Identifying Pine Wood Nematode Disease Using UAV Images and Deep Learning Algorithms

Pine wilt disease detection algorithm based on improved YOLOv5

Pine wilt disease (PWD) poses a significant threat to forests due to its high infectivity and lethality. The absence of an effective treatment underscores the importance of timely detection and isolation of infected trees for effective prevention and control. While deep learning techniques combined unmanned aerial vehicle (UAV) remote sensing images offer promise for accurate identification of diseased pine trees in their natural environments, they often demand extensive prior professional knowledge and struggle with efficiency. This paper proposes a detection model YOLOv5L-s-SimAM-ASFF, which achieves remarkable precision, maintains a lightweight structure, and facilitates real-time detection of diseased pine trees in UAV RGB images under natural conditions. This is achieved through the integration of the ShuffleNetV2 network, a simple parameter-free attention module known as SimAM, and adaptively spatial feature fusion (ASFF). The model boasts a mean average precision (mAP) of 95.64% and a recall rate of 91.28% in detecting pine wilt diseased trees, while operating at an impressive 95.70 frames per second (FPS). Furthermore, it significantly reduces model size and parameter count compared to the original YOLOv5-Lite. These findings indicate that the proposed model YOLOv5L-s-SimAM-ASFF is most suitable for real-time, high-accuracy, and lightweight detection of PWD-infected trees. This capability is crucial for precise localization and quantification of infected trees, thereby providing valuable guidance for effective management and eradication efforts.

Exploring the Close-Range Detection of UAV-Based Images on Pine Wilt Disease by an Improved Deep Learning Method

Pine wilt disease (PWD) is a significantly destructive forest disease. To control the spread of PWD, an urgent need exists for a real-time and efficient method to detect infected trees. However, existing object detection models have often faced challenges in balancing lightweight design and accuracy, particularly in complex mixed forests. To address this, an improvement was made to the YOLOv5s (You Only Look Once version 5s) algorithm, resulting in a real-time and efficient model named PWD-YOLO. First, a lightweight backbone was constructed, composed of multiple connected RepVGG Blocks, significantly enhancing the model's inference speed. Second, a C2fCA module was designed to incorporate rich gradient information flow and concentrate on key features, thereby preserving more detailed characteristics of PWD-infected trees. In addition, the GSConv network was utilized instead of conventional convolutions to reduce network complexity. Last, the Bidirectional Feature Pyramid Network strategy was used to enhance the propagation and sharing of multiscale features. The results demonstrate that on a self-built dataset, PWD-YOLO surpasses existing object detection models with respective measurements of model size (2.7 MB), computational complexity (3.5 GFLOPs), parameter volume (1.09 MB), and speed (98.0 frames/s). The Precision, Recall, and F1-score on the test set are 92.5%, 95.3%, and 93.9%, respectively, which confirms the effectiveness of the proposed method. It provides reliable technical support for daily monitoring and clearing of infected trees by forestry management departments.

Integrated Nematode Management in a World in Transition: Constraints, Policy, Processes, and Technologies for the Future

Plant-parasitic nematodes are one of the most insidious pests limiting agricultural production, parasitizing mostly belowground and occasionally aboveground plant parts. They are an important and underestimated component of the estimated 30% yield loss inflicted on crops globally by biotic constraints. Nematode damage is intensified by interactions with biotic and abiotic factors constraints: soilborne pathogens, soil fertility degradation, reduced soil biodiversity, climate variability, and policies influencing the development of improved management options. This review focuses on the following topics: (a) biotic and abiotic constraints, (b) modification of production systems, (c) agricultural policies, (d) the microbiome, (e) genetic solutions, and (f) remote sensing. Improving integrated nematode management (INM) across all scales of agricultural production and along the Global North-Global South divide, where inequalities influence access to technology, is discussed. The importance of the integration of technological development in INM is critical to improving food security and human well-being in the future.

