spatial distribution data of soil organic matter (SOM) involves combining an unmanned aerial vehicle (UAV) platform and imaging spectroscopy technology; this technique is suitable for precision agricultural management and real-time monitoring. In this study, the average spectral data were first extracted via circular regions of interest (ROIs) of different radii and modelled using the measured SOM to determine the optimal extraction range for the spectral data. Partial least-squares regression (PLSR) and support vector machine (SVM) models were constructed based on the raw spectra, standard normal transform spectra, multiple scattering-corrected spectra, and first-order differential spectra. The difference index, ratio index, and normalized index were calculated and analysed for their correlation with SOM content, and the spectral indices were screened to establish the SOM prediction model. Finally, the accuracy of the model was evaluated, and we selected the optimal model to map the spatial distribution of SOM. The results of our study show that 1) the radius of the ROI significantly affects the model’s accuracy; 2) the accuracy of the nonlinear SVM model is much higher than that of the linear PLSR model; 3) the prediction model based on spectral indices is better than full-band model. This study can serve as a model for the application of UAV imaging spectroscopy technology to field-scale SOM estimations and rapid monitoring, as well as provide technical support for precision agriculture and climate change studies.

Lightweight railroad semantic segmentation network and distance estimation for railroad Unmanned aerial vehicle images

Derailments significantly harm railroads in terms of severity and fatality rates. Manually monitoring railway tracks is a tedious and often insufficient task to prevent derailment accidents. This necessitates the development of an automated monitoring system to oversee the condition of railway tracks. In the foreseeable future, Unmanned Aerial Vehicles (UAVs), artificial intelligence, and computer vision will play a crucial role in periodically assessing the railway environment to ensure passenger safety. This paper proposes a lightweight and efficient railroad semantic segmentation network (Lite-RSNet), which segments real-time aerial railroad images into rails, gauges, and backgrounds. The segmented regions then compute the distance between rails and obstacles, identifying potential derailment hazards in railroad applications. Lite-RSNet incorporates a multi-level feature fusion framework that includes a residual layer, a multi-head attention layer, a Concurrent Spatial and Channel Squeeze Excitation (CSSE) block, and a Convolutional Block Attention Module (CBAM). The designed approach enhances onboard processing efficiency by streamlining the model to use fewer parameters and reduce storage demands. Performance assessment of the model utilized the Rail Segmentation Dataset (RSD), which consists of high-resolution, low-altitude aerial photographs of Indian railroads. The Lite-RSNet model outperforms current leading methods, maintaining a lean structure with only 6 million parameters and achieving notable metrics of 0.971 for the Dice Coefficient (DC) and 0.947 for the Jaccard Index (JI) on the test dataset. Furthermore, distance estimation between an obstacle and rail has been implemented using image processing techniques as an additional work of this proposal to know about the caution of an obstacle.

UAV imagery-based railroad station building inspection using hybrid learning architecture

The apparent defects of railroad station building such as the broken glass, missing screw, and rust corrosion need to be inspected regularly and timely to ensure the safety of passenger. Unmanned aerial vehicle (UAV) imagery-based inspections have the potential to revolutionize current manual visual inspections by providing a better overhead view and mitigating safety concerns. This paper proposes a hybrid learning architecture called YOLOS (you only look once station scene) to simultaneously detect and segment station building surface defects of UAV images. First, a novel squeeze-and-excitation (SE) attention block is integrated into the detection branch to adaptively learn the weights of the feature channels, thereby promoting the network to pay attention to the critical deep features of the objects. And then, a new semantic segmentation branch parallel to the detection branch is designed and assembled in YOLOS for pixel-level defect recognition. Finally, extensive experiments on railroad station dataset established with drone imagery prove the effectiveness and robustness of the SE-based network on station surface defect detection. This method can quickly convert UAV imagery into useful information with a high detection rate.

