Unmanned Aerial Vehicle Images Research Articles

Range–Visual–Inertial Odometry with Coarse-to-Fine Image Registration Fusion for UAV Localization

In Global Navigation Satellite System (GNSS)-denied environments, image registration has emerged as a prominent approach to utilize visual information for estimating the position of Unmanned Aerial Vehicles (UAVs). However, traditional image-registration-based localization methods encounter limitations, such as strong dependence on the prior initial position information. In this paper, we propose a systematic method for UAV geo-localization. In particular, an efficient range–visual–inertial odometry (RVIO) is proposed to provide local tracking, which utilizes measurements from a 1D Laser Range Finder (LRF) to suppress scale drift in the odometry. To overcome the differences in seasons, lighting conditions, and other factors between satellite and UAV images, we propose an image-registration-based geo-localization method in a coarse-to-fine manner that utilizes the powerful representation ability of Convolutional Neural Networks (CNNs). Furthermore, to ensure the accuracy of global optimization, we propose an adaptive weight assignment method based on the evaluation of the quality of image-registration-based localization. The proposed method is extensively evaluated in both synthetic and real-world environments. The results demonstrate that the proposed method achieves global drift-free estimation, enabling UAVs to accurately localize themselves in GNSS-denied environments.

Robust Coffee Rust Detection Using UAV-Based Aerial RGB Imagery

Timely detection of pests and diseases in crops is essential to mitigate severe damage and economic losses, especially in the context of climate change. This paper describes a method for detecting the presence of coffee leaf rust (CLR) using two databases: RoCoLe and a database obtained from an unmanned aerial vehicle (UAV) equipped with an RGB camera. The developed method follows a two-stage approach. In the first stage, images are processed using ImageJ software, while, in the second phase, Python is used to implement morphological filters and the Hough transform for rust identification. The algorithm’s performance is evaluated using the chi-square test, and its discriminatory capacity is assessed through the generation of a Receiver Operating Characteristic (ROC) curve. Additionally, Cohen’s kappa method is used to assess the agreement among observers, while Kendall’s rank correlation coefficient (KRCC) measures the correlation between the criteria of the observers and the classifications generated by the method. The results demonstrate that the developed method achieved an efficiency of 97% in detecting coffee rust in the RoCoLe dataset and over 93.5% in UAV images. These findings suggest that the developed method has the potential to be implemented in the future on a UAV for rust detection.

Classification of Unmanned Aerial Vehicle and Bird Images Using Deep Transfer Learning Methods

The increasing accessibility and affordability of unmanned aerial vehicles (UAVs), commonly known as drones, have led to the emergence of malicious users. In precaution to this perceived threat, various anti-UAV systems are being developed, including electro-optical systems utilizing cameras. It is possible to detect UAVs from images using various machine learning methods. However, the similarity between UAVs and birds poses a challenge, as birds can be mistakenly identified as UAVs, leading to false alarms in a security system. In order to avoid this problem, this study provided the classification of birds and unmanned aerial vehicles over images using deep learning methods. In this study, a data set consisting of 400 birds and 428 UAV images was used. The data were divided into 70% for training, 30% for testing and validation purposes. Three different deep learning models, based on DenseNet, VGG16, and VGG19 architectures, were trained using transfer learning techniques, and their performances were compared. Experimental results on the test data showed an accuracy of 94.64% with the DenseNet model, 89.67% with the VGG16 model, and 90.67% with the VGG19 model.

KLASIFIKASI KESEHATAN PADA TANAMAN PADI MENGGUNAKAN CITRA UNMANED AERIAL VEHICLE (UAV) DENGAN METODE CONVOLUTIONAL NEURAL NETWORKS (CNN)

Indonesia is a country with a majority of the population making rice the main food. With an increasing population, of course, it is necessary to maintain the quality of rice to reduce the risk of crop failure. In 2019, it was stated that nearly 40% of the world's crop was lost due to disease and pest infestation. Unmanned Aerial Vehicle (UAV) is a technology that has been widely used for the observation and mapping of rice plants. The UAV's small size allows it to maneuver more, making shooting land easier and faster. These diseases and pest attacks can be detected by looking at the plant parts. The easiest part to detect is on the leaves because the signs of the disease can be seen clearly. However, it is not easy to recognize these diseases, it requires experts to identify diseases through a more accurate UAV image. Convolutional Neural Network (CNN) is a deep learning method that is often used in digital image recognition. This is because CNN is trying to imitate the image recognition method in the human visual cortex. The CNN method in this study was used to classify healthy rice plants and diseased rice plants through UAV imagery

