Unmanned Aerial Vehicle Imagery Research Articles

Integrated sensing and machine learning: Predicting saccharine and bioenergy feedstocks in sugarcane

Predicting saccharine and bioenergy feedstocks in sugarcane enables growers and industries to determine the precise time and location for harvesting a better-quality product in the field. On one hand, Brix, Purity, and total recoverable sugars (TRS) can provide meaningful and reliable indicators of high-quality raw materials for first-generation (1 G) bioethanol. Conversely, Cellulose, Hemicellulose, and Lignin are the primary constituents of straw, directly contributing to second-generation (2G) bioethanol. However, analyzing these materials in the laboratory is a time-consuming and non-scalable task. Therefore, we propose an approach based on a multi-sensor framework, which includes multispectral unmanned aerial vehicle (UAV) imagery, thermal, photosynthetic active radiation (PAR), and chlorophyll fluorescence (ChlF) data, along with machine learning (ML) algorithms namely random forest (RF), multiple linear regression (MLR), decision tree (DT), and support vector machine (SVM), to develop a non-invasive and predictive framework for mapping sugarcane feedstocks. We collected samples of stalks and leaves/straw during the maturity stage while simultaneously collecting remote sensing data. The ML models played a crucial role in predicting 1 G (R2 = 0.88–0.93) and 2 G (R2 = 0.56–0.82) feedstocks. Notably, remote sensing data could serve as important features for the models, mainly through the spectral bands (Blue, Green, and RedEdge), DTemp and ChlF. Hence, the best features can be further implemented within a framework to predict sugarcane feedstocks. Our study marks a significant advancement in the industrial-scale prediction of sugarcane feedstocks, providing stakeholders with invaluable prescriptive harvesting strategies for both primary products and by-products.

Monitoring saltwater intrusion to estuaries based on UAV and satellite imagery with machine learning models

Saltwater intrusion is a natural mixture process between watershed freshwater and seawater that frequently occurs in estuaries. Station-based monitoring of saltwater intrusion is time-consuming and labor-intensive. To enable quick monitoring of saltwater intrusion, this study developed new remote sensing algorithms for water surface salinity measurement using four decision tree-based machine learning models. These models were built based on simultaneously collected in-situ salinity data from a waterway in the Pearl River Delta and Unmanned Aerial Vehicle (UAV) hyperspectral images. A 10-fold cross-validation was applied to assess the performance of the models, with XGBoost outperforming the other three models (R2=0.93, RMSE = 0.88 psu). Then the developed model was employed for Sentinel-2 multispectral satellite images to invert the estuarine salinity distribution at a larger spatial scale. Results displayed the high performance of the machine learning models proposed in this study for mapping the salinity distribution in river channels, making it an efficient and practical technique for monitoring saltwater intrusion in river channels at a regional scale.

Cercospora leaf spot detection in sugar beets using high spatio-temporal unmanned aerial vehicle imagery and unsupervised anomaly detection methods

Cercospora leaf spot detection in sugar beets using high spatio-temporal unmanned aerial vehicle imagery and unsupervised anomaly detection methods

Improving the estimation of rice above-ground biomass based on spatio-temporal UAV imagery and phenological stages.