Comparison Utilization of UAV Images &amp; Satellite Images for Geospatial Analysis

The rapid advancements in remote sensing technologies have opened new avenues for geospatial analysis by providing high-quality imagery and data. Unmanned Aerial Vehicles (UAVs) and satellites have emerged as prominent tools for capturing Earth's surface information, each offering unique advantages and limitations. This paper presents a comprehensive comparison of the utilisation of UAV images and satellite images in geospatial analysis. The practical implications of employing UAVs and satellites in diverse scenarios include environmental monitoring, disaster management, urban planning, and agriculture. The benefits of UAVs, such as their ability to capture high- resolution images with precision and on-demand deployment, are contrasted with satellites' global coverage and consistent monitoring capabilities. Integrating UAV and satellite data is emphasized as a complementary approach to geospatial analysis. Techniques for fusing data from these sources are discussed, enabling the creation of comprehensive datasets that combine detailed local information from UAVs with broader context from satellite imagery.

Diagnostic study of nitrogen nutrition in cotton based on unmanned aerial vehicle RGB images

Nitrogen fertilizer levels significantly affect crop growth and development, necessitating precision management. Most studies focus on nitrogen nutrient estimation using vegetation indices and textural features, overlooking the diagnostic potential of color features. Hence, we investigated cotton nitrogen nutrition status using unmanned aerial vehicle (UAV) image features and the nitrogen nutrient index (NNI). Random frog algorithm - and random forest-screened image feature sets significantly correlated with the NNI, which were substituted into four machine learning algorithms for NNI estimation modeling. The composite scores (F) of optimal image feature sets were calculated using the coefficient of variation method for comprehensive cotton nitrogen nutrient diagnosis. Validation of the model for determining the critical nitrogen concentration in cotton yielded a coefficient of determination R2 = 0.89, root mean square error RMSE = 0.50 g (100 g)-1, and mean absolute error MAE = 0.44, demonstrating improved performance. Additionally, our novel NNI estimation model constructed based on the optimal image feature sets exhibited R2c = 0.97, RMSEc = 0.02, MAEc = 0.02, R2v = 0.85, RMSEv = 0.05, and MAEv = 0.04. Polynomial fitting of the composite index with NNI indicated that the model was reliable and yielded the following diagnostic criterion: 0.48 &lt; F2 &lt; 0.67 indicated nitrogen overapplication, whereas F2 &lt; 0.48 or F2 &gt; 0.67 indicated nitrogen deficiency. This study demonstrates the superior effectiveness of using UAV RGB image feature sets for NNI estimation and the quick, accurate diagnosis of cotton nitrogen levels, which will help guide nitrogen fertilizer application.

Water function zone: A method to improve the accuracy of remote sensing retrieval of water bodies

In water monitoring, it is always a hot issue to exploring a method to improve the accuracy of remote sensing inversion. To this end, based on the actual investigation of the surrounding environment and water quality characteristics of the Fuyang river, this study has established five distinct water functional zones: reservoir (RS), village river (VR), industrial river (IR), artificial lake (AL), and urban river (UR), which are considered as subdivided datasets. Meanwhile, considering that lakes and reservoirs typically contain relatively stationary or slow-moving water bodies, while river channels are characterized by moving water bodies, three multi-type datasets have been constructed for comparison. These are based on the morphological and flow characteristics of different regions within the Fuyang river and include river channel (R), lake (L), and whole basin (W). Based on multi-spectral images of unmanned aerial vehicle (UAV) and measured water quality data, ten types of inversion models were to invert six kinds of water quality parameters, and compare and analyze the performance of the optimal inversion model of the corresponding data sets. The results show that the multivariate regression model is superior to the univariate regression model, and the mean coefficient of determination (R2) of the subdivided data set is 0.936, and the root mean square error (RMSE) and mean absolute error (MAE) appear decrease in different degrees compared with the W with 3.573 and 2.662, respectively. The mean ratio performance to interquartile (RPIQ) of the corresponding model in UR and VR are 3.963 and 2.748, respectively. Extremely Randomized Trees (ERT) model is more suitable for the inversion of multi-type data sets lacking obvious water quality characteristics and with complex components, while Categorical Boosting (CatBoost) model is more suitable for the inversion of subdivided data sets with obvious water quality characteristics. The current method has practical guiding significance for improving the application level of water monitoring technology in ecological environment protection and urban water resources protection.