Small object detection in UAV image based on improved YOLOv5

Less effective information is obtained by the object detection network, due to the small size of the detection object in the entire image, the complex background, and the dense object in unmanned aerial vehicle (UAV) images. In response to the difficulties encountered, a small object detection method in UAV images is proposed as an improved YOLOv5-based algorithm in this paper. First, the space-to-depth(SPD) conv module is introduced into the basic feature extraction network, to improve significant loss of image information during downsampling. Then, various attention mechanisms are added, to intensify the acquisition of regions of interest in UAV images. Finally, the multiscale detection module is improved, to enhance the network's ability to detect small objects in UAV images. By conducting experiments on the VisDrone-DET2019 dataset, the test results of the established model show. The improved algorithm achieved a Mean Average Precision (mAP) of 41.8%, which is 7.8% better than the baseline network. In addition, the detection performance is better than most current mainstream target detection algorithms and is of some practical value.

UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios.

Unmanned aerial vehicle (UAV) object detection plays a crucial role in civil, commercial, and military domains. However, the high proportion of small objects in UAV images and the limited platform resources lead to the low accuracy of most of the existing detection models embedded in UAVs, and it is difficult to strike a good balance between detection performance and resource consumption. To alleviate the above problems, we optimize YOLOv8 and propose an object detection model based on UAV aerial photography scenarios, called UAV-YOLOv8. Firstly, Wise-IoU (WIoU) v3 is used as a bounding box regression loss, and a wise gradient allocation strategy makes the model focus more on common-quality samples, thus improving the localization ability of the model. Secondly, an attention mechanism called BiFormer is introduced to optimize the backbone network, which improves the model's attention to critical information. Finally, we design a feature processing module named Focal FasterNet block (FFNB) and propose two new detection scales based on this module, which makes the shallow features and deep features fully integrated. The proposed multiscale feature fusion network substantially increased the detection performance of the model and reduces the missed detection rate of small objects. The experimental results show that our model has fewer parameters compared to the baseline model and has a mean detection accuracy higher than the baseline model by 7.7%. Compared with other mainstream models, the overall performance of our model is much better. The proposed method effectively improves the ability to detect small objects. There is room to optimize the detection effectiveness of our model for small and feature-less objects (such as bicycle-type vehicles), as we will address in subsequent research.

Precision Detection of Dense Litchi Fruit in UAV Images Based on Improved YOLOv5 Model

The utilization of unmanned aerial vehicles (UAVs) for the precise and convenient detection of litchi fruits, in order to estimate yields and perform statistical analysis, holds significant value in the complex and variable litchi orchard environment. Currently, litchi yield estimation relies predominantly on manual rough counts, which often result in discrepancies between the estimated values and the actual production figures. This study proposes a large-scene and high-density litchi fruit recognition method based on the improved You Only Look Once version 5 (YOLOv5) model. The main objective is to enhance the accuracy and efficiency of yield estimation in natural orchards. First, the PANet in the original YOLOv5 model is replaced with the improved Bi-directional Feature Pyramid Network (BiFPN) to enhance the model’s cross-scale feature fusion. Second, the P2 feature layer is fused into the BiFPN to enhance the learning capability of the model for high-resolution features. After that, the Normalized Gaussian Wasserstein Distance (NWD) metric is introduced into the regression loss function to enhance the learning ability of the model for litchi tiny targets. Finally, the Slicing Aided Hyper Inference (SAHI) is used to enhance the detection of tiny targets without increasing the model’s parameters or computational memory. The experimental results show that the overall AP value of the improved YOLOv5 model has been effectively increased by 22%, compared to the original YOLOv5 model’s AP value of 50.6%. Specifically, the APs value for detecting small targets has increased from 27.8% to 57.3%. The model size is only 3.6% larger than the original YOLOv5 model. Through ablation and comparative experiments, our method has successfully improved accuracy without compromising the model size and inference speed. Therefore, the proposed method in this paper holds practical applicability for detecting litchi fruits in orchards. It can serve as a valuable tool for providing guidance and suggestions for litchi yield estimation and subsequent harvesting processes. In future research, optimization can be continued for the small target detection problem, while it can be extended to study the small target tracking problem in dense scenarios, which is of great significance for litchi yield estimation.