Unmanned aerial vehicles (UAVs) equipped with visible and multispectral cameras provide reliable and efficient methods for remote crop monitoring and above-ground biomass (AGB) estimation in rice fields. However, existing research predominantly focuses on AGB estimation based on canopy spectral features or by incorporating plant height (PH) as a parameter. Insufficient consideration has been given to the spatial structure and the phenological stages of rice in these studies. In this study, a novel method was introduced by fully considering the three-dimensional growth dynamics of rice, integrating both horizontal (canopy cover, CC) and vertical (PH) aspects of canopy development, and accounting for the growing days of rice. To investigate the synergistic effects of combining spectral, spatial and temporal parameters, both small-scale plot experiments and large-scale field testing were conducted in Jiangsu Province, China from 2021 to 2022. Twenty vegetation indices (VIs) were used as spectral features, PH and CC as spatial parameters, and days after transplanting (DAT) as a temporal parameter. AGB estimation models were built with five regression methods (MSR, ENet, PLSR, RF and SVR), using the derived data from six feature combinations (VIs, PH+CC, PH+CC+DAT, VIs+PH +CC, VIs+DAT, VIs+PH+CC+DAT). The results showed a strong correlation between extracted and ground-measured PH (R2 = 0.89, RMSE=5.08 cm). Furthermore, VIs, PH and CC exhibit strong correlations with AGB during the mid-tillering to flowering stages. The optimal AGB estimation results during the mid-tillering to flowering stages on plot data were from the PLSR model with VIs and DAT as inputs (R 2 = 0.88, RMSE=1111kg/ha, NRMSE=9.76%), and with VIs, PH, CC, and DAT all as inputs (R 2 = 0.88, RMSE=1131 kg/ha, NRMSE=9.94%). For the field sampling data, the ENet model combined with different feature inputs had the best estimation results (%error=0.6%-13.5%), demonstrating excellent practical applicability. Model evaluation and feature importance ranking demonstrated that augmenting VIs with temporal and spatial parameters significantly enhanced the AGB estimation accuracy. In summary, the fusion of spectral and spatio-temporal features enhanced the actual physical significance of the AGB estimation models and showed great potential for accurate rice AGB estimation during the main phenological stages.

UAV imagery coupled deep learning approach for the development of an adaptive in-house web-based application for yield estimation in citrus orchard

Orchard yield estimation enables a farmer to make informed decisions. The limitations of visual inspection-based yield estimation approaches can be effectively addressed by the intervention of unmanned aerial vehicles (UAVs) and advanced image processing using deep learning algorithms. This study proposes a methodology combining deep learning-driven UAV imagery and an in-house web-based application, “DeepYield”; to measure yield in a citrus fruit orchard. The state-of-the-art deep learning object detection models SSD, Faster RCNN, YOLOv4, YOLOv5 and YOLOv7 were evaluated for detecting “harvest-ready” and “unripe” citrus fruits from the tree images. Fruit size estimation was carried out using traditional as well as deep learning-based image segmentation models. YOLOv7 outperformed other models with a mAP, Precision, Recall, and F1-Score of 86.48, 88.54, 83.66 and 86.03%, respectively. The developed solution was integrated into a web-based application as ‘DeepYield’ to enhance users’ convenience and equip them with an automated yield estimation solution.

Accounting for the impact of tree size and soil spatial variability on leaching from orchards

Commercial agricultural production of orchards is based on water and fertilizer applications. Over-application and orchard spatial variability lead to water and nitrogen (N) losses through leaching and environmental damage. This work introduces a novel advanced method to quantify N and water leaching at the orchard scale by combining soil monitoring, unmanned aerial vehicle (UAV) imagery to estimate tree size, leaf N and canopy content, and water flow and N transport models. Four neighboring commercial orange orchards were selected, and 48 representative trees were instrumented with suction cups and tensiometers at a depth of 90 cm. The physical properties of the soil profiles in the vicinity of each tree were determined. During 2019–2021, UAV structure-from-motion (SfM) photogrammetry was used to classify the tree sizes into small, medium, and big categories. Soil porewater extraction and soil matric potential measurements were conducted every three weeks, while leaf N contents (LNC) were determined through bimonthly leaf tissue sampling. The LNC, N leaching, soil water state, and N use efficiency (NUE) (the ratio between the mass of plant N uptake and the mass of N applied per area) were strongly related to tree size classification. Results of the calibrated hydrological model illustrated that the 'big' trees exhibited minimal N leaching due to higher transpiration compared to the other tree size categories. An NUE map was established using the calibrated model and field measurements, demonstrating that soil spatial variability minimally affected N leaching compared to tree size distribution. The presented holistic approach can be used to identify N-leaching hotspots, improve orchard scale NUE estimates, and promote sustainable agricultural management practices.

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.