Early Monitoring of Forest Wood-Boring Pests with Remote Sensing

Wood-boring pests (WBPs) pose an enormous threat to global forest ecosystems because their early stage infestations show no visible symptoms and can result in rapid and widespread infestations at later stages, leading to large-scale tree death. Therefore, early-stage WBP detection is crucial for prompt management response. Early detection of WBPs requires advanced and effective methods like remote sensing. This review summarizes the applications of various remote sensing sensors, platforms, and detection methods for monitoring WBP infestations. The current capabilities, gaps in capabilities, and future potential for the accurate and rapid detection of WBPs are highlighted.

Early detection of pine wilt disease tree candidates using time-series of spectral signatures

Pine wilt disease (PWD), caused by pine wood nematode (PWN), poses a tremendous threat to global pine forests because it can result in rapid and widespread infestations within months, leading to large-scale tree mortality. Therefore, the implementation of preventive measures relies on early detection of PWD. Unmanned aerial vehicle (UAV)-based hyperspectral images (HSI) can detect tree-level changes and are thus an effective tool for forest change detection. However, previous studies mainly used single-date UAV-based HSI data, which could not monitor the temporal changes of disease distribution and determine the optimal detection period. To achieve these purposes, multi-temporal data is required. In this study, Pinus koraiensis stands were surveyed in the field from May to October during an outbreak of PWD. Concurrently, multi-temporal UAV-based red, green, and blue bands (RGB) and HSI data were also obtained. During the survey, 59 trees were confirmed to be infested with PWD, and 59 non-infested trees were used as control. Spectral features of each tree crown, such as spectral reflectance, first and second-order spectral derivatives, and vegetation indices (VIs), were analyzed to identify those useful for early monitoring of PWD. The Random Forest (RF) classification algorithm was used to examine the separability between the two groups of trees (control and infested trees). The results showed that: (1) the responses of the tree crown spectral features to PWD infestation could be detected before symptoms were noticeable in RGB data and field surveys; (2) the spectral derivatives were the most discriminable variables, followed by spectral reflectance and VIs; (3) based on the HSI data from July to October, the two groups of trees were successfully separated using the RF classifier, with an overall classification accuracy of 0.75-0.95. Our results illustrate the potential of UAV-based HSI for PWD early monitoring.

Inversion of chlorophyll content under the stress of leaf mite for jujube based on model PSO-ELM method

During the growth season, jujube trees are susceptible to infestation by the leaf mite, which reduces the fruit quality and productivity. Traditional monitoring techniques for mites are time-consuming, difficult, subjective, and result in a time lag. In this study, the method based on a particle swarm optimization (PSO) algorithm extreme learning machine for estimation of leaf chlorophyll content (SPAD) under leaf mite infestation in jujube was proposed. Initially, image data and SPAD values for jujube orchards under four severities of leaf mite infestation were collected for analysis. Six vegetation indices and SPAD value were chosen for correlation analysis to establish the estimation model for SPAD and the vegetation indices. To address the influence of colinearity between spectral bands, the feature band with the highest correlation coefficient was retrieved first using the successive projection algorithm. In the modeling process, the PSO correlation coefficient was initialized with the convergent optimal approximation of the fitness function value; the root mean square error (RMSE) of the predicted and measured values was derived as an indicator of PSO goodness-of-fit to solve the problems of ELM model weights, threshold randomness, and uncertainty of network parameters; and finally, an iterative update method was used to determine the particle fitness value to optimize the minimum error or iteration number. The results reflected that significant differences were observed in the spectral reflectance of the jujube canopy corresponding with the severity of leaf mite infestation, and the infestation severity was negatively correlated with the SPAD value of jujube leaves. The selected vegetation indices NDVI, RVI, PhRI, and MCARI were positively correlated with SPAD, whereas TCARI and GI were negatively correlated with SPAD. The accuracy of the optimized PSO-ELM model (R ² = 0.856, RMSE = 0.796) was superior to that of the ELM model alone (R ² = 0.748, RMSE = 1.689). The PSO-ELM model for remote sensing estimation of relative leaf chlorophyll content of jujube shows high fault tolerance and improved data-processing efficiency. The results provide a reference for the utility of UAV remote sensing for monitoring leaf mite infestation of jujube.