Automatic area estimation of algal blooms in water bodies from UAV images using texture analysis

Algal blooms, the spread of algae on the surface of water bodies, have adverse effects not only on aquatic ecosystems but also on human life. The adverse effects of harmful algal blooms (HABs) necessitate a convenient solution for detection and monitoring. Unmanned aerial vehicles (UAVs) have recently emerged as a tool for algal bloom detection, efficiently providing on-demand images at high spatiotemporal resolutions. This study developed an image processing method for algal bloom area estimation from the aerial images (obtained from the internet) captured using UAVs. As a remote sensing method of HAB detection, analysis, and monitoring, a combination of histogram and texture analyses was used to efficiently estimate the area of HABs. Statistical features like entropy (using the Kullback–Leibler method) were emphasized with the aid of a gray-level co-occurrence matrix. The results showed that the orthogonal images demonstrated fewer errors, and the morphological filter best detected algal blooms in real time, with a precision of 80%. This study provided efficient image processing approaches using on-board UAVs for HAB monitoring.

Drone-YOLO: An Efficient Neural Network Method for Target Detection in Drone Images

Object detection in unmanned aerial vehicle (UAV) imagery is a meaningful foundation in various research domains. However, UAV imagery poses unique challenges, including large image sizes, small sizes detection objects, dense distribution, overlapping instances, and insufficient lighting impacting the effectiveness of object detection. In this article, we propose Drone-YOLO, a series of multi-scale UAV image object detection algorithms based on the YOLOv8 model, designed to overcome the specific challenges associated with UAV image object detection. To address the issues of large scene sizes and small detection objects, we introduce improvements to the neck component of the YOLOv8 model. Specifically, we employ a three-layer PAFPN structure and incorporate a detection head tailored for small-sized objects using large-scale feature maps, significantly enhancing the algorithm’s capability to detect small-sized targets. Furthermore, we integrate the sandwich-fusion module into each layer of the neck’s up–down branch. This fusion mechanism combines network features with low-level features, providing rich spatial information about the objects at different layer detection heads. We achieve this fusion using depthwise separable evolution, which balances parameter costs and a large receptive field. In the network backbone, we employ RepVGG modules as downsampling layers, enhancing the network’s ability to learn multi-scale features and outperforming traditional convolutional layers. The proposed Drone-YOLO methods have been evaluated in ablation experiments and compared with other state-of-the-art approaches on the VisDrone2019 dataset. The results demonstrate that our Drone-YOLO (large) outperforms other baseline methods in the accuracy of object detection. Compared to YOLOv8, our method achieves a significant improvement in mAP0.5 metrics, with a 13.4% increase on the VisDrone2019-test and a 17.40% increase on the VisDrone2019-val. Additionally, the parameter-efficient Drone-YOLO (tiny) with only 5.25 M parameters performs equivalently or better than the baseline method with 9.66M parameters on the dataset. These experiments validate the effectiveness of the Drone-YOLO methods in the task of object detection in drone imagery.

Quantitative Trait Locus (QTL) Mapping for Common Wheat Plant Heights Based on Unmanned Aerial Vehicle Images

The application of unmanned aerial vehicle (UAV) remote sensing technology for high-throughput acquisition of phenotypic values of field plant height is of great significance in plant height monitoring of wheat varieties (lines). Based on the UAV, mounted with high-resolution digital cameras, a low-altitude remote sensing platform was built to obtain images of the Berkut/Worrakatta recombinant inbred lines (RIL) wheat population (297 lines). The optimal digital surface model (DSM) for plant height extraction was constructed by combining the actual wheat plant heights measured in the field. Using a wheat 50K SNP chip, quantitative trait locus (QTL) analysis was performed for field plant height of the RIL population using UAV plant height data to detect the locus related to plant height. We verified the effectiveness of QTL analysis using the UAV plant height data. The results of the DSM plant height extraction method showed that the plant height extraction models during the entire growth period had a highly significant correlation (p < 0.001); the measured plant height correlated with the predicted plant height, with prediction model accuracy R2 = 0.7527 and verification model accuracy R2 = 0.8214. QTL analysis was conducted on the manually and UAV-measured plant height traits. For the manually measured plant height phenotypes, one locus related to plant height was detected on wheat chromosome 6A and explained 13.12% of phenotypic variation. For the UAV-measured phenotypes, one locus related to plant height was also detected on wheat chromosome 6A and explained 9.62% of phenotypic variation. The QPH.xjau-6A locus on chromosome 6A, which featured in the results of the two measurement methods, is a stable locus, indicating that the mapping results obtained using the actual plant height values were in good agreement with those obtained using the UAV extracted values. Three candidate genes related to plant height were screened: they encode protein kinase, NAC domain protein, and cytochrome P450, respectively. Therefore, this study provided reference information for monitoring plant phenotype and growth of wheat and also for the extraction of plant height for wheat breeding in the future.