Estimation of Evaporation and Drought Stress of Pistachio Plant Using UAV Multispectral Images and a Surface Energy Balance Approach

Water scarcity is a critical abiotic stress factor for plants in arid and semi-arid regions, impacting crop development and production yield and quality. Monitoring water stress at finer scales (e.g., farm and plant), requires multispectral imagery with thermal capabilities at centimeter resolution. This study investigates drought stress in pistachio trees in a farm located in Yazd province, Iran, by using Unmanned Aerial Vehicle (UAV) images to quantify evapotranspiration and assess drought stress in individual trees. Images were captured on 10 July 2022, using a Matrix 300 UAV with a MicaSense Altum multispectral sensor. By employing the Surface Energy Balance Algorithm for Land (SEBAL), actual field evapotranspiration was accurately calculated (10 cm spatial resolution). Maps of the optimum crop coefficient (Kc) were developed from the Normalized Difference Vegetation Index (NDVI) based on standard evapotranspiration using the Food and Agriculture Organization (FAO) 56 methodology. The comparison between actual and standard evapotranspiration allowed us to identify drought-stressed trees. Results showed an average and maximum daily evaporation of 4.3 and 8.0 mm/day, respectively, in pistachio trees. The real crop coefficient (Kc) for pistachio was 0.66, contrasting with the FAO 56 standard of 1.17 due to the stress factor (Ks). A significant correlation was found between Kc and NDVI (R2 = 0.67, p &lt; 0.01). The regression model produced a crop coefficient map, valuable to support precise irrigation management and drought prevention, considering the heterogeneity at the farm scale.

Weed species classification with UAV imagery and standard CNN models: Assessing the frontiers of training and inference phases

Accurate weed species identification is crucial for effective site-specific weed management (SSWM), enabling targeted and timely control measures for each weed in crop field. This study advanced the current approach to species-level weed identification during the early growth stage by integrating unmanned aerial vehicles (UAVs) imagery with standard convolutional neural networks (CNNs) models such as VGG16, Resnet152 and Inception-Resnet-v2. For this, a robust dataset was created with 33,467 labels of weeds (Atriplex patula, Chenopodium album, Convolvulus arvensis, Cyperus rotundus, Lolium rigidum, Portulaca oleracea, Salsola kali, Solanum nigrum) and crops (maize, tomato), which was subjected to different training, validation and test scenarios. Model inputs were adjusted in order to align them with the information represented by the UAV images. Initially, models were developed in balanced scenarios, gradually increasing label numbers to assess their performance. Inception-ResNet-v2 achieved over 90% accuracy with 400 labels, while ResNet152 and VGG16 required 600 and 800 labels, respectively, for similar accuracy. In a more complex and realistic scenarios with unbalanced datasets, Inception-ResNet-v2 outperformed, likely due to its deeper architecture and enhanced capability to capture intricate features and patterns within UAV images. The study emphasized the importance of the minority-to-majority species ratio in unbalanced datasets, which affects minority species classification. To prevent misclassification, it is crucial to determine the right number of labels for CNN model training and validation. Weed maps were generated after species classification using the Faster R–CNN algorithm as an object detector. This advancement in methodology facilitates the precise and efficient implementation of SSWM techniques.