A survey on deep learning-based identification of plant and crop diseases from UAV-based aerial images

The agricultural crop productivity can be affected and reduced due to many factors such as weeds, pests, and diseases. Traditional methods that are based on terrestrial engines, devices, and farmers' naked eyes are facing many limitations in terms of accuracy and the required time to cover large fields. Currently, precision agriculture that is based on the use of deep learning algorithms and Unmanned Aerial Vehicles (UAVs) provides an effective solution to achieve agriculture applications, including plant disease identification and treatment. In the last few years, plant disease monitoring using UAV platforms is one of the most important agriculture applications that have gained increasing interest by researchers. Accurate detection and treatment of plant diseases at early stages is crucial to improving agricultural production. To this end, in this review, we analyze the recent advances in the use of computer vision techniques that are based on deep learning algorithms and UAV technologies to identify and treat crop diseases.

UAV-Based Forest Health Monitoring: A Systematic Review

In recent years, technological advances have led to the increasing use of unmanned aerial vehicles (UAVs) for forestry applications. One emerging field for drone application is forest health monitoring (FHM). Common approaches for FHM involve small-scale resource-extensive fieldwork combined with traditional remote sensing platforms. However, the highly dynamic nature of forests requires timely and repetitive data acquisition, often at very high spatial resolution, where conventional remote sensing techniques reach the limits of feasibility. UAVs have shown that they can meet the demands of flexible operation and high spatial resolution. This is also reflected in a rapidly growing number of publications using drones to study forest health. Only a few reviews exist which do not cover the whole research history of UAV-based FHM. Since a comprehensive review is becoming critical to identify research gaps, trends, and drawbacks, we offer a systematic analysis of 99 papers covering the last ten years of research related to UAV-based monitoring of forests threatened by biotic and abiotic stressors. Advances in drone technology are being rapidly adopted and put into practice, further improving the economical use of UAVs. Despite the many advantages of UAVs, such as their flexibility, relatively low costs, and the possibility to fly below cloud cover, we also identified some shortcomings: (1) multitemporal and long-term monitoring of forests is clearly underrepresented; (2) the rare use of hyperspectral and LiDAR sensors must drastically increase; (3) complementary data from other RS sources are not sufficiently being exploited; (4) a lack of standardized workflows poses a problem to ensure data uniformity; (5) complex machine learning algorithms and workflows obscure interpretability and hinders widespread adoption; (6) the data pipeline from acquisition to final analysis often relies on commercial software at the expense of open-source tools.

Detection of Standing Dead Trees after Pine Wilt Disease Outbreak with Airborne Remote Sensing Imagery by Multi-Scale Spatial Attention Deep Learning and Gaussian Kernel Approach

The continuous and extensive pinewood nematode disease has seriously threatened the sustainable development of forestry in China. At present, many studies have used high-resolution remote sensing images combined with a deep semantic segmentation algorithm to identify standing dead trees in the red attack period. However, due to the complex background, closely distributed detection scenes, and unbalanced training samples, it is difficult to detect standing dead trees (SDTs) in a variety of complex scenes by using conventional segmentation models. In order to further solve the above problems and improve the recognition accuracy, we proposed a new detection method called multi-scale spatial supervision convolutional network (MSSCN) to identify SDTs in a wide range of complex scenes based on airborne remote sensing imagery. In the method, a Gaussian kernel approach was used to generate a confidence map from SDTs marked as points for training samples, and a multi-scale spatial attention block was added into fully convolutional neural networks to reduce the loss of spatial information. Further, an augmentation strategy called copy–pasting was used to overcome the lack of efficient samples in this research area. Validation at four different forest areas belonging to two forest types and two diseased outbreak intensities showed that (1) the copy–pasting method helps to augment training samples and can improve the detecting accuracy with a suitable oversampling rate, and the best oversampling rate should be carefully determined by the input training samples and image data. (2) Based on the two-dimensional spatial Gaussian kernel distribution function and the multi-scale spatial attention structure, the MSSCN model can effectively find the dead tree extent in a confidence map, and by following this with maximum location searching we can easily locate the individual dead trees. The averaged precision, recall, and F1-score across different forest types and disease-outbreak-intensity areas can achieve 0.94, 0.84, and 0.89, respectively, which is the best performance among FCN8s and U-Net. (3) In terms of forest type and outbreak intensity, the MSSCN performs best in pure pine forest type and low-outbreak-intensity areas. Compared with FCN8s and U-Net, the MSSCN can achieve the best recall accuracy in all forest types and outbreak-intensity areas. Meanwhile, the precision metric is also maintained at a high level, which means that the proposed method provides a trade-off between the precision and recall in detection accuracy.