Assessment of Soybean Lodging Using UAV Imagery and Machine Learning.

Plant lodging is one of the most essential phenotypes for soybean breeding programs. Soybean lodging is conventionally evaluated visually by breeders, which is time-consuming and subject to human errors. This study aimed to investigate the potential of unmanned aerial vehicle (UAV)-based imagery and machine learning in assessing the lodging conditions of soybean breeding lines. A UAV imaging system equipped with an RGB (red-green-blue) camera was used to collect the imagery data of 1266 four-row plots in a soybean breeding field at the reproductive stage. Soybean lodging scores were visually assessed by experienced breeders, and the scores were grouped into four classes, i.e., non-lodging, moderate lodging, high lodging, and severe lodging. UAV images were stitched to build orthomosaics, and soybean plots were segmented using a grid method. Twelve image features were extracted from the collected images to assess the lodging scores of each breeding line. Four models, i.e., extreme gradient boosting (XGBoost), random forest (RF), K-nearest neighbor (KNN) and artificial neural network (ANN), were evaluated to classify soybean lodging classes. Five data preprocessing methods were used to treat the imbalanced dataset to improve classification accuracy. Results indicate that the preprocessing method SMOTE-ENN consistently performs well for all four (XGBoost, RF, KNN, and ANN) classifiers, achieving the highest overall accuracy (OA), lowest misclassification, higher F1-score, and higher Kappa coefficient. This suggests that Synthetic Minority Oversampling-Edited Nearest Neighbor (SMOTE-ENN) may be a good preprocessing method for using unbalanced datasets and the classification task. Furthermore, an overall accuracy of 96% was obtained using the SMOTE-ENN dataset and ANN classifier. The study indicated that an imagery-based classification model could be implemented in a breeding program to differentiate soybean lodging phenotype and classify lodging scores effectively.

Using convolutional neural networks to identify illegal roofs from unmanned aerial vehicle images

ABSTRACT Illegal structures, which are structures illegally built on land or buildings, are common in Taiwan. Urban residents frequently inform authorities of illegal roofs, a type of illegal structure, because of the potential fire hazards they pose. However, the government does not conduct timely inspection on illegal roofs because this process requires additional human resources. Therefore, developing an efficient and correct method for inspecting and reporting illegal structures is necessary. In this study, unmanned aerial vehicles (UAVs) were used to rapidly capture images, which were then used to generate orthophotos, a 3D building model, a digital surface model (DSM), and a data set containing 400 images of illegal roofs and 400 images of legal roofs. The data set was then used in a convolutional neural network (CNN) to train and evaluate image classification. The results revealed an illegal roof classification accuracy of 96.0%, with a loss of 0.09. In addition, You Only Look Once v3 (YOLOv3) was used to detect illegal buildings, and DSMs higher than 9 m were overlaid to improve the accuracy of the illegal roof identification model. Overall, the study results can help inspectors build a comprehensive database of illegal roofs, which can serve as a reference for budgeting demolition costs and human resources.