Rice Counting and Localization in Unmanned Aerial Vehicle Imagery Using Enhanced Feature Fusion

In rice cultivation and breeding, obtaining accurate information on the quantity and spatial distribution of rice plants is crucial. However, traditional field sampling methods can only provide rough estimates of the plant count and fail to capture precise plant locations. To address these problems, this paper proposes P2PNet-EFF for the counting and localization of rice plants. Firstly, through the introduction of the enhanced feature fusion (EFF), the model improves its ability to integrate deep semantic information while preserving shallow spatial details. This allows the model to holistically analyze the morphology of plants rather than focusing solely on their central points, substantially reducing errors caused by leaf overlap. Secondly, by integrating efficient multi-scale attention (EMA) into the backbone, the model enhances its feature extraction capabilities and suppresses interference from similar backgrounds. Finally, to evaluate the effectiveness of the P2PNet-EFF method, we introduce the URCAL dataset for rice counting and localization, gathered using UAV. This dataset consists of 365 high-resolution images and 173,352 point annotations. Experimental results on the URCAL demonstrate that the proposed method achieves a 34.87% reduction in MAE and a 28.19% reduction in RMSE compared to the original P2PNet while increasing R2 by 3.03%. Furthermore, we conducted extensive experiments on three frequently used plant counting datasets. The results demonstrate the excellent performance of the proposed method.

Mapping and Characterizing Eelgrass Meadows Using UAV Imagery in Placentia Bay and Trinity Bay, Newfoundland and Labrador, Canada

Sustainable coastal social–ecological systems rely on healthy ecosystems known to provide benefits to both nature and people. A key ecosystem found globally is seagrass, for which maps at a scale relevant to inform conservation and management efforts are often missing. Eelgrass (Zostera marina), a species of seagrass found throughout the northern hemisphere, has been declining in Placentia Bay, an ecologically and biologically significant area of Canada’s east coast subject to an increasing human impact. This research provides baseline information on the distribution of eelgrass meadows and their anthropogenic stressors at seven sites of Placentia Bay and three sites of the adjacent Trinity Bay, on the island of Newfoundland. High-resolution maps of eelgrass meadows were created by combining ground-truth underwater videos with unmanned aerial vehicle imagery classified with an object-based image analysis approach. Visual analyses of the imagery and underwater videos were conducted to characterize sites based on the presence of physical disturbances and the semi-quantitative cover of epiphytes, an indication of nutrient enrichment. A total eelgrass area of ~1 km2 was mapped across the 10 sites, with an overall map accuracy of over 80% for 8 of the 10 sites. Results indicated minimum pressures of physical disturbance and eutrophication affecting eelgrass in the region, likely due to the small population size of the communities near the eelgrass meadows. These baseline data will promote the sustainability of potential future coastal development in the region by facilitating the future monitoring and conservation of eelgrass ecosystems.

Monitoring the spatial–temporal distribution of invasive plant in urban water using deep learning and remote sensing technology

Despite water ecosystems being capable of sustaining biodiversity and enhancing the overall resilience of the urban environment, they are highly susceptible to biological invasions. Invasive aquatic plants (IAPs) threaten the natural environment by reducing the diversity of native aquatic plants and animal communities. Detecting IAPs and mapping their distribution is crucial for the protection of urban water ecosystems. This study is the first of its kind to use high-resolution unmanned aerial vehicle (UAV) imagery and deep learning approaches to monitor the expansion of Pistia stratiotes (water lettuce). A DJI Matrice 300 RTK was utilized to capture time-series images with a resolution of 0.018 m on the Guanyin Lake, Cangshan District, Fuzhzou, China, during an outbreak and subsequent rapid growth stage of water lettuce. Three deep learning model architectures and three backbones were combined to detect water lettuce. Model performance and the ability to generalize the model were evaluated to determine the optimal model for water lettuce detection from time-series high-resolution UAV imagery. Results show that the DeepLabv3 + model with ResNet-34 achieved superior performance in detecting water lettuce from time-series imagery, yielding an average accuracy of 90.24 % (85.33 %≤F1_score ≤ 96.54 %) for water lettuce detection on five different dates. For the UAV image acquired on September 26th, the U-Net model with ResNet-18 yielded the highest accuracy (F1_score = 92.46 %), but it was not the optimal model for multi-temporal water lettuce detection on subsequent dates. The distribution of water lettuce can have large variations at different times, with an average change rate of 49.50 % every two days and the highest change rate up to 60.33 %. The study demonstrates that the combination of UAV imagery and a deep learning model can achieve excellent accuracy for water lettuce monitoring and provide a method to map IAPs in dynamic urban water systems over time.