Recent Advances in Forest Insect Pests and Diseases Monitoring Using UAV-Based Data: A Systematic Review

Unmanned aerial vehicles (UAVs) are platforms that have been increasingly used over the last decade to collect data for forest insect pest and disease (FIPD) monitoring. These machines provide flexibility, cost efficiency, and a high temporal and spatial resolution of remotely sensed data. The purpose of this review is to summarize recent contributions and to identify knowledge gaps in UAV remote sensing for FIPD monitoring. A systematic review was performed using the preferred reporting items for systematic reviews and meta-analysis (PRISMA) protocol. We reviewed the full text of 49 studies published between 2015 and 2021. The parameters examined were the taxonomic characteristics, the type of UAV and sensor, data collection and pre-processing, processing and analytical methods, and software used. We found that the number of papers on this topic has increased in recent years, with most being studies located in China and Europe. The main FIPDs studied were pine wilt disease (PWD) and bark beetles (BB) using UAV multirotor architectures. Among the sensor types, multispectral and red–green–blue (RGB) bands were preferred for the monitoring tasks. Regarding the analytical methods, random forest (RF) and deep learning (DL) classifiers were the most frequently applied in UAV imagery processing. This paper discusses the advantages and limitations associated with the use of UAVs and the processing methods for FIPDs, and research gaps and challenges are presented.

The Potential of Widespread UAV Cameras in the Identification of Conifers and the Delineation of Their Crowns

With the ever-improving advances in computer vision and Earth observation capabilities, Unmanned Aerial Vehicles (UAVs) allow extensive forest inventory and the description of stand structure indirectly. We performed several flights with different UAVs and popular sensors over two sites with coniferous forests of various ages and flight levels using the custom settings preset by solution suppliers. The data were processed using image-matching techniques, yielding digital surface models, which were further analyzed using the lidR package in R. Consumer-grade RGB cameras were consistently more successful in the identification of individual trees at all of the flight levels (84–77% for Phantom 4), compared to the success of multispectral cameras, which decreased with higher flight levels and smaller crowns (77–54% for RedEdge-M). Regarding the accuracy of the measured crown diameters, RGB cameras yielded satisfactory results (Mean Absolute Error—MAE of 0.79–0.99 m and 0.88–1.16 m for Phantom 4 and Zenmuse X5S, respectively); multispectral cameras overestimated the height, especially in the full-grown forests (MAE = 1.26–1.77 m). We conclude that widely used low-cost RGB cameras yield very satisfactory results for the description of the structural forest information at a 150 m flight altitude. When (multi)spectral information is needed, we recommend reducing the flight level to 100 m in order to acquire sufficient structural forest information. The study contributes to the current knowledge by directly comparing widely used consumer-grade UAV cameras and providing a clear elementary workflow for inexperienced users, thus helping entry-level users with the initial steps and supporting the usability of such data in practice.