Multi-sensor and multi-platform retrieval of water chlorophyll a concentration in karst wetlands using transfer learning frameworks with ASD, UAV, and Planet CubeSate reflectance data

China has one of the widest distributions of carbonate rocks in the world. Karst wetland is a special and important ecosystem of carbonate rock regions. Chlorophyll-a (Chla) concentration is a key indicator of eutrophication, and could quantitatively evaluate water quality status of karst wetland. However, the spectral reflectance characteristics of the water bodies of karst wetland are not yet clear, resulting in remote sensing retrieval of Chla with great challenges. This study is a pioneer in utilizing field-based full-spectrum hyperspectral data to reveal the spectral response characteristics of karst wetland water body and determine the sensitive spectral bands of Chla. We further evaluated the Chla retrieval performance of multi-platform spectral data between Analytical Spectral Device (ASD), Unmanned aerial vehicle (UAV), and PlanetScope (Planet). We proposed two multi-sensor weighted integration strategies and two transfer learning frameworks for estimating water Chla from the largest karst wetland in China by combing a partial least square with adaptive ensemble algorithms. The results showed that: (1) In the range of 500–850 nm, the spectral reflectance of water bodies in the karst wetland was overall 0.001–0.105 higher than the inland water bodies, and the sensitive spectral ranges of water Chla focus on 603–778 nm; (2) UAV images outperformed ASD and Planet data, and produced the highest inversion accuracy (R2 = 0.670) for water Chla in karst wetland; (3) Multi-sensor weighted integration retrieval methods improved the Chla estimation accuracy (R2 = 0.716). Integration retrieval methods with the different weights produced the better Chla estimation accuracy than that of methods with the equal weights; (4) The transfer learning methods from ASD to UAV platform provided the better retrieval performance (the average R2 = 0.669) than that of methods from UAV to Planet platform. The transfer learning methods obtained the highest estimation accuracy of Chla (R2 = 0.814) when the ratio of the training and test data in the target domain was 7:3. The transfer learning methods produced the higher estimation accuracies with the distribution of the absolute residuals between predicted and measured values <20.957 mg/m3 compared to the multi-sensor weighted integration retrieval methods, which demonstrated that transfer learning is more suitable for estimating Chla in karst wetland water bodies using multi-platform and multi-sensor data. The results provide a scientific basis for the protection and sustainable development of karst wetlands.

Grain yield prediction using multi-temporal UAV-based multispectral vegetation indices and endmember abundance in rice

Timely and accurately predicting grain yield before harvest is of great importance for rice production management and grain trade. Numerous methods based on remote sensing (RS) technology have explored to estimate rice grain yield. However, in most cases, these methods are negatively affected by the mixed pixels of RS images due to the effect of background and panicles. To resolve such issues, the abundance information of leaves, soil and water background and rice panicles were extracted from the multispectral images of unmanned aerial vehicle (UAV) for the multiple endmember spectral mixture analysis (MESMA) method. Based on the analysis of contribution of vegetation index (VI) and abundance (ABD) to rice grain yield, a rice grain yield prediction model was developed by combining multi-stage time-series, ABD and VI. Results showed that MESMA can mitigate endmember variability in the estimation of rice yield, and achieve higher accuracy than conventional spectral mixture analysis (SMA). The NDRE and the sum of leaf and panicle abundance (ABDL+P) can be well correlated to grain yield before heading stage (R2 = 0.75) and at heading stage (R2 = 0.72), respectively. In comparison to them, the multi-stage time-series model consisted of VI and ABD [∑(VI&ABD)] produces the highest correlation (R2 = 0.80). It could also resolve the issues about the underestimation of yield using different datasets from various multi-spectral camera in comparison to the single-parameter models ∑VI and ∑ABD, and produce the good validation accuracy with R2 = 0.73, RRMSE= 0.22 and R2 = 0.75, RRMSE= 0.15, respectively. This study suggests that the combination of UAV multi-temporal VI and ABD data can achieve accurate prediction of rice grain yield. This method effectively utilizes the optical information of leaves and rice panicles and reduces background effects, which provides a new idea for accurate rice yield prediction.

UAV Image Target Recognition Algorithm based on Machine Learning

Target recognition in aerial operation of unmanned aerial vehicle (UAV) has the characteristics of complex environment, easy deformation of moving image target, single target feature and small volume. To solve these problems, different advantages of visual saliency algorithm in time, space and frequency domains are studied. The candidate region of the target is extracted, and the final target is further determined by using region feature extraction and SVM. The recognition results on the test data sets show that the recall rate of the MDVS algorithm used in the study exceeds 99% on both test sets, and the F1 index is also above 85%. After adding SVM classifier for classification and recognition, the precision rate has been significantly improved, and the values of the three indicators have exceeded 90%. The recognition algorithm proposed for UAV images, compared with several common recognition algorithms, is effective and has better recognition effect and robustness.