Enhancing Crop Yield Predictions with PEnsemble 4: IoT and ML-Driven for Precision Agriculture

This research introduces the PEnsemble 4 model, a weighted ensemble prediction model that integrates multiple individual machine learning models to achieve accurate maize yield forecasting. The model incorporates unmanned aerial vehicle (UAV) imagery and Internet of Things (IoT)-based environmental data, providing a comprehensive and data-driven approach to yield prediction in maize cultivation. Considering the projected growth in global maize demand and the vulnerability of maize crops to weather conditions, improved prediction capabilities are of paramount importance. The PEnsemble 4 model addresses this need by leveraging comprehensive datasets encompassing soil attributes, nutrient composition, weather conditions, and UAV-captured vegetation imagery. By employing a combination of Huber and M estimates, the model effectively analyzes temporal patterns in vegetation indices, in particular CIre and NDRE, which serve as reliable indicators of canopy density and plant height. Notably, the PEnsemble 4 model demonstrates a remarkable accuracy rate of 91%. It advances the timeline for yield prediction from the conventional reproductive stage (R6) to the blister stage (R2), enabling earlier estimation and enhancing decision-making processes in farming operations. Moreover, the model extends its benefits beyond yield prediction, facilitating the detection of water and crop stress, as well as disease monitoring in broader agricultural contexts. By synergistically integrating IoT and machine learning technologies, the PEnsemble 4 model presents a novel and promising solution for maize yield prediction. Its application holds the potential to revolutionize crop management and protection, contributing to efficient and sustainable farming practices.

In-Season Cotton Yield Prediction with Scale-Aware Convolutional Neural Network Models and Unmanned Aerial Vehicle RGB Imagery.

In the pursuit of sustainable agriculture, efficient water management remains crucial, with growers relying on advanced techniques for informed decision-making. Cotton yield prediction, a critical aspect of agricultural planning, benefits from cutting-edge technologies. However, traditional methods often struggle to capture the nuanced complexities of crop health and growth. This study introduces a novel approach to cotton yield prediction, leveraging the synergy between Unmanned Aerial Vehicles (UAVs) and scale-aware convolutional neural networks (CNNs). The proposed model seeks to harness the spatiotemporal dynamics inherent in high-resolution UAV imagery to improve the accuracy of the cotton yield prediction. The CNN component adeptly extracts spatial features from UAV-derived imagery, capturing intricate details related to crop health and growth, modeling temporal dependencies, and facilitating the recognition of trends and patterns over time. Research experiments were carried out in a cotton field at the USDA-ARS Cropping Systems Research Laboratory (CSRL) in Lubbock, Texas, with three replications evaluating four irrigation treatments (rainfed, full irrigation, percent deficit of full irrigation, and time delay of full irrigation) on cotton yield. The prediction revealed that the proposed CNN regression models outperformed conventional CNN models, such as AlexNet, CNN-3D, CNN-LSTM, ResNet. The proposed CNN model showed state-of-art performance at different image scales, with the R2 exceeding 0.9. At the cotton row level, the mean absolute error (MAE) and mean absolute percentage error (MAPE) were 3.08 pounds per row and 7.76%, respectively. At the cotton grid level, the MAE and MAPE were 0.05 pounds and 10%, respectively. This shows the proposed model's adaptability to the dynamic interplay between spatial and temporal factors that affect cotton yield. The authors conclude that integrating UAV-derived imagery and CNN regression models is a potent strategy for advancing precision agriculture, providing growers with a powerful tool to optimize cultivation practices and enhance overall cotton productivity.

Rapidly count crop seedling emergence based on waveform Method(WM) using drone imagery at the early stage