An Adaptively Attention-Driven Cascade Part-Based Graph Embedding Framework for UAV Object Re-Identification

With the rapid development of unmanned aerial vehicles (UAVs), object re-identification (Re-ID) based on the UAV platforms has attracted increasing attention, and several excellent achievements have been shown in the traditional scenarios. However, object Re-ID in aerial imagery acquired from the UAVs is still a challenging task, which is mainly due to the reason that variable locations and diverse viewpoints in UAVs platform are always resulting in more appearance ambiguities among the intra-objects and inter-objects. To address the above issues, in this paper, we proposed an adaptively attention-driven cascade part-based graph embedding framework (AAD-CPGE) for UAV object Re-ID. The AAD-CPGE aims to optimally fuse node features and their topological characteristics on the multi-scale structured graphs of parts-based objects, and then adaptively learn the most correlated information for improving the object Re-ID performance. Specifically, we first executed GCNs on the parts-based cascade node feature graphs and topological feature graphs for acquiring multi-scale structured-graph feature representations. After that, we designed a self-attention-based module for adaptive node and topological features fusion on the constructed hierarchical parts-based graphs. Finally, these learning hybrid graph-structured features with the most correlation discriminative capability were applied for object Re-ID. Several experimental verifications on three widely used UAVs-based benchmark datasets were carried out, and comparison with some state-of-the-art object Re-ID approaches validated the effectiveness and benefits of our proposed AAD-CPGE Re-ID framework.

Logging Trail Segmentation via a Novel U-Net Convolutional Neural Network and High-Density Laser Scanning Data

Logging trails are one of the main components of modern forestry. However, spotting the accurate locations of old logging trails through common approaches is challenging and time consuming. This study was established to develop an approach, using cutting-edge deep-learning convolutional neural networks and high-density laser scanning data, to detect logging trails in different stages of commercial thinning, in Southern Finland. We constructed a U-Net architecture, consisting of encoder and decoder paths with several convolutional layers, pooling and non-linear operations. The canopy height model (CHM), digital surface model (DSM), and digital elevation models (DEMs) were derived from the laser scanning data and were used as image datasets for training the model. The labeled dataset for the logging trails was generated from different references as well. Three forest areas were selected to test the efficiency of the algorithm that was developed for detecting logging trails. We designed 21 routes, including 390 samples of the logging trails and non-logging trails, covering all logging trails inside the stands. The results indicated that the trained U-Net using DSM (k = 0.846 and IoU = 0.867) shows superior performance over the trained model using CHM (k = 0.734 and IoU = 0.782), DEMavg (k = 0.542 and IoU = 0.667), and DEMmin (k = 0.136 and IoU = 0.155) in distinguishing logging trails from non-logging trails. Although the efficiency of the developed approach in young and mature stands that had undergone the commercial thinning is approximately perfect, it needs to be improved in old stands that have not received the second or third commercial thinning.

A Deep Learning-Based Generalized System for Detecting Pine Wilt Disease Using RGB-Based UAV Images

Pine wilt is a devastating disease that typically kills affected pine trees within a few months. In this paper, we confront the problem of detecting pine wilt disease. In the image samples that have been used for pine wilt disease detection, there is high ambiguity due to poor image resolution and the presence of “disease-like” objects. We therefore created a new dataset using large-sized orthophotographs collected from 32 cities, 167 regions, and 6121 pine wilt disease hotspots in South Korea. In our system, pine wilt disease was detected in two stages: n the first stage, the disease and hard negative samples were collected using a convolutional neural network. Because the diseased areas varied in size and color, and as the disease manifests differently from the early stage to the late stage, hard negative samples were further categorized into six different classes to simplify the complexity of the dataset. Then, in the second stage, we used an object detection model to localize the disease and “disease-like” hard negative samples. We used several image augmentation methods to boost system performance and avoid overfitting. The test process was divided into two phases: a patch-based test and a real-world test. During the patch-based test, we used the test-time augmentation method to obtain the average prediction of our system across multiple augmented samples of data, and the prediction results showed a mean average precision of 89.44% in five-fold cross validation, thus representing an increase of around 5% over the alternative system. In the real-world test, we collected 10 orthophotographs in various resolutions and areas, and our system successfully detected 711 out of 730 potential disease spots.