Semi-supervised cooperative regression model for small sample estimation of citrus leaf nitrogen content with UAV images

ABSTRACT Nitrogen is an essential nutrient element for the growth of citrus tree. The accurate estimation of leaf nitrogen content (LNC) is important to guarantee fruit quality and yield. The unmanned aerial vehicle (UAV) remote sensing has shown great potential for monitoring the LNC of crops. However, the number of training samples is always limited due to the high cost and time consumption of acquiring LNC samples. Obtaining satisfactory results is difficult for most machine-learning models with insufficient samples. Thus, a semi-supervised regression model is designed in this paper to improve the performance of estimating citrus LNC from UAV images under the condition of small samples. First, the local binary pattern (LBP) operator is employed to fully extract textural features in UAV images. Second, semi-supervised cooperative regression models based on ridge regression (Ridge), support vector regression (SVR), and random forest (RF) are constructed by combining spectral and textural features. Finally, the best learning model is used to realize the accurate limited sample LNC estimation from the available training samples. The experiments confirm that the semi-supervised cooperative regression model has better and promising results than other machine-learning methods under the condition of small samples. The RF-based cooperative regression model (CoRF) performs best among other models, with a determination coefficient (R2) of 0.716 and a root mean square error (RMSE) of 0.620 g·kg−1. The CoRF model also achieves superior performance when combining LBP textural features. The results estimated by the semi-supervised cooperative regression model is capable of providing instructions for the production and management of citrus orchard.

LSVL: Large-scale season-invariant visual localization for UAVs

Localization of autonomous unmanned aerial vehicles (UAVs) relies heavily on Global Navigation Satellite Systems (GNSS), which are susceptible to interference. Especially in security applications, robust localization algorithms independent of GNSS are needed to provide dependable operations of autonomous UAVs also in interfered conditions. Typical non-GNSS visual localization approaches rely on known starting pose, work only on a small-sized map, or require known flight paths before a mission starts. We consider the problem of localization with no information on initial pose or planned flight path. We propose a solution for global visual localization on large maps, based on matching orthoprojected UAV images to satellite imagery using learned season-invariant descriptors, and test with environment sizes up to 100 km2. We show that the method is able to determine heading, latitude and longitude of the UAV at 12.6–18.7 m lateral translation error in as few as 23.2–44.4 updates from an uninformed initialization, also in situations of significant seasonal appearance difference (winter–summer) between the UAV image and the map. We evaluate the characteristics of multiple neural network architectures for generating the descriptors, and likelihood estimation methods that are able to provide fast convergence and low localization error. We also evaluate the operation of the algorithm using real UAV data and evaluate running time on a real-time embedded platform. We believe this is the first work that is able to recover the pose of an UAV at this scale and rate of convergence, while allowing significant seasonal difference between camera observations and map.

Maize Nitrogen Grading Estimation Method Based on UAV Images and an Improved Shufflenet Network

Maize is a vital crop in China for both food and industry. The nitrogen content plays a crucial role in its growth and yield. Previous researchers have conducted numerous studies on the issue of the nitrogen content in single maize plants from a regression perspective; however, partition management techniques of precision agriculture require plants to be divided by zones and classes. Therefore, in this study, the focus is shifted to the problems of plot classification and graded nitrogen estimation in maize plots performed based on various machine learning and deep learning methods. Firstly, the panoramic unmanned aerial vehicle (UAV) images of maize farmland are collected by UAV and preprocessed to obtain UAV images of each maize plot to construct the required datasets. The dataset includes three classes—low nitrogen, medium nitrogen, and high nitrogen, with 154, 94, and 46 sets of UAV images, respectively, in each class. The training set accounts for eighty percent of the entire dataset and the test set accounts for the other twenty percent. Then, the dataset is used to train models based on machine learning and convolutional neural network algorithms and subsequently the models are evaluated. Comparisons are made between five machine learning classifiers and four convolutional neural networks to assess their respective performances, followed by a separate assessment of the most optimal machine learning classifier and convolutional neural networks. Finally, the ShuffleNet network is enhanced by incorporating SENet and improving the kernel size of the Depthwise separable convolution. The findings demonstrate that the enhanced ShuffleNet network has the highest performance; its classification accuracy, precision, recall, and F1 scores were 96.8%, 97.0%, 97.1%, and 97.0%, respectively. The RegNet, the optimal model among deep learning models, achieved accuracy, precision, recall, and F1 scores of 96.4%, 96.9%, 96.5%, and 96.6%, respectively. In comparison, logistic regression, the optimal model among the machine learning classifiers, attained accuracy of 77.6%, precision of 79.5%, recall of 77.6%, and an F1 score of 72.6%. Notably, the logistic regression exhibited significant enhancements of 19.2% in accuracy, 17.5% in precision, 19.5% in recall, and 24.4% in the F1 score. In contrast, RegNet demonstrated modest improvements of 0.4% in accuracy, 0.1% in precision, 0.6% in recall, and 0.4% in the F1 score. Moreover, ShuffleNet-improvement boasted a substantially lower loss rate of 0.117, which was 0.039 lower than that of RegNet (0.156). The results indicated the significance of ShuffleNet-improvement in the nitrogen classification of maize plots, providing strong support for agricultural zoning management and precise fertilization.