Soybean seedling detection and counting from UAV images based on an improved YOLOv8 Network

Abstract. The utilization of unmanned aerial vehicle (UAV) for soybean seedling detection is an effective way to estimate soybean yield, which plays a crucial role in agricultural planning and decision-making. However, the soybean seedlings objects in the UAV image are small, in clusters, and occluded each other, which makes it very challenging to achieve accurate object detection and counting. To address these issues, we optimize the YOLOv8 model and propose a GAS-YOLOv8 network, aiming to enhance the detection accuracy for the task of soybean seedling detection based on UAV images. Firstly, a global attention mechanism (GAM) is incorporated into the neck module of YOLOv8, which reallocates weights and prioritizes global information to more effectively extract soybean seedling features. Secondly, the CIOU loss function is replaced with the SIOU loss, which includes an angle loss term to guide the regression of bounding boxes. Experimental results show that, on the soybean seedling dataset, the proposed GAS-YOLOv8 model achieves a 1.3% improvement in mAP@0.5 and a 6% enhancement in detection performance in dense seedling areas, when compared to the baseline model YOLOv8s.When compared to other object detection models (YOLOv5, Faster R-CNN, etc.), the GAS-YOLOv8 model similarly achieved the best detection performance. These results demonstrate the effectiveness of the GAS-YOLOv8 in detecting dense soybean seedlings, providing more accurate theoretical support for subsequent yield estimation.

FS_YOLOv8: A Deep Learning Network for Ground Fissures Instance Segmentation in UAV Images of the Coal Mining Area

Abstract. The ground fissures caused by coal mining have seriously affected the ecological environment of the land. Timely and accurate identification and landfill treatment of ground fissures can avoid secondary geological disasters in coal mine areas. At present, the fissure identification methods based on deep learning show excellent performance on roads and walls, etc. Nevertheless, the automatic and reliable segmentation of ground fissures in remote sensing images poses a challenge for deep learning networks, due to the diverse and complex texture information included in the mining ground fissures and background. To overcome these challenges, we propose an improved YOLOv8 instance segmentation network to automatically and efficiently segment the ground fissures in coal mining areas. In detail, a model called FS_YOLOv8 is proposed. The DSPP (Dynamic Snake convolutional Pyramid Pooling) module is incorporated into the FS_YOLOv8 model to establish a multi-scale dynamic snake convolution feature aggregation structure. This module replaces the conventional convolution found in the SPPF module of YOLOv8 and aims to enhance the model's ability to extract features related to fissures with tubular structures. Furthermore, the D-LKA (Deformable Large Kernel Attention) module is employed to autonomously collect fissure context information. To enhance the detection capability of challenging samples in remote sensing images with intricate background and fissure texture, we employ a Slide Loss function. Ultimately, the ground fissure dataset of unmanned aerial vehicle (UAV) images in coal mine areas is subjected to experimental analysis. The experimental findings demonstrate that FS_YOLOv8 exhibits exceptional proficiency in segmenting ground fissures within intricate and expansive mining areas.

An improved algorithm based on YOLOv5 for detecting Ambrosia trifida in UAV images.

A YOLOv5-based YOLOv5-KE unmanned aerial vehicle (UAV) image detection algorithm is proposed to address the low detection accuracy caused by the small size, high density, and overlapping leaves of Ambrosia trifida targets in UAV images. The YOLOv5-KE algorithm builds upon the YOLOv5 algorithm by adding a micro-scale detection layer, adjusting the hierarchical detection settings based on k-Means for Anchor Box, improving the loss function of CIoU, reselecting and improving the detection box fusion algorithm. Comparative validation experiments of the YOLOv5-KE algorithm for Ambrosia trifida recognition were conducted using a self-built dataset. The experimental results show that the best detection accuracy of Ambrosia trifida in UAV images is 93.9%, which is 15.2% higher than the original YOLOv5. Furthermore, this algorithm also outperforms other existing object detection algorithms such as YOLOv7, DC-YOLOv8, YOLO-NAS, RT-DETR, Faster RCNN, SSD, and Retina Net. Therefore, YOLOv5-KE is a practical algorithm for detecting Ambrosia trifida under complex field conditions. This algorithm shows good potential in detecting weeds of small, high-density, and overlapping leafy targets in UAV images, it could provide technical reference for the detection of similar plants.