Unmanned Aerial Vehicles (UAV) in Precision Agriculture: Applications and Challenges

Agriculture is the primary source of income in developing countries like India. Agriculture accounts for 17 percent of India’s total GDP, with almost 60 percent of the people directly or indirectly employed. While researchers and planters focus on a variety of elements to boost productivity, crop loss due to disease is one of the most serious issues they confront. Crop growth monitoring and early detection of pest infestations are still a problem. With the expansion of cultivation to wider fields, manual intervention to monitor and diagnose insect and pest infestations is becoming increasingly difficult. Failure to apply on time fertilizers and pesticides results in more crop loss and so lower output. Farmers are putting in greater effort to conserve crops, but they are failing most of the time because they are unable to adequately monitor the crops when they are infected by pests and insects. Pest infestation is also difficult to predict because it is not evenly distributed. In the recent past, modern equipment, tools, and approaches have been used to replace manual involvement. Unmanned aerial vehicles serve a critical role in crop disease surveillance and early detection in this setting. This research attempts to give a review of the most successful techniques to have precision-based crop monitoring and pest management in agriculture fields utilizing unmanned aerial vehicles (UAVs) or unmanned aircraft. The researchers’ reports on the various types of UAVs and their applications to early detection of agricultural diseases are rigorously assessed and compared. This paper also discusses the deployment of aerial, satellite, and other remote sensing technologies for disease detection, as well as their Quality of Service (QoS).

Detection of Bark Beetle Disturbance at Tree Level Using UAS Multispectral Imagery and Deep Learning

This study aimed to examine the potential of convolutional neural networks (CNNs) for the detection of individual trees infested by bark beetles in a multispectral high-resolution dataset acquired by an unmanned aerial system (UAS). We compared the performance of three CNN architectures and the random forest (RF) model to classify the trees into four categories: pines, sbbd (longer infested trees when needles turn yellow), sbbg (trees under green attack) and non-infested trees (sh). The best performance was achieved by the Nez4c3b CNN (kappa 0.80) and Safaugu4c3b CNN (kappa 0.76) using only RGB bands. The main misclassifications were between sbbd and sbbg because of the similar spectral responses. Merging sbbd and sbbg into a more general class of infested trees made the selection of model type less important. All tested model types, including RF, were able to detect infested trees with an F-score of the class over 0.90. Nevertheless, the best overall metrics were achieved again by the Safaugu3c3b model (kappa 0.92) and Nez3cb model (kappa 0.87) using only RGB bands. The performance of both models is comparable, but the Nez model has a higher learning rate for this task. Based on our findings, we conclude that the Nez and Safaugu CNN models are superior to the RF models and transfer learning models for the identification of infested trees and for distinguishing between different infestation stages. Therefore, these models can be used not only for basic identification of infested trees but also for monitoring the development of bark beetle disturbance.

Three-Dimensional Convolutional Neural Network Model for Early Detection of Pine Wilt Disease Using UAV-Based Hyperspectral Images

As one of the most devastating disasters to pine forests, pine wilt disease (PWD) has caused tremendous ecological and economic losses in China. An effective way to prevent large-scale PWD outbreaks is to detect and remove the damaged pine trees at the early stage of PWD infection. However, early infected pine trees do not show obvious changes in morphology or color in the visible wavelength range, making early detection of PWD tricky. Unmanned aerial vehicle (UAV)-based hyperspectral imagery (HI) has great potential for early detection of PWD. However, the commonly used methods, such as the two-dimensional convolutional neural network (2D-CNN), fail to simultaneously extract and fully utilize the spatial and spectral information, whereas the three-dimensional convolutional neural network (3D-CNN) is able to collect this information from raw hyperspectral data. In this paper, we applied the residual block to 3D-CNN and constructed a 3D-Res CNN model, the performance of which was then compared with that of 3D-CNN, 2D-CNN, and 2D-Res CNN in identifying PWD-infected pine trees from the hyperspectral images. The 3D-Res CNN model outperformed the other models, achieving an overall accuracy (OA) of 88.11% and an accuracy of 72.86% for detecting early infected pine trees (EIPs). Using only 20% of the training samples, the OA and EIP accuracy of 3D-Res CNN can still achieve 81.06% and 51.97%, which is superior to the state-of-the-art method in the early detection of PWD based on hyperspectral images. Collectively, 3D-Res CNN was more accurate and effective in early detection of PWD. In conclusion, 3D-Res CNN is proposed for early detection of PWD in this paper, making the prediction and control of PWD more accurate and effective. This model can also be applied to detect pine trees damaged by other diseases or insect pests in the forest.