Image Splicing Compression Algorithm Based on the Extended Kalman Filter for Unmanned Aerial Vehicles Communication

The technology of unmanned aerial vehicles (UAVs) is extensively utilized across various domains due to its exceptional mobility, cost-effectiveness, rapid deployment, and flexible configuration. However, its limited storage space and the contradiction between the large amount of image data returned and the limited bandwidth in emergency scenarios necessitate the development of a suitable UAVs image compression technology. In this research, we propose an image splicing compression algorithm based on the extended Kalman filter for UAV communication (SEKF-UC). Firstly, we introduce the concept of image splicing to enhance the compression ratio while ensuring image quality, leveraging the characteristics of deep learning-based compression, which are relatively unaffected by the size of the compressed data. Secondly, to address the issue of slow processing speed of deep neural networks (DNN) caused by the substantial volume of data involved in image splicing, we incorporate an extended Kalman filter module to expedite the process. Simulation experiments show that our proposed algorithm outperforms existing methods in multiple ways, achieving a significant compression ratio improvement, from 2:1 to 25:1, with a marginal reduction of 6.5% in structural similarity (SSIM) compared to the non-spliced approach. Moreover, for deep neural networks (DNN), our method incorporating the extended Kalman filter module achieves the same error level with only 30 iterations—a significant reduction compared to the traditional BP algorithm’s requirement of over 4000 iterations—while improving the average network operation speed by an impressive 89.76%. Additionally, our algorithm excels in image quality, with peak signal-to-noise ratio (PSNR) improving by 92.7% and SSIM by 42.1%, at most, compared to other algorithms. These results establish our algorithm as a highly efficient and effective solution, suitable for various image processing and data compression applications.

Effects of UAV flight height on biomass estimation of desert shrub communities

Accurate estimation of desert vegetation biomass is crucial for monitoring changes in carbon stocks and productivity status. Unmanned aerial vehicle (UAV) remote sensing allows large-scale biomass surveys at the individual or patch scale. However, since desert shrubs are short and sparse, the UAV-based techniques do not always accurately capture biomass-related indicators at any flight height. This study investigated the effects of flight height on above-ground biomass (AGB) estimation using UAV images of typical shrub communities (Reaumuria soongarica) captured at different heights (i.e., 30 m, 50 m, 70 m, 90 m, 110 m, 130 m, and 150 m) in desert-grassland ecosystems. Several structural indicators associated with shrub allometric growth were extracted for AGB modeling, including canopy area (horizontal properties), canopy height (vertical properties), and canopy volume. Results revealed that the values of canopy height and volume decreased with increasing flight height, which made the poor performance of AGB models based on these indicators worse. For example, the variance explained (VE) of the models based on the mean canopy height decreased from about 62% to -137%, while the root mean square error (RMSE) increased from about 39 g to 92 g. In contrast, the canopy area was less affected by flight height, maintaining stable AGB models with VE around 72% and RMSE at 33 g. Adjusting the coefficients of linear models based on canopy height and volume with flight height significantly improved their predictive performance, with VE between 54% and 77% and RMSE between 30 g and 43 g for the optimized models based on mean canopy height. Furthermore, a higher flight height (e.g., 90–110 m) could be chosen to enhance operational efficiency while ensuring the accuracy of biomass observation. Our study offers valuable insights and guidance for vegetation surveys and research in desert-grassland ecosystems.