Effectively monitoring seedling emergence is critical to identify missing cotton seedling at early stages, allowing the prompt replenishment of the seedlings to maintain crop yield. However, traditional manual inspections have the limitations with low efficiency, poor timeliness, and large counting errors. Although UAV imagery has been applied in seedling monitoring, there are still chance in cotton seedling monitoring under complex environment conditions. Therefore, there is a urgent need for an efficient, rapid, and low-cost method for monitoring early seedling emergence in cotton crops. This study utilizes RGB images of early seedling emergence captured from an unmanned aerial vehicle (UAV) at a flight height of 10 m and a resolution of 0.33 cm in Shihezi, Xinjiang, on 7 and 12 days after seeding (DAS). The modified Hough transform method is constructed for line detection, and crop rows are subsequently extracted from the lines and masked images. After masking, the waveform is extracted from the excess green index (ExG) greyscale map and smoothed to determine the peaks. Seedlings are counted and located by numbering and positioning the peaks, meanwhile their coordinates and distance determine the number and location of missing seedlings. Images with varying resolutions (ranging from 0.33 to 2.5 cm) and intensity changes (0.8 to 1.2) verify the accuracy and efficiency of the proposed waveform method(WM). The results shown that at 7 DAS, the root mean square error (RMSE) is less than 2.0 plants/row, the relative root mean squared error (RRMSE) is less than 2 %, and the coefficient of determination (R2) is stable at 0.95–0.96 when the resolution is below 1.0 cm. The RMSE, RRMSE and R2 fluctuate more when the resolution is less than 1.0 cm. At 12 DAS, the counting accuracy is stable under different conditions, and the RMSE and RRMSE are distributed smoothly over the range of 1.76–4.39 plants/row and 1.29–5.47 % with different resolutions. The R2 is in the range of 0.88–0.97, RRMSE is 1.90–3.39 % and the RMSE is 1.65–2.90 plants/row under different intensities. The results of cotton seedling counting using the waveform method are less affected by image resolution and intensity changes. Therefore, the proposed WM provides efficient, accurate, and automatic counting for cotton seedlings in response to complex weather conditions. Furthermore, it would give a novel approach to accurately countequally spaced row-sown crops based on UAV images.

Large-scale assessment of date palm plantations based on UAV remote sensing and multiscale vision transformer

Timely and efficient mapping of date palm plantations through unmanned aerial vehicle (UAV) remote sensing is critical for continuous observation, health and risk evaluation, pest management, resource optimization, and ensuring the long-term sustainability of the dates industry. This study presents an efficient and cost-effective transformer-based approach to identify, countify, monitor, and evaluate the overall well-being of palm trees using extensive UAV imagery. The suggested approach integrates an improved multiscale vision transformer, feature pyramid network, Mask R–CNN, and improved slicing-aided hyper inference for practical large-scale assessments. This combination enabled the extraction of multiscale features, capturing long-range dependencies in the data and boosting the model's generalizability. The proposed architecture outperformed several CNN-based architectures (including Mask R–CNN, Cascade Mask R–CNN, Point-based Rendering, and You Only Look At CoefficientTs), achieving F-scores of 94.33% and 94.2% for date palm tree detection and segmentation, respectively. The transformer-based architecture was optimized using transfer learning to differentiate between healthy and unhealthy date palm trees, particularly those with severe infestations. The potential generic condition of date palm trees was predicted with an F-score of 88.4%. Further advancements in this field could pave the way for a proactive strategy, enabling timely detection, which would aid in pest management and support the sustainable growth of the dates sector.

Assessing radiometric calibration methods for multispectral UAV imagery and the influence of illumination, flight altitude and flight time on reflectance, vegetation index and inversion of winter wheat AGB and LAI