Automatic Identification and Monitoring of Plant Diseases Using Unmanned Aerial Vehicles: A Review

Disease diagnosis is one of the major tasks for increasing food production in agriculture. Although precision agriculture (PA) takes less time and provides a more precise application of agricultural activities, the detection of disease using an Unmanned Aerial System (UAS) is a challenging task. Several Unmanned Aerial Vehicles (UAVs) and sensors have been used for this purpose. The UAVs’ platforms and their peripherals have their own limitations in accurately diagnosing plant diseases. Several types of image processing software are available for vignetting and orthorectification. The training and validation of datasets are important characteristics of data analysis. Currently, different algorithms and architectures of machine learning models are used to classify and detect plant diseases. These models help in image segmentation and feature extractions to interpret results. Researchers also use the values of vegetative indices, such as Normalized Difference Vegetative Index (NDVI), Crop Water Stress Index (CWSI), etc., acquired from different multispectral and hyperspectral sensors to fit into the statistical models to deliver results. There are still various drifts in the automatic detection of plant diseases as imaging sensors are limited by their own spectral bandwidth, resolution, background noise of the image, etc. The future of crop health monitoring using UAVs should include a gimble consisting of multiple sensors, large datasets for training and validation, the development of site-specific irradiance systems, and so on. This review briefly highlights the advantages of automatic detection of plant diseases to the growers.

Evaluation of Deep Learning Segmentation Models for Detection of Pine Wilt Disease in Unmanned Aerial Vehicle Images

Pine wilt disease (PWD) is a serious threat to pine forests. Combining unmanned aerial vehicle (UAV) images and deep learning (DL) techniques to identify infected pines is the most efficient method to determine the potential spread of PWD over a large area. In particular, image segmentation using DL obtains the detailed shape and size of infected pines to assess the disease’s degree of damage. However, the performance of such segmentation models has not been thoroughly studied. We used a fixed-wing UAV to collect images from a pine forest in Laoshan, Qingdao, China, and conducted a ground survey to collect samples of infected pines and construct prior knowledge to interpret the images. Then, training and test sets were annotated on selected images, and we obtained 2352 samples of infected pines annotated over different backgrounds. Finally, high-performance DL models (e.g., fully convolutional networks for semantic segmentation, DeepLabv3+, and PSPNet) were trained and evaluated. The results demonstrated that focal loss provided a higher accuracy and a finer boundary than Dice loss, with the average intersection over union (IoU) for all models increasing from 0.656 to 0.701. From the evaluated models, DeepLLabv3+ achieved the highest IoU and an F1 score of 0.720 and 0.832, respectively. Also, an atrous spatial pyramid pooling module encoded multiscale context information, and the encoder–decoder architecture recovered location/spatial information, being the best architecture for segmenting trees infected by the PWD. Furthermore, segmentation accuracy did not improve as the depth of the backbone network increased, and neither ResNet34 nor ResNet50 was the appropriate backbone for most segmentation models.