Updating Orthophotos around Gas Pipelines based on "Cloud Control" Photogrammetry

Abstract. As a clean energy source, natural gas is widely used and primarily transported through long-distance pipelines. Regular maintenance and inspection of long-distance gas pipelines are crucial tasks. Due to the extensive coverage and distance of these pipelines, the workload is enormous. It is necessary to first identify areas of change, which can be carried out using multiple sets of orthophotos produced by unmanned aerial vehicles (UAVs). However, UAV images have small footprints and significant geometric distortions, requiring a large number of ground control points (GCPs) for accurate positioning. Measuring these points in the field is challenging and time-consuming, becoming a key factor limiting the rapid production of orthophotos. To overcome this challenge, this paper introduces the "cloud control" photogrammetry technology to achieve fully automatic updates of orthophotos around long-distance pipelines, providing foundational data for the maintenance and inspection of these gas pipelines. This method replaces GCPs with images containing known orientation parameters, serving as control information. By matching tie points between new and old images, the "cloud control points" are transferred to the new images, enabling the image registration and production of orthophotos. The experiments conducted on the Fumin and Zhaotong segments of a long-distance gas pipeline in Yunnan Province demonstrate that, for UAV images with a ground resolution of 0.05 meters, using the "cloud control" method achieves a planar accuracy of 0.05 meters and an elevation accuracy of 0.07 meters. These results are comparable to the accuracy obtained by orienting the results using GCPs.

Accuracy Assessment of UAV Photogrammetry System with RTK Measurements for Direct Georeferencing

Abstract. The direct georeferencing accuracy of unmanned aerial vehicle (UAV) images with real-time kinematic (RTK) measurements is a concerned topic in the community of photogrammetry. This study assesses the capabilities of a multi-rotor platform equipped with RTK technology, specifically a DJI Phantom 4 RTK UAV, for robust direct georeferencing. The UAV surveyed a square and a building at Wuhan University to assess the accuracy and spatial consistency of direct georeferencing in close-range photography. We tested checkpoint errors under various ground control points (GCPs) configurations. The results show that without GCP, an analysis of 71 spatially distributed checkpoints produced a root mean square error (RMSE) of 5.58 cm in the Z direction. This finding indicates that RTK-equipped UAVs can achieve acceptable error margins even without using GCPs, thereby fulfilling the precision requirements for large-scale mapping.

MFEFNet: A Multi-Scale Feature Information Extraction and Fusion Network for Multi-Scale Object Detection in UAV Aerial Images

Unmanned aerial vehicles (UAVs) are now widely used in many fields. Due to the randomness of UAV flight height and shooting angle, UAV images usually have the following characteristics: many small objects, large changes in object scale, and complex background. Therefore, object detection in UAV aerial images is a very challenging task. To address the challenges posed by these characteristics, this paper proposes a novel UAV image object detection method based on global feature aggregation and context feature extraction named the multi-scale feature information extraction and fusion network (MFEFNet). Specifically, first of all, to extract the feature information of objects more effectively from complex backgrounds, we propose an efficient spatial information extraction (SIEM) module, which combines residual connection to build long-distance feature dependencies and effectively extracts the most useful feature information by building contextual feature relations around objects. Secondly, to improve the feature fusion efficiency and reduce the burden brought by redundant feature fusion networks, we propose a global aggregation progressive feature fusion network (GAFN). This network adopts a three-level adaptive feature fusion method, which can adaptively fuse multi-scale features according to the importance of different feature layers and reduce unnecessary intermediate redundant features by utilizing the adaptive feature fusion module (AFFM). Furthermore, we use the MPDIoU loss function as the bounding-box regression loss function, which not only enhances model robustness to noise but also simplifies the calculation process and improves the final detection efficiency. Finally, the proposed MFEFNet was tested on VisDrone and UAVDT datasets, and the mAP0.5 value increased by 2.7% and 2.2%, respectively.