Radiometric correction is essential to unmanned aerial vehicle (UAV) precision agriculture applications, especially for crop multi-period analysis and quantitative inversion of phenotypic and physiological parameters. In this study, we investigated the performance of four radiometric correction methods: “Camera only” (A), “Camera and sun irradiance” (B) and “Camera, sun irradiance and sun angle” (C) methods provided by Pix4d Mapper and an irradiance sensor-based method (D) implemented with the R software. UAV campaigns were conducted at flight altitudes of 30 m, 60 m and 90 m under clear and cloudy skies at different times over an experimental field of winter wheat. The influences of illumination, flight altitude and flight time on reflectance and vegetation indexes derived from different radiometric calibration methods were analyzed. Moreover, we further assessed the impact of reflectance and vegetation index variations on the above-ground biomass (AGB) and leaf area index (LAI) estimations of winter wheat. Results showed that method D is a promising approach for radiometric calibration, which produced consistent reflectance with method A at noon (e.g., 10:44:41 AM March 17 and 11:39:37 AM April 7) and mid-afternoon (e.g., 15:30:02 PM May 1) and more reliable reflectance in the morning (e.g., 7:15:44 AM March 17). Methods B and C seriously underestimated the reflectance at 10:44:41 AM March 17 and 11:39:37 AM April 7. This was caused by the incorrect attitude angles of the irradiance sensor and further miscalculation of the solar irradiance by Pix4d Mapper. Interestingly, these errors were eliminated in the calculation of the ratio type of vegetation indexes. Methods B and C yielded vegetation indexes that were almost the same as those of methods A and D. Under cloudy sky, when direct sunlight is not blocked by clouds, method D was effective; with cloud occlusion, results on April 24 indicated that the method failed to estimate the total sunlight and direct sunlight ratio. Reflectance and vegetation indexes obtained from different radiometric correction methods were all obviously affected by flight altitude. Furthermore, the variations of NDVI with flight altitude increasing were different with reflectance. Changes in reflectance and vegetation indexes with flight altitude had little effect on the correlation coefficients yielded with AGB, but showed a significant influence on those of LAI. Through analyzing the variation of observed solar radiation at different time intervals, caution is recommended when using the assumption that solar radiation is stable during the UAV flight. The longer the flight, the greater the variation in solar radiation, especially at sunrise and sunset. Even at noon, when the flight duration is 30 min, the change in solar radiation may exceed 10 % (e.g., 16.5 % on March 20).

Improving soybean yield prediction by integrating UAV nadir and cross-circling oblique imaging

High-throughput estimation of soybean yield using unmanned aerial vehicle (UAV) imagery can help improve the efficiency of soybean breeding. Previous studies have mainly focused on the extraction of vegetation indices and texture features from two-dimensional(2D) orthophotos to construct empirical models of yield, lacking spatial structure information of crops. Therefore, UAV cross-circling oblique (CCO) photography combined with SfM-MVS algorithm was used to reconstruct three-dimensional(3D) soybean canopy structure. Then canopy 3D related phenotypic features are extracted and combined with features from RGB nadir and multispectral images to analyze the capability of different modal data fusion on soybean yield prediction. In addition, Shapley value was used to evaluate the importance of features across different machine learning models. Based on the Shapley value, a bagging-stacking ensemble learning framework was developed using Lasso, Random Forest (RF), Ridge Regression (RR), and XGBoost as base learners for yield prediction. The performance of the traditional stacking method was evaluated and compared with weighted average methods such as Bayesian Model Averaging (BMA) and Entropy Weighted Average (EWA) as meta-learners in the ensemble framework. The results show that 3D canopy structure of soybean can be obtained from UAV CCO photography. The inclusion of 3D structural features can improve the accuracy of yield estimation. Among different modal data combinations, the highest estimation accuracy was achieved when combining RGB nadir features with CCO 3D features. The performance of the above base learners was improved by 8.8%, 3.5%, 7.1%, and 8.0% respectively when using the Shapley value method. The accuracy of yield prediction applied on independent dataset of year 2023 was further calculated by using the bagging-stacking ensemble learning method. When using BMA as the meta-learner, the best performance is obtained with an R2 of 0.7. Therefore, UAV CCO photography with SfM-MVS algorithm provides a new approach to obtain high-quality point clouds of the crop canopy at low cost. UAV multimodal data combined with ensemble learning models allow accurate estimation of yield prediction in breeding materials of soybeans at the plot scale.

A Practical Deep Learning Architecture for Large-Area Solid Wastes Monitoring Based on UAV Imagery

The development of global urbanization has brought about a significant amount of solid waste. These untreated wastes may be dumped in any corner, causing serious pollution to the environment. Thus, it is necessary to accurately obtain their distribution locations and detailed edge information. In this study, a practical deep learning network for recognizing solid waste piles over extensive areas using unmanned aerial vehicle (UAV) imagery has been proposed and verified. Firstly, a high-resolution dataset serving to solid waste detection was created based on UAV aerial data. Then, a dual-branch solid waste semantic segmentation model was constructed to address the characteristics of the integration of solid waste distribution with the environment and the irregular edge morphology. The Context feature branch is responsible for extracting high-level semantic features, while the Spatial feature branch is designed to capture fine-grained spatial details. After information fusion, the model obtained more comprehensive feature representation and segmentation ability. The effectiveness of the improvement was verified through ablation experiments and compared with 13 commonly used semantic segmentation models, demonstrating the advantages of the method in solid waste segmentation tasks, with an overall accuracy of over 94%, and a recall rate of 88.6%—much better than the best performing baselines. Finally, a spatial distribution map of solid waste over Jiaxing district, China was generated by the model inference, which assisted the environmental protection department in completing environmental management. The proposed method provides a feasible approach for the accurately monitoring of solid waste, so as to provide policy support for environmental protection.

Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning-A Comparison between High-End and Low-Cost Multispectral Sensors.

In order to meet the increasing demand for crops under challenging climate conditions, efficient and sustainable cultivation strategies are becoming essential in agriculture. Targeted herbicide use reduces environmental pollution and effectively controls weeds as a major cause of yield reduction. The key requirement is a reliable weed detection system that is accessible to a wide range of end users. This research paper introduces a self-built, low-cost, multispectral camera system and evaluates it against the high-end MicaSense Altum system. Pixel-based weed and crop classification was performed on UAV datasets collected with both sensors in maize using a U-Net. The training and testing data were generated via an index-based thresholding approach followed by annotation. As a result, the F1-score for the weed class reached 82% on the Altum system and 76% on the low-cost system, with recall values of 75% and 68%, respectively. Misclassifications occurred on the low-cost system images for small weeds and overlaps, with minor oversegmentation. However, with a precision of 90%, the results show great potential for application in automated weed control. The proposed system thereby enables sustainable precision farming for the general public. In future research, its spectral properties, as well as its use on different crops with real-time on-board processing, should be further investigated.

Diurnal Change of NDVI from UAV in Trees of a Temperate Unavenged Forest Stand

NDVI elucidates the ecophysiological mechanisms faced by vegetation. With the flexibility and versatility of unmanned aerial vehicles (UAVs), temporal, spatial and spectral resolutions have been useful in supporting decision-making. Here, we modeled diurnal change in the NDVI derived from UAV imagery for individual trees in a natural forest stand. Eight flights were conducted during daylight hours over one day to assess the dynamics of the NDVI of the genera Pinus, Juniperus, and Quercus. The results showed unstable NDVI values over time, with a parabolic quadratic trend in the model. The NDVI reached its maximum around 13:00 h and the values differed significantly according to genus: the highest value was found in Pinus with significant differences presented with Juniperus and Quercus, which showed similar values between them (p=0.533). As a validation strategy, we test the model generated using 124 trees independent of those that were sampled, which strengthened our results in terms of reliability. The similarities of statistical parameters confer a high variability of application of the results in models of simulation of similar forests ecosystems. We recommend to study more spectral indices of vegetation, including calibration of the sensor, particularly in longer-term seasonal studies. We conclude that the NDVI measured using UAV should consider image acquisition time to calibrate the records and thus improve the interpretation of results.

Crop mapping in smallholder farms using unmanned aerial vehicle imagery and geospatial cloud computing infrastructure

Smallholder farms are major contributors to agricultural production, food security, and socio-economic growth in many developing countries. However, they generally lack the resources to fully maximize their potential. Subsequently they require innovative, evidence-based and lower-cost solutions to optimize their productivity. Recently, precision agricultural practices facilitated by unmanned aerial vehicles (UAVs) have gained traction in the agricultural sector and have great potential for smallholder farm applications. Furthermore, advances in geospatial cloud computing have opened new and exciting possibilities in the remote sensing arena. In light of these recent developments, the focus of this study was to explore and demonstrate the utility of using the advanced image processing capabilities of the Google Earth Engine (GEE) geospatial cloud computing platform to process and analyse a very high spatial resolution multispectral UAV image for mapping land use land cover (LULC) within smallholder farms. The results showed that LULC could be mapped at a 0.50 m spatial resolution with an overall accuracy of 91%. Overall, we found GEE to be an extremely useful platform for conducting advanced image analysis on UAV imagery and rapid communication of results. Notwithstanding the limitations of the study, the findings presented herein are quite promising and clearly demonstrate how modern agricultural practices can be implemented to facilitate improved agricultural management in smallholder farmers.