Effect of Attention Mechanism in Deep Learning-Based Remote Sensing Image Processing: A Systematic Literature Review

Machine learning, particularly deep learning (DL), has become a central and state-of-the-art method for several computer vision applications and remote sensing (RS) image processing. Researchers are continually trying to improve the performance of the DL methods by developing new architectural designs of the networks and/or developing new techniques, such as attention mechanisms. Since the attention mechanism has been proposed, regardless of its type, it has been increasingly used for diverse RS applications to improve the performances of the existing DL methods. However, these methods are scattered over different studies impeding the selection and application of the feasible approaches. This study provides an overview of the developed attention mechanisms and how to integrate them with different deep learning neural network architectures. In addition, it aims to investigate the effect of the attention mechanism on deep learning-based RS image processing. We identified and analyzed the advances in the corresponding attention mechanism-based deep learning (At-DL) methods. A systematic literature review was performed to identify the trends in publications, publishers, improved DL methods, data types used, attention types used, overall accuracies achieved using At-DL methods, and extracted the current research directions, weaknesses, and open problems to provide insights and recommendations for future studies. For this, five main research questions were formulated to extract the required data and information from the literature. Furthermore, we categorized the papers regarding the addressed RS image processing tasks (e.g., image classification, object detection, and change detection) and discussed the results within each group. In total, 270 papers were retrieved, of which 176 papers were selected according to the defined exclusion criteria for further analysis and detailed review. The results reveal that most of the papers reported an increase in overall accuracy when using the attention mechanism within the DL methods for image classification, image segmentation, change detection, and object detection using remote sensing images.

Deep Learning in Forestry Using UAV-Acquired RGB Data: A Practical Review

Forests are the planet’s main CO2 filtering agent as well as important economical, environmental and social assets. Climate change is exerting an increased stress, resulting in a need for improved research methodologies to study their health, composition or evolution. Traditionally, information about forests has been collected using expensive and work-intensive field inventories, but in recent years unoccupied autonomous vehicles (UAVs) have become very popular as they represent a simple and inexpensive way to gather high resolution data of large forested areas. In addition to this trend, deep learning (DL) has also been gaining much attention in the field of forestry as a way to include the knowledge of forestry experts into automatic software pipelines tackling problems such as tree detection or tree health/species classification. Among the many sensors that UAVs can carry, RGB cameras are fast, cost-effective and allow for straightforward data interpretation. This has resulted in a large increase in the amount of UAV-acquired RGB data available for forest studies. In this review, we focus on studies that use DL and RGB images gathered by UAVs to solve practical forestry research problems. We summarize the existing studies, provide a detailed analysis of their strengths paired with a critical assessment on common methodological problems and include other information, such as available public data and code resources that we believe can be useful for researchers that want to start working in this area. We structure our discussion using three main families of forestry problems: (1) individual Tree Detection, (2) tree Species Classification, and (3) forest Anomaly Detection (forest fires and insect Infestation).

Forest Land Cover Mapping at a Regional Scale Using Multi-Temporal Sentinel-2 Imagery and RF Models

Over the last several decades, thanks to improvements in and the diversification of open-access satellite imagery, land cover mapping techniques have evolved significantly. Notable changes in these techniques involve the automation of different steps, yielding promising results in terms of accuracy, class detection and efficiency. The most successful methodologies that have arisen rely on the use of multi-temporal data. Several different approaches have proven successful. In this study, one of the most recently developed methodologies is tested in the region of Galicia (in Northwestern Spain), with the aim of filling gaps in the mapping needs of the Galician forestry sector. The methodology mainly consists of performing a supervised classification of individual images from a selected time series and then combining them through aggregation using decision criteria. Several of the steps of the methodology can be addressed in multiple ways: pixel resolution selection, classification model building and aggregation methods. The effectiveness of these three tasks as well as some others are tested and evaluated and the most accurate and efficient parameters for the case study area are highlighted. The final land cover map that is obtained for Galicia has high accuracy metrics (an overall accuracy of 91.6%), which is in line with previous studies that have followed this methodology in other regions. This study has led to the development of an efficient open-access solution to support the mapping needs of the forestry sector.